summaryrefslogtreecommitdiff
path: root/src/mongo/db/s/balancer/cluster_statistics_impl.cpp
blob: 83b022294b4a51f75a49f0ecf0b74a149d62ff69 (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
/**
 *    Copyright (C) 2018-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.
 */


#include "mongo/platform/basic.h"

#include "mongo/db/s/balancer/cluster_statistics_impl.h"

#include <algorithm>

#include "mongo/base/status_with.h"
#include "mongo/bson/util/bson_extract.h"
#include "mongo/client/read_preference.h"
#include "mongo/logv2/log.h"
#include "mongo/s/catalog/type_shard.h"
#include "mongo/s/client/shard_registry.h"
#include "mongo/s/grid.h"
#include "mongo/s/shard_util.h"
#include "mongo/util/str.h"

#define MONGO_LOGV2_DEFAULT_COMPONENT ::mongo::logv2::LogComponent::kSharding


namespace mongo {
namespace {

const char kVersionField[] = "version";

/**
 * Executes the serverStatus command against the specified shard and obtains the version of the
 * running MongoD service.
 *
 * Returns the MongoD version in strig format or an error. Known error codes are:
 *  ShardNotFound if shard by that id is not available on the registry
 *  NoSuchKey if the version could not be retrieved
 */
StatusWith<std::string> retrieveShardMongoDVersion(OperationContext* opCtx, ShardId shardId) {
    auto shardRegistry = Grid::get(opCtx)->shardRegistry();
    auto shardStatus = shardRegistry->getShard(opCtx, shardId);
    if (!shardStatus.isOK()) {
        return shardStatus.getStatus();
    }
    auto shard = shardStatus.getValue();

    auto commandResponse =
        shard->runCommandWithFixedRetryAttempts(opCtx,
                                                ReadPreferenceSetting{ReadPreference::PrimaryOnly},
                                                "admin",
                                                BSON("serverStatus" << 1),
                                                Shard::RetryPolicy::kIdempotent);
    if (!commandResponse.isOK()) {
        return commandResponse.getStatus();
    }
    if (!commandResponse.getValue().commandStatus.isOK()) {
        return commandResponse.getValue().commandStatus;
    }

    BSONObj serverStatus = std::move(commandResponse.getValue().response);

    std::string version;
    Status status = bsonExtractStringField(serverStatus, kVersionField, &version);
    if (!status.isOK()) {
        return status;
    }

    return version;
}
}  // namespace

using ShardStatistics = ClusterStatistics::ShardStatistics;

ClusterStatisticsImpl::ClusterStatisticsImpl(BalancerRandomSource& random) : _random(random) {}

ClusterStatisticsImpl::~ClusterStatisticsImpl() = default;

StatusWith<std::vector<ShardStatistics>> ClusterStatisticsImpl::getStats(OperationContext* opCtx) {
    return _getStats(opCtx, boost::none);
}

StatusWith<std::vector<ShardStatistics>> ClusterStatisticsImpl::getCollStats(
    OperationContext* opCtx, NamespaceString const& ns) {
    return _getStats(opCtx, ns);
}

StatusWith<std::vector<ShardStatistics>> ClusterStatisticsImpl::_getStats(
    OperationContext* opCtx, boost::optional<NamespaceString> ns) {
    // Get a list of all the shards that are participating in this balance round along with any
    // maximum allowed quotas and current utilization. We get the latter by issuing
    // db.serverStatus() (mem.mapped) to all shards.
    //
    // TODO: skip unresponsive shards and mark information as stale.
    auto shardsStatus = Grid::get(opCtx)->catalogClient()->getAllShards(
        opCtx, repl::ReadConcernLevel::kMajorityReadConcern);
    if (!shardsStatus.isOK()) {
        return shardsStatus.getStatus();
    }

    auto& shards = shardsStatus.getValue().value;

    std::shuffle(shards.begin(), shards.end(), _random);

    std::vector<ShardStatistics> stats;

    for (const auto& shard : shards) {
        const auto shardSizeStatus = [&]() -> StatusWith<long long> {
            if (ns) {
                return shardutil::retrieveCollectionShardSize(opCtx, shard.getName(), *ns);
            }
            // optimization for the case where the balancer does not care about the dataSize
            if (!shard.getMaxSizeMB()) {
                return 0;
            }
            return shardutil::retrieveTotalShardSize(opCtx, shard.getName());
        }();

        if (!shardSizeStatus.isOK()) {
            const auto& status = shardSizeStatus.getStatus();

            return status.withContext(str::stream()
                                      << "Unable to obtain shard utilization information for "
                                      << shard.getName());
        }

        std::string mongoDVersion;

        auto mongoDVersionStatus = retrieveShardMongoDVersion(opCtx, shard.getName());
        if (mongoDVersionStatus.isOK()) {
            mongoDVersion = std::move(mongoDVersionStatus.getValue());
        } else {
            // Since the mongod version is only used for reporting, there is no need to fail the
            // entire round if it cannot be retrieved, so just leave it empty
            LOGV2(21895,
                  "Unable to obtain shard version for {shardId}: {error}",
                  "Unable to obtain shard version",
                  "shardId"_attr = shard.getName(),
                  "error"_attr = mongoDVersionStatus.getStatus());
        }

        std::set<std::string> shardZones;

        for (const auto& shardZone : shard.getTags()) {
            shardZones.insert(shardZone);
        }

        stats.emplace_back(shard.getName(),
                           shard.getMaxSizeMB() * 1024 * 1024,
                           shardSizeStatus.getValue(),
                           shard.getDraining(),
                           std::move(shardZones),
                           std::move(mongoDVersion),
                           ShardStatistics::use_bytes_t{});
    }

    return stats;
}

}  // namespace mongo