给您的 MongoDB 定期做个体检：MongoDB 诊断

给您的 MongoDB 定期做个体检：MongoDB 诊断-51CTO.COM

随着 MongoDB 的不断运行且数据量日益增多，就会不免产生一些问题。当问题出现时，该怎么办呢？我们会从以下几个方面进行探讨。

当有个长期运行的 MongoDB 进程时，我们可能想自己写个脚本来定期轮转日志文件。其实不用，MongoDB 已经提供了 logrotate 命令来完成这个操作，可以直接从 shell 里启动使用：

use admin


rs0:PRIMARY> db.runCommand({logRotate: 1})
{
    "ok" : 1,
    "$clusterTime" : {
        "clusterTime" : Timestamp(1679966896, 1),
        "signature" : {
            "hash" : BinData(0,"50vWhFp/59fAKwBbUQUDxApF/+g="),
            "keyId" : NumberLong("7173500260914823169")
        }
    },
    "operationTime" : Timestamp(1679966896, 1)
}

需要注意：logRotate 是区分大小写的。

或者可以向 Mongo 进程发送 SIGUSR1 信号：

$ kill -SIGUSR1 <mongo_pid>

MongoDB 包含了许多命令可以报告内部状态，这些命令背后都是监控 MongoDB。下面是一些常见命令的参考命令，希望对大家有所帮助：

01全局服务器信息统计

该命令输出的信息非常详细，当 MongoDB 出现问题时，是一个不错的诊断命令。

rs0:PRIMARY> db.serverStatus()
{
    "host" : "mongo03.tyun.cn",
    "version" : "4.4.15",
    "process" : "mongod",
    "pid" : NumberLong(14092),
    "uptime" : 18727504,
    "uptimeMillis" : NumberLong("18727504137"),
    "uptimeEstimate" : NumberLong(18727504),
    "localTime" : ISODate("2023-03-28T01:30:35.805Z"),
    "asserts" : {
        "regular" : 0,
        "warning" : 0,
        "msg" : 0,
        "user" : 1380727,
        "rollovers" : 0
    },
    "connections" : {
        "current" : 17,
        "available" : 51183,
        "totalCreated" : 3253,
        "active" : 7,
        "exhaustIsMaster" : 3,
        "exhaustHello" : 2,
        "awaitingTopologyChanges" : 176
    },
    "defaultRWConcern" : {
        "localUpdateWallClockTime" : ISODate("2022-08-23T07:25:32.995Z")
    },


        "tcmalloc" : {
            "pageheap_free_bytes" : 94162944,
            "pageheap_unmapped_bytes" : 349478912,
            "max_total_thread_cache_bytes" : 1024458752,
            "current_total_thread_cache_bytes" : 238198560,
            "total_free_bytes" : 637257904,
            "central_cache_free_bytes" : 397502736,
            "transfer_cache_free_bytes" : 1556608,
            "thread_cache_free_bytes" : 238198560,
            "aggressive_memory_decommit" : 0,
            "pageheap_committed_bytes" : NumberLong("3653197824"),
            "pageheap_scavenge_count" : 13297522,
            "pageheap_commit_count" : 14804116,
            "pageheap_total_commit_bytes" : NumberLong("60304102580224"),
            "pageheap_decommit_count" : 13297522,
            "pageheap_total_decommit_bytes" : NumberLong("60300449382400"),
            "pageheap_reserve_count" : 459,
            "pageheap_total_reserve_bytes" : NumberLong("4002676736"),
            "spinlock_total_delay_ns" : NumberLong("111430768421"),
            "release_rate" : 1,
            "formattedString" : "------------------------------------------------\nMALLOC:     2921777552 ( 2786.4 MiB) Bytes in use by application\nMALLOC: +     94162944 (   89.8 MiB) Bytes in page heap freelist\nMALLOC: +    397502736 (  379.1 MiB) Bytes in central cache freelist\nMALLOC: +      1556608 (    1.5 MiB) Bytes in transfer cache freelist\nMALLOC: +    238197984 (  227.2 MiB) Bytes in thread cache freelists\nMALLOC: +     24510464 (   23.4 MiB) Bytes in malloc metadata\nMALLOC:   ------------\nMALLOC: =   3677708288 ( 3507.3 MiB) Actual memory used (physical + swap)\nMALLOC: +    349478912 (  333.3 MiB) Bytes released to OS (aka unmapped)\nMALLOC:   ------------\nMALLOC: =   4027187200 ( 3840.6 MiB) Virtual address space used\nMALLOC:\nMALLOC:         265177              Spans in use\nMALLOC:             72              Thread heaps in use\nMALLOC:           4096              Tcmalloc page size\n------------------------------------------------\nCall ReleaseFreeMemory() to release freelist memory to the OS (via madvise()).\nBytes released to the OS take up virtual address space but no physical memory.\n"
        }
    },
    "trafficRecording" : {
        "running" : false
    },
    "transactions" : {
        "retriedCommandsCount" : NumberLong(0),
        "retriedStatementsCount" : NumberLong(0),
        "transactionsCollectionWriteCount" : NumberLong(0),
        "currentActive" : NumberLong(0),
        "currentInactive" : NumberLong(0),
        "currentOpen" : NumberLong(0),
        "totalAborted" : NumberLong(0),
        "totalCommitted" : NumberLong(0),
        "totalStarted" : NumberLong(0),
        "totalPrepared" : NumberLong(0),
        "totalPreparedThenCommitted" : NumberLong(0),
        "totalPreparedThenAborted" : NumberLong(0),
        "currentPrepared" : NumberLong(0)
    },
    "transportSecurity" : {
        "1.0" : NumberLong(0),
        "1.1" : NumberLong(0),
        "1.2" : NumberLong(0),
        "1.3" : NumberLong(0),
        "unknown" : NumberLong(0)
    },
    "twoPhaseCommitCoordinator" : {
        "totalCreated" : NumberLong(0),
        "totalStartedTwoPhaseCommit" : NumberLong(0),
        "totalAbortedTwoPhaseCommit" : NumberLong(0),
        "totalCommittedTwoPhaseCommit" : NumberLong(0),
        "currentInSteps" : {
            "writingParticipantList" : NumberLong(0),
            "waitingForVotes" : NumberLong(0),
            "writingDecision" : NumberLong(0),
            "waitingForDecisionAcks" : NumberLong(0),
            "deletingCoordinatorDoc" : NumberLong(0)
        }
    },
    "wiredTiger" : {
        "uri" : "statistics:",
        "block-manager" : {
            "blocks pre-loaded" : 23,
            "blocks read" : 4268362,
            "blocks written" : 39421996,
            "bytes read" : 48401854464,
            "bytes read via memory map API" : 0,
            "bytes read via system call API" : 0,
            "bytes written" : 418967826432,
            "bytes written for checkpoint" : 305570754560,
            "bytes written via memory map API" : 0,
            "bytes written via system call API" : 0,
            "mapped blocks read" : 0,
            "mapped bytes read" : 0,
            "number of times the file was remapped because it changed size via fallocate or truncate" : 0,
            "number of times the region was remapped via write" : 0
        },


        "capacity" : {
            "background fsync file handles considered" : 0,
            "background fsync file handles synced" : 0,
            "background fsync time (msecs)" : 0,
            "bytes read" : 39614959616,
            "bytes written for checkpoint" : 239185165378,
            "bytes written for eviction" : 97795992160,
            "bytes written for log" : 157233860864,
            "bytes written total" : 494215018402,
            "threshold to call fsync" : 0,
            "time waiting due to total capacity (usecs)" : 0,
            "time waiting during checkpoint (usecs)" : 0,
            "time waiting during eviction (usecs)" : 0,
            "time waiting during logging (usecs)" : 0,
            "time waiting during read (usecs)" : 0
        },
        "checkpoint-cleanup" : {
            "pages added for eviction" : 81667,
            "pages removed" : 16946,
            "pages skipped during tree walk" : 3064011324,
            "pages visited" : 5381579176
        },
        "connection" : {
            "auto adjusting condition resets" : 6326104,
            "auto adjusting condition wait calls" : 121447994,
            "auto adjusting condition wait raced to update timeout and skipped updating" : 61,
            "detected system time went backwards" : 0,
            "files currently open" : 71,
            "hash bucket array size for data handles" : 512,
            "hash bucket array size general" : 512,
            "memory allocations" : 14030754494,
            "memory frees" : 14027269174,
            "memory re-allocations" : 161883962,
            "pthread mutex condition wait calls" : 314479507,
            "pthread mutex shared lock read-lock calls" : 12181240198,
            "pthread mutex shared lock write-lock calls" : 743154980,
            "total fsync I/Os" : 275579938,
            "total read I/Os" : 4582332,
            "total write I/Os" : 313739357
        },


    "mem" : {
        "bits" : 64,
        "resident" : 3423,
        "virtual" : 5564,
        "supported" : true
    },
    "metrics" : {
        "aggStageCounters" : {
            "$_internalInhibitOptimization" : NumberLong(0),
            "$_internalSplitPipeline" : NumberLong(0),
            "$addFields" : NumberLong(1),
            "$bucket" : NumberLong(0),
            "$bucketAuto" : NumberLong(0),
            "$changeStream" : NumberLong(0),
            "$collStats" : NumberLong(0),
            "$count" : NumberLong(0),
            "$currentOp" : NumberLong(0),
            "$documents" : NumberLong(0),
            "$facet" : NumberLong(0),
            "$geoNear" : NumberLong(0),
            "$graphLookup" : NumberLong(0),
            "$group" : NumberLong(0),
            "$indexStats" : NumberLong(0),
            "$limit" : NumberLong(0),
            "$listLocalSessions" : NumberLong(0),
            "$listSessions" : NumberLong(0),
            "$lookup" : NumberLong(0),
            "$match" : NumberLong(1),
            "$merge" : NumberLong(0),
            "$mergeCursors" : NumberLong(0),
            "$out" : NumberLong(0),
            "$planCacheStats" : NumberLong(0),
            "$project" : NumberLong(2),
            "$queue" : NumberLong(0),
            "$redact" : NumberLong(0),
            "$replaceRoot" : NumberLong(0),
            "$replaceWith" : NumberLong(0),
            "$sample" : NumberLong(0),
            "$set" : NumberLong(46126),
            "$skip" : NumberLong(0),
            "$sort" : NumberLong(1),
            "$sortByCount" : NumberLong(0),
            "$unionWith" : NumberLong(0),
            "$unset" : NumberLong(0),
            "$unwind" : NumberLong(0)
        },
        "commands" : {
            "<UNKNOWN>" : NumberLong(2),
            "_isSelf" : {
                "failed" : NumberLong(0),
                "total" : NumberLong(13)
            },
            "buildInfo" : {
                "failed" : NumberLong(0),
                "total" : NumberLong(690365)
            },
            "count" : {
                "failed" : NumberLong(0),
                "total" : NumberLong(6)
            },
            "delete" : {
                "failed" : NumberLong(0),
                "total" : NumberLong(48)
            },
            "endSessions" : {
                "failed" : NumberLong(0),
                "total" : NumberLong(134)
            },
            "find" : {
                "failed" : NumberLong(0),
                "total" : NumberLong(2142077)
            },
            "getCmdLineOpts" : {
                "failed" : NumberLong(0),
                "total" : NumberLong(1380235)
            },
            "getDiagnosticData" : {
                "failed" : NumberLong(0),
                "total" : NumberLong(2070345)
            },
            "getFreeMonitoringStatus" : {
                "failed" : NumberLong(0),
                "total" : NumberLong(5)
            },
            "getLastError" : {
                "failed" : NumberLong(0),
                "total" : NumberLong(101)
            },
            "getLog" : {
                "failed" : NumberLong(0),
                "total" : NumberLong(5)
            },
            "getMore" : {
                "failed" : NumberLong(1),
                "total" : NumberLong(465344562)
            },
            "getnonce" : {
                "failed" : NumberLong(0),
                "total" : NumberLong(2)
            },
            "hello" : {
                "failed" : NumberLong(268),
                "total" : NumberLong(1384888)
            },
            "insert" : {
                "failed" : NumberLong(0),
                "total" : NumberLong(1)
            },
            "isMaster" : {
                "failed" : NumberLong(2),
                "total" : NumberLong(7731521)
            },
            "killCursors" : {
                "failed" : NumberLong(0),
                "total" : NumberLong(5)
            },
            "listCollections" : {
                "failed" : NumberLong(0),
                "total" : NumberLong(10)
            },
            "listDatabases" : {
                "failed" : NumberLong(0),
                "total" : NumberLong(57515)
            },
            "listIndexes" : {
                "failed" : NumberLong(3),
                "total" : NumberLong(124851)
            },
            "logRotate" : {
                "failed" : NumberLong(0),
                "total" : NumberLong(1)
            },
            "ping" : {
                "failed" : NumberLong(0),
                "total" : NumberLong(4436308)
            },
            "replSetGetConfig" : {
                "failed" : NumberLong(0),
                "total" : NumberLong(2070345)
            },
            "replSetGetRBID" : {
                "failed" : NumberLong(0),
                "total" : NumberLong(6)
            },
            "replSetGetStatus" : {
                "failed" : NumberLong(0),
                "total" : NumberLong(690128)
            },
            "replSetHeartbeat" : {
                "failed" : NumberLong(0),
                "total" : NumberLong(17000850)
            },
            "replSetRequestVotes" : {
                "failed" : NumberLong(0),
                "total" : NumberLong(4)
            },
            "replSetUpdatePosition" : {
                "failed" : NumberLong(0),
                "total" : NumberLong(390211482)
            },
            "rolesInfo" : {
                "failed" : NumberLong(0),
                "total" : NumberLong(1)
            },
            "saslContinue" : {
                "failed" : NumberLong(6),
                "total" : NumberLong(62466)
            },
            "saslStart" : {
                "failed" : NumberLong(0),
                "total" : NumberLong(57875)
            },
            "serverStatus" : {
                "failed" : NumberLong(0),
                "total" : NumberLong(1)
            },
            "update" : {
                "arrayFilters" : NumberLong(0),
                "failed" : NumberLong(0),
                "pipeline" : NumberLong(23063),
                "total" : NumberLong(511271)
            },
            "usersInfo" : {
                "failed" : NumberLong(0),
                "total" : NumberLong(1)
            },
            "whatsmyuri" : {
                "failed" : NumberLong(0),
                "total" : NumberLong(5)
            }
        },
        "cursor" : {
            "timedOut" : NumberLong(0),
            "open" : {
                "noTimeout" : NumberLong(0),
                "pinned" : NumberLong(1),
                "total" : NumberLong(1)
            }
        },
        "document" : {
            "deleted" : NumberLong(0),
            "inserted" : NumberLong(1),
            "returned" : NumberLong(322743825),
            "updated" : NumberLong(522796)
        },
        "getLastError" : {
            "wtime" : {
                "num" : 11577,
                "totalMillis" : 37265
            },
            "wtimeouts" : NumberLong(1),
            "default" : {
                "unsatisfiable" : NumberLong(0),
                "wtimeouts" : NumberLong(0)
            }
        },
        "operation" : {
            "scanAndOrder" : NumberLong(15),
            "writeConflicts" : NumberLong(9825)
        },


        "query" : {
            "planCacheTotalSizeEstimateBytes" : NumberLong(0),
            "updateOneOpStyleBroadcastWithExactIDCount" : NumberLong(0),
            "multiPlanner" : {
                "classicCount" : NumberLong(0),
                "classicMicros" : NumberLong(0),
                "classicWorks" : NumberLong(0),
                "histograms" : {
                    "classicMicros" : [
                        {
                            "lowerBound" : NumberLong(0),
                            "count" : NumberLong(0)
                        },
                        {
                            "lowerBound" : NumberLong(1024),
                            "count" : NumberLong(0)
                        },
                        {
                            "lowerBound" : NumberLong(4096),
                            "count" : NumberLong(0)
                        },
                        {
                            "lowerBound" : NumberLong(16384),
                            "count" : NumberLong(0)
                        },
                        {
                            "lowerBound" : NumberLong(65536),
                            "count" : NumberLong(0)
                        },
                        {
                            "lowerBound" : NumberLong(262144),
                            "count" : NumberLong(0)
                        },
                        {
                            "lowerBound" : NumberLong(1048576),
                            "count" : NumberLong(0)
                        },
                        {
                            "lowerBound" : NumberLong(4194304),
                            "count" : NumberLong(0)
                        },
                        {
                            "lowerBound" : NumberLong(16777216),
                            "count" : NumberLong(0)
                        },
                        {
                            "lowerBound" : NumberLong(67108864),
                            "count" : NumberLong(0)
                        },
                        {
                            "lowerBound" : NumberLong(268435456),
                            "count" : NumberLong(0)
                        },
                        {
                            "lowerBound" : NumberLong(1073741824),
                            "count" : NumberLong(0)
                        }
                    ],
                    "classicNumPlans" : [
                        {
                            "lowerBound" : NumberLong(0),
                            "count" : NumberLong(0)
                        },
                        {
                            "lowerBound" : NumberLong(2),
                            "count" : NumberLong(0)
                        },
                        {
                            "lowerBound" : NumberLong(4),
                            "count" : NumberLong(0)
                        },
                        {
                            "lowerBound" : NumberLong(8),
                            "count" : NumberLong(0)
                        },
                        {
                            "lowerBound" : NumberLong(16),
                            "count" : NumberLong(0)
                        },
                        {
                            "lowerBound" : NumberLong(32),
                            "count" : NumberLong(0)
                        }
                    ],
                    "classicWorks" : [
                        {
                            "lowerBound" : NumberLong(0),
                            "count" : NumberLong(0)
                        },
                        {
                            "lowerBound" : NumberLong(128),
                            "count" : NumberLong(0)
                        },
                        {
                            "lowerBound" : NumberLong(256),
                            "count" : NumberLong(0)
                        },
                        {
                            "lowerBound" : NumberLong(512),
                            "count" : NumberLong(0)
                        },
                        {
                            "lowerBound" : NumberLong(1024),
                            "count" : NumberLong(0)
                        },
                        {
                            "lowerBound" : NumberLong(2048),
                            "count" : NumberLong(0)
                        },
                        {
                            "lowerBound" : NumberLong(4096),
                            "count" : NumberLong(0)
                        },
                        {
                            "lowerBound" : NumberLong(8192),
                            "count" : NumberLong(0)
                        },
                        {
                            "lowerBound" : NumberLong(16384),
                            "count" : NumberLong(0)
                        },
                        {
                            "lowerBound" : NumberLong(32768),
                            "count" : NumberLong(0)
                        }
                    ]
                }
            }
        },
        "queryExecutor" : {
            "scanned" : NumberLong(1070392),
            "scannedObjects" : NumberLong(323266658),
            "collectionScans" : {
                "nonTailable" : NumberLong(1386454),
                "total" : NumberLong(1386461)
            }
        },
        "record" : {
            "moves" : NumberLong(0)
        },
        "repl" : {
            "executor" : {
                "pool" : {
                    "inProgressCount" : 0
                },
                "queues" : {
                    "networkInProgress" : 0,
                    "sleepers" : 3
                },
                "unsignaledEvents" : 0,
                "shuttingDown" : false,
                "networkInterface" : "DEPRECATED: getDiagnosticString is deprecated in NetworkInterfaceTL"
            },
            "apply" : {
                "attemptsToBecomeSecondary" : NumberLong(19),
                "batchSize" : NumberLong(318318346),
                "batches" : {
                    "num" : 278600198,
                    "totalMillis" : 5795319
                },
                "ops" : NumberLong(318318943)
            },
            "buffer" : {
                "count" : NumberLong(0),
                "maxSizeBytes" : NumberLong(268435456),
                "sizeBytes" : NumberLong(0)
            },
            "initialSync" : {
                "completed" : NumberLong(0),
                "failedAttempts" : NumberLong(0),
                "failures" : NumberLong(0)
            },
            "network" : {
                "bytes" : NumberLong("57955381887"),
                "getmores" : {
                    "num" : 364468339,
                    "totalMillis" : 15110995960,
                    "numEmptyBatches" : NumberLong(67943454)
                },
                "notPrimaryLegacyUnacknowledgedWrites" : NumberLong(0),
                "notPrimaryUnacknowledgedWrites" : NumberLong(0),
                "oplogGetMoresProcessed" : {
                    "num" : 465344548,
                    "totalMillis" : 200161
                },
                "ops" : NumberLong(318318349),
                "readersCreated" : NumberLong(5),
                "replSetUpdatePosition" : {
                    "num" : NumberLong(455260555)
                }
            },
            "stateTransition" : {
                "lastStateTransition" : "stepUp",
                "userOperationsKilled" : NumberLong(0),
                "userOperationsRunning" : NumberLong(5)
            },
            "syncSource" : {
                "numSelections" : NumberLong(28),
                "numTimesChoseDifferent" : NumberLong(3),
                "numTimesChoseSame" : NumberLong(0),
                "numTimesCouldNotFind" : NumberLong(25)
            }
        },
        "ttl" : {
            "deletedDocuments" : NumberLong(9),
            "passes" : NumberLong(312121)
        }
    },
    "ok" : 1,
    "$clusterTime" : {
        "clusterTime" : Timestamp(1679967033, 3),
        "signature" : {
            "hash" : BinData(0,"7p9I6mnYmAqWdGWHZuVRCfEIJtU="),
            "keyId" : NumberLong("7173500260914823169")
        }
    },
    "operationTime" : Timestamp(1679967033, 3)
}