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
|
/**
* Copyright (C) 2020-present MongoDB, Inc.
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the Server Side Public License, version 1,
* as published by MongoDB, Inc.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* Server Side Public License for more details.
*
* You should have received a copy of the Server Side Public License
* along with this program. If not, see
* <http://www.mongodb.com/licensing/server-side-public-license>.
*
* As a special exception, the copyright holders give permission to link the
* code of portions of this program with the OpenSSL library under certain
* conditions as described in each individual source file and distribute
* linked combinations including the program with the OpenSSL library. You
* must comply with the Server Side Public License in all respects for
* all of the code used other than as permitted herein. If you modify file(s)
* with this exception, you may extend this exception to your version of the
* file(s), but you are not obligated to do so. If you do not wish to do so,
* delete this exception statement from your version. If you delete this
* exception statement from all source files in the program, then also delete
* it in the license file.
*/
#pragma once
#include <boost/optional.hpp>
#include "mongo/base/status_with.h"
#include "mongo/client/dbclient_base.h"
#include "mongo/db/cancelable_operation_context.h"
#include "mongo/db/namespace_string.h"
#include "mongo/db/operation_context.h"
#include "mongo/db/pipeline/expression_context.h"
#include "mongo/db/s/resharding/donor_oplog_id_gen.h"
#include "mongo/db/s/resharding/resharding_donor_oplog_iterator.h"
#include "mongo/db/service_context.h"
#include "mongo/db/shard_id.h"
#include "mongo/platform/mutex.h"
#include "mongo/s/client/shard.h"
#include "mongo/util/background.h"
#include "mongo/util/cancellation.h"
#include "mongo/util/future.h"
#include "mongo/util/time_support.h"
#include "mongo/util/uuid.h"
namespace mongo {
class ReshardingMetrics;
class ReshardingOplogFetcher : public resharding::OnInsertAwaitable {
public:
class Env {
public:
Env(ServiceContext* service, ReshardingMetrics* metrics)
: _service(service), _metrics(metrics) {}
ServiceContext* service() const {
return _service;
}
ReshardingMetrics* metrics() const {
return _metrics;
}
private:
ServiceContext* _service;
ReshardingMetrics* _metrics;
};
// Special value to use for startAt to indicate there are no more oplog entries needing to be
// fetched.
static const ReshardingDonorOplogId kFinalOpAlreadyFetched;
ReshardingOplogFetcher(std::unique_ptr<Env> env,
UUID reshardingUUID,
UUID collUUID,
ReshardingDonorOplogId startAt,
ShardId donorShard,
ShardId recipientShard,
NamespaceString toWriteInto);
~ReshardingOplogFetcher();
Future<void> awaitInsert(const ReshardingDonorOplogId& lastSeen) override;
/**
* Schedules a task that will do the following:
*
* - Find a valid connection to fetch oplog entries from.
* - Send an aggregation request + getMores until either:
* -- The "final resharding" oplog entry is found.
* -- An interruption occurs.
* -- The fetcher concludes it's fallen off the oplog.
* -- A different error occurs.
*
* In the first two circumstances, the task will terminate. If the fetcher has fallen off the
* oplog, this is thrown as a fatal resharding exception. In the last circumstance, the task
* will be rescheduled in a way that resumes where it had left off from.
*/
ExecutorFuture<void> schedule(std::shared_ptr<executor::TaskExecutor> executor,
const CancellationToken& cancelToken,
CancelableOperationContextFactory factory);
/**
* Given a shard, fetches and copies oplog entries until
* - reaching an error,
* - coming across a sentinel finish oplog entry, or
* - hitting the end of the donor's oplog.
*
* Returns true if there are more oplog entries to be copied, and returns false if the sentinel
* finish oplog entry has been copied.
*/
bool consume(Client* client, CancelableOperationContextFactory factory, Shard* shard);
bool iterate(Client* client, CancelableOperationContextFactory factory);
int getNumOplogEntriesCopied() const {
return _numOplogEntriesCopied;
}
ReshardingDonorOplogId getLastSeenTimestamp() const {
return _startAt;
}
void setInitialBatchSizeForTest(int size) {
_initialBatchSize = size;
}
void useReadConcernForTest(bool use) {
_useReadConcern = use;
}
void setMaxBatchesForTest(int maxBatches) {
_maxBatches = maxBatches;
}
private:
/**
* Returns true if there's more work to do and the task should be rescheduled.
*/
void _ensureCollection(Client* client,
CancelableOperationContextFactory factory,
NamespaceString nss);
AggregateCommandRequest _makeAggregateCommandRequest(Client* client,
CancelableOperationContextFactory factory);
ExecutorFuture<void> _reschedule(std::shared_ptr<executor::TaskExecutor> executor,
const CancellationToken& cancelToken,
CancelableOperationContextFactory factory);
ServiceContext* _service() const {
return _env->service();
}
std::unique_ptr<Env> _env;
const UUID _reshardingUUID;
const UUID _collUUID;
ReshardingDonorOplogId _startAt;
const ShardId _donorShard;
const ShardId _recipientShard;
const NamespaceString _toWriteInto;
int _numOplogEntriesCopied = 0;
Mutex _mutex = MONGO_MAKE_LATCH("ReshardingOplogFetcher::_mutex");
Promise<void> _onInsertPromise;
Future<void> _onInsertFuture;
// For testing to control behavior.
// The aggregation batch size. This only affects the original call and not `getmore`s.
int _initialBatchSize = 0;
// Setting to false will omit the `afterClusterTime` and `majority` read concern.
bool _useReadConcern = true;
// Dictates how many batches get processed before returning control from a call to `consume`.
int _maxBatches = -1;
};
} // namespace mongo
|
