Be节点异常挂掉以前输出大量日志

💬 StarRocks 用户问答 日常运维
#1

【详述】
【背景】做过哪些操作？
【业务影响】
【StarRocks版本】2.2.5
【集群规模】3fe（1 follower+2observer）+ 3be（fe与be混部）
【机器信息】4C/16G
【附件】

挂掉前出现大量类似日志
I1214 15:01:04.320932 104184 plan_fragment_executor.cpp:69] Prepare(): query_id=13182000-7b7d-11ed-8e46-525400ec31ae fragment_instance_id=13182000-7b7d-11ed-8e46-525400ec31c4 backend_num=83

I1214 15:01:04.368798 104052 plan_fragment_executor.cpp:450] Fragment 13182000-7b7d-11ed-8e46-525400ec3204:(Active: 11.284ms, non-child: 1.48%)

  • AverageThreadTokens: 0.00
  • MemoryLimit: 2.00 GB
  • PeakMemoryUsage: 2.03 MB
  • RowsProduced: 41.23K
    DataStreamSender (dst_id=149, dst_fragments=[131820007b7d11ed-8e46525400ec3207]):(Active: 5.388ms, non-child: 47.75%)
    • PartType: UNPARTITIONED
    • BytesSent: 170.52 KB
    • CompressTime: 1.344ms
    • IgnoreRows: 0
    • OverallThroughput: 30.90 MB/sec
    • SendRequestTime: 154.789us
    • SerializeChunkTime: 122.103us
    • ShuffleDispatchTime: 0.000ns
    • ShuffleHashTime: 0.000ns
    • UncompressedBytes: 362.66 KB
    • WaitResponseTime: 3.683ms
      OLAP_SCAN_NODE (id=148):(Active: 5.729ms, non-child: 0.00%)
    • Table: table1
    • Rollup: table1
    • BytesRead: 362.35 KB
    • IOTaskCount : 12
    • NumDiskAccess: 0
    • PeakMemoryUsage: 0
    • RowsRead: 41.23K
    • RowsReturned: 41.23K
    • RowsReturnedRate: 7.20 M/sec
    • ScanConcurrency : 12
    • ScanTime: 50.737ms
    • ScannerThreadsInvoluntaryContextSwitches: 0
    • ScannerThreadsTotalWallClockTime: 0.000ns
      • MaterializeTupleTime(*): 0.000ns
      • ScannerThreadsSysTime: 0.000ns
      • ScannerThreadsUserTime: 0.000ns
    • ScannerThreadsVoluntaryContextSwitches: 0
    • TabletCount : 12
    • TotalRawReadTime(*): 0.000ns
    • TotalReadThroughput: 0.00 /sec
      SCAN:(Active: 50.694ms, non-child: 100.00%)
      • CachedPagesNum: 0
      • CompressedBytesRead: 127.42 KB
      • CreateSegmentIter: 82.087us
      • IOTime: 45.599ms
      • PushdownPredicates: 0
      • RawRowsRead: 41.23K
      • ReadPagesNum: 14
      • SegmentInit: 4.443ms
        • BitmapIndexFilter: 0.000ns
        • BitmapIndexFilterRows: 0
        • BloomFilterFilterRows: 0
        • SegmentZoneMapFilterRows: 0
        • ShortKeyFilterRows: 0
        • ZoneMapIndexFilterRows: 0
      • SegmentRead: 46.224ms
        • BlockFetch: 139.573us
        • BlockFetchCount: 20
        • BlockSeek: 46.049ms
        • BlockSeekCount: 20
        • ChunkCopy: 0.000ns
        • DecompressT: 0.000ns
        • DelVecFilterRows: 0
        • IndexLoad: 0.000ns
        • PredFilter: 0.000ns
        • PredFilterRows: 0
        • RowsetsReadCount: 24
        • SegmentsReadCount: 12
        • TotalColumnsDataPageCount: 14
      • UncompressedBytesRead: 127.00 KB
#2

麻烦您发下crash后那个时间段的be.out堆栈日志

#3

terminate called after throwing an instance of ‘std::bad_alloc’
what(): std::bad_alloc
*** Aborted at 1671001369 (unix time) try “date -d @1671001369” if you are using GNU date ***
PC: @ 0x7f6221de9387 __GI_raise
*** SIGABRT (@0x3e8000195a2) received by PID 103842 (TID 0x7f61954cf700) from PID 103842; stack trace: ***
@ 0x3cb75d2 google::(anonymous namespace)::FailureSignalHandler()
@ 0x7f622289e630 (unknown)
@ 0x7f6221de9387 __GI_raise
@ 0x7f6221deaa78 __GI_abort
@ 0x17ba04d _ZN9__gnu_cxx27__verbose_terminate_handlerEv.cold
@ 0x5675086 __cxxabiv1::__terminate()
@ 0x5719379 __cxa_call_terminate
@ 0x5674aa1 __gxx_personality_v0
@ 0x571ffce _Unwind_RaiseException_Phase2
@ 0x5720ac6 _Unwind_Resume
@ 0x16d18d2 _ZN4brpc6policy17ProcessRpcRequestEPNS_16InputMessageBaseE.cold
@ 0x3ddfd97 brpc::ProcessInputMessage()
@ 0x3de0c43 brpc::InputMessenger::OnNewMessages()
@ 0x3e8790e brpc::Socket::ProcessEvent()
@ 0x3d9589f bthread::TaskGroup::task_runner()
@ 0x3f1e081 bthread_make_fcontext

京ICP备2022026421号-1