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
|
/**
* Copyright (C) 2022-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.
*/
#define MONGO_LOGV2_DEFAULT_COMPONENT ::mongo::logv2::LogComponent::kSharding
#include "mongo/platform/basic.h"
#include "mongo/db/s/topology_time_ticker.h"
#include "mongo/db/repl/replication_coordinator.h"
#include "mongo/db/vector_clock_mutable.h"
#include "mongo/logv2/log.h"
namespace mongo {
namespace {
// The number of pending topologyTime tick points (stored in _topologyTimeByLocalCommitTime) is
// generally expected to be small (since shard topology operations should be infrequent, relative to
// any config server replication lag). If its size exceeds this constant (when a tick point is
// added), then a warning (with id 4740600) will be logged.
constexpr size_t kPossiblyExcessiveNumTopologyTimeTickPoints = 3;
const auto serviceDecorator = ServiceContext::declareDecoration<TopologyTimeTicker>();
} // namespace
namespace topology_time_ticker_utils {
bool inRecoveryMode(OperationContext* opCtx) {
invariant(opCtx->lockState()->isRSTLLocked());
const auto replCoord = repl::ReplicationCoordinator::get(opCtx);
if (!replCoord->isReplEnabled()) {
return false;
}
const auto memberState = replCoord->getMemberState();
return memberState.startup2() || memberState.rollback();
}
} // namespace topology_time_ticker_utils
TopologyTimeTicker& TopologyTimeTicker::get(ServiceContext* serviceContext) {
return serviceDecorator(serviceContext);
}
TopologyTimeTicker& TopologyTimeTicker::get(OperationContext* opCtx) {
return get(opCtx->getServiceContext());
}
void TopologyTimeTicker::onNewLocallyCommittedTopologyTimeAvailable(Timestamp commitTime,
Timestamp topologyTime) {
const auto numTickPoints = [&] {
stdx::lock_guard lg(_mutex);
bool skipCausalConsistencyCheck = [] {
auto opCtx = cc().getOperationContext();
if (!opCtx || opCtx->isEnforcingConstraints()) {
// Default case.
return false;
}
// The callback is being invoked within the context of an oplog application, where
// entries may be received in non strict order for optimisation reasons. Such case may
// be considered safe.
return true;
}();
invariant(skipCausalConsistencyCheck || _topologyTimeByLocalCommitTime.size() == 0 ||
_topologyTimeByLocalCommitTime.crbegin()->first < commitTime);
_topologyTimeByLocalCommitTime.emplace(commitTime, topologyTime);
return _topologyTimeByLocalCommitTime.size();
}();
if (numTickPoints >= kPossiblyExcessiveNumTopologyTimeTickPoints) {
LOGV2_WARNING(4740600,
"possibly excessive number of topologyTime tick points",
"numTickPoints"_attr = numTickPoints,
"kPossiblyExcessiveNumTopologyTimeTickPoints"_attr =
kPossiblyExcessiveNumTopologyTimeTickPoints);
}
}
void TopologyTimeTicker::onMajorityCommitPointUpdate(ServiceContext* service,
const repl::OpTime& newCommitPoint) {
Timestamp newMajorityTimestamp = newCommitPoint.getTimestamp();
stdx::lock_guard lg(_mutex);
if (_topologyTimeByLocalCommitTime.empty())
return;
// Looking for the first tick point that is not majority committed
auto itFirstTickPointNonMajorityCommitted =
_topologyTimeByLocalCommitTime.upper_bound(newMajorityTimestamp);
if (itFirstTickPointNonMajorityCommitted != _topologyTimeByLocalCommitTime.begin()) {
// If some ticks were majority committed, advance the TopologyTime to the most recent one
const auto maxMajorityCommittedTopologyTime =
std::prev(itFirstTickPointNonMajorityCommitted)->second;
VectorClockMutable::get(service)->tickTopologyTimeTo(
LogicalTime(maxMajorityCommittedTopologyTime));
_topologyTimeByLocalCommitTime.erase(_topologyTimeByLocalCommitTime.begin(),
itFirstTickPointNonMajorityCommitted);
}
}
void TopologyTimeTicker::onReplicationRollback(const repl::OpTime& lastAppliedOpTime) {
Timestamp newestTimestamp = lastAppliedOpTime.getTimestamp();
stdx::lock_guard lg(_mutex);
auto itFirstElemToBeRemoved = _topologyTimeByLocalCommitTime.upper_bound(newestTimestamp);
_topologyTimeByLocalCommitTime.erase(itFirstElemToBeRemoved,
_topologyTimeByLocalCommitTime.end());
}
} // namespace mongo
|
