git-p4: use -m when running p4 changesls/p4-changes-block-size

Simply running "p4 changes" on a large branch can result in a "too
many rows scanned" error from the Perforce server. It is better to
use a sequence of smaller calls to "p4 changes", using the "-m"
option to limit the size of each call.

Signed-off-by: Lex Spoon <lex@lexspoon.org>
Acked-by: Luke Diamand <luke@diamand.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 41 insertions, 11 deletions

diff --git a/git-p4.py b/git-p4.py
index 549022e97c..e28033f4e1 100755
--- a/git-p4.py
+++ b/git-p4.py
@@ -740,17 +740,43 @@ def createOrUpdateBranchesFromOrigin(localRefPrefix = "refs/remotes/p4/", silent
 def originP4BranchesExist():
         return gitBranchExists("origin") or gitBranchExists("origin/p4") or gitBranchExists("origin/p4/master")
 
-def p4ChangesForPaths(depotPaths, changeRange):
+def p4ChangesForPaths(depotPaths, changeRange, block_size):
     assert depotPaths
-    cmd = ['changes']
-    for p in depotPaths:
-        cmd += ["%s...%s" % (p, changeRange)]
-    output = p4_read_pipe_lines(cmd)
+    assert block_size
+
+    # Parse the change range into start and end
+    if changeRange is None or changeRange == '':
+        changeStart = '@1'
+        changeEnd = '#head'
+    else:
+        parts = changeRange.split(',')
+        assert len(parts) == 2
+        changeStart = parts[0]
+        changeEnd = parts[1]
 
+    # Accumulate change numbers in a dictionary to avoid duplicates
     changes = {}
-    for line in output:
-        changeNum = int(line.split(" ")[1])
-        changes[changeNum] = True
+
+    for p in depotPaths:
+        # Retrieve changes a block at a time, to prevent running
+        # into a MaxScanRows error from the server.
+        start = changeStart
+        end = changeEnd
+        get_another_block = True
+        while get_another_block:
+            new_changes = []
+            cmd = ['changes']
+            cmd += ['-m', str(block_size)]
+            cmd += ["%s...%s,%s" % (p, start, end)]
+            for line in p4_read_pipe_lines(cmd):
+                changeNum = int(line.split(" ")[1])
+                new_changes.append(changeNum)
+                changes[changeNum] = True
+            if len(new_changes) == block_size:
+                get_another_block = True
+                end = '@' + str(min(new_changes))
+            else:
+                get_another_block = False
 
     changelist = changes.keys()
     changelist.sort()
@@ -1911,7 +1937,10 @@ class P4Sync(Command, P4UserMap):
                 optparse.make_option("--import-labels", dest="importLabels", action="store_true"),
                 optparse.make_option("--import-local", dest="importIntoRemotes", action="store_false",
                                      help="Import into refs/heads/ , not refs/remotes"),
-                optparse.make_option("--max-changes", dest="maxChanges"),
+                optparse.make_option("--max-changes", dest="maxChanges",
+                                     help="Maximum number of changes to import"),
+                optparse.make_option("--changes-block-size", dest="changes_block_size", type="int",
+                                     help="Internal block size to use when iteratively calling p4 changes"),
                 optparse.make_option("--keep-path", dest="keepRepoPath", action='store_true',
                                      help="Keep entire BRANCH/DIR/SUBDIR prefix during import"),
                 optparse.make_option("--use-client-spec", dest="useClientSpec", action='store_true',
@@ -1940,6 +1969,7 @@ class P4Sync(Command, P4UserMap):
         self.syncWithOrigin = True
         self.importIntoRemotes = True
         self.maxChanges = ""
+        self.changes_block_size = 500
         self.keepRepoPath = False
         self.depotPaths = None
         self.p4BranchesInGit = []
@@ -2586,7 +2616,7 @@ class P4Sync(Command, P4UserMap):
         branchPrefix = self.depotPaths[0] + branch + "/"
         range = "@1,%s" % maxChange
         #print "prefix" + branchPrefix
-        changes = p4ChangesForPaths([branchPrefix], range)
+        changes = p4ChangesForPaths([branchPrefix], range, self.changes_block_size)
         if len(changes) <= 0:
             return False
         firstChange = changes[0]
@@ -3002,7 +3032,7 @@ class P4Sync(Command, P4UserMap):
                 if self.verbose:
                     print "Getting p4 changes for %s...%s" % (', '.join(self.depotPaths),
                                                               self.changeRange)
-                changes = p4ChangesForPaths(self.depotPaths, self.changeRange)
+                changes = p4ChangesForPaths(self.depotPaths, self.changeRange, self.changes_block_size)
 
                 if len(self.maxChanges) > 0:
                     changes = changes[:min(int(self.maxChanges), len(changes))]