summaryrefslogtreecommitdiff
path: root/src/cluster.c
blob: c05e46f7620e5f7d12c064650b7f362d111cd550 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
5281
5282
5283
5284
5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
5317
5318
5319
5320
5321
5322
5323
5324
5325
5326
5327
5328
5329
5330
5331
5332
5333
5334
5335
5336
5337
5338
5339
5340
5341
5342
5343
5344
5345
5346
5347
5348
5349
5350
5351
5352
5353
5354
5355
5356
5357
5358
5359
5360
5361
5362
5363
5364
5365
5366
5367
5368
5369
5370
5371
5372
5373
5374
5375
5376
5377
5378
5379
5380
5381
5382
5383
5384
5385
5386
5387
5388
5389
5390
5391
5392
5393
5394
5395
5396
5397
5398
5399
5400
5401
5402
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
5416
5417
5418
5419
5420
5421
5422
5423
5424
5425
5426
5427
5428
5429
5430
5431
5432
5433
5434
5435
5436
5437
5438
5439
5440
5441
5442
5443
5444
5445
5446
5447
5448
5449
5450
5451
5452
5453
5454
5455
5456
5457
5458
5459
5460
5461
5462
5463
5464
5465
5466
5467
5468
5469
5470
5471
5472
5473
5474
5475
5476
5477
5478
5479
5480
5481
5482
5483
5484
5485
5486
5487
5488
5489
5490
5491
5492
5493
5494
5495
5496
5497
5498
5499
5500
5501
5502
5503
5504
5505
5506
5507
5508
5509
5510
5511
5512
5513
5514
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
5526
5527
5528
5529
5530
5531
5532
5533
5534
5535
5536
5537
5538
5539
5540
5541
5542
5543
5544
5545
5546
5547
5548
5549
5550
5551
5552
5553
5554
5555
5556
5557
5558
5559
5560
5561
5562
5563
5564
5565
5566
5567
5568
5569
5570
5571
5572
5573
5574
5575
5576
5577
5578
5579
5580
5581
5582
5583
5584
5585
5586
5587
5588
5589
5590
5591
5592
5593
5594
5595
5596
5597
5598
5599
5600
5601
5602
5603
5604
5605
5606
5607
5608
5609
5610
5611
5612
5613
5614
5615
5616
5617
5618
5619
5620
5621
5622
5623
5624
5625
5626
5627
5628
5629
5630
5631
5632
5633
5634
5635
5636
5637
5638
5639
5640
5641
5642
5643
5644
5645
5646
5647
5648
5649
5650
5651
5652
5653
5654
5655
5656
5657
5658
5659
5660
5661
5662
5663
5664
5665
5666
5667
5668
5669
5670
5671
5672
5673
5674
5675
5676
5677
5678
5679
5680
5681
5682
5683
5684
5685
5686
5687
5688
5689
5690
5691
5692
5693
5694
5695
5696
5697
5698
5699
5700
5701
5702
5703
5704
5705
5706
5707
5708
5709
5710
5711
5712
5713
5714
5715
5716
5717
5718
5719
5720
5721
5722
5723
5724
5725
5726
5727
5728
5729
5730
5731
5732
5733
5734
5735
5736
5737
5738
5739
5740
5741
5742
5743
5744
5745
5746
5747
5748
5749
5750
5751
5752
5753
5754
5755
5756
5757
5758
5759
5760
5761
5762
5763
5764
5765
5766
5767
5768
5769
5770
5771
5772
/* Redis Cluster implementation.
 *
 * Copyright (c) 2009-2012, Salvatore Sanfilippo <antirez at gmail dot com>
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions are met:
 *
 *   * Redistributions of source code must retain the above copyright notice,
 *     this list of conditions and the following disclaimer.
 *   * Redistributions in binary form must reproduce the above copyright
 *     notice, this list of conditions and the following disclaimer in the
 *     documentation and/or other materials provided with the distribution.
 *   * Neither the name of Redis nor the names of its contributors may be used
 *     to endorse or promote products derived from this software without
 *     specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
 * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
 * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
 * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
 * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
 * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
 * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
 * POSSIBILITY OF SUCH DAMAGE.
 */

#include "server.h"
#include "cluster.h"
#include "endianconv.h"

#include <sys/types.h>
#include <sys/socket.h>
#include <arpa/inet.h>
#include <fcntl.h>
#include <unistd.h>
#include <sys/stat.h>
#include <sys/file.h>
#include <math.h>

/* A global reference to myself is handy to make code more clear.
 * Myself always points to server.cluster->myself, that is, the clusterNode
 * that represents this node. */
clusterNode *myself = NULL;

clusterNode *createClusterNode(char *nodename, int flags);
int clusterAddNode(clusterNode *node);
void clusterAcceptHandler(aeEventLoop *el, int fd, void *privdata, int mask);
void clusterReadHandler(connection *conn);
void clusterSendPing(clusterLink *link, int type);
void clusterSendFail(char *nodename);
void clusterSendFailoverAuthIfNeeded(clusterNode *node, clusterMsg *request);
void clusterUpdateState(void);
int clusterNodeGetSlotBit(clusterNode *n, int slot);
sds clusterGenNodesDescription(int filter);
clusterNode *clusterLookupNode(const char *name);
int clusterNodeAddSlave(clusterNode *master, clusterNode *slave);
int clusterAddSlot(clusterNode *n, int slot);
int clusterDelSlot(int slot);
int clusterDelNodeSlots(clusterNode *node);
int clusterNodeSetSlotBit(clusterNode *n, int slot);
void clusterSetMaster(clusterNode *n);
void clusterHandleSlaveFailover(void);
void clusterHandleSlaveMigration(int max_slaves);
int bitmapTestBit(unsigned char *bitmap, int pos);
void clusterDoBeforeSleep(int flags);
void clusterSendUpdate(clusterLink *link, clusterNode *node);
void resetManualFailover(void);
void clusterCloseAllSlots(void);
void clusterSetNodeAsMaster(clusterNode *n);
void clusterDelNode(clusterNode *delnode);
sds representClusterNodeFlags(sds ci, uint16_t flags);
uint64_t clusterGetMaxEpoch(void);
int clusterBumpConfigEpochWithoutConsensus(void);
void moduleCallClusterReceivers(const char *sender_id, uint64_t module_id, uint8_t type, const unsigned char *payload, uint32_t len);

/* -----------------------------------------------------------------------------
 * Initialization
 * -------------------------------------------------------------------------- */

/* Load the cluster config from 'filename'.
 *
 * If the file does not exist or is zero-length (this may happen because
 * when we lock the nodes.conf file, we create a zero-length one for the
 * sake of locking if it does not already exist), C_ERR is returned.
 * If the configuration was loaded from the file, C_OK is returned. */
int clusterLoadConfig(char *filename) {
    FILE *fp = fopen(filename,"r");
    struct stat sb;
    char *line;
    int maxline, j;

    if (fp == NULL) {
        if (errno == ENOENT) {
            return C_ERR;
        } else {
            serverLog(LL_WARNING,
                "Loading the cluster node config from %s: %s",
                filename, strerror(errno));
            exit(1);
        }
    }

    /* Check if the file is zero-length: if so return C_ERR to signal
     * we have to write the config. */
    if (fstat(fileno(fp),&sb) != -1 && sb.st_size == 0) {
        fclose(fp);
        return C_ERR;
    }

    /* Parse the file. Note that single lines of the cluster config file can
     * be really long as they include all the hash slots of the node.
     * This means in the worst possible case, half of the Redis slots will be
     * present in a single line, possibly in importing or migrating state, so
     * together with the node ID of the sender/receiver.
     *
     * To simplify we allocate 1024+CLUSTER_SLOTS*128 bytes per line. */
    maxline = 1024+CLUSTER_SLOTS*128;
    line = zmalloc(maxline);
    while(fgets(line,maxline,fp) != NULL) {
        int argc;
        sds *argv;
        clusterNode *n, *master;
        char *p, *s;

        /* Skip blank lines, they can be created either by users manually
         * editing nodes.conf or by the config writing process if stopped
         * before the truncate() call. */
        if (line[0] == '\n' || line[0] == '\0') continue;

        /* Split the line into arguments for processing. */
        argv = sdssplitargs(line,&argc);
        if (argv == NULL) goto fmterr;

        /* Handle the special "vars" line. Don't pretend it is the last
         * line even if it actually is when generated by Redis. */
        if (strcasecmp(argv[0],"vars") == 0) {
            if (!(argc % 2)) goto fmterr;
            for (j = 1; j < argc; j += 2) {
                if (strcasecmp(argv[j],"currentEpoch") == 0) {
                    server.cluster->currentEpoch =
                            strtoull(argv[j+1],NULL,10);
                } else if (strcasecmp(argv[j],"lastVoteEpoch") == 0) {
                    server.cluster->lastVoteEpoch =
                            strtoull(argv[j+1],NULL,10);
                } else {
                    serverLog(LL_WARNING,
                        "Skipping unknown cluster config variable '%s'",
                        argv[j]);
                }
            }
            sdsfreesplitres(argv,argc);
            continue;
        }

        /* Regular config lines have at least eight fields */
        if (argc < 8) {
            sdsfreesplitres(argv,argc);
            goto fmterr;
        }

        /* Create this node if it does not exist */
        n = clusterLookupNode(argv[0]);
        if (!n) {
            n = createClusterNode(argv[0],0);
            clusterAddNode(n);
        }
        /* Address and port */
        if ((p = strrchr(argv[1],':')) == NULL) {
            sdsfreesplitres(argv,argc);
            goto fmterr;
        }
        *p = '\0';
        memcpy(n->ip,argv[1],strlen(argv[1])+1);
        char *port = p+1;
        char *busp = strchr(port,'@');
        if (busp) {
            *busp = '\0';
            busp++;
        }
        n->port = atoi(port);
        /* In older versions of nodes.conf the "@busport" part is missing.
         * In this case we set it to the default offset of 10000 from the
         * base port. */
        n->cport = busp ? atoi(busp) : n->port + CLUSTER_PORT_INCR;

        /* Parse flags */
        p = s = argv[2];
        while(p) {
            p = strchr(s,',');
            if (p) *p = '\0';
            if (!strcasecmp(s,"myself")) {
                serverAssert(server.cluster->myself == NULL);
                myself = server.cluster->myself = n;
                n->flags |= CLUSTER_NODE_MYSELF;
            } else if (!strcasecmp(s,"master")) {
                n->flags |= CLUSTER_NODE_MASTER;
            } else if (!strcasecmp(s,"slave")) {
                n->flags |= CLUSTER_NODE_SLAVE;
            } else if (!strcasecmp(s,"fail?")) {
                n->flags |= CLUSTER_NODE_PFAIL;
            } else if (!strcasecmp(s,"fail")) {
                n->flags |= CLUSTER_NODE_FAIL;
                n->fail_time = mstime();
            } else if (!strcasecmp(s,"handshake")) {
                n->flags |= CLUSTER_NODE_HANDSHAKE;
            } else if (!strcasecmp(s,"noaddr")) {
                n->flags |= CLUSTER_NODE_NOADDR;
            } else if (!strcasecmp(s,"nofailover")) {
                n->flags |= CLUSTER_NODE_NOFAILOVER;
            } else if (!strcasecmp(s,"noflags")) {
                /* nothing to do */
            } else {
                serverPanic("Unknown flag in redis cluster config file");
            }
            if (p) s = p+1;
        }

        /* Get master if any. Set the master and populate master's
         * slave list. */
        if (argv[3][0] != '-') {
            master = clusterLookupNode(argv[3]);
            if (!master) {
                master = createClusterNode(argv[3],0);
                clusterAddNode(master);
            }
            n->slaveof = master;
            clusterNodeAddSlave(master,n);
        }

        /* Set ping sent / pong received timestamps */
        if (atoi(argv[4])) n->ping_sent = mstime();
        if (atoi(argv[5])) n->pong_received = mstime();

        /* Set configEpoch for this node. */
        n->configEpoch = strtoull(argv[6],NULL,10);

        /* Populate hash slots served by this instance. */
        for (j = 8; j < argc; j++) {
            int start, stop;

            if (argv[j][0] == '[') {
                /* Here we handle migrating / importing slots */
                int slot;
                char direction;
                clusterNode *cn;

                p = strchr(argv[j],'-');
                serverAssert(p != NULL);
                *p = '\0';
                direction = p[1]; /* Either '>' or '<' */
                slot = atoi(argv[j]+1);
                if (slot < 0 || slot >= CLUSTER_SLOTS) {
                    sdsfreesplitres(argv,argc);
                    goto fmterr;
                }
                p += 3;
                cn = clusterLookupNode(p);
                if (!cn) {
                    cn = createClusterNode(p,0);
                    clusterAddNode(cn);
                }
                if (direction == '>') {
                    server.cluster->migrating_slots_to[slot] = cn;
                } else {
                    server.cluster->importing_slots_from[slot] = cn;
                }
                continue;
            } else if ((p = strchr(argv[j],'-')) != NULL) {
                *p = '\0';
                start = atoi(argv[j]);
                stop = atoi(p+1);
            } else {
                start = stop = atoi(argv[j]);
            }
            if (start < 0 || start >= CLUSTER_SLOTS ||
                stop < 0 || stop >= CLUSTER_SLOTS)
            {
                sdsfreesplitres(argv,argc);
                goto fmterr;
            }
            while(start <= stop) clusterAddSlot(n, start++);
        }

        sdsfreesplitres(argv,argc);
    }
    /* Config sanity check */
    if (server.cluster->myself == NULL) goto fmterr;

    zfree(line);
    fclose(fp);

    serverLog(LL_NOTICE,"Node configuration loaded, I'm %.40s", myself->name);

    /* Something that should never happen: currentEpoch smaller than
     * the max epoch found in the nodes configuration. However we handle this
     * as some form of protection against manual editing of critical files. */
    if (clusterGetMaxEpoch() > server.cluster->currentEpoch) {
        server.cluster->currentEpoch = clusterGetMaxEpoch();
    }
    return C_OK;

fmterr:
    serverLog(LL_WARNING,
        "Unrecoverable error: corrupted cluster config file.");
    zfree(line);
    if (fp) fclose(fp);
    exit(1);
}

/* Cluster node configuration is exactly the same as CLUSTER NODES output.
 *
 * This function writes the node config and returns 0, on error -1
 * is returned.
 *
 * Note: we need to write the file in an atomic way from the point of view
 * of the POSIX filesystem semantics, so that if the server is stopped
 * or crashes during the write, we'll end with either the old file or the
 * new one. Since we have the full payload to write available we can use
 * a single write to write the whole file. If the pre-existing file was
 * bigger we pad our payload with newlines that are anyway ignored and truncate
 * the file afterward. */
int clusterSaveConfig(int do_fsync) {
    sds ci;
    size_t content_size;
    struct stat sb;
    int fd;

    server.cluster->todo_before_sleep &= ~CLUSTER_TODO_SAVE_CONFIG;

    /* Get the nodes description and concatenate our "vars" directive to
     * save currentEpoch and lastVoteEpoch. */
    ci = clusterGenNodesDescription(CLUSTER_NODE_HANDSHAKE);
    ci = sdscatprintf(ci,"vars currentEpoch %llu lastVoteEpoch %llu\n",
        (unsigned long long) server.cluster->currentEpoch,
        (unsigned long long) server.cluster->lastVoteEpoch);
    content_size = sdslen(ci);

    if ((fd = open(server.cluster_configfile,O_WRONLY|O_CREAT,0644))
        == -1) goto err;

    /* Pad the new payload if the existing file length is greater. */
    if (fstat(fd,&sb) != -1) {
        if (sb.st_size > (off_t)content_size) {
            ci = sdsgrowzero(ci,sb.st_size);
            memset(ci+content_size,'\n',sb.st_size-content_size);
        }
    }
    if (write(fd,ci,sdslen(ci)) != (ssize_t)sdslen(ci)) goto err;
    if (do_fsync) {
        server.cluster->todo_before_sleep &= ~CLUSTER_TODO_FSYNC_CONFIG;
        fsync(fd);
    }

    /* Truncate the file if needed to remove the final \n padding that
     * is just garbage. */
    if (content_size != sdslen(ci) && ftruncate(fd,content_size) == -1) {
        /* ftruncate() failing is not a critical error. */
    }
    close(fd);
    sdsfree(ci);
    return 0;

err:
    if (fd != -1) close(fd);
    sdsfree(ci);
    return -1;
}

void clusterSaveConfigOrDie(int do_fsync) {
    if (clusterSaveConfig(do_fsync) == -1) {
        serverLog(LL_WARNING,"Fatal: can't update cluster config file.");
        exit(1);
    }
}

/* Lock the cluster config using flock(), and leaks the file descritor used to
 * acquire the lock so that the file will be locked forever.
 *
 * This works because we always update nodes.conf with a new version
 * in-place, reopening the file, and writing to it in place (later adjusting
 * the length with ftruncate()).
 *
 * On success C_OK is returned, otherwise an error is logged and
 * the function returns C_ERR to signal a lock was not acquired. */
int clusterLockConfig(char *filename) {
/* flock() does not exist on Solaris
 * and a fcntl-based solution won't help, as we constantly re-open that file,
 * which will release _all_ locks anyway
 */
#if !defined(__sun)
    /* To lock it, we need to open the file in a way it is created if
     * it does not exist, otherwise there is a race condition with other
     * processes. */
    int fd = open(filename,O_WRONLY|O_CREAT,0644);
    if (fd == -1) {
        serverLog(LL_WARNING,
            "Can't open %s in order to acquire a lock: %s",
            filename, strerror(errno));
        return C_ERR;
    }

    if (flock(fd,LOCK_EX|LOCK_NB) == -1) {
        if (errno == EWOULDBLOCK) {
            serverLog(LL_WARNING,
                 "Sorry, the cluster configuration file %s is already used "
                 "by a different Redis Cluster node. Please make sure that "
                 "different nodes use different cluster configuration "
                 "files.", filename);
        } else {
            serverLog(LL_WARNING,
                "Impossible to lock %s: %s", filename, strerror(errno));
        }
        close(fd);
        return C_ERR;
    }
    /* Lock acquired: leak the 'fd' by not closing it, so that we'll retain the
     * lock to the file as long as the process exists. */
#endif /* __sun */

    return C_OK;
}

/* Some flags (currently just the NOFAILOVER flag) may need to be updated
 * in the "myself" node based on the current configuration of the node,
 * that may change at runtime via CONFIG SET. This function changes the
 * set of flags in myself->flags accordingly. */
void clusterUpdateMyselfFlags(void) {
    int oldflags = myself->flags;
    int nofailover = server.cluster_slave_no_failover ?
                     CLUSTER_NODE_NOFAILOVER : 0;
    myself->flags &= ~CLUSTER_NODE_NOFAILOVER;
    myself->flags |= nofailover;
    if (myself->flags != oldflags) {
        clusterDoBeforeSleep(CLUSTER_TODO_SAVE_CONFIG|
                             CLUSTER_TODO_UPDATE_STATE);
    }
}

void clusterInit(void) {
    int saveconf = 0;

    server.cluster = zmalloc(sizeof(clusterState));
    server.cluster->myself = NULL;
    server.cluster->currentEpoch = 0;
    server.cluster->state = CLUSTER_FAIL;
    server.cluster->size = 1;
    server.cluster->todo_before_sleep = 0;
    server.cluster->nodes = dictCreate(&clusterNodesDictType,NULL);
    server.cluster->nodes_black_list =
        dictCreate(&clusterNodesBlackListDictType,NULL);
    server.cluster->failover_auth_time = 0;
    server.cluster->failover_auth_count = 0;
    server.cluster->failover_auth_rank = 0;
    server.cluster->failover_auth_epoch = 0;
    server.cluster->cant_failover_reason = CLUSTER_CANT_FAILOVER_NONE;
    server.cluster->lastVoteEpoch = 0;
    for (int i = 0; i < CLUSTERMSG_TYPE_COUNT; i++) {
        server.cluster->stats_bus_messages_sent[i] = 0;
        server.cluster->stats_bus_messages_received[i] = 0;
    }
    server.cluster->stats_pfail_nodes = 0;
    memset(server.cluster->slots,0, sizeof(server.cluster->slots));
    clusterCloseAllSlots();

    /* Lock the cluster config file to make sure every node uses
     * its own nodes.conf. */
    if (clusterLockConfig(server.cluster_configfile) == C_ERR)
        exit(1);

    /* Load or create a new nodes configuration. */
    if (clusterLoadConfig(server.cluster_configfile) == C_ERR) {
        /* No configuration found. We will just use the random name provided
         * by the createClusterNode() function. */
        myself = server.cluster->myself =
            createClusterNode(NULL,CLUSTER_NODE_MYSELF|CLUSTER_NODE_MASTER);
        serverLog(LL_NOTICE,"No cluster configuration found, I'm %.40s",
            myself->name);
        clusterAddNode(myself);
        saveconf = 1;
    }
    if (saveconf) clusterSaveConfigOrDie(1);

    /* We need a listening TCP port for our cluster messaging needs. */
    server.cfd_count = 0;

    /* Port sanity check II
     * The other handshake port check is triggered too late to stop
     * us from trying to use a too-high cluster port number. */
    int port = server.tls_cluster ? server.tls_port : server.port;
    if (port > (65535-CLUSTER_PORT_INCR)) {
        serverLog(LL_WARNING, "Redis port number too high. "
                   "Cluster communication port is 10,000 port "
                   "numbers higher than your Redis port. "
                   "Your Redis port number must be "
                   "lower than 55535.");
        exit(1);
    }
    if (listenToPort(port+CLUSTER_PORT_INCR,
        server.cfd,&server.cfd_count) == C_ERR)
    {
        exit(1);
    } else {
        int j;

        for (j = 0; j < server.cfd_count; j++) {
            if (aeCreateFileEvent(server.el, server.cfd[j], AE_READABLE,
                clusterAcceptHandler, NULL) == AE_ERR)
                    serverPanic("Unrecoverable error creating Redis Cluster "
                                "file event.");
        }
    }

    /* The slots -> keys map is a radix tree. Initialize it here. */
    server.cluster->slots_to_keys = raxNew();
    memset(server.cluster->slots_keys_count,0,
           sizeof(server.cluster->slots_keys_count));

    /* Set myself->port / cport to my listening ports, we'll just need to
     * discover the IP address via MEET messages. */
    myself->port = port;
    myself->cport = port+CLUSTER_PORT_INCR;
    if (server.cluster_announce_port)
        myself->port = server.cluster_announce_port;
    if (server.cluster_announce_bus_port)
        myself->cport = server.cluster_announce_bus_port;

    server.cluster->mf_end = 0;
    resetManualFailover();
    clusterUpdateMyselfFlags();
}

/* Reset a node performing a soft or hard reset:
 *
 * 1) All other nodes are forget.
 * 2) All the assigned / open slots are released.
 * 3) If the node is a slave, it turns into a master.
 * 5) Only for hard reset: a new Node ID is generated.
 * 6) Only for hard reset: currentEpoch and configEpoch are set to 0.
 * 7) The new configuration is saved and the cluster state updated.
 * 8) If the node was a slave, the whole data set is flushed away. */
void clusterReset(int hard) {
    dictIterator *di;
    dictEntry *de;
    int j;

    /* Turn into master. */
    if (nodeIsSlave(myself)) {
        clusterSetNodeAsMaster(myself);
        replicationUnsetMaster();
        emptyDb(-1,EMPTYDB_NO_FLAGS,NULL);
    }

    /* Close slots, reset manual failover state. */
    clusterCloseAllSlots();
    resetManualFailover();

    /* Unassign all the slots. */
    for (j = 0; j < CLUSTER_SLOTS; j++) clusterDelSlot(j);

    /* Forget all the nodes, but myself. */
    di = dictGetSafeIterator(server.cluster->nodes);
    while((de = dictNext(di)) != NULL) {
        clusterNode *node = dictGetVal(de);

        if (node == myself) continue;
        clusterDelNode(node);
    }
    dictReleaseIterator(di);

    /* Hard reset only: set epochs to 0, change node ID. */
    if (hard) {
        sds oldname;

        server.cluster->currentEpoch = 0;
        server.cluster->lastVoteEpoch = 0;
        myself->configEpoch = 0;
        serverLog(LL_WARNING, "configEpoch set to 0 via CLUSTER RESET HARD");

        /* To change the Node ID we need to remove the old name from the
         * nodes table, change the ID, and re-add back with new name. */
        oldname = sdsnewlen(myself->name, CLUSTER_NAMELEN);
        dictDelete(server.cluster->nodes,oldname);
        sdsfree(oldname);
        getRandomHexChars(myself->name, CLUSTER_NAMELEN);
        clusterAddNode(myself);
        serverLog(LL_NOTICE,"Node hard reset, now I'm %.40s", myself->name);
    }

    /* Make sure to persist the new config and update the state. */
    clusterDoBeforeSleep(CLUSTER_TODO_SAVE_CONFIG|
                         CLUSTER_TODO_UPDATE_STATE|
                         CLUSTER_TODO_FSYNC_CONFIG);
}

/* -----------------------------------------------------------------------------
 * CLUSTER communication link
 * -------------------------------------------------------------------------- */

clusterLink *createClusterLink(clusterNode *node) {
    clusterLink *link = zmalloc(sizeof(*link));
    link->ctime = mstime();
    link->sndbuf = sdsempty();
    link->rcvbuf = sdsempty();
    link->node = node;
    link->conn = NULL;
    return link;
}

/* Free a cluster link, but does not free the associated node of course.
 * This function will just make sure that the original node associated
 * with this link will have the 'link' field set to NULL. */
void freeClusterLink(clusterLink *link) {
    if (link->conn) {
        connClose(link->conn);
        link->conn = NULL;
    }
    sdsfree(link->sndbuf);
    sdsfree(link->rcvbuf);
    if (link->node)
        link->node->link = NULL;
    zfree(link);
}

static void clusterConnAcceptHandler(connection *conn) {
    clusterLink *link;

    if (connGetState(conn) != CONN_STATE_CONNECTED) {
        serverLog(LL_VERBOSE,
                "Error accepting cluster node connection: %s", connGetLastError(conn));
        connClose(conn);
        return;
    }

    /* Create a link object we use to handle the connection.
     * It gets passed to the readable handler when data is available.
     * Initiallly the link->node pointer is set to NULL as we don't know
     * which node is, but the right node is references once we know the
     * node identity. */
    link = createClusterLink(NULL);
    link->conn = conn;
    connSetPrivateData(conn, link);

    /* Register read handler */
    connSetReadHandler(conn, clusterReadHandler);
}

#define MAX_CLUSTER_ACCEPTS_PER_CALL 1000
void clusterAcceptHandler(aeEventLoop *el, int fd, void *privdata, int mask) {
    int cport, cfd;
    int max = MAX_CLUSTER_ACCEPTS_PER_CALL;
    char cip[NET_IP_STR_LEN];
    UNUSED(el);
    UNUSED(mask);
    UNUSED(privdata);

    /* If the server is starting up, don't accept cluster connections:
     * UPDATE messages may interact with the database content. */
    if (server.masterhost == NULL && server.loading) return;

    while(max--) {
        cfd = anetTcpAccept(server.neterr, fd, cip, sizeof(cip), &cport);
        if (cfd == ANET_ERR) {
            if (errno != EWOULDBLOCK)
                serverLog(LL_VERBOSE,
                    "Error accepting cluster node: %s", server.neterr);
            return;
        }

        connection *conn = server.tls_cluster ? connCreateAcceptedTLS(cfd,1) : connCreateAcceptedSocket(cfd);
        connNonBlock(conn);
        connEnableTcpNoDelay(conn);

        /* Use non-blocking I/O for cluster messages. */
        serverLog(LL_VERBOSE,"Accepting cluster node connection from %s:%d", cip, cport);

        /* Accept the connection now.  connAccept() may call our handler directly
         * or schedule it for later depending on connection implementation.
         */
        if (connAccept(conn, clusterConnAcceptHandler) == C_ERR) {
            serverLog(LL_VERBOSE,
                    "Error accepting cluster node connection: %s",
                    connGetLastError(conn));
            connClose(conn);
            return;
        }
    }
}

/* -----------------------------------------------------------------------------
 * Key space handling
 * -------------------------------------------------------------------------- */

/* We have 16384 hash slots. The hash slot of a given key is obtained
 * as the least significant 14 bits of the crc16 of the key.
 *
 * However if the key contains the {...} pattern, only the part between
 * { and } is hashed. This may be useful in the future to force certain
 * keys to be in the same node (assuming no resharding is in progress). */
unsigned int keyHashSlot(char *key, int keylen) {
    int s, e; /* start-end indexes of { and } */

    for (s = 0; s < keylen; s++)
        if (key[s] == '{') break;

    /* No '{' ? Hash the whole key. This is the base case. */
    if (s == keylen) return crc16(key,keylen) & 0x3FFF;

    /* '{' found? Check if we have the corresponding '}'. */
    for (e = s+1; e < keylen; e++)
        if (key[e] == '}') break;

    /* No '}' or nothing between {} ? Hash the whole key. */
    if (e == keylen || e == s+1) return crc16(key,keylen) & 0x3FFF;

    /* If we are here there is both a { and a } on its right. Hash
     * what is in the middle between { and }. */
    return crc16(key+s+1,e-s-1) & 0x3FFF;
}

/* -----------------------------------------------------------------------------
 * CLUSTER node API
 * -------------------------------------------------------------------------- */

/* Create a new cluster node, with the specified flags.
 * If "nodename" is NULL this is considered a first handshake and a random
 * node name is assigned to this node (it will be fixed later when we'll
 * receive the first pong).
 *
 * The node is created and returned to the user, but it is not automatically
 * added to the nodes hash table. */
clusterNode *createClusterNode(char *nodename, int flags) {
    clusterNode *node = zmalloc(sizeof(*node));

    if (nodename)
        memcpy(node->name, nodename, CLUSTER_NAMELEN);
    else
        getRandomHexChars(node->name, CLUSTER_NAMELEN);
    node->ctime = mstime();
    node->configEpoch = 0;
    node->flags = flags;
    memset(node->slots,0,sizeof(node->slots));
    node->numslots = 0;
    node->numslaves = 0;
    node->slaves = NULL;
    node->slaveof = NULL;
    node->ping_sent = node->pong_received = 0;
    node->fail_time = 0;
    node->link = NULL;
    memset(node->ip,0,sizeof(node->ip));
    node->port = 0;
    node->cport = 0;
    node->fail_reports = listCreate();
    node->voted_time = 0;
    node->orphaned_time = 0;
    node->repl_offset_time = 0;
    node->repl_offset = 0;
    listSetFreeMethod(node->fail_reports,zfree);
    return node;
}

/* This function is called every time we get a failure report from a node.
 * The side effect is to populate the fail_reports list (or to update
 * the timestamp of an existing report).
 *
 * 'failing' is the node that is in failure state according to the
 * 'sender' node.
 *
 * The function returns 0 if it just updates a timestamp of an existing
 * failure report from the same sender. 1 is returned if a new failure
 * report is created. */
int clusterNodeAddFailureReport(clusterNode *failing, clusterNode *sender) {
    list *l = failing->fail_reports;
    listNode *ln;
    listIter li;
    clusterNodeFailReport *fr;

    /* If a failure report from the same sender already exists, just update
     * the timestamp. */
    listRewind(l,&li);
    while ((ln = listNext(&li)) != NULL) {
        fr = ln->value;
        if (fr->node == sender) {
            fr->time = mstime();
            return 0;
        }
    }

    /* Otherwise create a new report. */
    fr = zmalloc(sizeof(*fr));
    fr->node = sender;
    fr->time = mstime();
    listAddNodeTail(l,fr);
    return 1;
}

/* Remove failure reports that are too old, where too old means reasonably
 * older than the global node timeout. Note that anyway for a node to be
 * flagged as FAIL we need to have a local PFAIL state that is at least
 * older than the global node timeout, so we don't just trust the number
 * of failure reports from other nodes. */
void clusterNodeCleanupFailureReports(clusterNode *node) {
    list *l = node->fail_reports;
    listNode *ln;
    listIter li;
    clusterNodeFailReport *fr;
    mstime_t maxtime = server.cluster_node_timeout *
                     CLUSTER_FAIL_REPORT_VALIDITY_MULT;
    mstime_t now = mstime();

    listRewind(l,&li);
    while ((ln = listNext(&li)) != NULL) {
        fr = ln->value;
        if (now - fr->time > maxtime) listDelNode(l,ln);
    }
}

/* Remove the failing report for 'node' if it was previously considered
 * failing by 'sender'. This function is called when a node informs us via
 * gossip that a node is OK from its point of view (no FAIL or PFAIL flags).
 *
 * Note that this function is called relatively often as it gets called even
 * when there are no nodes failing, and is O(N), however when the cluster is
 * fine the failure reports list is empty so the function runs in constant
 * time.
 *
 * The function returns 1 if the failure report was found and removed.
 * Otherwise 0 is returned. */
int clusterNodeDelFailureReport(clusterNode *node, clusterNode *sender) {
    list *l = node->fail_reports;
    listNode *ln;
    listIter li;
    clusterNodeFailReport *fr;

    /* Search for a failure report from this sender. */
    listRewind(l,&li);
    while ((ln = listNext(&li)) != NULL) {
        fr = ln->value;
        if (fr->node == sender) break;
    }
    if (!ln) return 0; /* No failure report from this sender. */

    /* Remove the failure report. */
    listDelNode(l,ln);
    clusterNodeCleanupFailureReports(node);
    return 1;
}

/* Return the number of external nodes that believe 'node' is failing,
 * not including this node, that may have a PFAIL or FAIL state for this
 * node as well. */
int clusterNodeFailureReportsCount(clusterNode *node) {
    clusterNodeCleanupFailureReports(node);
    return listLength(node->fail_reports);
}

int clusterNodeRemoveSlave(clusterNode *master, clusterNode *slave) {
    int j;

    for (j = 0; j < master->numslaves; j++) {
        if (master->slaves[j] == slave) {
            if ((j+1) < master->numslaves) {
                int remaining_slaves = (master->numslaves - j) - 1;
                memmove(master->slaves+j,master->slaves+(j+1),
                        (sizeof(*master->slaves) * remaining_slaves));
            }
            master->numslaves--;
            if (master->numslaves == 0)
                master->flags &= ~CLUSTER_NODE_MIGRATE_TO;
            return C_OK;
        }
    }
    return C_ERR;
}

int clusterNodeAddSlave(clusterNode *master, clusterNode *slave) {
    int j;

    /* If it's already a slave, don't add it again. */
    for (j = 0; j < master->numslaves; j++)
        if (master->slaves[j] == slave) return C_ERR;
    master->slaves = zrealloc(master->slaves,
        sizeof(clusterNode*)*(master->numslaves+1));
    master->slaves[master->numslaves] = slave;
    master->numslaves++;
    master->flags |= CLUSTER_NODE_MIGRATE_TO;
    return C_OK;
}

int clusterCountNonFailingSlaves(clusterNode *n) {
    int j, okslaves = 0;

    for (j = 0; j < n->numslaves; j++)
        if (!nodeFailed(n->slaves[j])) okslaves++;
    return okslaves;
}

/* Low level cleanup of the node structure. Only called by clusterDelNode(). */
void freeClusterNode(clusterNode *n) {
    sds nodename;
    int j;

    /* If the node has associated slaves, we have to set
     * all the slaves->slaveof fields to NULL (unknown). */
    for (j = 0; j < n->numslaves; j++)
        n->slaves[j]->slaveof = NULL;

    /* Remove this node from the list of slaves of its master. */
    if (nodeIsSlave(n) && n->slaveof) clusterNodeRemoveSlave(n->slaveof,n);

    /* Unlink from the set of nodes. */
    nodename = sdsnewlen(n->name, CLUSTER_NAMELEN);
    serverAssert(dictDelete(server.cluster->nodes,nodename) == DICT_OK);
    sdsfree(nodename);

    /* Release link and associated data structures. */
    if (n->link) freeClusterLink(n->link);
    listRelease(n->fail_reports);
    zfree(n->slaves);
    zfree(n);
}

/* Add a node to the nodes hash table */
int clusterAddNode(clusterNode *node) {
    int retval;

    retval = dictAdd(server.cluster->nodes,
            sdsnewlen(node->name,CLUSTER_NAMELEN), node);
    return (retval == DICT_OK) ? C_OK : C_ERR;
}

/* Remove a node from the cluster. The functio performs the high level
 * cleanup, calling freeClusterNode() for the low level cleanup.
 * Here we do the following:
 *
 * 1) Mark all the slots handled by it as unassigned.
 * 2) Remove all the failure reports sent by this node and referenced by
 *    other nodes.
 * 3) Free the node with freeClusterNode() that will in turn remove it
 *    from the hash table and from the list of slaves of its master, if
 *    it is a slave node.
 */
void clusterDelNode(clusterNode *delnode) {
    int j;
    dictIterator *di;
    dictEntry *de;

    /* 1) Mark slots as unassigned. */
    for (j = 0; j < CLUSTER_SLOTS; j++) {
        if (server.cluster->importing_slots_from[j] == delnode)
            server.cluster->importing_slots_from[j] = NULL;
        if (server.cluster->migrating_slots_to[j] == delnode)
            server.cluster->migrating_slots_to[j] = NULL;
        if (server.cluster->slots[j] == delnode)
            clusterDelSlot(j);
    }

    /* 2) Remove failure reports. */
    di = dictGetSafeIterator(server.cluster->nodes);
    while((de = dictNext(di)) != NULL) {
        clusterNode *node = dictGetVal(de);

        if (node == delnode) continue;
        clusterNodeDelFailureReport(node,delnode);
    }
    dictReleaseIterator(di);

    /* 3) Free the node, unlinking it from the cluster. */
    freeClusterNode(delnode);
}

/* Node lookup by name */
clusterNode *clusterLookupNode(const char *name) {
    sds s = sdsnewlen(name, CLUSTER_NAMELEN);
    dictEntry *de;

    de = dictFind(server.cluster->nodes,s);
    sdsfree(s);
    if (de == NULL) return NULL;
    return dictGetVal(de);
}

/* This is only used after the handshake. When we connect a given IP/PORT
 * as a result of CLUSTER MEET we don't have the node name yet, so we
 * pick a random one, and will fix it when we receive the PONG request using
 * this function. */
void clusterRenameNode(clusterNode *node, char *newname) {
    int retval;
    sds s = sdsnewlen(node->name, CLUSTER_NAMELEN);

    serverLog(LL_DEBUG,"Renaming node %.40s into %.40s",
        node->name, newname);
    retval = dictDelete(server.cluster->nodes, s);
    sdsfree(s);
    serverAssert(retval == DICT_OK);
    memcpy(node->name, newname, CLUSTER_NAMELEN);
    clusterAddNode(node);
}

/* -----------------------------------------------------------------------------
 * CLUSTER config epoch handling
 * -------------------------------------------------------------------------- */

/* Return the greatest configEpoch found in the cluster, or the current
 * epoch if greater than any node configEpoch. */
uint64_t clusterGetMaxEpoch(void) {
    uint64_t max = 0;
    dictIterator *di;
    dictEntry *de;

    di = dictGetSafeIterator(server.cluster->nodes);
    while((de = dictNext(di)) != NULL) {
        clusterNode *node = dictGetVal(de);
        if (node->configEpoch > max) max = node->configEpoch;
    }
    dictReleaseIterator(di);
    if (max < server.cluster->currentEpoch) max = server.cluster->currentEpoch;
    return max;
}

/* If this node epoch is zero or is not already the greatest across the
 * cluster (from the POV of the local configuration), this function will:
 *
 * 1) Generate a new config epoch, incrementing the current epoch.
 * 2) Assign the new epoch to this node, WITHOUT any consensus.
 * 3) Persist the configuration on disk before sending packets with the
 *    new configuration.
 *
 * If the new config epoch is generated and assigend, C_OK is returned,
 * otherwise C_ERR is returned (since the node has already the greatest
 * configuration around) and no operation is performed.
 *
 * Important note: this function violates the principle that config epochs
 * should be generated with consensus and should be unique across the cluster.
 * However Redis Cluster uses this auto-generated new config epochs in two
 * cases:
 *
 * 1) When slots are closed after importing. Otherwise resharding would be
 *    too expensive.
 * 2) When CLUSTER FAILOVER is called with options that force a slave to
 *    failover its master even if there is not master majority able to
 *    create a new configuration epoch.
 *
 * Redis Cluster will not explode using this function, even in the case of
 * a collision between this node and another node, generating the same
 * configuration epoch unilaterally, because the config epoch conflict
 * resolution algorithm will eventually move colliding nodes to different
 * config epochs. However using this function may violate the "last failover
 * wins" rule, so should only be used with care. */
int clusterBumpConfigEpochWithoutConsensus(void) {
    uint64_t maxEpoch = clusterGetMaxEpoch();

    if (myself->configEpoch == 0 ||
        myself->configEpoch != maxEpoch)
    {
        server.cluster->currentEpoch++;
        myself->configEpoch = server.cluster->currentEpoch;
        clusterDoBeforeSleep(CLUSTER_TODO_SAVE_CONFIG|
                             CLUSTER_TODO_FSYNC_CONFIG);
        serverLog(LL_WARNING,
            "New configEpoch set to %llu",
            (unsigned long long) myself->configEpoch);
        return C_OK;
    } else {
        return C_ERR;
    }
}

/* This function is called when this node is a master, and we receive from
 * another master a configuration epoch that is equal to our configuration
 * epoch.
 *
 * BACKGROUND
 *
 * It is not possible that different slaves get the same config
 * epoch during a failover election, because the slaves need to get voted
 * by a majority. However when we perform a manual resharding of the cluster
 * the node will assign a configuration epoch to itself without to ask
 * for agreement. Usually resharding happens when the cluster is working well
 * and is supervised by the sysadmin, however it is possible for a failover
 * to happen exactly while the node we are resharding a slot to assigns itself
 * a new configuration epoch, but before it is able to propagate it.
 *
 * So technically it is possible in this condition that two nodes end with
 * the same configuration epoch.
 *
 * Another possibility is that there are bugs in the implementation causing
 * this to happen.
 *
 * Moreover when a new cluster is created, all the nodes start with the same
 * configEpoch. This collision resolution code allows nodes to automatically
 * end with a different configEpoch at startup automatically.
 *
 * In all the cases, we want a mechanism that resolves this issue automatically
 * as a safeguard. The same configuration epoch for masters serving different
 * set of slots is not harmful, but it is if the nodes end serving the same
 * slots for some reason (manual errors or software bugs) without a proper
 * failover procedure.
 *
 * In general we want a system that eventually always ends with different
 * masters having different configuration epochs whatever happened, since
 * nothign is worse than a split-brain condition in a distributed system.
 *
 * BEHAVIOR
 *
 * When this function gets called, what happens is that if this node
 * has the lexicographically smaller Node ID compared to the other node
 * with the conflicting epoch (the 'sender' node), it will assign itself
 * the greatest configuration epoch currently detected among nodes plus 1.
 *
 * This means that even if there are multiple nodes colliding, the node
 * with the greatest Node ID never moves forward, so eventually all the nodes
 * end with a different configuration epoch.
 */
void clusterHandleConfigEpochCollision(clusterNode *sender) {
    /* Prerequisites: nodes have the same configEpoch and are both masters. */
    if (sender->configEpoch != myself->configEpoch ||
        !nodeIsMaster(sender) || !nodeIsMaster(myself)) return;
    /* Don't act if the colliding node has a smaller Node ID. */
    if (memcmp(sender->name,myself->name,CLUSTER_NAMELEN) <= 0) return;
    /* Get the next ID available at the best of this node knowledge. */
    server.cluster->currentEpoch++;
    myself->configEpoch = server.cluster->currentEpoch;
    clusterSaveConfigOrDie(1);
    serverLog(LL_VERBOSE,
        "WARNING: configEpoch collision with node %.40s."
        " configEpoch set to %llu",
        sender->name,
        (unsigned long long) myself->configEpoch);
}

/* -----------------------------------------------------------------------------
 * CLUSTER nodes blacklist
 *
 * The nodes blacklist is just a way to ensure that a given node with a given
 * Node ID is not readded before some time elapsed (this time is specified
 * in seconds in CLUSTER_BLACKLIST_TTL).
 *
 * This is useful when we want to remove a node from the cluster completely:
 * when CLUSTER FORGET is called, it also puts the node into the blacklist so
 * that even if we receive gossip messages from other nodes that still remember
 * about the node we want to remove, we don't re-add it before some time.
 *
 * Currently the CLUSTER_BLACKLIST_TTL is set to 1 minute, this means
 * that redis-trib has 60 seconds to send CLUSTER FORGET messages to nodes
 * in the cluster without dealing with the problem of other nodes re-adding
 * back the node to nodes we already sent the FORGET command to.
 *
 * The data structure used is a hash table with an sds string representing
 * the node ID as key, and the time when it is ok to re-add the node as
 * value.
 * -------------------------------------------------------------------------- */

#define CLUSTER_BLACKLIST_TTL 60      /* 1 minute. */


/* Before of the addNode() or Exists() operations we always remove expired
 * entries from the black list. This is an O(N) operation but it is not a
 * problem since add / exists operations are called very infrequently and
 * the hash table is supposed to contain very little elements at max.
 * However without the cleanup during long uptimes and with some automated
 * node add/removal procedures, entries could accumulate. */
void clusterBlacklistCleanup(void) {
    dictIterator *di;
    dictEntry *de;

    di = dictGetSafeIterator(server.cluster->nodes_black_list);
    while((de = dictNext(di)) != NULL) {
        int64_t expire = dictGetUnsignedIntegerVal(de);

        if (expire < server.unixtime)
            dictDelete(server.cluster->nodes_black_list,dictGetKey(de));
    }
    dictReleaseIterator(di);
}

/* Cleanup the blacklist and add a new node ID to the black list. */
void clusterBlacklistAddNode(clusterNode *node) {
    dictEntry *de;
    sds id = sdsnewlen(node->name,CLUSTER_NAMELEN);

    clusterBlacklistCleanup();
    if (dictAdd(server.cluster->nodes_black_list,id,NULL) == DICT_OK) {
        /* If the key was added, duplicate the sds string representation of
         * the key for the next lookup. We'll free it at the end. */
        id = sdsdup(id);
    }
    de = dictFind(server.cluster->nodes_black_list,id);
    dictSetUnsignedIntegerVal(de,time(NULL)+CLUSTER_BLACKLIST_TTL);
    sdsfree(id);
}

/* Return non-zero if the specified node ID exists in the blacklist.
 * You don't need to pass an sds string here, any pointer to 40 bytes
 * will work. */
int clusterBlacklistExists(char *nodeid) {
    sds id = sdsnewlen(nodeid,CLUSTER_NAMELEN);
    int retval;

    clusterBlacklistCleanup();
    retval = dictFind(server.cluster->nodes_black_list,id) != NULL;
    sdsfree(id);
    return retval;
}

/* -----------------------------------------------------------------------------
 * CLUSTER messages exchange - PING/PONG and gossip
 * -------------------------------------------------------------------------- */

/* This function checks if a given node should be marked as FAIL.
 * It happens if the following conditions are met:
 *
 * 1) We received enough failure reports from other master nodes via gossip.
 *    Enough means that the majority of the masters signaled the node is
 *    down recently.
 * 2) We believe this node is in PFAIL state.
 *
 * If a failure is detected we also inform the whole cluster about this
 * event trying to force every other node to set the FAIL flag for the node.
 *
 * Note that the form of agreement used here is weak, as we collect the majority
 * of masters state during some time, and even if we force agreement by
 * propagating the FAIL message, because of partitions we may not reach every
 * node. However:
 *
 * 1) Either we reach the majority and eventually the FAIL state will propagate
 *    to all the cluster.
 * 2) Or there is no majority so no slave promotion will be authorized and the
 *    FAIL flag will be cleared after some time.
 */
void markNodeAsFailingIfNeeded(clusterNode *node) {
    int failures;
    int needed_quorum = (server.cluster->size / 2) + 1;

    if (!nodeTimedOut(node)) return; /* We can reach it. */
    if (nodeFailed(node)) return; /* Already FAILing. */

    failures = clusterNodeFailureReportsCount(node);
    /* Also count myself as a voter if I'm a master. */
    if (nodeIsMaster(myself)) failures++;
    if (failures < needed_quorum) return; /* No weak agreement from masters. */

    serverLog(LL_NOTICE,
        "Marking node %.40s as failing (quorum reached).", node->name);

    /* Mark the node as failing. */
    node->flags &= ~CLUSTER_NODE_PFAIL;
    node->flags |= CLUSTER_NODE_FAIL;
    node->fail_time = mstime();

    /* Broadcast the failing node name to everybody, forcing all the other
     * reachable nodes to flag the node as FAIL. */
    if (nodeIsMaster(myself)) clusterSendFail(node->name);
    clusterDoBeforeSleep(CLUSTER_TODO_UPDATE_STATE|CLUSTER_TODO_SAVE_CONFIG);
}

/* This function is called only if a node is marked as FAIL, but we are able
 * to reach it again. It checks if there are the conditions to undo the FAIL
 * state. */
void clearNodeFailureIfNeeded(clusterNode *node) {
    mstime_t now = mstime();

    serverAssert(nodeFailed(node));

    /* For slaves we always clear the FAIL flag if we can contact the
     * node again. */
    if (nodeIsSlave(node) || node->numslots == 0) {
        serverLog(LL_NOTICE,
            "Clear FAIL state for node %.40s: %s is reachable again.",
                node->name,
                nodeIsSlave(node) ? "replica" : "master without slots");
        node->flags &= ~CLUSTER_NODE_FAIL;
        clusterDoBeforeSleep(CLUSTER_TODO_UPDATE_STATE|CLUSTER_TODO_SAVE_CONFIG);
    }

    /* If it is a master and...
     * 1) The FAIL state is old enough.
     * 2) It is yet serving slots from our point of view (not failed over).
     * Apparently no one is going to fix these slots, clear the FAIL flag. */
    if (nodeIsMaster(node) && node->numslots > 0 &&
        (now - node->fail_time) >
        (server.cluster_node_timeout * CLUSTER_FAIL_UNDO_TIME_MULT))
    {
        serverLog(LL_NOTICE,
            "Clear FAIL state for node %.40s: is reachable again and nobody is serving its slots after some time.",
                node->name);
        node->flags &= ~CLUSTER_NODE_FAIL;
        clusterDoBeforeSleep(CLUSTER_TODO_UPDATE_STATE|CLUSTER_TODO_SAVE_CONFIG);
    }
}

/* Return true if we already have a node in HANDSHAKE state matching the
 * specified ip address and port number. This function is used in order to
 * avoid adding a new handshake node for the same address multiple times. */
int clusterHandshakeInProgress(char *ip, int port, int cport) {
    dictIterator *di;
    dictEntry *de;

    di = dictGetSafeIterator(server.cluster->nodes);
    while((de = dictNext(di)) != NULL) {
        clusterNode *node = dictGetVal(de);

        if (!nodeInHandshake(node)) continue;
        if (!strcasecmp(node->ip,ip) &&
            node->port == port &&
            node->cport == cport) break;
    }
    dictReleaseIterator(di);
    return de != NULL;
}

/* Start an handshake with the specified address if there is not one
 * already in progress. Returns non-zero if the handshake was actually
 * started. On error zero is returned and errno is set to one of the
 * following values:
 *
 * EAGAIN - There is already an handshake in progress for this address.
 * EINVAL - IP or port are not valid. */
int clusterStartHandshake(char *ip, int port, int cport) {
    clusterNode *n;
    char norm_ip[NET_IP_STR_LEN];
    struct sockaddr_storage sa;

    /* IP sanity check */
    if (inet_pton(AF_INET,ip,
            &(((struct sockaddr_in *)&sa)->sin_addr)))
    {
        sa.ss_family = AF_INET;
    } else if (inet_pton(AF_INET6,ip,
            &(((struct sockaddr_in6 *)&sa)->sin6_addr)))
    {
        sa.ss_family = AF_INET6;
    } else {
        errno = EINVAL;
        return 0;
    }

    /* Port sanity check */
    if (port <= 0 || port > 65535 || cport <= 0 || cport > 65535) {
        errno = EINVAL;
        return 0;
    }

    /* Set norm_ip as the normalized string representation of the node
     * IP address. */
    memset(norm_ip,0,NET_IP_STR_LEN);
    if (sa.ss_family == AF_INET)
        inet_ntop(AF_INET,
            (void*)&(((struct sockaddr_in *)&sa)->sin_addr),
            norm_ip,NET_IP_STR_LEN);
    else
        inet_ntop(AF_INET6,
            (void*)&(((struct sockaddr_in6 *)&sa)->sin6_addr),
            norm_ip,NET_IP_STR_LEN);

    if (clusterHandshakeInProgress(norm_ip,port,cport)) {
        errno = EAGAIN;
        return 0;
    }

    /* Add the node with a random address (NULL as first argument to
     * createClusterNode()). Everything will be fixed during the
     * handshake. */
    n = createClusterNode(NULL,CLUSTER_NODE_HANDSHAKE|CLUSTER_NODE_MEET);
    memcpy(n->ip,norm_ip,sizeof(n->ip));
    n->port = port;
    n->cport = cport;
    clusterAddNode(n);
    return 1;
}

/* Process the gossip section of PING or PONG packets.
 * Note that this function assumes that the packet is already sanity-checked
 * by the caller, not in the content of the gossip section, but in the
 * length. */
void clusterProcessGossipSection(clusterMsg *hdr, clusterLink *link) {
    uint16_t count = ntohs(hdr->count);
    clusterMsgDataGossip *g = (clusterMsgDataGossip*) hdr->data.ping.gossip;
    clusterNode *sender = link->node ? link->node : clusterLookupNode(hdr->sender);

    while(count--) {
        uint16_t flags = ntohs(g->flags);
        clusterNode *node;
        sds ci;

        if (server.verbosity == LL_DEBUG) {
            ci = representClusterNodeFlags(sdsempty(), flags);
            serverLog(LL_DEBUG,"GOSSIP %.40s %s:%d@%d %s",
                g->nodename,
                g->ip,
                ntohs(g->port),
                ntohs(g->cport),
                ci);
            sdsfree(ci);
        }

        /* Update our state accordingly to the gossip sections */
        node = clusterLookupNode(g->nodename);
        if (node) {
            /* We already know this node.
               Handle failure reports, only when the sender is a master. */
            if (sender && nodeIsMaster(sender) && node != myself) {
                if (flags & (CLUSTER_NODE_FAIL|CLUSTER_NODE_PFAIL)) {
                    if (clusterNodeAddFailureReport(node,sender)) {
                        serverLog(LL_VERBOSE,
                            "Node %.40s reported node %.40s as not reachable.",
                            sender->name, node->name);
                    }
                    markNodeAsFailingIfNeeded(node);
                } else {
                    if (clusterNodeDelFailureReport(node,sender)) {
                        serverLog(LL_VERBOSE,
                            "Node %.40s reported node %.40s is back online.",
                            sender->name, node->name);
                    }
                }
            }

            /* If from our POV the node is up (no failure flags are set),
             * we have no pending ping for the node, nor we have failure
             * reports for this node, update the last pong time with the
             * one we see from the other nodes. */
            if (!(flags & (CLUSTER_NODE_FAIL|CLUSTER_NODE_PFAIL)) &&
                node->ping_sent == 0 &&
                clusterNodeFailureReportsCount(node) == 0)
            {
                mstime_t pongtime = ntohl(g->pong_received);
                pongtime *= 1000; /* Convert back to milliseconds. */

                /* Replace the pong time with the received one only if
                 * it's greater than our view but is not in the future
                 * (with 500 milliseconds tolerance) from the POV of our
                 * clock. */
                if (pongtime <= (server.mstime+500) &&
                    pongtime > node->pong_received)
                {
                    node->pong_received = pongtime;
                }
            }

            /* If we already know this node, but it is not reachable, and
             * we see a different address in the gossip section of a node that
             * can talk with this other node, update the address, disconnect
             * the old link if any, so that we'll attempt to connect with the
             * new address. */
            if (node->flags & (CLUSTER_NODE_FAIL|CLUSTER_NODE_PFAIL) &&
                !(flags & CLUSTER_NODE_NOADDR) &&
                !(flags & (CLUSTER_NODE_FAIL|CLUSTER_NODE_PFAIL)) &&
                (strcasecmp(node->ip,g->ip) ||
                 node->port != ntohs(g->port) ||
                 node->cport != ntohs(g->cport)))
            {
                if (node->link) freeClusterLink(node->link);
                memcpy(node->ip,g->ip,NET_IP_STR_LEN);
                node->port = ntohs(g->port);
                node->cport = ntohs(g->cport);
                node->flags &= ~CLUSTER_NODE_NOADDR;
            }
        } else {
            /* If it's not in NOADDR state and we don't have it, we
             * start a handshake process against this IP/PORT pairs.
             *
             * Note that we require that the sender of this gossip message
             * is a well known node in our cluster, otherwise we risk
             * joining another cluster. */
            if (sender &&
                !(flags & CLUSTER_NODE_NOADDR) &&
                !clusterBlacklistExists(g->nodename))
            {
                clusterStartHandshake(g->ip,ntohs(g->port),ntohs(g->cport));
            }
        }

        /* Next node */
        g++;
    }
}

/* IP -> string conversion. 'buf' is supposed to at least be 46 bytes.
 * If 'announced_ip' length is non-zero, it is used instead of extracting
 * the IP from the socket peer address. */
void nodeIp2String(char *buf, clusterLink *link, char *announced_ip) {
    if (announced_ip[0] != '\0') {
        memcpy(buf,announced_ip,NET_IP_STR_LEN);
        buf[NET_IP_STR_LEN-1] = '\0'; /* We are not sure the input is sane. */
    } else {
        connPeerToString(link->conn, buf, NET_IP_STR_LEN, NULL);
    }
}

/* Update the node address to the IP address that can be extracted
 * from link->fd, or if hdr->myip is non empty, to the address the node
 * is announcing us. The port is taken from the packet header as well.
 *
 * If the address or port changed, disconnect the node link so that we'll
 * connect again to the new address.
 *
 * If the ip/port pair are already correct no operation is performed at
 * all.
 *
 * The function returns 0 if the node address is still the same,
 * otherwise 1 is returned. */
int nodeUpdateAddressIfNeeded(clusterNode *node, clusterLink *link,
                              clusterMsg *hdr)
{
    char ip[NET_IP_STR_LEN] = {0};
    int port = ntohs(hdr->port);
    int cport = ntohs(hdr->cport);

    /* We don't proceed if the link is the same as the sender link, as this
     * function is designed to see if the node link is consistent with the
     * symmetric link that is used to receive PINGs from the node.
     *
     * As a side effect this function never frees the passed 'link', so
     * it is safe to call during packet processing. */
    if (link == node->link) return 0;

    nodeIp2String(ip,link,hdr->myip);
    if (node->port == port && node->cport == cport &&
        strcmp(ip,node->ip) == 0) return 0;

    /* IP / port is different, update it. */
    memcpy(node->ip,ip,sizeof(ip));
    node->port = port;
    node->cport = cport;
    if (node->link) freeClusterLink(node->link);
    node->flags &= ~CLUSTER_NODE_NOADDR;
    serverLog(LL_WARNING,"Address updated for node %.40s, now %s:%d",
        node->name, node->ip, node->port);

    /* Check if this is our master and we have to change the
     * replication target as well. */
    if (nodeIsSlave(myself) && myself->slaveof == node)
        replicationSetMaster(node->ip, node->port);
    return 1;
}

/* Reconfigure the specified node 'n' as a master. This function is called when
 * a node that we believed to be a slave is now acting as master in order to
 * update the state of the node. */
void clusterSetNodeAsMaster(clusterNode *n) {
    if (nodeIsMaster(n)) return;

    if (n->slaveof) {
        clusterNodeRemoveSlave(n->slaveof,n);
        if (n != myself) n->flags |= CLUSTER_NODE_MIGRATE_TO;
    }
    n->flags &= ~CLUSTER_NODE_SLAVE;
    n->flags |= CLUSTER_NODE_MASTER;
    n->slaveof = NULL;

    /* Update config and state. */
    clusterDoBeforeSleep(CLUSTER_TODO_SAVE_CONFIG|
                         CLUSTER_TODO_UPDATE_STATE);
}

/* This function is called when we receive a master configuration via a
 * PING, PONG or UPDATE packet. What we receive is a node, a configEpoch of the
 * node, and the set of slots claimed under this configEpoch.
 *
 * What we do is to rebind the slots with newer configuration compared to our
 * local configuration, and if needed, we turn ourself into a replica of the
 * node (see the function comments for more info).
 *
 * The 'sender' is the node for which we received a configuration update.
 * Sometimes it is not actually the "Sender" of the information, like in the
 * case we receive the info via an UPDATE packet. */
void clusterUpdateSlotsConfigWith(clusterNode *sender, uint64_t senderConfigEpoch, unsigned char *slots) {
    int j;
    clusterNode *curmaster, *newmaster = NULL;
    /* The dirty slots list is a list of slots for which we lose the ownership
     * while having still keys inside. This usually happens after a failover
     * or after a manual cluster reconfiguration operated by the admin.
     *
     * If the update message is not able to demote a master to slave (in this
     * case we'll resync with the master updating the whole key space), we
     * need to delete all the keys in the slots we lost ownership. */
    uint16_t dirty_slots[CLUSTER_SLOTS];
    int dirty_slots_count = 0;

    /* Here we set curmaster to this node or the node this node
     * replicates to if it's a slave. In the for loop we are
     * interested to check if slots are taken away from curmaster. */
    curmaster = nodeIsMaster(myself) ? myself : myself->slaveof;

    if (sender == myself) {
        serverLog(LL_WARNING,"Discarding UPDATE message about myself.");
        return;
    }

    for (j = 0; j < CLUSTER_SLOTS; j++) {
        if (bitmapTestBit(slots,j)) {
            /* The slot is already bound to the sender of this message. */
            if (server.cluster->slots[j] == sender) continue;

            /* The slot is in importing state, it should be modified only
             * manually via redis-trib (example: a resharding is in progress
             * and the migrating side slot was already closed and is advertising
             * a new config. We still want the slot to be closed manually). */
            if (server.cluster->importing_slots_from[j]) continue;

            /* We rebind the slot to the new node claiming it if:
             * 1) The slot was unassigned or the new node claims it with a
             *    greater configEpoch.
             * 2) We are not currently importing the slot. */
            if (server.cluster->slots[j] == NULL ||
                server.cluster->slots[j]->configEpoch < senderConfigEpoch)
            {
                /* Was this slot mine, and still contains keys? Mark it as
                 * a dirty slot. */
                if (server.cluster->slots[j] == myself &&
                    countKeysInSlot(j) &&
                    sender != myself)
                {
                    dirty_slots[dirty_slots_count] = j;
                    dirty_slots_count++;
                }

                if (server.cluster->slots[j] == curmaster)
                    newmaster = sender;
                clusterDelSlot(j);
                clusterAddSlot(sender,j);
                clusterDoBeforeSleep(CLUSTER_TODO_SAVE_CONFIG|
                                     CLUSTER_TODO_UPDATE_STATE|
                                     CLUSTER_TODO_FSYNC_CONFIG);
            }
        }
    }

    /* After updating the slots configuration, don't do any actual change
     * in the state of the server if a module disabled Redis Cluster
     * keys redirections. */
    if (server.cluster_module_flags & CLUSTER_MODULE_FLAG_NO_REDIRECTION)
        return;

    /* If at least one slot was reassigned from a node to another node
     * with a greater configEpoch, it is possible that:
     * 1) We are a master left without slots. This means that we were
     *    failed over and we should turn into a replica of the new
     *    master.
     * 2) We are a slave and our master is left without slots. We need
     *    to replicate to the new slots owner. */
    if (newmaster && curmaster->numslots == 0) {
        serverLog(LL_WARNING,
            "Configuration change detected. Reconfiguring myself "
            "as a replica of %.40s", sender->name);
        clusterSetMaster(sender);
        clusterDoBeforeSleep(CLUSTER_TODO_SAVE_CONFIG|
                             CLUSTER_TODO_UPDATE_STATE|
                             CLUSTER_TODO_FSYNC_CONFIG);
    } else if (dirty_slots_count) {
        /* If we are here, we received an update message which removed
         * ownership for certain slots we still have keys about, but still
         * we are serving some slots, so this master node was not demoted to
         * a slave.
         *
         * In order to maintain a consistent state between keys and slots
         * we need to remove all the keys from the slots we lost. */
        for (j = 0; j < dirty_slots_count; j++)
            delKeysInSlot(dirty_slots[j]);
    }
}

/* When this function is called, there is a packet to process starting
 * at node->rcvbuf. Releasing the buffer is up to the caller, so this
 * function should just handle the higher level stuff of processing the
 * packet, modifying the cluster state if needed.
 *
 * The function returns 1 if the link is still valid after the packet
 * was processed, otherwise 0 if the link was freed since the packet
 * processing lead to some inconsistency error (for instance a PONG
 * received from the wrong sender ID). */
int clusterProcessPacket(clusterLink *link) {
    clusterMsg *hdr = (clusterMsg*) link->rcvbuf;
    uint32_t totlen = ntohl(hdr->totlen);
    uint16_t type = ntohs(hdr->type);

    if (type < CLUSTERMSG_TYPE_COUNT)
        server.cluster->stats_bus_messages_received[type]++;
    serverLog(LL_DEBUG,"--- Processing packet of type %d, %lu bytes",
        type, (unsigned long) totlen);

    /* Perform sanity checks */
    if (totlen < 16) return 1; /* At least signature, version, totlen, count. */
    if (totlen > sdslen(link->rcvbuf)) return 1;

    if (ntohs(hdr->ver) != CLUSTER_PROTO_VER) {
        /* Can't handle messages of different versions. */
        return 1;
    }

    uint16_t flags = ntohs(hdr->flags);
    uint64_t senderCurrentEpoch = 0, senderConfigEpoch = 0;
    clusterNode *sender;

    if (type == CLUSTERMSG_TYPE_PING || type == CLUSTERMSG_TYPE_PONG ||
        type == CLUSTERMSG_TYPE_MEET)
    {
        uint16_t count = ntohs(hdr->count);
        uint32_t explen; /* expected length of this packet */

        explen = sizeof(clusterMsg)-sizeof(union clusterMsgData);
        explen += (sizeof(clusterMsgDataGossip)*count);
        if (totlen != explen) return 1;
    } else if (type == CLUSTERMSG_TYPE_FAIL) {
        uint32_t explen = sizeof(clusterMsg)-sizeof(union clusterMsgData);

        explen += sizeof(clusterMsgDataFail);
        if (totlen != explen) return 1;
    } else if (type == CLUSTERMSG_TYPE_PUBLISH) {
        uint32_t explen = sizeof(clusterMsg)-sizeof(union clusterMsgData);

        explen += sizeof(clusterMsgDataPublish) -
                8 +
                ntohl(hdr->data.publish.msg.channel_len) +
                ntohl(hdr->data.publish.msg.message_len);
        if (totlen != explen) return 1;
    } else if (type == CLUSTERMSG_TYPE_FAILOVER_AUTH_REQUEST ||
               type == CLUSTERMSG_TYPE_FAILOVER_AUTH_ACK ||
               type == CLUSTERMSG_TYPE_MFSTART)
    {
        uint32_t explen = sizeof(clusterMsg)-sizeof(union clusterMsgData);

        if (totlen != explen) return 1;
    } else if (type == CLUSTERMSG_TYPE_UPDATE) {
        uint32_t explen = sizeof(clusterMsg)-sizeof(union clusterMsgData);

        explen += sizeof(clusterMsgDataUpdate);
        if (totlen != explen) return 1;
    } else if (type == CLUSTERMSG_TYPE_MODULE) {
        uint32_t explen = sizeof(clusterMsg)-sizeof(union clusterMsgData);

        explen += sizeof(clusterMsgDataPublish) -
                3 + ntohl(hdr->data.module.msg.len);
        if (totlen != explen) return 1;
    }

    /* Check if the sender is a known node. */
    sender = clusterLookupNode(hdr->sender);
    if (sender && !nodeInHandshake(sender)) {
        /* Update our curretEpoch if we see a newer epoch in the cluster. */
        senderCurrentEpoch = ntohu64(hdr->currentEpoch);
        senderConfigEpoch = ntohu64(hdr->configEpoch);
        if (senderCurrentEpoch > server.cluster->currentEpoch)
            server.cluster->currentEpoch = senderCurrentEpoch;
        /* Update the sender configEpoch if it is publishing a newer one. */
        if (senderConfigEpoch > sender->configEpoch) {
            sender->configEpoch = senderConfigEpoch;
            clusterDoBeforeSleep(CLUSTER_TODO_SAVE_CONFIG|
                                 CLUSTER_TODO_FSYNC_CONFIG);
        }
        /* Update the replication offset info for this node. */
        sender->repl_offset = ntohu64(hdr->offset);
        sender->repl_offset_time = mstime();
        /* If we are a slave performing a manual failover and our master
         * sent its offset while already paused, populate the MF state. */
        if (server.cluster->mf_end &&
            nodeIsSlave(myself) &&
            myself->slaveof == sender &&
            hdr->mflags[0] & CLUSTERMSG_FLAG0_PAUSED &&
            server.cluster->mf_master_offset == 0)
        {
            server.cluster->mf_master_offset = sender->repl_offset;
            serverLog(LL_WARNING,
                "Received replication offset for paused "
                "master manual failover: %lld",
                server.cluster->mf_master_offset);
        }
    }

    /* Initial processing of PING and MEET requests replying with a PONG. */
    if (type == CLUSTERMSG_TYPE_PING || type == CLUSTERMSG_TYPE_MEET) {
        serverLog(LL_DEBUG,"Ping packet received: %p", (void*)link->node);

        /* We use incoming MEET messages in order to set the address
         * for 'myself', since only other cluster nodes will send us
         * MEET messages on handshakes, when the cluster joins, or
         * later if we changed address, and those nodes will use our
         * official address to connect to us. So by obtaining this address
         * from the socket is a simple way to discover / update our own
         * address in the cluster without it being hardcoded in the config.
         *
         * However if we don't have an address at all, we update the address
         * even with a normal PING packet. If it's wrong it will be fixed
         * by MEET later. */
        if ((type == CLUSTERMSG_TYPE_MEET || myself->ip[0] == '\0') &&
            server.cluster_announce_ip == NULL)
        {
            char ip[NET_IP_STR_LEN];

            if (connSockName(link->conn,ip,sizeof(ip),NULL) != -1 &&
                strcmp(ip,myself->ip))
            {
                memcpy(myself->ip,ip,NET_IP_STR_LEN);
                serverLog(LL_WARNING,"IP address for this node updated to %s",
                    myself->ip);
                clusterDoBeforeSleep(CLUSTER_TODO_SAVE_CONFIG);
            }
        }

        /* Add this node if it is new for us and the msg type is MEET.
         * In this stage we don't try to add the node with the right
         * flags, slaveof pointer, and so forth, as this details will be
         * resolved when we'll receive PONGs from the node. */
        if (!sender && type == CLUSTERMSG_TYPE_MEET) {
            clusterNode *node;

            node = createClusterNode(NULL,CLUSTER_NODE_HANDSHAKE);
            nodeIp2String(node->ip,link,hdr->myip);
            node->port = ntohs(hdr->port);
            node->cport = ntohs(hdr->cport);
            clusterAddNode(node);
            clusterDoBeforeSleep(CLUSTER_TODO_SAVE_CONFIG);
        }

        /* If this is a MEET packet from an unknown node, we still process
         * the gossip section here since we have to trust the sender because
         * of the message type. */
        if (!sender && type == CLUSTERMSG_TYPE_MEET)
            clusterProcessGossipSection(hdr,link);

        /* Anyway reply with a PONG */
        clusterSendPing(link,CLUSTERMSG_TYPE_PONG);
    }

    /* PING, PONG, MEET: process config information. */
    if (type == CLUSTERMSG_TYPE_PING || type == CLUSTERMSG_TYPE_PONG ||
        type == CLUSTERMSG_TYPE_MEET)
    {
        serverLog(LL_DEBUG,"%s packet received: %p",
            type == CLUSTERMSG_TYPE_PING ? "ping" : "pong",
            (void*)link->node);
        if (link->node) {
            if (nodeInHandshake(link->node)) {
                /* If we already have this node, try to change the
                 * IP/port of the node with the new one. */
                if (sender) {
                    serverLog(LL_VERBOSE,
                        "Handshake: we already know node %.40s, "
                        "updating the address if needed.", sender->name);
                    if (nodeUpdateAddressIfNeeded(sender,link,hdr))
                    {
                        clusterDoBeforeSleep(CLUSTER_TODO_SAVE_CONFIG|
                                             CLUSTER_TODO_UPDATE_STATE);
                    }
                    /* Free this node as we already have it. This will
                     * cause the link to be freed as well. */
                    clusterDelNode(link->node);
                    return 0;
                }

                /* First thing to do is replacing the random name with the
                 * right node name if this was a handshake stage. */
                clusterRenameNode(link->node, hdr->sender);
                serverLog(LL_DEBUG,"Handshake with node %.40s completed.",
                    link->node->name);
                link->node->flags &= ~CLUSTER_NODE_HANDSHAKE;
                link->node->flags |= flags&(CLUSTER_NODE_MASTER|CLUSTER_NODE_SLAVE);
                clusterDoBeforeSleep(CLUSTER_TODO_SAVE_CONFIG);
            } else if (memcmp(link->node->name,hdr->sender,
                        CLUSTER_NAMELEN) != 0)
            {
                /* If the reply has a non matching node ID we
                 * disconnect this node and set it as not having an associated
                 * address. */
                serverLog(LL_DEBUG,"PONG contains mismatching sender ID. About node %.40s added %d ms ago, having flags %d",
                    link->node->name,
                    (int)(mstime()-(link->node->ctime)),
                    link->node->flags);
                link->node->flags |= CLUSTER_NODE_NOADDR;
                link->node->ip[0] = '\0';
                link->node->port = 0;
                link->node->cport = 0;
                freeClusterLink(link);
                clusterDoBeforeSleep(CLUSTER_TODO_SAVE_CONFIG);
                return 0;
            }
        }

        /* Copy the CLUSTER_NODE_NOFAILOVER flag from what the sender
         * announced. This is a dynamic flag that we receive from the
         * sender, and the latest status must be trusted. We need it to
         * be propagated because the slave ranking used to understand the
         * delay of each slave in the voting process, needs to know
         * what are the instances really competing. */
        if (sender) {
            int nofailover = flags & CLUSTER_NODE_NOFAILOVER;
            sender->flags &= ~CLUSTER_NODE_NOFAILOVER;
            sender->flags |= nofailover;
        }

        /* Update the node address if it changed. */
        if (sender && type == CLUSTERMSG_TYPE_PING &&
            !nodeInHandshake(sender) &&
            nodeUpdateAddressIfNeeded(sender,link,hdr))
        {
            clusterDoBeforeSleep(CLUSTER_TODO_SAVE_CONFIG|
                                 CLUSTER_TODO_UPDATE_STATE);
        }

        /* Update our info about the node */
        if (link->node && type == CLUSTERMSG_TYPE_PONG) {
            link->node->pong_received = mstime();
            link->node->ping_sent = 0;

            /* The PFAIL condition can be reversed without external
             * help if it is momentary (that is, if it does not
             * turn into a FAIL state).
             *
             * The FAIL condition is also reversible under specific
             * conditions detected by clearNodeFailureIfNeeded(). */
            if (nodeTimedOut(link->node)) {
                link->node->flags &= ~CLUSTER_NODE_PFAIL;
                clusterDoBeforeSleep(CLUSTER_TODO_SAVE_CONFIG|
                                     CLUSTER_TODO_UPDATE_STATE);
            } else if (nodeFailed(link->node)) {
                clearNodeFailureIfNeeded(link->node);
            }
        }

        /* Check for role switch: slave -> master or master -> slave. */
        if (sender) {
            if (!memcmp(hdr->slaveof,CLUSTER_NODE_NULL_NAME,
                sizeof(hdr->slaveof)))
            {
                /* Node is a master. */
                clusterSetNodeAsMaster(sender);
            } else {
                /* Node is a slave. */
                clusterNode *master = clusterLookupNode(hdr->slaveof);

                if (nodeIsMaster(sender)) {
                    /* Master turned into a slave! Reconfigure the node. */
                    clusterDelNodeSlots(sender);
                    sender->flags &= ~(CLUSTER_NODE_MASTER|
                                       CLUSTER_NODE_MIGRATE_TO);
                    sender->flags |= CLUSTER_NODE_SLAVE;

                    /* Update config and state. */
                    clusterDoBeforeSleep(CLUSTER_TODO_SAVE_CONFIG|
                                         CLUSTER_TODO_UPDATE_STATE);
                }

                /* Master node changed for this slave? */
                if (master && sender->slaveof != master) {
                    if (sender->slaveof)
                        clusterNodeRemoveSlave(sender->slaveof,sender);
                    clusterNodeAddSlave(master,sender);
                    sender->slaveof = master;

                    /* Update config. */
                    clusterDoBeforeSleep(CLUSTER_TODO_SAVE_CONFIG);
                }
            }
        }

        /* Update our info about served slots.
         *
         * Note: this MUST happen after we update the master/slave state
         * so that CLUSTER_NODE_MASTER flag will be set. */

        /* Many checks are only needed if the set of served slots this
         * instance claims is different compared to the set of slots we have
         * for it. Check this ASAP to avoid other computational expansive
         * checks later. */
        clusterNode *sender_master = NULL; /* Sender or its master if slave. */
        int dirty_slots = 0; /* Sender claimed slots don't match my view? */

        if (sender) {
            sender_master = nodeIsMaster(sender) ? sender : sender->slaveof;
            if (sender_master) {
                dirty_slots = memcmp(sender_master->slots,
                        hdr->myslots,sizeof(hdr->myslots)) != 0;
            }
        }

        /* 1) If the sender of the message is a master, and we detected that
         *    the set of slots it claims changed, scan the slots to see if we
         *    need to update our configuration. */
        if (sender && nodeIsMaster(sender) && dirty_slots)
            clusterUpdateSlotsConfigWith(sender,senderConfigEpoch,hdr->myslots);

        /* 2) We also check for the reverse condition, that is, the sender
         *    claims to serve slots we know are served by a master with a
         *    greater configEpoch. If this happens we inform the sender.
         *
         * This is useful because sometimes after a partition heals, a
         * reappearing master may be the last one to claim a given set of
         * hash slots, but with a configuration that other instances know to
         * be deprecated. Example:
         *
         * A and B are master and slave for slots 1,2,3.
         * A is partitioned away, B gets promoted.
         * B is partitioned away, and A returns available.
         *
         * Usually B would PING A publishing its set of served slots and its
         * configEpoch, but because of the partition B can't inform A of the
         * new configuration, so other nodes that have an updated table must
         * do it. In this way A will stop to act as a master (or can try to
         * failover if there are the conditions to win the election). */
        if (sender && dirty_slots) {
            int j;

            for (j = 0; j < CLUSTER_SLOTS; j++) {
                if (bitmapTestBit(hdr->myslots,j)) {
                    if (server.cluster->slots[j] == sender ||
                        server.cluster->slots[j] == NULL) continue;
                    if (server.cluster->slots[j]->configEpoch >
                        senderConfigEpoch)
                    {
                        serverLog(LL_VERBOSE,
                            "Node %.40s has old slots configuration, sending "
                            "an UPDATE message about %.40s",
                                sender->name, server.cluster->slots[j]->name);
                        clusterSendUpdate(sender->link,
                            server.cluster->slots[j]);

                        /* TODO: instead of exiting the loop send every other
                         * UPDATE packet for other nodes that are the new owner
                         * of sender's slots. */
                        break;
                    }
                }
            }
        }

        /* If our config epoch collides with the sender's try to fix
         * the problem. */
        if (sender &&
            nodeIsMaster(myself) && nodeIsMaster(sender) &&
            senderConfigEpoch == myself->configEpoch)
        {
            clusterHandleConfigEpochCollision(sender);
        }

        /* Get info from the gossip section */
        if (sender) clusterProcessGossipSection(hdr,link);
    } else if (type == CLUSTERMSG_TYPE_FAIL) {
        clusterNode *failing;

        if (sender) {
            failing = clusterLookupNode(hdr->data.fail.about.nodename);
            if (failing &&
                !(failing->flags & (CLUSTER_NODE_FAIL|CLUSTER_NODE_MYSELF)))
            {
                serverLog(LL_NOTICE,
                    "FAIL message received from %.40s about %.40s",
                    hdr->sender, hdr->data.fail.about.nodename);
                failing->flags |= CLUSTER_NODE_FAIL;
                failing->fail_time = mstime();
                failing->flags &= ~CLUSTER_NODE_PFAIL;
                clusterDoBeforeSleep(CLUSTER_TODO_SAVE_CONFIG|
                                     CLUSTER_TODO_UPDATE_STATE);
            }
        } else {
            serverLog(LL_NOTICE,
                "Ignoring FAIL message from unknown node %.40s about %.40s",
                hdr->sender, hdr->data.fail.about.nodename);
        }
    } else if (type == CLUSTERMSG_TYPE_PUBLISH) {
        robj *channel, *message;
        uint32_t channel_len, message_len;

        /* Don't bother creating useless objects if there are no
         * Pub/Sub subscribers. */
        if (dictSize(server.pubsub_channels) ||
           listLength(server.pubsub_patterns))
        {
            channel_len = ntohl(hdr->data.publish.msg.channel_len);
            message_len = ntohl(hdr->data.publish.msg.message_len);
            channel = createStringObject(
                        (char*)hdr->data.publish.msg.bulk_data,channel_len);
            message = createStringObject(
                        (char*)hdr->data.publish.msg.bulk_data+channel_len,
                        message_len);
            pubsubPublishMessage(channel,message);
            decrRefCount(channel);
            decrRefCount(message);
        }
    } else if (type == CLUSTERMSG_TYPE_FAILOVER_AUTH_REQUEST) {
        if (!sender) return 1;  /* We don't know that node. */
        clusterSendFailoverAuthIfNeeded(sender,hdr);
    } else if (type == CLUSTERMSG_TYPE_FAILOVER_AUTH_ACK) {
        if (!sender) return 1;  /* We don't know that node. */
        /* We consider this vote only if the sender is a master serving
         * a non zero number of slots, and its currentEpoch is greater or
         * equal to epoch where this node started the election. */
        if (nodeIsMaster(sender) && sender->numslots > 0 &&
            senderCurrentEpoch >= server.cluster->failover_auth_epoch)
        {
            server.cluster->failover_auth_count++;
            /* Maybe we reached a quorum here, set a flag to make sure
             * we check ASAP. */
            clusterDoBeforeSleep(CLUSTER_TODO_HANDLE_FAILOVER);
        }
    } else if (type == CLUSTERMSG_TYPE_MFSTART) {
        /* This message is acceptable only if I'm a master and the sender
         * is one of my slaves. */
        if (!sender || sender->slaveof != myself) return 1;
        /* Manual failover requested from slaves. Initialize the state
         * accordingly. */
        resetManualFailover();
        server.cluster->mf_end = mstime() + CLUSTER_MF_TIMEOUT;
        server.cluster->mf_slave = sender;
        pauseClients(mstime()+(CLUSTER_MF_TIMEOUT*2));
        serverLog(LL_WARNING,"Manual failover requested by replica %.40s.",
            sender->name);
    } else if (type == CLUSTERMSG_TYPE_UPDATE) {
        clusterNode *n; /* The node the update is about. */
        uint64_t reportedConfigEpoch =
                    ntohu64(hdr->data.update.nodecfg.configEpoch);

        if (!sender) return 1;  /* We don't know the sender. */
        n = clusterLookupNode(hdr->data.update.nodecfg.nodename);
        if (!n) return 1;   /* We don't know the reported node. */
        if (n->configEpoch >= reportedConfigEpoch) return 1; /* Nothing new. */

        /* If in our current config the node is a slave, set it as a master. */
        if (nodeIsSlave(n)) clusterSetNodeAsMaster(n);

        /* Update the node's configEpoch. */
        n->configEpoch = reportedConfigEpoch;
        clusterDoBeforeSleep(CLUSTER_TODO_SAVE_CONFIG|
                             CLUSTER_TODO_FSYNC_CONFIG);

        /* Check the bitmap of served slots and update our
         * config accordingly. */
        clusterUpdateSlotsConfigWith(n,reportedConfigEpoch,
            hdr->data.update.nodecfg.slots);
    } else if (type == CLUSTERMSG_TYPE_MODULE) {
        if (!sender) return 1;  /* Protect the module from unknown nodes. */
        /* We need to route this message back to the right module subscribed
         * for the right message type. */
        uint64_t module_id = hdr->data.module.msg.module_id; /* Endian-safe ID */
        uint32_t len = ntohl(hdr->data.module.msg.len);
        uint8_t type = hdr->data.module.msg.type;
        unsigned char *payload = hdr->data.module.msg.bulk_data;
        moduleCallClusterReceivers(sender->name,module_id,type,payload,len);
    } else {
        serverLog(LL_WARNING,"Received unknown packet type: %d", type);
    }
    return 1;
}

/* This function is called when we detect the link with this node is lost.
   We set the node as no longer connected. The Cluster Cron will detect
   this connection and will try to get it connected again.

   Instead if the node is a temporary node used to accept a query, we
   completely free the node on error. */
void handleLinkIOError(clusterLink *link) {
    freeClusterLink(link);
}

/* Send data. This is handled using a trivial send buffer that gets
 * consumed by write(). We don't try to optimize this for speed too much
 * as this is a very low traffic channel. */
void clusterWriteHandler(connection *conn) {
    clusterLink *link = connGetPrivateData(conn);
    ssize_t nwritten;

    nwritten = connWrite(conn, link->sndbuf, sdslen(link->sndbuf));
    if (nwritten <= 0) {
        serverLog(LL_DEBUG,"I/O error writing to node link: %s",
            (nwritten == -1) ? connGetLastError(conn) : "short write");
        handleLinkIOError(link);
        return;
    }
    sdsrange(link->sndbuf,nwritten,-1);
    if (sdslen(link->sndbuf) == 0)
        connSetWriteHandler(link->conn, NULL);
}

/* A connect handler that gets called when a connection to another node
 * gets established.
 */
void clusterLinkConnectHandler(connection *conn) {
    clusterLink *link = connGetPrivateData(conn);
    clusterNode *node = link->node;

    /* Check if connection succeeded */
    if (connGetState(conn) != CONN_STATE_CONNECTED) {
        serverLog(LL_VERBOSE, "Connection with Node %.40s at %s:%d failed: %s",
                node->name, node->ip, node->cport,
                connGetLastError(conn));
        freeClusterLink(link);
        return;
    }

    /* Register a read handler from now on */
    connSetReadHandler(conn, clusterReadHandler);

    /* Queue a PING in the new connection ASAP: this is crucial
     * to avoid false positives in failure detection.
     *
     * If the node is flagged as MEET, we send a MEET message instead
     * of a PING one, to force the receiver to add us in its node
     * table. */
    mstime_t old_ping_sent = node->ping_sent;
    clusterSendPing(link, node->flags & CLUSTER_NODE_MEET ?
            CLUSTERMSG_TYPE_MEET : CLUSTERMSG_TYPE_PING);
    if (old_ping_sent) {
        /* If there was an active ping before the link was
         * disconnected, we want to restore the ping time, otherwise
         * replaced by the clusterSendPing() call. */
        node->ping_sent = old_ping_sent;
    }
    /* We can clear the flag after the first packet is sent.
     * If we'll never receive a PONG, we'll never send new packets
     * to this node. Instead after the PONG is received and we
     * are no longer in meet/handshake status, we want to send
     * normal PING packets. */
    node->flags &= ~CLUSTER_NODE_MEET;

    serverLog(LL_DEBUG,"Connecting with Node %.40s at %s:%d",
            node->name, node->ip, node->cport);
}

/* Read data. Try to read the first field of the header first to check the
 * full length of the packet. When a whole packet is in memory this function
 * will call the function to process the packet. And so forth. */
void clusterReadHandler(connection *conn) {
    clusterMsg buf[1];
    ssize_t nread;
    clusterMsg *hdr;
    clusterLink *link = connGetPrivateData(conn);
    unsigned int readlen, rcvbuflen;

    while(1) { /* Read as long as there is data to read. */
        rcvbuflen = sdslen(link->rcvbuf);
        if (rcvbuflen < 8) {
            /* First, obtain the first 8 bytes to get the full message
             * length. */
            readlen = 8 - rcvbuflen;
        } else {
            /* Finally read the full message. */
            hdr = (clusterMsg*) link->rcvbuf;
            if (rcvbuflen == 8) {
                /* Perform some sanity check on the message signature
                 * and length. */
                if (memcmp(hdr->sig,"RCmb",4) != 0 ||
                    ntohl(hdr->totlen) < CLUSTERMSG_MIN_LEN)
                {
                    serverLog(LL_WARNING,
                        "Bad message length or signature received "
                        "from Cluster bus.");
                    handleLinkIOError(link);
                    return;
                }
            }
            readlen = ntohl(hdr->totlen) - rcvbuflen;
            if (readlen > sizeof(buf)) readlen = sizeof(buf);
        }

        nread = connRead(conn,buf,readlen);
        if (nread == -1 && (connGetState(conn) == CONN_STATE_CONNECTED)) return; /* No more data ready. */

        if (nread <= 0) {
            /* I/O error... */
            serverLog(LL_DEBUG,"I/O error reading from node link: %s",
                (nread == 0) ? "connection closed" : connGetLastError(conn));
            handleLinkIOError(link);
            return;
        } else {
            /* Read data and recast the pointer to the new buffer. */
            link->rcvbuf = sdscatlen(link->rcvbuf,buf,nread);
            hdr = (clusterMsg*) link->rcvbuf;
            rcvbuflen += nread;
        }

        /* Total length obtained? Process this packet. */
        if (rcvbuflen >= 8 && rcvbuflen == ntohl(hdr->totlen)) {
            if (clusterProcessPacket(link)) {
                sdsfree(link->rcvbuf);
                link->rcvbuf = sdsempty();
            } else {
                return; /* Link no longer valid. */
            }
        }
    }
}

/* Put stuff into the send buffer.
 *
 * It is guaranteed that this function will never have as a side effect
 * the link to be invalidated, so it is safe to call this function
 * from event handlers that will do stuff with the same link later. */
void clusterSendMessage(clusterLink *link, unsigned char *msg, size_t msglen) {
    if (sdslen(link->sndbuf) == 0 && msglen != 0)
        connSetWriteHandlerWithBarrier(link->conn, clusterWriteHandler, 1);

    link->sndbuf = sdscatlen(link->sndbuf, msg, msglen);

    /* Populate sent messages stats. */
    clusterMsg *hdr = (clusterMsg*) msg;
    uint16_t type = ntohs(hdr->type);
    if (type < CLUSTERMSG_TYPE_COUNT)
        server.cluster->stats_bus_messages_sent[type]++;
}

/* Send a message to all the nodes that are part of the cluster having
 * a connected link.
 *
 * It is guaranteed that this function will never have as a side effect
 * some node->link to be invalidated, so it is safe to call this function
 * from event handlers that will do stuff with node links later. */
void clusterBroadcastMessage(void *buf, size_t len) {
    dictIterator *di;
    dictEntry *de;

    di = dictGetSafeIterator(server.cluster->nodes);
    while((de = dictNext(di)) != NULL) {
        clusterNode *node = dictGetVal(de);

        if (!node->link) continue;
        if (node->flags & (CLUSTER_NODE_MYSELF|CLUSTER_NODE_HANDSHAKE))
            continue;
        clusterSendMessage(node->link,buf,len);
    }
    dictReleaseIterator(di);
}

/* Build the message header. hdr must point to a buffer at least
 * sizeof(clusterMsg) in bytes. */
void clusterBuildMessageHdr(clusterMsg *hdr, int type) {
    int totlen = 0;
    uint64_t offset;
    clusterNode *master;

    /* If this node is a master, we send its slots bitmap and configEpoch.
     * If this node is a slave we send the master's information instead (the
     * node is flagged as slave so the receiver knows that it is NOT really
     * in charge for this slots. */
    master = (nodeIsSlave(myself) && myself->slaveof) ?
              myself->slaveof : myself;

    memset(hdr,0,sizeof(*hdr));
    hdr->ver = htons(CLUSTER_PROTO_VER);
    hdr->sig[0] = 'R';
    hdr->sig[1] = 'C';
    hdr->sig[2] = 'm';
    hdr->sig[3] = 'b';
    hdr->type = htons(type);
    memcpy(hdr->sender,myself->name,CLUSTER_NAMELEN);

    /* If cluster-announce-ip option is enabled, force the receivers of our
     * packets to use the specified address for this node. Otherwise if the
     * first byte is zero, they'll do auto discovery. */
    memset(hdr->myip,0,NET_IP_STR_LEN);
    if (server.cluster_announce_ip) {
        strncpy(hdr->myip,server.cluster_announce_ip,NET_IP_STR_LEN);
        hdr->myip[NET_IP_STR_LEN-1] = '\0';
    }

    /* Handle cluster-announce-port as well. */
    int port = server.tls_cluster ? server.tls_port : server.port;
    int announced_port = server.cluster_announce_port ?
                         server.cluster_announce_port : port;
    int announced_cport = server.cluster_announce_bus_port ?
                          server.cluster_announce_bus_port :
                          (port + CLUSTER_PORT_INCR);

    memcpy(hdr->myslots,master->slots,sizeof(hdr->myslots));
    memset(hdr->slaveof,0,CLUSTER_NAMELEN);
    if (myself->slaveof != NULL)
        memcpy(hdr->slaveof,myself->slaveof->name, CLUSTER_NAMELEN);
    hdr->port = htons(announced_port);
    hdr->cport = htons(announced_cport);
    hdr->flags = htons(myself->flags);
    hdr->state = server.cluster->state;

    /* Set the currentEpoch and configEpochs. */
    hdr->currentEpoch = htonu64(server.cluster->currentEpoch);
    hdr->configEpoch = htonu64(master->configEpoch);

    /* Set the replication offset. */
    if (nodeIsSlave(myself))
        offset = replicationGetSlaveOffset();
    else
        offset = server.master_repl_offset;
    hdr->offset = htonu64(offset);

    /* Set the message flags. */
    if (nodeIsMaster(myself) && server.cluster->mf_end)
        hdr->mflags[0] |= CLUSTERMSG_FLAG0_PAUSED;

    /* Compute the message length for certain messages. For other messages
     * this is up to the caller. */
    if (type == CLUSTERMSG_TYPE_FAIL) {
        totlen = sizeof(clusterMsg)-sizeof(union clusterMsgData);
        totlen += sizeof(clusterMsgDataFail);
    } else if (type == CLUSTERMSG_TYPE_UPDATE) {
        totlen = sizeof(clusterMsg)-sizeof(union clusterMsgData);
        totlen += sizeof(clusterMsgDataUpdate);
    }
    hdr->totlen = htonl(totlen);
    /* For PING, PONG, and MEET, fixing the totlen field is up to the caller. */
}

/* Return non zero if the node is already present in the gossip section of the
 * message pointed by 'hdr' and having 'count' gossip entries. Otherwise
 * zero is returned. Helper for clusterSendPing(). */
int clusterNodeIsInGossipSection(clusterMsg *hdr, int count, clusterNode *n) {
    int j;
    for (j = 0; j < count; j++) {
        if (memcmp(hdr->data.ping.gossip[j].nodename,n->name,
                CLUSTER_NAMELEN) == 0) break;
    }
    return j != count;
}

/* Set the i-th entry of the gossip section in the message pointed by 'hdr'
 * to the info of the specified node 'n'. */
void clusterSetGossipEntry(clusterMsg *hdr, int i, clusterNode *n) {
    clusterMsgDataGossip *gossip;
    gossip = &(hdr->data.ping.gossip[i]);
    memcpy(gossip->nodename,n->name,CLUSTER_NAMELEN);
    gossip->ping_sent = htonl(n->ping_sent/1000);
    gossip->pong_received = htonl(n->pong_received/1000);
    memcpy(gossip->ip,n->ip,sizeof(n->ip));
    gossip->port = htons(n->port);
    gossip->cport = htons(n->cport);
    gossip->flags = htons(n->flags);
    gossip->notused1 = 0;
}

/* Send a PING or PONG packet to the specified node, making sure to add enough
 * gossip informations. */
void clusterSendPing(clusterLink *link, int type) {
    unsigned char *buf;
    clusterMsg *hdr;
    int gossipcount = 0; /* Number of gossip sections added so far. */
    int wanted; /* Number of gossip sections we want to append if possible. */
    int totlen; /* Total packet length. */
    /* freshnodes is the max number of nodes we can hope to append at all:
     * nodes available minus two (ourself and the node we are sending the
     * message to). However practically there may be less valid nodes since
     * nodes in handshake state, disconnected, are not considered. */
    int freshnodes = dictSize(server.cluster->nodes)-2;

    /* How many gossip sections we want to add? 1/10 of the number of nodes
     * and anyway at least 3. Why 1/10?
     *
     * If we have N masters, with N/10 entries, and we consider that in
     * node_timeout we exchange with each other node at least 4 packets
     * (we ping in the worst case in node_timeout/2 time, and we also
     * receive two pings from the host), we have a total of 8 packets
     * in the node_timeout*2 falure reports validity time. So we have
     * that, for a single PFAIL node, we can expect to receive the following
     * number of failure reports (in the specified window of time):
     *
     * PROB * GOSSIP_ENTRIES_PER_PACKET * TOTAL_PACKETS:
     *
     * PROB = probability of being featured in a single gossip entry,
     *        which is 1 / NUM_OF_NODES.
     * ENTRIES = 10.
     * TOTAL_PACKETS = 2 * 4 * NUM_OF_MASTERS.
     *
     * If we assume we have just masters (so num of nodes and num of masters
     * is the same), with 1/10 we always get over the majority, and specifically
     * 80% of the number of nodes, to account for many masters failing at the
     * same time.
     *
     * Since we have non-voting slaves that lower the probability of an entry
     * to feature our node, we set the number of entries per packet as
     * 10% of the total nodes we have. */
    wanted = floor(dictSize(server.cluster->nodes)/10);
    if (wanted < 3) wanted = 3;
    if (wanted > freshnodes) wanted = freshnodes;

    /* Include all the nodes in PFAIL state, so that failure reports are
     * faster to propagate to go from PFAIL to FAIL state. */
    int pfail_wanted = server.cluster->stats_pfail_nodes;

    /* Compute the maxium totlen to allocate our buffer. We'll fix the totlen
     * later according to the number of gossip sections we really were able
     * to put inside the packet. */
    totlen = sizeof(clusterMsg)-sizeof(union clusterMsgData);
    totlen += (sizeof(clusterMsgDataGossip)*(wanted+pfail_wanted));
    /* Note: clusterBuildMessageHdr() expects the buffer to be always at least
     * sizeof(clusterMsg) or more. */
    if (totlen < (int)sizeof(clusterMsg)) totlen = sizeof(clusterMsg);
    buf = zcalloc(totlen);
    hdr = (clusterMsg*) buf;

    /* Populate the header. */
    if (link->node && type == CLUSTERMSG_TYPE_PING)
        link->node->ping_sent = mstime();
    clusterBuildMessageHdr(hdr,type);

    /* Populate the gossip fields */
    int maxiterations = wanted*3;
    while(freshnodes > 0 && gossipcount < wanted && maxiterations--) {
        dictEntry *de = dictGetRandomKey(server.cluster->nodes);
        clusterNode *this = dictGetVal(de);

        /* Don't include this node: the whole packet header is about us
         * already, so we just gossip about other nodes. */
        if (this == myself) continue;

        /* PFAIL nodes will be added later. */
        if (this->flags & CLUSTER_NODE_PFAIL) continue;

        /* In the gossip section don't include:
         * 1) Nodes in HANDSHAKE state.
         * 3) Nodes with the NOADDR flag set.
         * 4) Disconnected nodes if they don't have configured slots.
         */
        if (this->flags & (CLUSTER_NODE_HANDSHAKE|CLUSTER_NODE_NOADDR) ||
            (this->link == NULL && this->numslots == 0))
        {
            freshnodes--; /* Tecnically not correct, but saves CPU. */
            continue;
        }

        /* Do not add a node we already have. */
        if (clusterNodeIsInGossipSection(hdr,gossipcount,this)) continue;

        /* Add it */
        clusterSetGossipEntry(hdr,gossipcount,this);
        freshnodes--;
        gossipcount++;
    }

    /* If there are PFAIL nodes, add them at the end. */
    if (pfail_wanted) {
        dictIterator *di;
        dictEntry *de;

        di = dictGetSafeIterator(server.cluster->nodes);
        while((de = dictNext(di)) != NULL && pfail_wanted > 0) {
            clusterNode *node = dictGetVal(de);
            if (node->flags & CLUSTER_NODE_HANDSHAKE) continue;
            if (node->flags & CLUSTER_NODE_NOADDR) continue;
            if (!(node->flags & CLUSTER_NODE_PFAIL)) continue;
            clusterSetGossipEntry(hdr,gossipcount,node);
            freshnodes--;
            gossipcount++;
            /* We take the count of the slots we allocated, since the
             * PFAIL stats may not match perfectly with the current number
             * of PFAIL nodes. */
            pfail_wanted--;
        }
        dictReleaseIterator(di);
    }

    /* Ready to send... fix the totlen fiend and queue the message in the
     * output buffer. */
    totlen = sizeof(clusterMsg)-sizeof(union clusterMsgData);
    totlen += (sizeof(clusterMsgDataGossip)*gossipcount);
    hdr->count = htons(gossipcount);
    hdr->totlen = htonl(totlen);
    clusterSendMessage(link,buf,totlen);
    zfree(buf);
}

/* Send a PONG packet to every connected node that's not in handshake state
 * and for which we have a valid link.
 *
 * In Redis Cluster pongs are not used just for failure detection, but also
 * to carry important configuration information. So broadcasting a pong is
 * useful when something changes in the configuration and we want to make
 * the cluster aware ASAP (for instance after a slave promotion).
 *
 * The 'target' argument specifies the receiving instances using the
 * defines below:
 *
 * CLUSTER_BROADCAST_ALL -> All known instances.
 * CLUSTER_BROADCAST_LOCAL_SLAVES -> All slaves in my master-slaves ring.
 */
#define CLUSTER_BROADCAST_ALL 0
#define CLUSTER_BROADCAST_LOCAL_SLAVES 1
void clusterBroadcastPong(int target) {
    dictIterator *di;
    dictEntry *de;

    di = dictGetSafeIterator(server.cluster->nodes);
    while((de = dictNext(di)) != NULL) {
        clusterNode *node = dictGetVal(de);

        if (!node->link) continue;
        if (node == myself || nodeInHandshake(node)) continue;
        if (target == CLUSTER_BROADCAST_LOCAL_SLAVES) {
            int local_slave =
                nodeIsSlave(node) && node->slaveof &&
                (node->slaveof == myself || node->slaveof == myself->slaveof);
            if (!local_slave) continue;
        }
        clusterSendPing(node->link,CLUSTERMSG_TYPE_PONG);
    }
    dictReleaseIterator(di);
}

/* Send a PUBLISH message.
 *
 * If link is NULL, then the message is broadcasted to the whole cluster. */
void clusterSendPublish(clusterLink *link, robj *channel, robj *message) {
    unsigned char *payload;
    clusterMsg buf[1];
    clusterMsg *hdr = (clusterMsg*) buf;
    uint32_t totlen;
    uint32_t channel_len, message_len;

    channel = getDecodedObject(channel);
    message = getDecodedObject(message);
    channel_len = sdslen(channel->ptr);
    message_len = sdslen(message->ptr);

    clusterBuildMessageHdr(hdr,CLUSTERMSG_TYPE_PUBLISH);
    totlen = sizeof(clusterMsg)-sizeof(union clusterMsgData);
    totlen += sizeof(clusterMsgDataPublish) - 8 + channel_len + message_len;

    hdr->data.publish.msg.channel_len = htonl(channel_len);
    hdr->data.publish.msg.message_len = htonl(message_len);
    hdr->totlen = htonl(totlen);

    /* Try to use the local buffer if possible */
    if (totlen < sizeof(buf)) {
        payload = (unsigned char*)buf;
    } else {
        payload = zmalloc(totlen);
        memcpy(payload,hdr,sizeof(*hdr));
        hdr = (clusterMsg*) payload;
    }
    memcpy(hdr->data.publish.msg.bulk_data,channel->ptr,sdslen(channel->ptr));
    memcpy(hdr->data.publish.msg.bulk_data+sdslen(channel->ptr),
        message->ptr,sdslen(message->ptr));

    if (link)
        clusterSendMessage(link,payload,totlen);
    else
        clusterBroadcastMessage(payload,totlen);

    decrRefCount(channel);
    decrRefCount(message);
    if (payload != (unsigned char*)buf) zfree(payload);
}

/* Send a FAIL message to all the nodes we are able to contact.
 * The FAIL message is sent when we detect that a node is failing
 * (CLUSTER_NODE_PFAIL) and we also receive a gossip confirmation of this:
 * we switch the node state to CLUSTER_NODE_FAIL and ask all the other
 * nodes to do the same ASAP. */
void clusterSendFail(char *nodename) {
    clusterMsg buf[1];
    clusterMsg *hdr = (clusterMsg*) buf;

    clusterBuildMessageHdr(hdr,CLUSTERMSG_TYPE_FAIL);
    memcpy(hdr->data.fail.about.nodename,nodename,CLUSTER_NAMELEN);
    clusterBroadcastMessage(buf,ntohl(hdr->totlen));
}

/* Send an UPDATE message to the specified link carrying the specified 'node'
 * slots configuration. The node name, slots bitmap, and configEpoch info
 * are included. */
void clusterSendUpdate(clusterLink *link, clusterNode *node) {
    clusterMsg buf[1];
    clusterMsg *hdr = (clusterMsg*) buf;

    if (link == NULL) return;
    clusterBuildMessageHdr(hdr,CLUSTERMSG_TYPE_UPDATE);
    memcpy(hdr->data.update.nodecfg.nodename,node->name,CLUSTER_NAMELEN);
    hdr->data.update.nodecfg.configEpoch = htonu64(node->configEpoch);
    memcpy(hdr->data.update.nodecfg.slots,node->slots,sizeof(node->slots));
    clusterSendMessage(link,(unsigned char*)buf,ntohl(hdr->totlen));
}

/* Send a MODULE message.
 *
 * If link is NULL, then the message is broadcasted to the whole cluster. */
void clusterSendModule(clusterLink *link, uint64_t module_id, uint8_t type,
                       unsigned char *payload, uint32_t len) {
    unsigned char *heapbuf;
    clusterMsg buf[1];
    clusterMsg *hdr = (clusterMsg*) buf;
    uint32_t totlen;

    clusterBuildMessageHdr(hdr,CLUSTERMSG_TYPE_MODULE);
    totlen = sizeof(clusterMsg)-sizeof(union clusterMsgData);
    totlen += sizeof(clusterMsgModule) - 3 + len;

    hdr->data.module.msg.module_id = module_id; /* Already endian adjusted. */
    hdr->data.module.msg.type = type;
    hdr->data.module.msg.len = htonl(len);
    hdr->totlen = htonl(totlen);

    /* Try to use the local buffer if possible */
    if (totlen < sizeof(buf)) {
        heapbuf = (unsigned char*)buf;
    } else {
        heapbuf = zmalloc(totlen);
        memcpy(heapbuf,hdr,sizeof(*hdr));
        hdr = (clusterMsg*) heapbuf;
    }
    memcpy(hdr->data.module.msg.bulk_data,payload,len);

    if (link)
        clusterSendMessage(link,heapbuf,totlen);
    else
        clusterBroadcastMessage(heapbuf,totlen);

    if (heapbuf != (unsigned char*)buf) zfree(heapbuf);
}

/* This function gets a cluster node ID string as target, the same way the nodes
 * addresses are represented in the modules side, resolves the node, and sends
 * the message. If the target is NULL the message is broadcasted.
 *
 * The function returns C_OK if the target is valid, otherwise C_ERR is
 * returned. */
int clusterSendModuleMessageToTarget(const char *target, uint64_t module_id, uint8_t type, unsigned char *payload, uint32_t len) {
    clusterNode *node = NULL;

    if (target != NULL) {
        node = clusterLookupNode(target);
        if (node == NULL || node->link == NULL) return C_ERR;
    }

    clusterSendModule(target ? node->link : NULL,
                      module_id, type, payload, len);
    return C_OK;
}

/* -----------------------------------------------------------------------------
 * CLUSTER Pub/Sub support
 *
 * For now we do very little, just propagating PUBLISH messages across the whole
 * cluster. In the future we'll try to get smarter and avoiding propagating those
 * messages to hosts without receives for a given channel.
 * -------------------------------------------------------------------------- */
void clusterPropagatePublish(robj *channel, robj *message) {
    clusterSendPublish(NULL, channel, message);
}

/* -----------------------------------------------------------------------------
 * SLAVE node specific functions
 * -------------------------------------------------------------------------- */

/* This function sends a FAILOVE_AUTH_REQUEST message to every node in order to
 * see if there is the quorum for this slave instance to failover its failing
 * master.
 *
 * Note that we send the failover request to everybody, master and slave nodes,
 * but only the masters are supposed to reply to our query. */
void clusterRequestFailoverAuth(void) {
    clusterMsg buf[1];
    clusterMsg *hdr = (clusterMsg*) buf;
    uint32_t totlen;

    clusterBuildMessageHdr(hdr,CLUSTERMSG_TYPE_FAILOVER_AUTH_REQUEST);
    /* If this is a manual failover, set the CLUSTERMSG_FLAG0_FORCEACK bit
     * in the header to communicate the nodes receiving the message that
     * they should authorized the failover even if the master is working. */
    if (server.cluster->mf_end) hdr->mflags[0] |= CLUSTERMSG_FLAG0_FORCEACK;
    totlen = sizeof(clusterMsg)-sizeof(union clusterMsgData);
    hdr->totlen = htonl(totlen);
    clusterBroadcastMessage(buf,totlen);
}

/* Send a FAILOVER_AUTH_ACK message to the specified node. */
void clusterSendFailoverAuth(clusterNode *node) {
    clusterMsg buf[1];
    clusterMsg *hdr = (clusterMsg*) buf;
    uint32_t totlen;

    if (!node->link) return;
    clusterBuildMessageHdr(hdr,CLUSTERMSG_TYPE_FAILOVER_AUTH_ACK);
    totlen = sizeof(clusterMsg)-sizeof(union clusterMsgData);
    hdr->totlen = htonl(totlen);
    clusterSendMessage(node->link,(unsigned char*)buf,totlen);
}

/* Send a MFSTART message to the specified node. */
void clusterSendMFStart(clusterNode *node) {
    clusterMsg buf[1];
    clusterMsg *hdr = (clusterMsg*) buf;
    uint32_t totlen;

    if (!node->link) return;
    clusterBuildMessageHdr(hdr,CLUSTERMSG_TYPE_MFSTART);
    totlen = sizeof(clusterMsg)-sizeof(union clusterMsgData);
    hdr->totlen = htonl(totlen);
    clusterSendMessage(node->link,(unsigned char*)buf,totlen);
}

/* Vote for the node asking for our vote if there are the conditions. */
void clusterSendFailoverAuthIfNeeded(clusterNode *node, clusterMsg *request) {
    clusterNode *master = node->slaveof;
    uint64_t requestCurrentEpoch = ntohu64(request->currentEpoch);
    uint64_t requestConfigEpoch = ntohu64(request->configEpoch);
    unsigned char *claimed_slots = request->myslots;
    int force_ack = request->mflags[0] & CLUSTERMSG_FLAG0_FORCEACK;
    int j;

    /* IF we are not a master serving at least 1 slot, we don't have the
     * right to vote, as the cluster size in Redis Cluster is the number
     * of masters serving at least one slot, and quorum is the cluster
     * size + 1 */
    if (nodeIsSlave(myself) || myself->numslots == 0) return;

    /* Request epoch must be >= our currentEpoch.
     * Note that it is impossible for it to actually be greater since
     * our currentEpoch was updated as a side effect of receiving this
     * request, if the request epoch was greater. */
    if (requestCurrentEpoch < server.cluster->currentEpoch) {
        serverLog(LL_WARNING,
            "Failover auth denied to %.40s: reqEpoch (%llu) < curEpoch(%llu)",
            node->name,
            (unsigned long long) requestCurrentEpoch,
            (unsigned long long) server.cluster->currentEpoch);
        return;
    }

    /* I already voted for this epoch? Return ASAP. */
    if (server.cluster->lastVoteEpoch == server.cluster->currentEpoch) {
        serverLog(LL_WARNING,
                "Failover auth denied to %.40s: already voted for epoch %llu",
                node->name,
                (unsigned long long) server.cluster->currentEpoch);
        return;
    }

    /* Node must be a slave and its master down.
     * The master can be non failing if the request is flagged
     * with CLUSTERMSG_FLAG0_FORCEACK (manual failover). */
    if (nodeIsMaster(node) || master == NULL ||
        (!nodeFailed(master) && !force_ack))
    {
        if (nodeIsMaster(node)) {
            serverLog(LL_WARNING,
                    "Failover auth denied to %.40s: it is a master node",
                    node->name);
        } else if (master == NULL) {
            serverLog(LL_WARNING,
                    "Failover auth denied to %.40s: I don't know its master",
                    node->name);
        } else if (!nodeFailed(master)) {
            serverLog(LL_WARNING,
                    "Failover auth denied to %.40s: its master is up",
                    node->name);
        }
        return;
    }

    /* We did not voted for a slave about this master for two
     * times the node timeout. This is not strictly needed for correctness
     * of the algorithm but makes the base case more linear. */
    if (mstime() - node->slaveof->voted_time < server.cluster_node_timeout * 2)
    {
        serverLog(LL_WARNING,
                "Failover auth denied to %.40s: "
                "can't vote about this master before %lld milliseconds",
                node->name,
                (long long) ((server.cluster_node_timeout*2)-
                             (mstime() - node->slaveof->voted_time)));
        return;
    }

    /* The slave requesting the vote must have a configEpoch for the claimed
     * slots that is >= the one of the masters currently serving the same
     * slots in the current configuration. */
    for (j = 0; j < CLUSTER_SLOTS; j++) {
        if (bitmapTestBit(claimed_slots, j) == 0) continue;
        if (server.cluster->slots[j] == NULL ||
            server.cluster->slots[j]->configEpoch <= requestConfigEpoch)
        {
            continue;
        }
        /* If we reached this point we found a slot that in our current slots
         * is served by a master with a greater configEpoch than the one claimed
         * by the slave requesting our vote. Refuse to vote for this slave. */
        serverLog(LL_WARNING,
                "Failover auth denied to %.40s: "
                "slot %d epoch (%llu) > reqEpoch (%llu)",
                node->name, j,
                (unsigned long long) server.cluster->slots[j]->configEpoch,
                (unsigned long long) requestConfigEpoch);
        return;
    }

    /* We can vote for this slave. */
    server.cluster->lastVoteEpoch = server.cluster->currentEpoch;
    node->slaveof->voted_time = mstime();
    clusterDoBeforeSleep(CLUSTER_TODO_SAVE_CONFIG|CLUSTER_TODO_FSYNC_CONFIG);
    clusterSendFailoverAuth(node);
    serverLog(LL_WARNING, "Failover auth granted to %.40s for epoch %llu",
        node->name, (unsigned long long) server.cluster->currentEpoch);
}

/* This function returns the "rank" of this instance, a slave, in the context
 * of its master-slaves ring. The rank of the slave is given by the number of
 * other slaves for the same master that have a better replication offset
 * compared to the local one (better means, greater, so they claim more data).
 *
 * A slave with rank 0 is the one with the greatest (most up to date)
 * replication offset, and so forth. Note that because how the rank is computed
 * multiple slaves may have the same rank, in case they have the same offset.
 *
 * The slave rank is used to add a delay to start an election in order to
 * get voted and replace a failing master. Slaves with better replication
 * offsets are more likely to win. */
int clusterGetSlaveRank(void) {
    long long myoffset;
    int j, rank = 0;
    clusterNode *master;

    serverAssert(nodeIsSlave(myself));
    master = myself->slaveof;
    if (master == NULL) return 0; /* Never called by slaves without master. */

    myoffset = replicationGetSlaveOffset();
    for (j = 0; j < master->numslaves; j++)
        if (master->slaves[j] != myself &&
            !nodeCantFailover(master->slaves[j]) &&
            master->slaves[j]->repl_offset > myoffset) rank++;
    return rank;
}

/* This function is called by clusterHandleSlaveFailover() in order to
 * let the slave log why it is not able to failover. Sometimes there are
 * not the conditions, but since the failover function is called again and
 * again, we can't log the same things continuously.
 *
 * This function works by logging only if a given set of conditions are
 * true:
 *
 * 1) The reason for which the failover can't be initiated changed.
 *    The reasons also include a NONE reason we reset the state to
 *    when the slave finds that its master is fine (no FAIL flag).
 * 2) Also, the log is emitted again if the master is still down and
 *    the reason for not failing over is still the same, but more than
 *    CLUSTER_CANT_FAILOVER_RELOG_PERIOD seconds elapsed.
 * 3) Finally, the function only logs if the slave is down for more than
 *    five seconds + NODE_TIMEOUT. This way nothing is logged when a
 *    failover starts in a reasonable time.
 *
 * The function is called with the reason why the slave can't failover
 * which is one of the integer macros CLUSTER_CANT_FAILOVER_*.
 *
 * The function is guaranteed to be called only if 'myself' is a slave. */
void clusterLogCantFailover(int reason) {
    char *msg;
    static time_t lastlog_time = 0;
    mstime_t nolog_fail_time = server.cluster_node_timeout + 5000;

    /* Don't log if we have the same reason for some time. */
    if (reason == server.cluster->cant_failover_reason &&
        time(NULL)-lastlog_time < CLUSTER_CANT_FAILOVER_RELOG_PERIOD)
        return;

    server.cluster->cant_failover_reason = reason;

    /* We also don't emit any log if the master failed no long ago, the
     * goal of this function is to log slaves in a stalled condition for
     * a long time. */
    if (myself->slaveof &&
        nodeFailed(myself->slaveof) &&
        (mstime() - myself->slaveof->fail_time) < nolog_fail_time) return;

    switch(reason) {
    case CLUSTER_CANT_FAILOVER_DATA_AGE:
        msg = "Disconnected from master for longer than allowed. "
              "Please check the 'cluster-replica-validity-factor' configuration "
              "option.";
        break;
    case CLUSTER_CANT_FAILOVER_WAITING_DELAY:
        msg = "Waiting the delay before I can start a new failover.";
        break;
    case CLUSTER_CANT_FAILOVER_EXPIRED:
        msg = "Failover attempt expired.";
        break;
    case CLUSTER_CANT_FAILOVER_WAITING_VOTES:
        msg = "Waiting for votes, but majority still not reached.";
        break;
    default:
        msg = "Unknown reason code.";
        break;
    }
    lastlog_time = time(NULL);
    serverLog(LL_WARNING,"Currently unable to failover: %s", msg);
}

/* This function implements the final part of automatic and manual failovers,
 * where the slave grabs its master's hash slots, and propagates the new
 * configuration.
 *
 * Note that it's up to the caller to be sure that the node got a new
 * configuration epoch already. */
void clusterFailoverReplaceYourMaster(void) {
    int j;
    clusterNode *oldmaster = myself->slaveof;

    if (nodeIsMaster(myself) || oldmaster == NULL) return;

    /* 1) Turn this node into a master. */
    clusterSetNodeAsMaster(myself);
    replicationUnsetMaster();

    /* 2) Claim all the slots assigned to our master. */
    for (j = 0; j < CLUSTER_SLOTS; j++) {
        if (clusterNodeGetSlotBit(oldmaster,j)) {
            clusterDelSlot(j);
            clusterAddSlot(myself,j);
        }
    }

    /* 3) Update state and save config. */
    clusterUpdateState();
    clusterSaveConfigOrDie(1);

    /* 4) Pong all the other nodes so that they can update the state
     *    accordingly and detect that we switched to master role. */
    clusterBroadcastPong(CLUSTER_BROADCAST_ALL);

    /* 5) If there was a manual failover in progress, clear the state. */
    resetManualFailover();
}

/* This function is called if we are a slave node and our master serving
 * a non-zero amount of hash slots is in FAIL state.
 *
 * The gaol of this function is:
 * 1) To check if we are able to perform a failover, is our data updated?
 * 2) Try to get elected by masters.
 * 3) Perform the failover informing all the other nodes.
 */
void clusterHandleSlaveFailover(void) {
    mstime_t data_age;
    mstime_t auth_age = mstime() - server.cluster->failover_auth_time;
    int needed_quorum = (server.cluster->size / 2) + 1;
    int manual_failover = server.cluster->mf_end != 0 &&
                          server.cluster->mf_can_start;
    mstime_t auth_timeout, auth_retry_time;

    server.cluster->todo_before_sleep &= ~CLUSTER_TODO_HANDLE_FAILOVER;

    /* Compute the failover timeout (the max time we have to send votes
     * and wait for replies), and the failover retry time (the time to wait
     * before trying to get voted again).
     *
     * Timeout is MAX(NODE_TIMEOUT*2,2000) milliseconds.
     * Retry is two times the Timeout.
     */
    auth_timeout = server.cluster_node_timeout*2;
    if (auth_timeout < 2000) auth_timeout = 2000;
    auth_retry_time = auth_timeout*2;

    /* Pre conditions to run the function, that must be met both in case
     * of an automatic or manual failover:
     * 1) We are a slave.
     * 2) Our master is flagged as FAIL, or this is a manual failover.
     * 3) We don't have the no failover configuration set, and this is
     *    not a manual failover.
     * 4) It is serving slots. */
    if (nodeIsMaster(myself) ||
        myself->slaveof == NULL ||
        (!nodeFailed(myself->slaveof) && !manual_failover) ||
        (server.cluster_slave_no_failover && !manual_failover) ||
        myself->slaveof->numslots == 0)
    {
        /* There are no reasons to failover, so we set the reason why we
         * are returning without failing over to NONE. */
        server.cluster->cant_failover_reason = CLUSTER_CANT_FAILOVER_NONE;
        return;
    }

    /* Set data_age to the number of seconds we are disconnected from
     * the master. */
    if (server.repl_state == REPL_STATE_CONNECTED) {
        data_age = (mstime_t)(server.unixtime - server.master->lastinteraction)
                   * 1000;
    } else {
        data_age = (mstime_t)(server.unixtime - server.repl_down_since) * 1000;
    }

    /* Remove the node timeout from the data age as it is fine that we are
     * disconnected from our master at least for the time it was down to be
     * flagged as FAIL, that's the baseline. */
    if (data_age > server.cluster_node_timeout)
        data_age -= server.cluster_node_timeout;

    /* Check if our data is recent enough according to the slave validity
     * factor configured by the user.
     *
     * Check bypassed for manual failovers. */
    if (server.cluster_slave_validity_factor &&
        data_age >
        (((mstime_t)server.repl_ping_slave_period * 1000) +
         (server.cluster_node_timeout * server.cluster_slave_validity_factor)))
    {
        if (!manual_failover) {
            clusterLogCantFailover(CLUSTER_CANT_FAILOVER_DATA_AGE);
            return;
        }
    }

    /* If the previous failover attempt timedout and the retry time has
     * elapsed, we can setup a new one. */
    if (auth_age > auth_retry_time) {
        server.cluster->failover_auth_time = mstime() +
            500 + /* Fixed delay of 500 milliseconds, let FAIL msg propagate. */
            random() % 500; /* Random delay between 0 and 500 milliseconds. */
        server.cluster->failover_auth_count = 0;
        server.cluster->failover_auth_sent = 0;
        server.cluster->failover_auth_rank = clusterGetSlaveRank();
        /* We add another delay that is proportional to the slave rank.
         * Specifically 1 second * rank. This way slaves that have a probably
         * less updated replication offset, are penalized. */
        server.cluster->failover_auth_time +=
            server.cluster->failover_auth_rank * 1000;
        /* However if this is a manual failover, no delay is needed. */
        if (server.cluster->mf_end) {
            server.cluster->failover_auth_time = mstime();
            server.cluster->failover_auth_rank = 0;
	    clusterDoBeforeSleep(CLUSTER_TODO_HANDLE_FAILOVER);
        }
        serverLog(LL_WARNING,
            "Start of election delayed for %lld milliseconds "
            "(rank #%d, offset %lld).",
            server.cluster->failover_auth_time - mstime(),
            server.cluster->failover_auth_rank,
            replicationGetSlaveOffset());
        /* Now that we have a scheduled election, broadcast our offset
         * to all the other slaves so that they'll updated their offsets
         * if our offset is better. */
        clusterBroadcastPong(CLUSTER_BROADCAST_LOCAL_SLAVES);
        return;
    }

    /* It is possible that we received more updated offsets from other
     * slaves for the same master since we computed our election delay.
     * Update the delay if our rank changed.
     *
     * Not performed if this is a manual failover. */
    if (server.cluster->failover_auth_sent == 0 &&
        server.cluster->mf_end == 0)
    {
        int newrank = clusterGetSlaveRank();
        if (newrank > server.cluster->failover_auth_rank) {
            long long added_delay =
                (newrank - server.cluster->failover_auth_rank) * 1000;
            server.cluster->failover_auth_time += added_delay;
            server.cluster->failover_auth_rank = newrank;
            serverLog(LL_WARNING,
                "Replica rank updated to #%d, added %lld milliseconds of delay.",
                newrank, added_delay);
        }
    }

    /* Return ASAP if we can't still start the election. */
    if (mstime() < server.cluster->failover_auth_time) {
        clusterLogCantFailover(CLUSTER_CANT_FAILOVER_WAITING_DELAY);
        return;
    }

    /* Return ASAP if the election is too old to be valid. */
    if (auth_age > auth_timeout) {
        clusterLogCantFailover(CLUSTER_CANT_FAILOVER_EXPIRED);
        return;
    }

    /* Ask for votes if needed. */
    if (server.cluster->failover_auth_sent == 0) {
        server.cluster->currentEpoch++;
        server.cluster->failover_auth_epoch = server.cluster->currentEpoch;
        serverLog(LL_WARNING,"Starting a failover election for epoch %llu.",
            (unsigned long long) server.cluster->currentEpoch);
        clusterRequestFailoverAuth();
        server.cluster->failover_auth_sent = 1;
        clusterDoBeforeSleep(CLUSTER_TODO_SAVE_CONFIG|
                             CLUSTER_TODO_UPDATE_STATE|
                             CLUSTER_TODO_FSYNC_CONFIG);
        return; /* Wait for replies. */
    }

    /* Check if we reached the quorum. */
    if (server.cluster->failover_auth_count >= needed_quorum) {
        /* We have the quorum, we can finally failover the master. */

        serverLog(LL_WARNING,
            "Failover election won: I'm the new master.");

        /* Update my configEpoch to the epoch of the election. */
        if (myself->configEpoch < server.cluster->failover_auth_epoch) {
            myself->configEpoch = server.cluster->failover_auth_epoch;
            serverLog(LL_WARNING,
                "configEpoch set to %llu after successful failover",
                (unsigned long long) myself->configEpoch);
        }

        /* Take responsibility for the cluster slots. */
        clusterFailoverReplaceYourMaster();
    } else {
        clusterLogCantFailover(CLUSTER_CANT_FAILOVER_WAITING_VOTES);
    }
}

/* -----------------------------------------------------------------------------
 * CLUSTER slave migration
 *
 * Slave migration is the process that allows a slave of a master that is
 * already covered by at least another slave, to "migrate" to a master that
 * is orpaned, that is, left with no working slaves.
 * ------------------------------------------------------------------------- */

/* This function is responsible to decide if this replica should be migrated
 * to a different (orphaned) master. It is called by the clusterCron() function
 * only if:
 *
 * 1) We are a slave node.
 * 2) It was detected that there is at least one orphaned master in
 *    the cluster.
 * 3) We are a slave of one of the masters with the greatest number of
 *    slaves.
 *
 * This checks are performed by the caller since it requires to iterate
 * the nodes anyway, so we spend time into clusterHandleSlaveMigration()
 * if definitely needed.
 *
 * The fuction is called with a pre-computed max_slaves, that is the max
 * number of working (not in FAIL state) slaves for a single master.
 *
 * Additional conditions for migration are examined inside the function.
 */
void clusterHandleSlaveMigration(int max_slaves) {
    int j, okslaves = 0;
    clusterNode *mymaster = myself->slaveof, *target = NULL, *candidate = NULL;
    dictIterator *di;
    dictEntry *de;

    /* Step 1: Don't migrate if the cluster state is not ok. */
    if (server.cluster->state != CLUSTER_OK) return;

    /* Step 2: Don't migrate if my master will not be left with at least
     *         'migration-barrier' slaves after my migration. */
    if (mymaster == NULL) return;
    for (j = 0; j < mymaster->numslaves; j++)
        if (!nodeFailed(mymaster->slaves[j]) &&
            !nodeTimedOut(mymaster->slaves[j])) okslaves++;
    if (okslaves <= server.cluster_migration_barrier) return;

    /* Step 3: Identify a candidate for migration, and check if among the
     * masters with the greatest number of ok slaves, I'm the one with the
     * smallest node ID (the "candidate slave").
     *
     * Note: this means that eventually a replica migration will occur
     * since slaves that are reachable again always have their FAIL flag
     * cleared, so eventually there must be a candidate. At the same time
     * this does not mean that there are no race conditions possible (two
     * slaves migrating at the same time), but this is unlikely to
     * happen, and harmless when happens. */
    candidate = myself;
    di = dictGetSafeIterator(server.cluster->nodes);
    while((de = dictNext(di)) != NULL) {
        clusterNode *node = dictGetVal(de);
        int okslaves = 0, is_orphaned = 1;

        /* We want to migrate only if this master is working, orphaned, and
         * used to have slaves or if failed over a master that had slaves
         * (MIGRATE_TO flag). This way we only migrate to instances that were
         * supposed to have replicas. */
        if (nodeIsSlave(node) || nodeFailed(node)) is_orphaned = 0;
        if (!(node->flags & CLUSTER_NODE_MIGRATE_TO)) is_orphaned = 0;

        /* Check number of working slaves. */
        if (nodeIsMaster(node)) okslaves = clusterCountNonFailingSlaves(node);
        if (okslaves > 0) is_orphaned = 0;

        if (is_orphaned) {
            if (!target && node->numslots > 0) target = node;

            /* Track the starting time of the orphaned condition for this
             * master. */
            if (!node->orphaned_time) node->orphaned_time = mstime();
        } else {
            node->orphaned_time = 0;
        }

        /* Check if I'm the slave candidate for the migration: attached
         * to a master with the maximum number of slaves and with the smallest
         * node ID. */
        if (okslaves == max_slaves) {
            for (j = 0; j < node->numslaves; j++) {
                if (memcmp(node->slaves[j]->name,
                           candidate->name,
                           CLUSTER_NAMELEN) < 0)
                {
                    candidate = node->slaves[j];
                }
            }
        }
    }
    dictReleaseIterator(di);

    /* Step 4: perform the migration if there is a target, and if I'm the
     * candidate, but only if the master is continuously orphaned for a
     * couple of seconds, so that during failovers, we give some time to
     * the natural slaves of this instance to advertise their switch from
     * the old master to the new one. */
    if (target && candidate == myself &&
        (mstime()-target->orphaned_time) > CLUSTER_SLAVE_MIGRATION_DELAY &&
       !(server.cluster_module_flags & CLUSTER_MODULE_FLAG_NO_FAILOVER))
    {
        serverLog(LL_WARNING,"Migrating to orphaned master %.40s",
            target->name);
        clusterSetMaster(target);
    }
}

/* -----------------------------------------------------------------------------
 * CLUSTER manual failover
 *
 * This are the important steps performed by slaves during a manual failover:
 * 1) User send CLUSTER FAILOVER command. The failover state is initialized
 *    setting mf_end to the millisecond unix time at which we'll abort the
 *    attempt.
 * 2) Slave sends a MFSTART message to the master requesting to pause clients
 *    for two times the manual failover timeout CLUSTER_MF_TIMEOUT.
 *    When master is paused for manual failover, it also starts to flag
 *    packets with CLUSTERMSG_FLAG0_PAUSED.
 * 3) Slave waits for master to send its replication offset flagged as PAUSED.
 * 4) If slave received the offset from the master, and its offset matches,
 *    mf_can_start is set to 1, and clusterHandleSlaveFailover() will perform
 *    the failover as usually, with the difference that the vote request
 *    will be modified to force masters to vote for a slave that has a
 *    working master.
 *
 * From the point of view of the master things are simpler: when a
 * PAUSE_CLIENTS packet is received the master sets mf_end as well and
 * the sender in mf_slave. During the time limit for the manual failover
 * the master will just send PINGs more often to this slave, flagged with
 * the PAUSED flag, so that the slave will set mf_master_offset when receiving
 * a packet from the master with this flag set.
 *
 * The gaol of the manual failover is to perform a fast failover without
 * data loss due to the asynchronous master-slave replication.
 * -------------------------------------------------------------------------- */

/* Reset the manual failover state. This works for both masters and slavesa
 * as all the state about manual failover is cleared.
 *
 * The function can be used both to initialize the manual failover state at
 * startup or to abort a manual failover in progress. */
void resetManualFailover(void) {
    if (server.cluster->mf_end && clientsArePaused()) {
        server.clients_pause_end_time = 0;
        clientsArePaused(); /* Just use the side effect of the function. */
    }
    server.cluster->mf_end = 0; /* No manual failover in progress. */
    server.cluster->mf_can_start = 0;
    server.cluster->mf_slave = NULL;
    server.cluster->mf_master_offset = 0;
}

/* If a manual failover timed out, abort it. */
void manualFailoverCheckTimeout(void) {
    if (server.cluster->mf_end && server.cluster->mf_end < mstime()) {
        serverLog(LL_WARNING,"Manual failover timed out.");
        resetManualFailover();
    }
}

/* This function is called from the cluster cron function in order to go
 * forward with a manual failover state machine. */
void clusterHandleManualFailover(void) {
    /* Return ASAP if no manual failover is in progress. */
    if (server.cluster->mf_end == 0) return;

    /* If mf_can_start is non-zero, the failover was already triggered so the
     * next steps are performed by clusterHandleSlaveFailover(). */
    if (server.cluster->mf_can_start) return;

    if (server.cluster->mf_master_offset == 0) return; /* Wait for offset... */

    if (server.cluster->mf_master_offset == replicationGetSlaveOffset()) {
        /* Our replication offset matches the master replication offset
         * announced after clients were paused. We can start the failover. */
        server.cluster->mf_can_start = 1;
        serverLog(LL_WARNING,
            "All master replication stream processed, "
            "manual failover can start.");
    }
}

/* -----------------------------------------------------------------------------
 * CLUSTER cron job
 * -------------------------------------------------------------------------- */

/* This is executed 10 times every second */
void clusterCron(void) {
    dictIterator *di;
    dictEntry *de;
    int update_state = 0;
    int orphaned_masters; /* How many masters there are without ok slaves. */
    int max_slaves; /* Max number of ok slaves for a single master. */
    int this_slaves; /* Number of ok slaves for our master (if we are slave). */
    mstime_t min_pong = 0, now = mstime();
    clusterNode *min_pong_node = NULL;
    static unsigned long long iteration = 0;
    mstime_t handshake_timeout;

    iteration++; /* Number of times this function was called so far. */

    /* We want to take myself->ip in sync with the cluster-announce-ip option.
     * The option can be set at runtime via CONFIG SET, so we periodically check
     * if the option changed to reflect this into myself->ip. */
    {
        static char *prev_ip = NULL;
        char *curr_ip = server.cluster_announce_ip;
        int changed = 0;

        if (prev_ip == NULL && curr_ip != NULL) changed = 1;
        else if (prev_ip != NULL && curr_ip == NULL) changed = 1;
        else if (prev_ip && curr_ip && strcmp(prev_ip,curr_ip)) changed = 1;

        if (changed) {
            if (prev_ip) zfree(prev_ip);
            prev_ip = curr_ip;

            if (curr_ip) {
                /* We always take a copy of the previous IP address, by
                 * duplicating the string. This way later we can check if
                 * the address really changed. */
                prev_ip = zstrdup(prev_ip);
                strncpy(myself->ip,server.cluster_announce_ip,NET_IP_STR_LEN);
                myself->ip[NET_IP_STR_LEN-1] = '\0';
            } else {
                myself->ip[0] = '\0'; /* Force autodetection. */
            }
        }
    }

    /* The handshake timeout is the time after which a handshake node that was
     * not turned into a normal node is removed from the nodes. Usually it is
     * just the NODE_TIMEOUT value, but when NODE_TIMEOUT is too small we use
     * the value of 1 second. */
    handshake_timeout = server.cluster_node_timeout;
    if (handshake_timeout < 1000) handshake_timeout = 1000;

    /* Update myself flags. */
    clusterUpdateMyselfFlags();

    /* Check if we have disconnected nodes and re-establish the connection.
     * Also update a few stats while we are here, that can be used to make
     * better decisions in other part of the code. */
    di = dictGetSafeIterator(server.cluster->nodes);
    server.cluster->stats_pfail_nodes = 0;
    while((de = dictNext(di)) != NULL) {
        clusterNode *node = dictGetVal(de);

        /* Not interested in reconnecting the link with myself or nodes
         * for which we have no address. */
        if (node->flags & (CLUSTER_NODE_MYSELF|CLUSTER_NODE_NOADDR)) continue;

        if (node->flags & CLUSTER_NODE_PFAIL)
            server.cluster->stats_pfail_nodes++;

        /* A Node in HANDSHAKE state has a limited lifespan equal to the
         * configured node timeout. */
        if (nodeInHandshake(node) && now - node->ctime > handshake_timeout) {
            clusterDelNode(node);
            continue;
        }

        if (node->link == NULL) {
            clusterLink *link = createClusterLink(node);
            link->conn = server.tls_cluster ? connCreateTLS() : connCreateSocket();
            connSetPrivateData(link->conn, link);
            if (connConnect(link->conn, node->ip, node->cport, NET_FIRST_BIND_ADDR,
                        clusterLinkConnectHandler) == -1) {
                /* We got a synchronous error from connect before
                 * clusterSendPing() had a chance to be called.
                 * If node->ping_sent is zero, failure detection can't work,
                 * so we claim we actually sent a ping now (that will
                 * be really sent as soon as the link is obtained). */
                if (node->ping_sent == 0) node->ping_sent = mstime();
                serverLog(LL_DEBUG, "Unable to connect to "
                    "Cluster Node [%s]:%d -> %s", node->ip,
                    node->cport, server.neterr);

                freeClusterLink(link);
                continue;
            }
            node->link = link;
        }
    }
    dictReleaseIterator(di);

    /* Ping some random node 1 time every 10 iterations, so that we usually ping
     * one random node every second. */
    if (!(iteration % 10)) {
        int j;

        /* Check a few random nodes and ping the one with the oldest
         * pong_received time. */
        for (j = 0; j < 5; j++) {
            de = dictGetRandomKey(server.cluster->nodes);
            clusterNode *this = dictGetVal(de);

            /* Don't ping nodes disconnected or with a ping currently active. */
            if (this->link == NULL || this->ping_sent != 0) continue;
            if (this->flags & (CLUSTER_NODE_MYSELF|CLUSTER_NODE_HANDSHAKE))
                continue;
            if (min_pong_node == NULL || min_pong > this->pong_received) {
                min_pong_node = this;
                min_pong = this->pong_received;
            }
        }
        if (min_pong_node) {
            serverLog(LL_DEBUG,"Pinging node %.40s", min_pong_node->name);
            clusterSendPing(min_pong_node->link, CLUSTERMSG_TYPE_PING);
        }
    }

    /* Iterate nodes to check if we need to flag something as failing.
     * This loop is also responsible to:
     * 1) Check if there are orphaned masters (masters without non failing
     *    slaves).
     * 2) Count the max number of non failing slaves for a single master.
     * 3) Count the number of slaves for our master, if we are a slave. */
    orphaned_masters = 0;
    max_slaves = 0;
    this_slaves = 0;
    di = dictGetSafeIterator(server.cluster->nodes);
    while((de = dictNext(di)) != NULL) {
        clusterNode *node = dictGetVal(de);
        now = mstime(); /* Use an updated time at every iteration. */
        mstime_t delay;

        if (node->flags &
            (CLUSTER_NODE_MYSELF|CLUSTER_NODE_NOADDR|CLUSTER_NODE_HANDSHAKE))
                continue;

        /* Orphaned master check, useful only if the current instance
         * is a slave that may migrate to another master. */
        if (nodeIsSlave(myself) && nodeIsMaster(node) && !nodeFailed(node)) {
            int okslaves = clusterCountNonFailingSlaves(node);

            /* A master is orphaned if it is serving a non-zero number of
             * slots, have no working slaves, but used to have at least one
             * slave, or failed over a master that used to have slaves. */
            if (okslaves == 0 && node->numslots > 0 &&
                node->flags & CLUSTER_NODE_MIGRATE_TO)
            {
                orphaned_masters++;
            }
            if (okslaves > max_slaves) max_slaves = okslaves;
            if (nodeIsSlave(myself) && myself->slaveof == node)
                this_slaves = okslaves;
        }

        /* If we are waiting for the PONG more than half the cluster
         * timeout, reconnect the link: maybe there is a connection
         * issue even if the node is alive. */
        if (node->link && /* is connected */
            now - node->link->ctime >
            server.cluster_node_timeout && /* was not already reconnected */
            node->ping_sent && /* we already sent a ping */
            node->pong_received < node->ping_sent && /* still waiting pong */
            /* and we are waiting for the pong more than timeout/2 */
            now - node->ping_sent > server.cluster_node_timeout/2)
        {
            /* Disconnect the link, it will be reconnected automatically. */
            freeClusterLink(node->link);
        }

        /* If we have currently no active ping in this instance, and the
         * received PONG is older than half the cluster timeout, send
         * a new ping now, to ensure all the nodes are pinged without
         * a too big delay. */
        if (node->link &&
            node->ping_sent == 0 &&
            (now - node->pong_received) > server.cluster_node_timeout/2)
        {
            clusterSendPing(node->link, CLUSTERMSG_TYPE_PING);
            continue;
        }

        /* If we are a master and one of the slaves requested a manual
         * failover, ping it continuously. */
        if (server.cluster->mf_end &&
            nodeIsMaster(myself) &&
            server.cluster->mf_slave == node &&
            node->link)
        {
            clusterSendPing(node->link, CLUSTERMSG_TYPE_PING);
            continue;
        }

        /* Check only if we have an active ping for this instance. */
        if (node->ping_sent == 0) continue;

        /* Compute the delay of the PONG. Note that if we already received
         * the PONG, then node->ping_sent is zero, so can't reach this
         * code at all. */
        delay = now - node->ping_sent;

        if (delay > server.cluster_node_timeout) {
            /* Timeout reached. Set the node as possibly failing if it is
             * not already in this state. */
            if (!(node->flags & (CLUSTER_NODE_PFAIL|CLUSTER_NODE_FAIL))) {
                serverLog(LL_DEBUG,"*** NODE %.40s possibly failing",
                    node->name);
                node->flags |= CLUSTER_NODE_PFAIL;
                update_state = 1;
            }
        }
    }
    dictReleaseIterator(di);

    /* If we are a slave node but the replication is still turned off,
     * enable it if we know the address of our master and it appears to
     * be up. */
    if (nodeIsSlave(myself) &&
        server.masterhost == NULL &&
        myself->slaveof &&
        nodeHasAddr(myself->slaveof))
    {
        replicationSetMaster(myself->slaveof->ip, myself->slaveof->port);
    }

    /* Abourt a manual failover if the timeout is reached. */
    manualFailoverCheckTimeout();

    if (nodeIsSlave(myself)) {
        clusterHandleManualFailover();
        if (!(server.cluster_module_flags & CLUSTER_MODULE_FLAG_NO_FAILOVER))
            clusterHandleSlaveFailover();
        /* If there are orphaned slaves, and we are a slave among the masters
         * with the max number of non-failing slaves, consider migrating to
         * the orphaned masters. Note that it does not make sense to try
         * a migration if there is no master with at least *two* working
         * slaves. */
        if (orphaned_masters && max_slaves >= 2 && this_slaves == max_slaves)
            clusterHandleSlaveMigration(max_slaves);
    }

    if (update_state || server.cluster->state == CLUSTER_FAIL)
        clusterUpdateState();
}

/* This function is called before the event handler returns to sleep for
 * events. It is useful to perform operations that must be done ASAP in
 * reaction to events fired but that are not safe to perform inside event
 * handlers, or to perform potentially expansive tasks that we need to do
 * a single time before replying to clients. */
void clusterBeforeSleep(void) {
    /* Handle failover, this is needed when it is likely that there is already
     * the quorum from masters in order to react fast. */
    if (server.cluster->todo_before_sleep & CLUSTER_TODO_HANDLE_FAILOVER)
        clusterHandleSlaveFailover();

    /* Update the cluster state. */
    if (server.cluster->todo_before_sleep & CLUSTER_TODO_UPDATE_STATE)
        clusterUpdateState();

    /* Save the config, possibly using fsync. */
    if (server.cluster->todo_before_sleep & CLUSTER_TODO_SAVE_CONFIG) {
        int fsync = server.cluster->todo_before_sleep &
                    CLUSTER_TODO_FSYNC_CONFIG;
        clusterSaveConfigOrDie(fsync);
    }

    /* Reset our flags (not strictly needed since every single function
     * called for flags set should be able to clear its flag). */
    server.cluster->todo_before_sleep = 0;
}

void clusterDoBeforeSleep(int flags) {
    server.cluster->todo_before_sleep |= flags;
}

/* -----------------------------------------------------------------------------
 * Slots management
 * -------------------------------------------------------------------------- */

/* Test bit 'pos' in a generic bitmap. Return 1 if the bit is set,
 * otherwise 0. */
int bitmapTestBit(unsigned char *bitmap, int pos) {
    off_t byte = pos/8;
    int bit = pos&7;
    return (bitmap[byte] & (1<<bit)) != 0;
}

/* Set the bit at position 'pos' in a bitmap. */
void bitmapSetBit(unsigned char *bitmap, int pos) {
    off_t byte = pos/8;
    int bit = pos&7;
    bitmap[byte] |= 1<<bit;
}

/* Clear the bit at position 'pos' in a bitmap. */
void bitmapClearBit(unsigned char *bitmap, int pos) {
    off_t byte = pos/8;
    int bit = pos&7;
    bitmap[byte] &= ~(1<<bit);
}

/* Return non-zero if there is at least one master with slaves in the cluster.
 * Otherwise zero is returned. Used by clusterNodeSetSlotBit() to set the
 * MIGRATE_TO flag the when a master gets the first slot. */
int clusterMastersHaveSlaves(void) {
    dictIterator *di = dictGetSafeIterator(server.cluster->nodes);
    dictEntry *de;
    int slaves = 0;
    while((de = dictNext(di)) != NULL) {
        clusterNode *node = dictGetVal(de);

        if (nodeIsSlave(node)) continue;
        slaves += node->numslaves;
    }
    dictReleaseIterator(di);
    return slaves != 0;
}

/* Set the slot bit and return the old value. */
int clusterNodeSetSlotBit(clusterNode *n, int slot) {
    int old = bitmapTestBit(n->slots,slot);
    bitmapSetBit(n->slots,slot);
    if (!old) {
        n->numslots++;
        /* When a master gets its first slot, even if it has no slaves,
         * it gets flagged with MIGRATE_TO, that is, the master is a valid
         * target for replicas migration, if and only if at least one of
         * the other masters has slaves right now.
         *
         * Normally masters are valid targerts of replica migration if:
         * 1. The used to have slaves (but no longer have).
         * 2. They are slaves failing over a master that used to have slaves.
         *
         * However new masters with slots assigned are considered valid
         * migration tagets if the rest of the cluster is not a slave-less.
         *
         * See https://github.com/antirez/redis/issues/3043 for more info. */
        if (n->numslots == 1 && clusterMastersHaveSlaves())
            n->flags |= CLUSTER_NODE_MIGRATE_TO;
    }
    return old;
}

/* Clear the slot bit and return the old value. */
int clusterNodeClearSlotBit(clusterNode *n, int slot) {
    int old = bitmapTestBit(n->slots,slot);
    bitmapClearBit(n->slots,slot);
    if (old) n->numslots--;
    return old;
}

/* Return the slot bit from the cluster node structure. */
int clusterNodeGetSlotBit(clusterNode *n, int slot) {
    return bitmapTestBit(n->slots,slot);
}

/* Add the specified slot to the list of slots that node 'n' will
 * serve. Return C_OK if the operation ended with success.
 * If the slot is already assigned to another instance this is considered
 * an error and C_ERR is returned. */
int clusterAddSlot(clusterNode *n, int slot) {
    if (server.cluster->slots[slot]) return C_ERR;
    clusterNodeSetSlotBit(n,slot);
    server.cluster->slots[slot] = n;
    return C_OK;
}

/* Delete the specified slot marking it as unassigned.
 * Returns C_OK if the slot was assigned, otherwise if the slot was
 * already unassigned C_ERR is returned. */
int clusterDelSlot(int slot) {
    clusterNode *n = server.cluster->slots[slot];

    if (!n) return C_ERR;
    serverAssert(clusterNodeClearSlotBit(n,slot) == 1);
    server.cluster->slots[slot] = NULL;
    return C_OK;
}

/* Delete all the slots associated with the specified node.
 * The number of deleted slots is returned. */
int clusterDelNodeSlots(clusterNode *node) {
    int deleted = 0, j;

    for (j = 0; j < CLUSTER_SLOTS; j++) {
        if (clusterNodeGetSlotBit(node,j)) {
            clusterDelSlot(j);
            deleted++;
        }
    }
    return deleted;
}

/* Clear the migrating / importing state for all the slots.
 * This is useful at initialization and when turning a master into slave. */
void clusterCloseAllSlots(void) {
    memset(server.cluster->migrating_slots_to,0,
        sizeof(server.cluster->migrating_slots_to));
    memset(server.cluster->importing_slots_from,0,
        sizeof(server.cluster->importing_slots_from));
}

/* -----------------------------------------------------------------------------
 * Cluster state evaluation function
 * -------------------------------------------------------------------------- */

/* The following are defines that are only used in the evaluation function
 * and are based on heuristics. Actually the main point about the rejoin and
 * writable delay is that they should be a few orders of magnitude larger
 * than the network latency. */
#define CLUSTER_MAX_REJOIN_DELAY 5000
#define CLUSTER_MIN_REJOIN_DELAY 500
#define CLUSTER_WRITABLE_DELAY 2000

void clusterUpdateState(void) {
    int j, new_state;
    int reachable_masters = 0;
    static mstime_t among_minority_time;
    static mstime_t first_call_time = 0;

    server.cluster->todo_before_sleep &= ~CLUSTER_TODO_UPDATE_STATE;

    /* If this is a master node, wait some time before turning the state
     * into OK, since it is not a good idea to rejoin the cluster as a writable
     * master, after a reboot, without giving the cluster a chance to
     * reconfigure this node. Note that the delay is calculated starting from
     * the first call to this function and not since the server start, in order
     * to don't count the DB loading time. */
    if (first_call_time == 0) first_call_time = mstime();
    if (nodeIsMaster(myself) &&
        server.cluster->state == CLUSTER_FAIL &&
        mstime() - first_call_time < CLUSTER_WRITABLE_DELAY) return;

    /* Start assuming the state is OK. We'll turn it into FAIL if there
     * are the right conditions. */
    new_state = CLUSTER_OK;

    /* Check if all the slots are covered. */
    if (server.cluster_require_full_coverage) {
        for (j = 0; j < CLUSTER_SLOTS; j++) {
            if (server.cluster->slots[j] == NULL ||
                server.cluster->slots[j]->flags & (CLUSTER_NODE_FAIL))
            {
                new_state = CLUSTER_FAIL;
                break;
            }
        }
    }

    /* Compute the cluster size, that is the number of master nodes
     * serving at least a single slot.
     *
     * At the same time count the number of reachable masters having
     * at least one slot. */
    {
        dictIterator *di;
        dictEntry *de;

        server.cluster->size = 0;
        di = dictGetSafeIterator(server.cluster->nodes);
        while((de = dictNext(di)) != NULL) {
            clusterNode *node = dictGetVal(de);

            if (nodeIsMaster(node) && node->numslots) {
                server.cluster->size++;
                if ((node->flags & (CLUSTER_NODE_FAIL|CLUSTER_NODE_PFAIL)) == 0)
                    reachable_masters++;
            }
        }
        dictReleaseIterator(di);
    }

    /* If we are in a minority partition, change the cluster state
     * to FAIL. */
    {
        int needed_quorum = (server.cluster->size / 2) + 1;

        if (reachable_masters < needed_quorum) {
            new_state = CLUSTER_FAIL;
            among_minority_time = mstime();
        }
    }

    /* Log a state change */
    if (new_state != server.cluster->state) {
        mstime_t rejoin_delay = server.cluster_node_timeout;

        /* If the instance is a master and was partitioned away with the
         * minority, don't let it accept queries for some time after the
         * partition heals, to make sure there is enough time to receive
         * a configuration update. */
        if (rejoin_delay > CLUSTER_MAX_REJOIN_DELAY)
            rejoin_delay = CLUSTER_MAX_REJOIN_DELAY;
        if (rejoin_delay < CLUSTER_MIN_REJOIN_DELAY)
            rejoin_delay = CLUSTER_MIN_REJOIN_DELAY;

        if (new_state == CLUSTER_OK &&
            nodeIsMaster(myself) &&
            mstime() - among_minority_time < rejoin_delay)
        {
            return;
        }

        /* Change the state and log the event. */
        serverLog(LL_WARNING,"Cluster state changed: %s",
            new_state == CLUSTER_OK ? "ok" : "fail");
        server.cluster->state = new_state;
    }
}

/* This function is called after the node startup in order to verify that data
 * loaded from disk is in agreement with the cluster configuration:
 *
 * 1) If we find keys about hash slots we have no responsibility for, the
 *    following happens:
 *    A) If no other node is in charge according to the current cluster
 *       configuration, we add these slots to our node.
 *    B) If according to our config other nodes are already in charge for
 *       this lots, we set the slots as IMPORTING from our point of view
 *       in order to justify we have those slots, and in order to make
 *       redis-trib aware of the issue, so that it can try to fix it.
 * 2) If we find data in a DB different than DB0 we return C_ERR to
 *    signal the caller it should quit the server with an error message
 *    or take other actions.
 *
 * The function always returns C_OK even if it will try to correct
 * the error described in "1". However if data is found in DB different
 * from DB0, C_ERR is returned.
 *
 * The function also uses the logging facility in order to warn the user
 * about desynchronizations between the data we have in memory and the
 * cluster configuration. */
int verifyClusterConfigWithData(void) {
    int j;
    int update_config = 0;

    /* Return ASAP if a module disabled cluster redirections. In that case
     * every master can store keys about every possible hash slot. */
    if (server.cluster_module_flags & CLUSTER_MODULE_FLAG_NO_REDIRECTION)
        return C_OK;

    /* If this node is a slave, don't perform the check at all as we
     * completely depend on the replication stream. */
    if (nodeIsSlave(myself)) return C_OK;

    /* Make sure we only have keys in DB0. */
    for (j = 1; j < server.dbnum; j++) {
        if (dictSize(server.db[j].dict)) return C_ERR;
    }

    /* Check that all the slots we see populated memory have a corresponding
     * entry in the cluster table. Otherwise fix the table. */
    for (j = 0; j < CLUSTER_SLOTS; j++) {
        if (!countKeysInSlot(j)) continue; /* No keys in this slot. */
        /* Check if we are assigned to this slot or if we are importing it.
         * In both cases check the next slot as the configuration makes
         * sense. */
        if (server.cluster->slots[j] == myself ||
            server.cluster->importing_slots_from[j] != NULL) continue;

        /* If we are here data and cluster config don't agree, and we have
         * slot 'j' populated even if we are not importing it, nor we are
         * assigned to this slot. Fix this condition. */

        update_config++;
        /* Case A: slot is unassigned. Take responsibility for it. */
        if (server.cluster->slots[j] == NULL) {
            serverLog(LL_WARNING, "I have keys for unassigned slot %d. "
                                    "Taking responsibility for it.",j);
            clusterAddSlot(myself,j);
        } else {
            serverLog(LL_WARNING, "I have keys for slot %d, but the slot is "
                                    "assigned to another node. "
                                    "Setting it to importing state.",j);
            server.cluster->importing_slots_from[j] = server.cluster->slots[j];
        }
    }
    if (update_config) clusterSaveConfigOrDie(1);
    return C_OK;
}

/* -----------------------------------------------------------------------------
 * SLAVE nodes handling
 * -------------------------------------------------------------------------- */

/* Set the specified node 'n' as master for this node.
 * If this node is currently a master, it is turned into a slave. */
void clusterSetMaster(clusterNode *n) {
    serverAssert(n != myself);
    serverAssert(myself->numslots == 0);

    if (nodeIsMaster(myself)) {
        myself->flags &= ~(CLUSTER_NODE_MASTER|CLUSTER_NODE_MIGRATE_TO);
        myself->flags |= CLUSTER_NODE_SLAVE;
        clusterCloseAllSlots();
    } else {
        if (myself->slaveof)
            clusterNodeRemoveSlave(myself->slaveof,myself);
    }
    myself->slaveof = n;
    clusterNodeAddSlave(n,myself);
    replicationSetMaster(n->ip, n->port);
    resetManualFailover();
}

/* -----------------------------------------------------------------------------
 * Nodes to string representation functions.
 * -------------------------------------------------------------------------- */

struct redisNodeFlags {
    uint16_t flag;
    char *name;
};

static struct redisNodeFlags redisNodeFlagsTable[] = {
    {CLUSTER_NODE_MYSELF,       "myself,"},
    {CLUSTER_NODE_MASTER,       "master,"},
    {CLUSTER_NODE_SLAVE,        "slave,"},
    {CLUSTER_NODE_PFAIL,        "fail?,"},
    {CLUSTER_NODE_FAIL,         "fail,"},
    {CLUSTER_NODE_HANDSHAKE,    "handshake,"},
    {CLUSTER_NODE_NOADDR,       "noaddr,"},
    {CLUSTER_NODE_NOFAILOVER,   "nofailover,"}
};

/* Concatenate the comma separated list of node flags to the given SDS
 * string 'ci'. */
sds representClusterNodeFlags(sds ci, uint16_t flags) {
    size_t orig_len = sdslen(ci);
    int i, size = sizeof(redisNodeFlagsTable)/sizeof(struct redisNodeFlags);
    for (i = 0; i < size; i++) {
        struct redisNodeFlags *nodeflag = redisNodeFlagsTable + i;
        if (flags & nodeflag->flag) ci = sdscat(ci, nodeflag->name);
    }
    /* If no flag was added, add the "noflags" special flag. */
    if (sdslen(ci) == orig_len) ci = sdscat(ci,"noflags,");
    sdsIncrLen(ci,-1); /* Remove trailing comma. */
    return ci;
}

/* Generate a csv-alike representation of the specified cluster node.
 * See clusterGenNodesDescription() top comment for more information.
 *
 * The function returns the string representation as an SDS string. */
sds clusterGenNodeDescription(clusterNode *node) {
    int j, start;
    sds ci;

    /* Node coordinates */
    ci = sdscatprintf(sdsempty(),"%.40s %s:%d@%d ",
        node->name,
        node->ip,
        node->port,
        node->cport);

    /* Flags */
    ci = representClusterNodeFlags(ci, node->flags);

    /* Slave of... or just "-" */
    if (node->slaveof)
        ci = sdscatprintf(ci," %.40s ",node->slaveof->name);
    else
        ci = sdscatlen(ci," - ",3);

    /* Latency from the POV of this node, config epoch, link status */
    ci = sdscatprintf(ci,"%lld %lld %llu %s",
        (long long) node->ping_sent,
        (long long) node->pong_received,
        (unsigned long long) node->configEpoch,
        (node->link || node->flags & CLUSTER_NODE_MYSELF) ?
                    "connected" : "disconnected");

    /* Slots served by this instance */
    start = -1;
    for (j = 0; j < CLUSTER_SLOTS; j++) {
        int bit;

        if ((bit = clusterNodeGetSlotBit(node,j)) != 0) {
            if (start == -1) start = j;
        }
        if (start != -1 && (!bit || j == CLUSTER_SLOTS-1)) {
            if (bit && j == CLUSTER_SLOTS-1) j++;

            if (start == j-1) {
                ci = sdscatprintf(ci," %d",start);
            } else {
                ci = sdscatprintf(ci," %d-%d",start,j-1);
            }
            start = -1;
        }
    }

    /* Just for MYSELF node we also dump info about slots that
     * we are migrating to other instances or importing from other
     * instances. */
    if (node->flags & CLUSTER_NODE_MYSELF) {
        for (j = 0; j < CLUSTER_SLOTS; j++) {
            if (server.cluster->migrating_slots_to[j]) {
                ci = sdscatprintf(ci," [%d->-%.40s]",j,
                    server.cluster->migrating_slots_to[j]->name);
            } else if (server.cluster->importing_slots_from[j]) {
                ci = sdscatprintf(ci," [%d-<-%.40s]",j,
                    server.cluster->importing_slots_from[j]->name);
            }
        }
    }
    return ci;
}

/* Generate a csv-alike representation of the nodes we are aware of,
 * including the "myself" node, and return an SDS string containing the
 * representation (it is up to the caller to free it).
 *
 * All the nodes matching at least one of the node flags specified in
 * "filter" are excluded from the output, so using zero as a filter will
 * include all the known nodes in the representation, including nodes in
 * the HANDSHAKE state.
 *
 * The representation obtained using this function is used for the output
 * of the CLUSTER NODES function, and as format for the cluster
 * configuration file (nodes.conf) for a given node. */
sds clusterGenNodesDescription(int filter) {
    sds ci = sdsempty(), ni;
    dictIterator *di;
    dictEntry *de;

    di = dictGetSafeIterator(server.cluster->nodes);
    while((de = dictNext(di)) != NULL) {
        clusterNode *node = dictGetVal(de);

        if (node->flags & filter) continue;
        ni = clusterGenNodeDescription(node);
        ci = sdscatsds(ci,ni);
        sdsfree(ni);
        ci = sdscatlen(ci,"\n",1);
    }
    dictReleaseIterator(di);
    return ci;
}

/* -----------------------------------------------------------------------------
 * CLUSTER command
 * -------------------------------------------------------------------------- */

const char *clusterGetMessageTypeString(int type) {
    switch(type) {
    case CLUSTERMSG_TYPE_PING: return "ping";
    case CLUSTERMSG_TYPE_PONG: return "pong";
    case CLUSTERMSG_TYPE_MEET: return "meet";
    case CLUSTERMSG_TYPE_FAIL: return "fail";
    case CLUSTERMSG_TYPE_PUBLISH: return "publish";
    case CLUSTERMSG_TYPE_FAILOVER_AUTH_REQUEST: return "auth-req";
    case CLUSTERMSG_TYPE_FAILOVER_AUTH_ACK: return "auth-ack";
    case CLUSTERMSG_TYPE_UPDATE: return "update";
    case CLUSTERMSG_TYPE_MFSTART: return "mfstart";
    case CLUSTERMSG_TYPE_MODULE: return "module";
    }
    return "unknown";
}

int getSlotOrReply(client *c, robj *o) {
    long long slot;

    if (getLongLongFromObject(o,&slot) != C_OK ||
        slot < 0 || slot >= CLUSTER_SLOTS)
    {
        addReplyError(c,"Invalid or out of range slot");
        return -1;
    }
    return (int) slot;
}

void clusterReplyMultiBulkSlots(client *c) {
    /* Format: 1) 1) start slot
     *            2) end slot
     *            3) 1) master IP
     *               2) master port
     *               3) node ID
     *            4) 1) replica IP
     *               2) replica port
     *               3) node ID
     *           ... continued until done
     */

    int num_masters = 0;
    void *slot_replylen = addReplyDeferredLen(c);

    dictEntry *de;
    dictIterator *di = dictGetSafeIterator(server.cluster->nodes);
    while((de = dictNext(di)) != NULL) {
        clusterNode *node = dictGetVal(de);
        int j = 0, start = -1;

        /* Skip slaves (that are iterated when producing the output of their
         * master) and  masters not serving any slot. */
        if (!nodeIsMaster(node) || node->numslots == 0) continue;

        for (j = 0; j < CLUSTER_SLOTS; j++) {
            int bit, i;

            if ((bit = clusterNodeGetSlotBit(node,j)) != 0) {
                if (start == -1) start = j;
            }
            if (start != -1 && (!bit || j == CLUSTER_SLOTS-1)) {
                int nested_elements = 3; /* slots (2) + master addr (1). */
                void *nested_replylen = addReplyDeferredLen(c);

                if (bit && j == CLUSTER_SLOTS-1) j++;

                /* If slot exists in output map, add to it's list.
                 * else, create a new output map for this slot */
                if (start == j-1) {
                    addReplyLongLong(c, start); /* only one slot; low==high */
                    addReplyLongLong(c, start);
                } else {
                    addReplyLongLong(c, start); /* low */
                    addReplyLongLong(c, j-1);   /* high */
                }
                start = -1;

                /* First node reply position is always the master */
                addReplyArrayLen(c, 3);
                addReplyBulkCString(c, node->ip);
                addReplyLongLong(c, node->port);
                addReplyBulkCBuffer(c, node->name, CLUSTER_NAMELEN);

                /* Remaining nodes in reply are replicas for slot range */
                for (i = 0; i < node->numslaves; i++) {
                    /* This loop is copy/pasted from clusterGenNodeDescription()
                     * with modifications for per-slot node aggregation */
                    if (nodeFailed(node->slaves[i])) continue;
                    addReplyArrayLen(c, 3);
                    addReplyBulkCString(c, node->slaves[i]->ip);
                    addReplyLongLong(c, node->slaves[i]->port);
                    addReplyBulkCBuffer(c, node->slaves[i]->name, CLUSTER_NAMELEN);
                    nested_elements++;
                }
                setDeferredArrayLen(c, nested_replylen, nested_elements);
                num_masters++;
            }
        }
    }
    dictReleaseIterator(di);
    setDeferredArrayLen(c, slot_replylen, num_masters);
}

void clusterCommand(client *c) {
    if (server.cluster_enabled == 0) {
        addReplyError(c,"This instance has cluster support disabled");
        return;
    }

    if (c->argc == 2 && !strcasecmp(c->argv[1]->ptr,"help")) {
        const char *help[] = {
"ADDSLOTS <slot> [slot ...] -- Assign slots to current node.",
"BUMPEPOCH -- Advance the cluster config epoch.",
"COUNT-failure-reports <node-id> -- Return number of failure reports for <node-id>.",
"COUNTKEYSINSLOT <slot> - Return the number of keys in <slot>.",
"DELSLOTS <slot> [slot ...] -- Delete slots information from current node.",
"FAILOVER [force|takeover] -- Promote current replica node to being a master.",
"FORGET <node-id> -- Remove a node from the cluster.",
"GETKEYSINSLOT <slot> <count> -- Return key names stored by current node in a slot.",
"FLUSHSLOTS -- Delete current node own slots information.",
"INFO - Return onformation about the cluster.",
"KEYSLOT <key> -- Return the hash slot for <key>.",
"MEET <ip> <port> [bus-port] -- Connect nodes into a working cluster.",
"MYID -- Return the node id.",
"NODES -- Return cluster configuration seen by node. Output format:",
"    <id> <ip:port> <flags> <master> <pings> <pongs> <epoch> <link> <slot> ... <slot>",
"REPLICATE <node-id> -- Configure current node as replica to <node-id>.",
"RESET [hard|soft] -- Reset current node (default: soft).",
"SET-config-epoch <epoch> - Set config epoch of current node.",
"SETSLOT <slot> (importing|migrating|stable|node <node-id>) -- Set slot state.",
"REPLICAS <node-id> -- Return <node-id> replicas.",
"SLOTS -- Return information about slots range mappings. Each range is made of:",
"    start, end, master and replicas IP addresses, ports and ids",
NULL
        };
        addReplyHelp(c, help);
    } else if (!strcasecmp(c->argv[1]->ptr,"meet") && (c->argc == 4 || c->argc == 5)) {
        /* CLUSTER MEET <ip> <port> [cport] */
        long long port, cport;

        if (getLongLongFromObject(c->argv[3], &port) != C_OK) {
            addReplyErrorFormat(c,"Invalid TCP base port specified: %s",
                                (char*)c->argv[3]->ptr);
            return;
        }

        if (c->argc == 5) {
            if (getLongLongFromObject(c->argv[4], &cport) != C_OK) {
                addReplyErrorFormat(c,"Invalid TCP bus port specified: %s",
                                    (char*)c->argv[4]->ptr);
                return;
            }
        } else {
            cport = port + CLUSTER_PORT_INCR;
        }

        if (clusterStartHandshake(c->argv[2]->ptr,port,cport) == 0 &&
            errno == EINVAL)
        {
            addReplyErrorFormat(c,"Invalid node address specified: %s:%s",
                            (char*)c->argv[2]->ptr, (char*)c->argv[3]->ptr);
        } else {
            addReply(c,shared.ok);
        }
    } else if (!strcasecmp(c->argv[1]->ptr,"nodes") && c->argc == 2) {
        /* CLUSTER NODES */
        sds nodes = clusterGenNodesDescription(0);
        addReplyVerbatim(c,nodes,sdslen(nodes),"txt");
        sdsfree(nodes);
    } else if (!strcasecmp(c->argv[1]->ptr,"myid") && c->argc == 2) {
        /* CLUSTER MYID */
        addReplyBulkCBuffer(c,myself->name, CLUSTER_NAMELEN);
    } else if (!strcasecmp(c->argv[1]->ptr,"slots") && c->argc == 2) {
        /* CLUSTER SLOTS */
        clusterReplyMultiBulkSlots(c);
    } else if (!strcasecmp(c->argv[1]->ptr,"flushslots") && c->argc == 2) {
        /* CLUSTER FLUSHSLOTS */
        if (dictSize(server.db[0].dict) != 0) {
            addReplyError(c,"DB must be empty to perform CLUSTER FLUSHSLOTS.");
            return;
        }
        clusterDelNodeSlots(myself);
        clusterDoBeforeSleep(CLUSTER_TODO_UPDATE_STATE|CLUSTER_TODO_SAVE_CONFIG);
        addReply(c,shared.ok);
    } else if ((!strcasecmp(c->argv[1]->ptr,"addslots") ||
               !strcasecmp(c->argv[1]->ptr,"delslots")) && c->argc >= 3)
    {
        /* CLUSTER ADDSLOTS <slot> [slot] ... */
        /* CLUSTER DELSLOTS <slot> [slot] ... */
        int j, slot;
        unsigned char *slots = zmalloc(CLUSTER_SLOTS);
        int del = !strcasecmp(c->argv[1]->ptr,"delslots");

        memset(slots,0,CLUSTER_SLOTS);
        /* Check that all the arguments are parseable and that all the
         * slots are not already busy. */
        for (j = 2; j < c->argc; j++) {
            if ((slot = getSlotOrReply(c,c->argv[j])) == -1) {
                zfree(slots);
                return;
            }
            if (del && server.cluster->slots[slot] == NULL) {
                addReplyErrorFormat(c,"Slot %d is already unassigned", slot);
                zfree(slots);
                return;
            } else if (!del && server.cluster->slots[slot]) {
                addReplyErrorFormat(c,"Slot %d is already busy", slot);
                zfree(slots);
                return;
            }
            if (slots[slot]++ == 1) {
                addReplyErrorFormat(c,"Slot %d specified multiple times",
                    (int)slot);
                zfree(slots);
                return;
            }
        }
        for (j = 0; j < CLUSTER_SLOTS; j++) {
            if (slots[j]) {
                int retval;

                /* If this slot was set as importing we can clear this
                 * state as now we are the real owner of the slot. */
                if (server.cluster->importing_slots_from[j])
                    server.cluster->importing_slots_from[j] = NULL;

                retval = del ? clusterDelSlot(j) :
                               clusterAddSlot(myself,j);
                serverAssertWithInfo(c,NULL,retval == C_OK);
            }
        }
        zfree(slots);
        clusterDoBeforeSleep(CLUSTER_TODO_UPDATE_STATE|CLUSTER_TODO_SAVE_CONFIG);
        addReply(c,shared.ok);
    } else if (!strcasecmp(c->argv[1]->ptr,"setslot") && c->argc >= 4) {
        /* SETSLOT 10 MIGRATING <node ID> */
        /* SETSLOT 10 IMPORTING <node ID> */
        /* SETSLOT 10 STABLE */
        /* SETSLOT 10 NODE <node ID> */
        int slot;
        clusterNode *n;

        if (nodeIsSlave(myself)) {
            addReplyError(c,"Please use SETSLOT only with masters.");
            return;
        }

        if ((slot = getSlotOrReply(c,c->argv[2])) == -1) return;

        if (!strcasecmp(c->argv[3]->ptr,"migrating") && c->argc == 5) {
            if (server.cluster->slots[slot] != myself) {
                addReplyErrorFormat(c,"I'm not the owner of hash slot %u",slot);
                return;
            }
            if ((n = clusterLookupNode(c->argv[4]->ptr)) == NULL) {
                addReplyErrorFormat(c,"I don't know about node %s",
                    (char*)c->argv[4]->ptr);
                return;
            }
            server.cluster->migrating_slots_to[slot] = n;
        } else if (!strcasecmp(c->argv[3]->ptr,"importing") && c->argc == 5) {
            if (server.cluster->slots[slot] == myself) {
                addReplyErrorFormat(c,
                    "I'm already the owner of hash slot %u",slot);
                return;
            }
            if ((n = clusterLookupNode(c->argv[4]->ptr)) == NULL) {
                addReplyErrorFormat(c,"I don't know about node %s",
                    (char*)c->argv[4]->ptr);
                return;
            }
            server.cluster->importing_slots_from[slot] = n;
        } else if (!strcasecmp(c->argv[3]->ptr,"stable") && c->argc == 4) {
            /* CLUSTER SETSLOT <SLOT> STABLE */
            server.cluster->importing_slots_from[slot] = NULL;
            server.cluster->migrating_slots_to[slot] = NULL;
        } else if (!strcasecmp(c->argv[3]->ptr,"node") && c->argc == 5) {
            /* CLUSTER SETSLOT <SLOT> NODE <NODE ID> */
            clusterNode *n = clusterLookupNode(c->argv[4]->ptr);

            if (!n) {
                addReplyErrorFormat(c,"Unknown node %s",
                    (char*)c->argv[4]->ptr);
                return;
            }
            /* If this hash slot was served by 'myself' before to switch
             * make sure there are no longer local keys for this hash slot. */
            if (server.cluster->slots[slot] == myself && n != myself) {
                if (countKeysInSlot(slot) != 0) {
                    addReplyErrorFormat(c,
                        "Can't assign hashslot %d to a different node "
                        "while I still hold keys for this hash slot.", slot);
                    return;
                }
            }
            /* If this slot is in migrating status but we have no keys
             * for it assigning the slot to another node will clear
             * the migratig status. */
            if (countKeysInSlot(slot) == 0 &&
                server.cluster->migrating_slots_to[slot])
                server.cluster->migrating_slots_to[slot] = NULL;

            /* If this node was importing this slot, assigning the slot to
             * itself also clears the importing status. */
            if (n == myself &&
                server.cluster->importing_slots_from[slot])
            {
                /* This slot was manually migrated, set this node configEpoch
                 * to a new epoch so that the new version can be propagated
                 * by the cluster.
                 *
                 * Note that if this ever results in a collision with another
                 * node getting the same configEpoch, for example because a
                 * failover happens at the same time we close the slot, the
                 * configEpoch collision resolution will fix it assigning
                 * a different epoch to each node. */
                if (clusterBumpConfigEpochWithoutConsensus() == C_OK) {
                    serverLog(LL_WARNING,
                        "configEpoch updated after importing slot %d", slot);
                }
                server.cluster->importing_slots_from[slot] = NULL;
            }
            clusterDelSlot(slot);
            clusterAddSlot(n,slot);
        } else {
            addReplyError(c,
                "Invalid CLUSTER SETSLOT action or number of arguments. Try CLUSTER HELP");
            return;
        }
        clusterDoBeforeSleep(CLUSTER_TODO_SAVE_CONFIG|CLUSTER_TODO_UPDATE_STATE);
        addReply(c,shared.ok);
    } else if (!strcasecmp(c->argv[1]->ptr,"bumpepoch") && c->argc == 2) {
        /* CLUSTER BUMPEPOCH */
        int retval = clusterBumpConfigEpochWithoutConsensus();
        sds reply = sdscatprintf(sdsempty(),"+%s %llu\r\n",
                (retval == C_OK) ? "BUMPED" : "STILL",
                (unsigned long long) myself->configEpoch);
        addReplySds(c,reply);
    } else if (!strcasecmp(c->argv[1]->ptr,"info") && c->argc == 2) {
        /* CLUSTER INFO */
        char *statestr[] = {"ok","fail","needhelp"};
        int slots_assigned = 0, slots_ok = 0, slots_pfail = 0, slots_fail = 0;
        uint64_t myepoch;
        int j;

        for (j = 0; j < CLUSTER_SLOTS; j++) {
            clusterNode *n = server.cluster->slots[j];

            if (n == NULL) continue;
            slots_assigned++;
            if (nodeFailed(n)) {
                slots_fail++;
            } else if (nodeTimedOut(n)) {
                slots_pfail++;
            } else {
                slots_ok++;
            }
        }

        myepoch = (nodeIsSlave(myself) && myself->slaveof) ?
                  myself->slaveof->configEpoch : myself->configEpoch;

        sds info = sdscatprintf(sdsempty(),
            "cluster_state:%s\r\n"
            "cluster_slots_assigned:%d\r\n"
            "cluster_slots_ok:%d\r\n"
            "cluster_slots_pfail:%d\r\n"
            "cluster_slots_fail:%d\r\n"
            "cluster_known_nodes:%lu\r\n"
            "cluster_size:%d\r\n"
            "cluster_current_epoch:%llu\r\n"
            "cluster_my_epoch:%llu\r\n"
            , statestr[server.cluster->state],
            slots_assigned,
            slots_ok,
            slots_pfail,
            slots_fail,
            dictSize(server.cluster->nodes),
            server.cluster->size,
            (unsigned long long) server.cluster->currentEpoch,
            (unsigned long long) myepoch
        );

        /* Show stats about messages sent and received. */
        long long tot_msg_sent = 0;
        long long tot_msg_received = 0;

        for (int i = 0; i < CLUSTERMSG_TYPE_COUNT; i++) {
            if (server.cluster->stats_bus_messages_sent[i] == 0) continue;
            tot_msg_sent += server.cluster->stats_bus_messages_sent[i];
            info = sdscatprintf(info,
                "cluster_stats_messages_%s_sent:%lld\r\n",
                clusterGetMessageTypeString(i),
                server.cluster->stats_bus_messages_sent[i]);
        }
        info = sdscatprintf(info,
            "cluster_stats_messages_sent:%lld\r\n", tot_msg_sent);

        for (int i = 0; i < CLUSTERMSG_TYPE_COUNT; i++) {
            if (server.cluster->stats_bus_messages_received[i] == 0) continue;
            tot_msg_received += server.cluster->stats_bus_messages_received[i];
            info = sdscatprintf(info,
                "cluster_stats_messages_%s_received:%lld\r\n",
                clusterGetMessageTypeString(i),
                server.cluster->stats_bus_messages_received[i]);
        }
        info = sdscatprintf(info,
            "cluster_stats_messages_received:%lld\r\n", tot_msg_received);

        /* Produce the reply protocol. */
        addReplyVerbatim(c,info,sdslen(info),"txt");
        sdsfree(info);
    } else if (!strcasecmp(c->argv[1]->ptr,"saveconfig") && c->argc == 2) {
        int retval = clusterSaveConfig(1);

        if (retval == 0)
            addReply(c,shared.ok);
        else
            addReplyErrorFormat(c,"error saving the cluster node config: %s",
                strerror(errno));
    } else if (!strcasecmp(c->argv[1]->ptr,"keyslot") && c->argc == 3) {
        /* CLUSTER KEYSLOT <key> */
        sds key = c->argv[2]->ptr;

        addReplyLongLong(c,keyHashSlot(key,sdslen(key)));
    } else if (!strcasecmp(c->argv[1]->ptr,"countkeysinslot") && c->argc == 3) {
        /* CLUSTER COUNTKEYSINSLOT <slot> */
        long long slot;

        if (getLongLongFromObjectOrReply(c,c->argv[2],&slot,NULL) != C_OK)
            return;
        if (slot < 0 || slot >= CLUSTER_SLOTS) {
            addReplyError(c,"Invalid slot");
            return;
        }
        addReplyLongLong(c,countKeysInSlot(slot));
    } else if (!strcasecmp(c->argv[1]->ptr,"getkeysinslot") && c->argc == 4) {
        /* CLUSTER GETKEYSINSLOT <slot> <count> */
        long long maxkeys, slot;
        unsigned int numkeys, j;
        robj **keys;

        if (getLongLongFromObjectOrReply(c,c->argv[2],&slot,NULL) != C_OK)
            return;
        if (getLongLongFromObjectOrReply(c,c->argv[3],&maxkeys,NULL)
            != C_OK)
            return;
        if (slot < 0 || slot >= CLUSTER_SLOTS || maxkeys < 0) {
            addReplyError(c,"Invalid slot or number of keys");
            return;
        }

        /* Avoid allocating more than needed in case of large COUNT argument
         * and smaller actual number of keys. */
        unsigned int keys_in_slot = countKeysInSlot(slot);
        if (maxkeys > keys_in_slot) maxkeys = keys_in_slot;

        keys = zmalloc(sizeof(robj*)*maxkeys);
        numkeys = getKeysInSlot(slot, keys, maxkeys);
        addReplyArrayLen(c,numkeys);
        for (j = 0; j < numkeys; j++) {
            addReplyBulk(c,keys[j]);
            decrRefCount(keys[j]);
        }
        zfree(keys);
    } else if (!strcasecmp(c->argv[1]->ptr,"forget") && c->argc == 3) {
        /* CLUSTER FORGET <NODE ID> */
        clusterNode *n = clusterLookupNode(c->argv[2]->ptr);

        if (!n) {
            addReplyErrorFormat(c,"Unknown node %s", (char*)c->argv[2]->ptr);
            return;
        } else if (n == myself) {
            addReplyError(c,"I tried hard but I can't forget myself...");
            return;
        } else if (nodeIsSlave(myself) && myself->slaveof == n) {
            addReplyError(c,"Can't forget my master!");
            return;
        }
        clusterBlacklistAddNode(n);
        clusterDelNode(n);
        clusterDoBeforeSleep(CLUSTER_TODO_UPDATE_STATE|
                             CLUSTER_TODO_SAVE_CONFIG);
        addReply(c,shared.ok);
    } else if (!strcasecmp(c->argv[1]->ptr,"replicate") && c->argc == 3) {
        /* CLUSTER REPLICATE <NODE ID> */
        clusterNode *n = clusterLookupNode(c->argv[2]->ptr);

        /* Lookup the specified node in our table. */
        if (!n) {
            addReplyErrorFormat(c,"Unknown node %s", (char*)c->argv[2]->ptr);
            return;
        }

        /* I can't replicate myself. */
        if (n == myself) {
            addReplyError(c,"Can't replicate myself");
            return;
        }

        /* Can't replicate a slave. */
        if (nodeIsSlave(n)) {
            addReplyError(c,"I can only replicate a master, not a replica.");
            return;
        }

        /* If the instance is currently a master, it should have no assigned
         * slots nor keys to accept to replicate some other node.
         * Slaves can switch to another master without issues. */
        if (nodeIsMaster(myself) &&
            (myself->numslots != 0 || dictSize(server.db[0].dict) != 0)) {
            addReplyError(c,
                "To set a master the node must be empty and "
                "without assigned slots.");
            return;
        }

        /* Set the master. */
        clusterSetMaster(n);
        clusterDoBeforeSleep(CLUSTER_TODO_UPDATE_STATE|CLUSTER_TODO_SAVE_CONFIG);
        addReply(c,shared.ok);
    } else if ((!strcasecmp(c->argv[1]->ptr,"slaves") ||
                !strcasecmp(c->argv[1]->ptr,"replicas")) && c->argc == 3) {
        /* CLUSTER SLAVES <NODE ID> */
        clusterNode *n = clusterLookupNode(c->argv[2]->ptr);
        int j;

        /* Lookup the specified node in our table. */
        if (!n) {
            addReplyErrorFormat(c,"Unknown node %s", (char*)c->argv[2]->ptr);
            return;
        }

        if (nodeIsSlave(n)) {
            addReplyError(c,"The specified node is not a master");
            return;
        }

        addReplyArrayLen(c,n->numslaves);
        for (j = 0; j < n->numslaves; j++) {
            sds ni = clusterGenNodeDescription(n->slaves[j]);
            addReplyBulkCString(c,ni);
            sdsfree(ni);
        }
    } else if (!strcasecmp(c->argv[1]->ptr,"count-failure-reports") &&
               c->argc == 3)
    {
        /* CLUSTER COUNT-FAILURE-REPORTS <NODE ID> */
        clusterNode *n = clusterLookupNode(c->argv[2]->ptr);

        if (!n) {
            addReplyErrorFormat(c,"Unknown node %s", (char*)c->argv[2]->ptr);
            return;
        } else {
            addReplyLongLong(c,clusterNodeFailureReportsCount(n));
        }
    } else if (!strcasecmp(c->argv[1]->ptr,"failover") &&
               (c->argc == 2 || c->argc == 3))
    {
        /* CLUSTER FAILOVER [FORCE|TAKEOVER] */
        int force = 0, takeover = 0;

        if (c->argc == 3) {
            if (!strcasecmp(c->argv[2]->ptr,"force")) {
                force = 1;
            } else if (!strcasecmp(c->argv[2]->ptr,"takeover")) {
                takeover = 1;
                force = 1; /* Takeover also implies force. */
            } else {
                addReply(c,shared.syntaxerr);
                return;
            }
        }

        /* Check preconditions. */
        if (nodeIsMaster(myself)) {
            addReplyError(c,"You should send CLUSTER FAILOVER to a replica");
            return;
        } else if (myself->slaveof == NULL) {
            addReplyError(c,"I'm a replica but my master is unknown to me");
            return;
        } else if (!force &&
                   (nodeFailed(myself->slaveof) ||
                    myself->slaveof->link == NULL))
        {
            addReplyError(c,"Master is down or failed, "
                            "please use CLUSTER FAILOVER FORCE");
            return;
        }
        resetManualFailover();
        server.cluster->mf_end = mstime() + CLUSTER_MF_TIMEOUT;

        if (takeover) {
            /* A takeover does not perform any initial check. It just
             * generates a new configuration epoch for this node without
             * consensus, claims the master's slots, and broadcast the new
             * configuration. */
            serverLog(LL_WARNING,"Taking over the master (user request).");
            clusterBumpConfigEpochWithoutConsensus();
            clusterFailoverReplaceYourMaster();
        } else if (force) {
            /* If this is a forced failover, we don't need to talk with our
             * master to agree about the offset. We just failover taking over
             * it without coordination. */
            serverLog(LL_WARNING,"Forced failover user request accepted.");
            server.cluster->mf_can_start = 1;
        } else {
            serverLog(LL_WARNING,"Manual failover user request accepted.");
            clusterSendMFStart(myself->slaveof);
        }
        addReply(c,shared.ok);
    } else if (!strcasecmp(c->argv[1]->ptr,"set-config-epoch") && c->argc == 3)
    {
        /* CLUSTER SET-CONFIG-EPOCH <epoch>
         *
         * The user is allowed to set the config epoch only when a node is
         * totally fresh: no config epoch, no other known node, and so forth.
         * This happens at cluster creation time to start with a cluster where
         * every node has a different node ID, without to rely on the conflicts
         * resolution system which is too slow when a big cluster is created. */
        long long epoch;

        if (getLongLongFromObjectOrReply(c,c->argv[2],&epoch,NULL) != C_OK)
            return;

        if (epoch < 0) {
            addReplyErrorFormat(c,"Invalid config epoch specified: %lld",epoch);
        } else if (dictSize(server.cluster->nodes) > 1) {
            addReplyError(c,"The user can assign a config epoch only when the "
                            "node does not know any other node.");
        } else if (myself->configEpoch != 0) {
            addReplyError(c,"Node config epoch is already non-zero");
        } else {
            myself->configEpoch = epoch;
            serverLog(LL_WARNING,
                "configEpoch set to %llu via CLUSTER SET-CONFIG-EPOCH",
                (unsigned long long) myself->configEpoch);

            if (server.cluster->currentEpoch < (uint64_t)epoch)
                server.cluster->currentEpoch = epoch;
            /* No need to fsync the config here since in the unlucky event
             * of a failure to persist the config, the conflict resolution code
             * will assign an unique config to this node. */
            clusterDoBeforeSleep(CLUSTER_TODO_UPDATE_STATE|
                                 CLUSTER_TODO_SAVE_CONFIG);
            addReply(c,shared.ok);
        }
    } else if (!strcasecmp(c->argv[1]->ptr,"reset") &&
               (c->argc == 2 || c->argc == 3))
    {
        /* CLUSTER RESET [SOFT|HARD] */
        int hard = 0;

        /* Parse soft/hard argument. Default is soft. */
        if (c->argc == 3) {
            if (!strcasecmp(c->argv[2]->ptr,"hard")) {
                hard = 1;
            } else if (!strcasecmp(c->argv[2]->ptr,"soft")) {
                hard = 0;
            } else {
                addReply(c,shared.syntaxerr);
                return;
            }
        }

        /* Slaves can be reset while containing data, but not master nodes
         * that must be empty. */
        if (nodeIsMaster(myself) && dictSize(c->db->dict) != 0) {
            addReplyError(c,"CLUSTER RESET can't be called with "
                            "master nodes containing keys");
            return;
        }
        clusterReset(hard);
        addReply(c,shared.ok);
    } else {
        addReplySubcommandSyntaxError(c);
        return;
    }
}

/* -----------------------------------------------------------------------------
 * DUMP, RESTORE and MIGRATE commands
 * -------------------------------------------------------------------------- */

/* Generates a DUMP-format representation of the object 'o', adding it to the
 * io stream pointed by 'rio'. This function can't fail. */
void createDumpPayload(rio *payload, robj *o, robj *key) {
    unsigned char buf[2];
    uint64_t crc;

    /* Serialize the object in a RDB-like format. It consist of an object type
     * byte followed by the serialized object. This is understood by RESTORE. */
    rioInitWithBuffer(payload,sdsempty());
    serverAssert(rdbSaveObjectType(payload,o));
    serverAssert(rdbSaveObject(payload,o,key));

    /* Write the footer, this is how it looks like:
     * ----------------+---------------------+---------------+
     * ... RDB payload | 2 bytes RDB version | 8 bytes CRC64 |
     * ----------------+---------------------+---------------+
     * RDB version and CRC are both in little endian.
     */

    /* RDB version */
    buf[0] = RDB_VERSION & 0xff;
    buf[1] = (RDB_VERSION >> 8) & 0xff;
    payload->io.buffer.ptr = sdscatlen(payload->io.buffer.ptr,buf,2);

    /* CRC64 */
    crc = crc64(0,(unsigned char*)payload->io.buffer.ptr,
                sdslen(payload->io.buffer.ptr));
    memrev64ifbe(&crc);
    payload->io.buffer.ptr = sdscatlen(payload->io.buffer.ptr,&crc,8);
}

/* Verify that the RDB version of the dump payload matches the one of this Redis
 * instance and that the checksum is ok.
 * If the DUMP payload looks valid C_OK is returned, otherwise C_ERR
 * is returned. */
int verifyDumpPayload(unsigned char *p, size_t len) {
    unsigned char *footer;
    uint16_t rdbver;
    uint64_t crc;

    /* At least 2 bytes of RDB version and 8 of CRC64 should be present. */
    if (len < 10) return C_ERR;
    footer = p+(len-10);

    /* Verify RDB version */
    rdbver = (footer[1] << 8) | footer[0];
    if (rdbver > RDB_VERSION) return C_ERR;

    /* Verify CRC64 */
    crc = crc64(0,p,len-8);
    memrev64ifbe(&crc);
    return (memcmp(&crc,footer+2,8) == 0) ? C_OK : C_ERR;
}

/* DUMP keyname
 * DUMP is actually not used by Redis Cluster but it is the obvious
 * complement of RESTORE and can be useful for different applications. */
void dumpCommand(client *c) {
    robj *o;
    rio payload;

    /* Check if the key is here. */
    if ((o = lookupKeyRead(c->db,c->argv[1])) == NULL) {
        addReplyNull(c);
        return;
    }

    /* Create the DUMP encoded representation. */
    createDumpPayload(&payload,o,c->argv[1]);

    /* Transfer to the client */
    addReplyBulkSds(c,payload.io.buffer.ptr);
    return;
}

/* RESTORE key ttl serialized-value [REPLACE] */
void restoreCommand(client *c) {
    long long ttl, lfu_freq = -1, lru_idle = -1, lru_clock = -1;
    rio payload;
    int j, type, replace = 0, absttl = 0;
    robj *obj;

    /* Parse additional options */
    for (j = 4; j < c->argc; j++) {
        int additional = c->argc-j-1;
        if (!strcasecmp(c->argv[j]->ptr,"replace")) {
            replace = 1;
        } else if (!strcasecmp(c->argv[j]->ptr,"absttl")) {
            absttl = 1;
        } else if (!strcasecmp(c->argv[j]->ptr,"idletime") && additional >= 1 &&
                   lfu_freq == -1)
        {
            if (getLongLongFromObjectOrReply(c,c->argv[j+1],&lru_idle,NULL)
                    != C_OK) return;
            if (lru_idle < 0) {
                addReplyError(c,"Invalid IDLETIME value, must be >= 0");
                return;
            }
            lru_clock = LRU_CLOCK();
            j++; /* Consume additional arg. */
        } else if (!strcasecmp(c->argv[j]->ptr,"freq") && additional >= 1 &&
                   lru_idle == -1)
        {
            if (getLongLongFromObjectOrReply(c,c->argv[j+1],&lfu_freq,NULL)
                    != C_OK) return;
            if (lfu_freq < 0 || lfu_freq > 255) {
                addReplyError(c,"Invalid FREQ value, must be >= 0 and <= 255");
                return;
            }
            j++; /* Consume additional arg. */
        } else {
            addReply(c,shared.syntaxerr);
            return;
        }
    }

    /* Make sure this key does not already exist here... */
    if (!replace && lookupKeyWrite(c->db,c->argv[1]) != NULL) {
        addReply(c,shared.busykeyerr);
        return;
    }

    /* Check if the TTL value makes sense */
    if (getLongLongFromObjectOrReply(c,c->argv[2],&ttl,NULL) != C_OK) {
        return;
    } else if (ttl < 0) {
        addReplyError(c,"Invalid TTL value, must be >= 0");
        return;
    }

    /* Verify RDB version and data checksum. */
    if (verifyDumpPayload(c->argv[3]->ptr,sdslen(c->argv[3]->ptr)) == C_ERR)
    {
        addReplyError(c,"DUMP payload version or checksum are wrong");
        return;
    }

    rioInitWithBuffer(&payload,c->argv[3]->ptr);
    if (((type = rdbLoadObjectType(&payload)) == -1) ||
        ((obj = rdbLoadObject(type,&payload,c->argv[1])) == NULL))
    {
        addReplyError(c,"Bad data format");
        return;
    }

    /* Remove the old key if needed. */
    if (replace) dbDelete(c->db,c->argv[1]);

    /* Create the key and set the TTL if any */
    dbAdd(c->db,c->argv[1],obj);
    if (ttl) {
        if (!absttl) ttl+=mstime();
        setExpire(c,c->db,c->argv[1],ttl);
    }
    objectSetLRUOrLFU(obj,lfu_freq,lru_idle,lru_clock,1000);
    signalModifiedKey(c->db,c->argv[1]);
    addReply(c,shared.ok);
    server.dirty++;
}

/* MIGRATE socket cache implementation.
 *
 * We take a map between host:ip and a TCP socket that we used to connect
 * to this instance in recent time.
 * This sockets are closed when the max number we cache is reached, and also
 * in serverCron() when they are around for more than a few seconds. */
#define MIGRATE_SOCKET_CACHE_ITEMS 64 /* max num of items in the cache. */
#define MIGRATE_SOCKET_CACHE_TTL 10 /* close cached sockets after 10 sec. */

typedef struct migrateCachedSocket {
    connection *conn;
    long last_dbid;
    time_t last_use_time;
} migrateCachedSocket;

/* Return a migrateCachedSocket containing a TCP socket connected with the
 * target instance, possibly returning a cached one.
 *
 * This function is responsible of sending errors to the client if a
 * connection can't be established. In this case -1 is returned.
 * Otherwise on success the socket is returned, and the caller should not
 * attempt to free it after usage.
 *
 * If the caller detects an error while using the socket, migrateCloseSocket()
 * should be called so that the connection will be created from scratch
 * the next time. */
migrateCachedSocket* migrateGetSocket(client *c, robj *host, robj *port, long timeout) {
    connection *conn;
    sds name = sdsempty();
    migrateCachedSocket *cs;

    /* Check if we have an already cached socket for this ip:port pair. */
    name = sdscatlen(name,host->ptr,sdslen(host->ptr));
    name = sdscatlen(name,":",1);
    name = sdscatlen(name,port->ptr,sdslen(port->ptr));
    cs = dictFetchValue(server.migrate_cached_sockets,name);
    if (cs) {
        sdsfree(name);
        cs->last_use_time = server.unixtime;
        return cs;
    }

    /* No cached socket, create one. */
    if (dictSize(server.migrate_cached_sockets) == MIGRATE_SOCKET_CACHE_ITEMS) {
        /* Too many items, drop one at random. */
        dictEntry *de = dictGetRandomKey(server.migrate_cached_sockets);
        cs = dictGetVal(de);
        connClose(cs->conn);
        zfree(cs);
        dictDelete(server.migrate_cached_sockets,dictGetKey(de));
    }

    /* Create the socket */
    conn = server.tls_cluster ? connCreateTLS() : connCreateSocket();
    if (connBlockingConnect(conn, c->argv[1]->ptr, atoi(c->argv[2]->ptr), timeout)
            != C_OK) {
        addReplySds(c,
            sdsnew("-IOERR error or timeout connecting to the client\r\n"));
        connClose(conn);
        sdsfree(name);
        return NULL;
    }
    connEnableTcpNoDelay(conn);

    /* Add to the cache and return it to the caller. */
    cs = zmalloc(sizeof(*cs));
    cs->conn = conn;

    cs->last_dbid = -1;
    cs->last_use_time = server.unixtime;
    dictAdd(server.migrate_cached_sockets,name,cs);
    return cs;
}

/* Free a migrate cached connection. */
void migrateCloseSocket(robj *host, robj *port) {
    sds name = sdsempty();
    migrateCachedSocket *cs;

    name = sdscatlen(name,host->ptr,sdslen(host->ptr));
    name = sdscatlen(name,":",1);
    name = sdscatlen(name,port->ptr,sdslen(port->ptr));
    cs = dictFetchValue(server.migrate_cached_sockets,name);
    if (!cs) {
        sdsfree(name);
        return;
    }

    connClose(cs->conn);
    zfree(cs);
    dictDelete(server.migrate_cached_sockets,name);
    sdsfree(name);
}

void migrateCloseTimedoutSockets(void) {
    dictIterator *di = dictGetSafeIterator(server.migrate_cached_sockets);
    dictEntry *de;

    while((de = dictNext(di)) != NULL) {
        migrateCachedSocket *cs = dictGetVal(de);

        if ((server.unixtime - cs->last_use_time) > MIGRATE_SOCKET_CACHE_TTL) {
            connClose(cs->conn);
            zfree(cs);
            dictDelete(server.migrate_cached_sockets,dictGetKey(de));
        }
    }
    dictReleaseIterator(di);
}

/* MIGRATE host port key dbid timeout [COPY | REPLACE | AUTH password]
 *
 * On in the multiple keys form:
 *
 * MIGRATE host port "" dbid timeout [COPY | REPLACE | AUTH password] KEYS key1
 * key2 ... keyN */
void migrateCommand(client *c) {
    migrateCachedSocket *cs;
    int copy = 0, replace = 0, j;
    char *password = NULL;
    long timeout;
    long dbid;
    robj **ov = NULL; /* Objects to migrate. */
    robj **kv = NULL; /* Key names. */
    robj **newargv = NULL; /* Used to rewrite the command as DEL ... keys ... */
    rio cmd, payload;
    int may_retry = 1;
    int write_error = 0;
    int argv_rewritten = 0;

    /* To support the KEYS option we need the following additional state. */
    int first_key = 3; /* Argument index of the first key. */
    int num_keys = 1;  /* By default only migrate the 'key' argument. */

    /* Parse additional options */
    for (j = 6; j < c->argc; j++) {
        int moreargs = j < c->argc-1;
        if (!strcasecmp(c->argv[j]->ptr,"copy")) {
            copy = 1;
        } else if (!strcasecmp(c->argv[j]->ptr,"replace")) {
            replace = 1;
        } else if (!strcasecmp(c->argv[j]->ptr,"auth")) {
            if (!moreargs) {
                addReply(c,shared.syntaxerr);
                return;
            }
            j++;
            password = c->argv[j]->ptr;
        } else if (!strcasecmp(c->argv[j]->ptr,"keys")) {
            if (sdslen(c->argv[3]->ptr) != 0) {
                addReplyError(c,
                    "When using MIGRATE KEYS option, the key argument"
                    " must be set to the empty string");
                return;
            }
            first_key = j+1;
            num_keys = c->argc - j - 1;
            break; /* All the remaining args are keys. */
        } else {
            addReply(c,shared.syntaxerr);
            return;
        }
    }

    /* Sanity check */
    if (getLongFromObjectOrReply(c,c->argv[5],&timeout,NULL) != C_OK ||
        getLongFromObjectOrReply(c,c->argv[4],&dbid,NULL) != C_OK)
    {
        return;
    }
    if (timeout <= 0) timeout = 1000;

    /* Check if the keys are here. If at least one key is to migrate, do it
     * otherwise if all the keys are missing reply with "NOKEY" to signal
     * the caller there was nothing to migrate. We don't return an error in
     * this case, since often this is due to a normal condition like the key
     * expiring in the meantime. */
    ov = zrealloc(ov,sizeof(robj*)*num_keys);
    kv = zrealloc(kv,sizeof(robj*)*num_keys);
    int oi = 0;

    for (j = 0; j < num_keys; j++) {
        if ((ov[oi] = lookupKeyRead(c->db,c->argv[first_key+j])) != NULL) {
            kv[oi] = c->argv[first_key+j];
            oi++;
        }
    }
    num_keys = oi;
    if (num_keys == 0) {
        zfree(ov); zfree(kv);
        addReplySds(c,sdsnew("+NOKEY\r\n"));
        return;
    }

try_again:
    write_error = 0;

    /* Connect */
    cs = migrateGetSocket(c,c->argv[1],c->argv[2],timeout);
    if (cs == NULL) {
        zfree(ov); zfree(kv);
        return; /* error sent to the client by migrateGetSocket() */
    }

    rioInitWithBuffer(&cmd,sdsempty());

    /* Authentication */
    if (password) {
        serverAssertWithInfo(c,NULL,rioWriteBulkCount(&cmd,'*',2));
        serverAssertWithInfo(c,NULL,rioWriteBulkString(&cmd,"AUTH",4));
        serverAssertWithInfo(c,NULL,rioWriteBulkString(&cmd,password,
            sdslen(password)));
    }

    /* Send the SELECT command if the current DB is not already selected. */
    int select = cs->last_dbid != dbid; /* Should we emit SELECT? */
    if (select) {
        serverAssertWithInfo(c,NULL,rioWriteBulkCount(&cmd,'*',2));
        serverAssertWithInfo(c,NULL,rioWriteBulkString(&cmd,"SELECT",6));
        serverAssertWithInfo(c,NULL,rioWriteBulkLongLong(&cmd,dbid));
    }

    int non_expired = 0; /* Number of keys that we'll find non expired.
                            Note that serializing large keys may take some time
                            so certain keys that were found non expired by the
                            lookupKey() function, may be expired later. */

    /* Create RESTORE payload and generate the protocol to call the command. */
    for (j = 0; j < num_keys; j++) {
        long long ttl = 0;
        long long expireat = getExpire(c->db,kv[j]);

        if (expireat != -1) {
            ttl = expireat-mstime();
            if (ttl < 0) {
                continue;
            }
            if (ttl < 1) ttl = 1;
        }

        /* Relocate valid (non expired) keys into the array in successive
         * positions to remove holes created by the keys that were present
         * in the first lookup but are now expired after the second lookup. */
        kv[non_expired++] = kv[j];

        serverAssertWithInfo(c,NULL,
            rioWriteBulkCount(&cmd,'*',replace ? 5 : 4));

        if (server.cluster_enabled)
            serverAssertWithInfo(c,NULL,
                rioWriteBulkString(&cmd,"RESTORE-ASKING",14));
        else
            serverAssertWithInfo(c,NULL,rioWriteBulkString(&cmd,"RESTORE",7));
        serverAssertWithInfo(c,NULL,sdsEncodedObject(kv[j]));
        serverAssertWithInfo(c,NULL,rioWriteBulkString(&cmd,kv[j]->ptr,
                sdslen(kv[j]->ptr)));
        serverAssertWithInfo(c,NULL,rioWriteBulkLongLong(&cmd,ttl));

        /* Emit the payload argument, that is the serialized object using
         * the DUMP format. */
        createDumpPayload(&payload,ov[j],kv[j]);
        serverAssertWithInfo(c,NULL,
            rioWriteBulkString(&cmd,payload.io.buffer.ptr,
                               sdslen(payload.io.buffer.ptr)));
        sdsfree(payload.io.buffer.ptr);

        /* Add the REPLACE option to the RESTORE command if it was specified
         * as a MIGRATE option. */
        if (replace)
            serverAssertWithInfo(c,NULL,rioWriteBulkString(&cmd,"REPLACE",7));
    }

    /* Fix the actual number of keys we are migrating. */
    num_keys = non_expired;

    /* Transfer the query to the other node in 64K chunks. */
    errno = 0;
    {
        sds buf = cmd.io.buffer.ptr;
        size_t pos = 0, towrite;
        int nwritten = 0;

        while ((towrite = sdslen(buf)-pos) > 0) {
            towrite = (towrite > (64*1024) ? (64*1024) : towrite);
            nwritten = connSyncWrite(cs->conn,buf+pos,towrite,timeout);
            if (nwritten != (signed)towrite) {
                write_error = 1;
                goto socket_err;
            }
            pos += nwritten;
        }
    }

    char buf0[1024]; /* Auth reply. */
    char buf1[1024]; /* Select reply. */
    char buf2[1024]; /* Restore reply. */

    /* Read the AUTH reply if needed. */
    if (password && connSyncReadLine(cs->conn, buf0, sizeof(buf0), timeout) <= 0)
        goto socket_err;

    /* Read the SELECT reply if needed. */
    if (select && connSyncReadLine(cs->conn, buf1, sizeof(buf1), timeout) <= 0)
        goto socket_err;

    /* Read the RESTORE replies. */
    int error_from_target = 0;
    int socket_error = 0;
    int del_idx = 1; /* Index of the key argument for the replicated DEL op. */

    /* Allocate the new argument vector that will replace the current command,
     * to propagate the MIGRATE as a DEL command (if no COPY option was given).
     * We allocate num_keys+1 because the additional argument is for "DEL"
     * command name itself. */
    if (!copy) newargv = zmalloc(sizeof(robj*)*(num_keys+1));

    for (j = 0; j < num_keys; j++) {
        if (connSyncReadLine(cs->conn, buf2, sizeof(buf2), timeout) <= 0) {
            socket_error = 1;
            break;
        }
        if ((password && buf0[0] == '-') ||
            (select && buf1[0] == '-') ||
            buf2[0] == '-')
        {
            /* On error assume that last_dbid is no longer valid. */
            if (!error_from_target) {
                cs->last_dbid = -1;
                char *errbuf;
                if (password && buf0[0] == '-') errbuf = buf0;
                else if (select && buf1[0] == '-') errbuf = buf1;
                else errbuf = buf2;

                error_from_target = 1;
                addReplyErrorFormat(c,"Target instance replied with error: %s",
                    errbuf+1);
            }
        } else {
            if (!copy) {
                /* No COPY option: remove the local key, signal the change. */
                dbDelete(c->db,kv[j]);
                signalModifiedKey(c->db,kv[j]);
                server.dirty++;

                /* Populate the argument vector to replace the old one. */
                newargv[del_idx++] = kv[j];
                incrRefCount(kv[j]);
            }
        }
    }

    /* On socket error, if we want to retry, do it now before rewriting the
     * command vector. We only retry if we are sure nothing was processed
     * and we failed to read the first reply (j == 0 test). */
    if (!error_from_target && socket_error && j == 0 && may_retry &&
        errno != ETIMEDOUT)
    {
        goto socket_err; /* A retry is guaranteed because of tested conditions.*/
    }

    /* On socket errors, close the migration socket now that we still have
     * the original host/port in the ARGV. Later the original command may be
     * rewritten to DEL and will be too later. */
    if (socket_error) migrateCloseSocket(c->argv[1],c->argv[2]);

    if (!copy) {
        /* Translate MIGRATE as DEL for replication/AOF. Note that we do
         * this only for the keys for which we received an acknowledgement
         * from the receiving Redis server, by using the del_idx index. */
        if (del_idx > 1) {
            newargv[0] = createStringObject("DEL",3);
            /* Note that the following call takes ownership of newargv. */
            replaceClientCommandVector(c,del_idx,newargv);
            argv_rewritten = 1;
        } else {
            /* No key transfer acknowledged, no need to rewrite as DEL. */
            zfree(newargv);
        }
        newargv = NULL; /* Make it safe to call zfree() on it in the future. */
    }

    /* If we are here and a socket error happened, we don't want to retry.
     * Just signal the problem to the client, but only do it if we did not
     * already queue a different error reported by the destination server. */
    if (!error_from_target && socket_error) {
        may_retry = 0;
        goto socket_err;
    }

    if (!error_from_target) {
        /* Success! Update the last_dbid in migrateCachedSocket, so that we can
         * avoid SELECT the next time if the target DB is the same. Reply +OK.
         *
         * Note: If we reached this point, even if socket_error is true
         * still the SELECT command succeeded (otherwise the code jumps to
         * socket_err label. */
        cs->last_dbid = dbid;
        addReply(c,shared.ok);
    } else {
        /* On error we already sent it in the for loop above, and set
         * the currently selected socket to -1 to force SELECT the next time. */
    }

    sdsfree(cmd.io.buffer.ptr);
    zfree(ov); zfree(kv); zfree(newargv);
    return;

/* On socket errors we try to close the cached socket and try again.
 * It is very common for the cached socket to get closed, if just reopening
 * it works it's a shame to notify the error to the caller. */
socket_err:
    /* Cleanup we want to perform in both the retry and no retry case.
     * Note: Closing the migrate socket will also force SELECT next time. */
    sdsfree(cmd.io.buffer.ptr);

    /* If the command was rewritten as DEL and there was a socket error,
     * we already closed the socket earlier. While migrateCloseSocket()
     * is idempotent, the host/port arguments are now gone, so don't do it
     * again. */
    if (!argv_rewritten) migrateCloseSocket(c->argv[1],c->argv[2]);
    zfree(newargv);
    newargv = NULL; /* This will get reallocated on retry. */

    /* Retry only if it's not a timeout and we never attempted a retry
     * (or the code jumping here did not set may_retry to zero). */
    if (errno != ETIMEDOUT && may_retry) {
        may_retry = 0;
        goto try_again;
    }

    /* Cleanup we want to do if no retry is attempted. */
    zfree(ov); zfree(kv);
    addReplySds(c,
        sdscatprintf(sdsempty(),
            "-IOERR error or timeout %s to target instance\r\n",
            write_error ? "writing" : "reading"));
    return;
}

/* -----------------------------------------------------------------------------
 * Cluster functions related to serving / redirecting clients
 * -------------------------------------------------------------------------- */

/* The ASKING command is required after a -ASK redirection.
 * The client should issue ASKING before to actually send the command to
 * the target instance. See the Redis Cluster specification for more
 * information. */
void askingCommand(client *c) {
    if (server.cluster_enabled == 0) {
        addReplyError(c,"This instance has cluster support disabled");
        return;
    }
    c->flags |= CLIENT_ASKING;
    addReply(c,shared.ok);
}

/* The READONLY command is used by clients to enter the read-only mode.
 * In this mode slaves will not redirect clients as long as clients access
 * with read-only commands to keys that are served by the slave's master. */
void readonlyCommand(client *c) {
    if (server.cluster_enabled == 0) {
        addReplyError(c,"This instance has cluster support disabled");
        return;
    }
    c->flags |= CLIENT_READONLY;
    addReply(c,shared.ok);
}

/* The READWRITE command just clears the READONLY command state. */
void readwriteCommand(client *c) {
    c->flags &= ~CLIENT_READONLY;
    addReply(c,shared.ok);
}

/* Return the pointer to the cluster node that is able to serve the command.
 * For the function to succeed the command should only target either:
 *
 * 1) A single key (even multiple times like LPOPRPUSH mylist mylist).
 * 2) Multiple keys in the same hash slot, while the slot is stable (no
 *    resharding in progress).
 *
 * On success the function returns the node that is able to serve the request.
 * If the node is not 'myself' a redirection must be perfomed. The kind of
 * redirection is specified setting the integer passed by reference
 * 'error_code', which will be set to CLUSTER_REDIR_ASK or
 * CLUSTER_REDIR_MOVED.
 *
 * When the node is 'myself' 'error_code' is set to CLUSTER_REDIR_NONE.
 *
 * If the command fails NULL is returned, and the reason of the failure is
 * provided via 'error_code', which will be set to:
 *
 * CLUSTER_REDIR_CROSS_SLOT if the request contains multiple keys that
 * don't belong to the same hash slot.
 *
 * CLUSTER_REDIR_UNSTABLE if the request contains multiple keys
 * belonging to the same slot, but the slot is not stable (in migration or
 * importing state, likely because a resharding is in progress).
 *
 * CLUSTER_REDIR_DOWN_UNBOUND if the request addresses a slot which is
 * not bound to any node. In this case the cluster global state should be
 * already "down" but it is fragile to rely on the update of the global state,
 * so we also handle it here.
 *
 * CLUSTER_REDIR_DOWN_STATE and CLUSTER_REDIR_DOWN_RO_STATE if the cluster is 
 * down but the user attempts to execute a command that addresses one or more keys. */
clusterNode *getNodeByQuery(client *c, struct redisCommand *cmd, robj **argv, int argc, int *hashslot, int *error_code) {
    clusterNode *n = NULL;
    robj *firstkey = NULL;
    int multiple_keys = 0;
    multiState *ms, _ms;
    multiCmd mc;
    int i, slot = 0, migrating_slot = 0, importing_slot = 0, missing_keys = 0;

    /* Allow any key to be set if a module disabled cluster redirections. */
    if (server.cluster_module_flags & CLUSTER_MODULE_FLAG_NO_REDIRECTION)
        return myself;

    /* Set error code optimistically for the base case. */
    if (error_code) *error_code = CLUSTER_REDIR_NONE;

    /* Modules can turn off Redis Cluster redirection: this is useful
     * when writing a module that implements a completely different
     * distributed system. */

    /* We handle all the cases as if they were EXEC commands, so we have
     * a common code path for everything */
    if (cmd->proc == execCommand) {
        /* If CLIENT_MULTI flag is not set EXEC is just going to return an
         * error. */
        if (!(c->flags & CLIENT_MULTI)) return myself;
        ms = &c->mstate;
    } else {
        /* In order to have a single codepath create a fake Multi State
         * structure if the client is not in MULTI/EXEC state, this way
         * we have a single codepath below. */
        ms = &_ms;
        _ms.commands = &mc;
        _ms.count = 1;
        mc.argv = argv;
        mc.argc = argc;
        mc.cmd = cmd;
    }

    /* Check that all the keys are in the same hash slot, and obtain this
     * slot and the node associated. */
    for (i = 0; i < ms->count; i++) {
        struct redisCommand *mcmd;
        robj **margv;
        int margc, *keyindex, numkeys, j;

        mcmd = ms->commands[i].cmd;
        margc = ms->commands[i].argc;
        margv = ms->commands[i].argv;

        keyindex = getKeysFromCommand(mcmd,margv,margc,&numkeys);
        for (j = 0; j < numkeys; j++) {
            robj *thiskey = margv[keyindex[j]];
            int thisslot = keyHashSlot((char*)thiskey->ptr,
                                       sdslen(thiskey->ptr));

            if (firstkey == NULL) {
                /* This is the first key we see. Check what is the slot
                 * and node. */
                firstkey = thiskey;
                slot = thisslot;
                n = server.cluster->slots[slot];

                /* Error: If a slot is not served, we are in "cluster down"
                 * state. However the state is yet to be updated, so this was
                 * not trapped earlier in processCommand(). Report the same
                 * error to the client. */
                if (n == NULL) {
                    getKeysFreeResult(keyindex);
                    if (error_code)
                        *error_code = CLUSTER_REDIR_DOWN_UNBOUND;
                    return NULL;
                }

                /* If we are migrating or importing this slot, we need to check
                 * if we have all the keys in the request (the only way we
                 * can safely serve the request, otherwise we return a TRYAGAIN
                 * error). To do so we set the importing/migrating state and
                 * increment a counter for every missing key. */
                if (n == myself &&
                    server.cluster->migrating_slots_to[slot] != NULL)
                {
                    migrating_slot = 1;
                } else if (server.cluster->importing_slots_from[slot] != NULL) {
                    importing_slot = 1;
                }
            } else {
                /* If it is not the first key, make sure it is exactly
                 * the same key as the first we saw. */
                if (!equalStringObjects(firstkey,thiskey)) {
                    if (slot != thisslot) {
                        /* Error: multiple keys from different slots. */
                        getKeysFreeResult(keyindex);
                        if (error_code)
                            *error_code = CLUSTER_REDIR_CROSS_SLOT;
                        return NULL;
                    } else {
                        /* Flag this request as one with multiple different
                         * keys. */
                        multiple_keys = 1;
                    }
                }
            }

            /* Migarting / Improrting slot? Count keys we don't have. */
            if ((migrating_slot || importing_slot) &&
                lookupKeyRead(&server.db[0],thiskey) == NULL)
            {
                missing_keys++;
            }
        }
        getKeysFreeResult(keyindex);
    }

    /* No key at all in command? then we can serve the request
     * without redirections or errors in all the cases. */
    if (n == NULL) return myself;

    /* Cluster is globally down but we got keys? We only serve the request
     * if it is a read command and when allow_reads_when_down is enabled. */
    if (server.cluster->state != CLUSTER_OK) {
        if (!server.cluster_allow_reads_when_down) {
            /* The cluster is configured to block commands when the
             * cluster is down. */
            if (error_code) *error_code = CLUSTER_REDIR_DOWN_STATE;
            return NULL;
        } else if (!(cmd->flags & CMD_READONLY) && !(cmd->proc == evalCommand)
                && !(cmd->proc == evalShaCommand))
        {
            /* The cluster is configured to allow read only commands
             * but this command is neither readonly, nor EVAL or
             * EVALSHA. */
            if (error_code) *error_code = CLUSTER_REDIR_DOWN_RO_STATE;
            return NULL;
        } else {
            /* Fall through and allow the command to be executed:
             * this happens when server.cluster_allow_reads_when_down is
             * true and the command is a readonly command or EVAL / EVALSHA. */
        }
    }

    /* Return the hashslot by reference. */
    if (hashslot) *hashslot = slot;

    /* MIGRATE always works in the context of the local node if the slot
     * is open (migrating or importing state). We need to be able to freely
     * move keys among instances in this case. */
    if ((migrating_slot || importing_slot) && cmd->proc == migrateCommand)
        return myself;

    /* If we don't have all the keys and we are migrating the slot, send
     * an ASK redirection. */
    if (migrating_slot && missing_keys) {
        if (error_code) *error_code = CLUSTER_REDIR_ASK;
        return server.cluster->migrating_slots_to[slot];
    }

    /* If we are receiving the slot, and the client correctly flagged the
     * request as "ASKING", we can serve the request. However if the request
     * involves multiple keys and we don't have them all, the only option is
     * to send a TRYAGAIN error. */
    if (importing_slot &&
        (c->flags & CLIENT_ASKING || cmd->flags & CMD_ASKING))
    {
        if (multiple_keys && missing_keys) {
            if (error_code) *error_code = CLUSTER_REDIR_UNSTABLE;
            return NULL;
        } else {
            return myself;
        }
    }

    /* Handle the read-only client case reading from a slave: if this
     * node is a slave and the request is about an hash slot our master
     * is serving, we can reply without redirection. */
    if (c->flags & CLIENT_READONLY &&
        (cmd->flags & CMD_READONLY || cmd->proc == evalCommand ||
         cmd->proc == evalShaCommand) &&
        nodeIsSlave(myself) &&
        myself->slaveof == n)
    {
        return myself;
    }

    /* Base case: just return the right node. However if this node is not
     * myself, set error_code to MOVED since we need to issue a rediretion. */
    if (n != myself && error_code) *error_code = CLUSTER_REDIR_MOVED;
    return n;
}

/* Send the client the right redirection code, according to error_code
 * that should be set to one of CLUSTER_REDIR_* macros.
 *
 * If CLUSTER_REDIR_ASK or CLUSTER_REDIR_MOVED error codes
 * are used, then the node 'n' should not be NULL, but should be the
 * node we want to mention in the redirection. Moreover hashslot should
 * be set to the hash slot that caused the redirection. */
void clusterRedirectClient(client *c, clusterNode *n, int hashslot, int error_code) {
    if (error_code == CLUSTER_REDIR_CROSS_SLOT) {
        addReplySds(c,sdsnew("-CROSSSLOT Keys in request don't hash to the same slot\r\n"));
    } else if (error_code == CLUSTER_REDIR_UNSTABLE) {
        /* The request spawns multiple keys in the same slot,
         * but the slot is not "stable" currently as there is
         * a migration or import in progress. */
        addReplySds(c,sdsnew("-TRYAGAIN Multiple keys request during rehashing of slot\r\n"));
    } else if (error_code == CLUSTER_REDIR_DOWN_STATE) {
        addReplySds(c,sdsnew("-CLUSTERDOWN The cluster is down\r\n"));
    } else if (error_code == CLUSTER_REDIR_DOWN_RO_STATE) {
        addReplySds(c,sdsnew("-CLUSTERDOWN The cluster is down and only accepts read commands\r\n"));
    } else if (error_code == CLUSTER_REDIR_DOWN_UNBOUND) {
        addReplySds(c,sdsnew("-CLUSTERDOWN Hash slot not served\r\n"));
    } else if (error_code == CLUSTER_REDIR_MOVED ||
               error_code == CLUSTER_REDIR_ASK)
    {
        addReplySds(c,sdscatprintf(sdsempty(),
            "-%s %d %s:%d\r\n",
            (error_code == CLUSTER_REDIR_ASK) ? "ASK" : "MOVED",
            hashslot,n->ip,n->port));
    } else {
        serverPanic("getNodeByQuery() unknown error.");
    }
}

/* This function is called by the function processing clients incrementally
 * to detect timeouts, in order to handle the following case:
 *
 * 1) A client blocks with BLPOP or similar blocking operation.
 * 2) The master migrates the hash slot elsewhere or turns into a slave.
 * 3) The client may remain blocked forever (or up to the max timeout time)
 *    waiting for a key change that will never happen.
 *
 * If the client is found to be blocked into an hash slot this node no
 * longer handles, the client is sent a redirection error, and the function
 * returns 1. Otherwise 0 is returned and no operation is performed. */
int clusterRedirectBlockedClientIfNeeded(client *c) {
    if (c->flags & CLIENT_BLOCKED &&
        (c->btype == BLOCKED_LIST ||
         c->btype == BLOCKED_ZSET ||
         c->btype == BLOCKED_STREAM))
    {
        dictEntry *de;
        dictIterator *di;

        /* If the cluster is down, unblock the client with the right error.
         * If the cluster is configured to allow reads on cluster down, we
         * still want to emit this error since a write will be required
         * to unblock them which may never come.  */
        if (server.cluster->state == CLUSTER_FAIL) {
            clusterRedirectClient(c,NULL,0,CLUSTER_REDIR_DOWN_STATE);
            return 1;
        }

        /* All keys must belong to the same slot, so check first key only. */
        di = dictGetIterator(c->bpop.keys);
        if ((de = dictNext(di)) != NULL) {
            robj *key = dictGetKey(de);
            int slot = keyHashSlot((char*)key->ptr, sdslen(key->ptr));
            clusterNode *node = server.cluster->slots[slot];

            /* We send an error and unblock the client if:
             * 1) The slot is unassigned, emitting a cluster down error.
             * 2) The slot is not handled by this node, nor being imported. */
            if (node != myself &&
                server.cluster->importing_slots_from[slot] == NULL)
            {
                if (node == NULL) {
                    clusterRedirectClient(c,NULL,0,
                        CLUSTER_REDIR_DOWN_UNBOUND);
                } else {
                    clusterRedirectClient(c,node,slot,
                        CLUSTER_REDIR_MOVED);
                }
                dictReleaseIterator(di);
                return 1;
            }
        }
        dictReleaseIterator(di);
    }
    return 0;
}