【测试类型：功能测试】【测试版本：5.1.1】【需求名称：资源池化】debug版本 kill 备机1进程备机2偶现core

【标题描述】:
【测试类型：SQL功能/存储功能/接口功能/工具功能/性能/并发/压力长稳/故障注入/安全/资料/编码规范】【测试版本：x.x.x】 问题描述

【操作系统和硬件信息】(查询命令: cat /etc/system-release, uname -a):openEuler release Linux host59 4.19.90-2003.4.0.0036.oe1.x86_64 #1 SMP Mon Mar 23 19:10:41 UTC 2020 x86_64 x86_64 x86_64 GNU/Linux20.03 (LTS

【测试环境】(单机/1主x备x级联备):一主两备

【被测功能】:资源池化

【测试类型】: 故障注入

【数据库版本】(查询命令: gaussdb -V):gaussdb (openGauss 5.1.1 build cc4bfd82) compiled at 2023-12-07 01:08:58 commit 0 last mr debug

【预置条件】:安装资源池化环境

【操作步骤】(请填写详细的操作步骤):
1. tpcc主机读写，两台备机读
2. 不断kill 备机1 数据库进程

【预期输出】:集群正常

【实际输出】: 备机2生成core

【原因分析】:
1. 这个问题的根因
2. 问题推断过程
3. 还有哪些原因可能造成类似现象
4. 该问题是否有临时规避措施
5. 问题解决方案
6. 预计修复问题时间

【日志信息】(请附上日志文件、截图、coredump信息):
#0  BBOX_CreateCoredump (file_name=0x7f416c0c4c70 "/data1/dst/omm/corefile//core-gaussdb-373914-2024_01_09_02_33_53-bbox.lz4") at bbox_create.cpp:404
#1  0x0000000001552e37 in bbox_handler (sig=6, si=0x7f416c0c52f0, uc=0x7f416c0c51c0) at gs_bbox.cpp:112
#2  <signal handler called>
#3  0x00007f4f37d276eb in raise () from /lib64/libc.so.6
#4  0x00007f4f37d28a11 in abort () from /lib64/libc.so.6
#5  0x00000000011fc3d5 in ExceptionalCondition (conditionName=0x78b8c19 "!(ref != __null)", errorType=0x78b6fe7 "FailedAssertion", fileName=0x78b731c "bufmgr.cpp", lineNumber=3503)
    at assert.cpp:46
#6  0x00000000023154ef in UnpinBuffer (buf=0x7f4464a021b0, fixOwner=true) at bufmgr.cpp:3503
#7  0x000000000231cfe2 in ReleaseBuffer (buffer=2902752) at bufmgr.cpp:5623
#8  0x0000000001f4d4cd in btendscan_internal (scan=0x7f416c7b6860) at nbtree.cpp:593
#9  0x0000000001f4b084 in btendscan (fcinfo=0x7f416c0c5b00) at nbtree.cpp:579
#10 0x00000000012212ec in FunctionCall1Coll (flinfo=0x7f416c500ba8, collation=0, arg1=139918969628768) at fmgr.cpp:1537
#11 0x0000000001f2d035 in index_endscan (scan=0x7f416c7b6860) at indexam.cpp:402
#12 0x000000000212c8a2 in scan_handler_idx_endscan (scan=0x7f416c7b6860) at hbindex_am.cpp:595
#13 0x0000000001bb7601 in ExecEndIndexScan (node=0x7f416c650060) at nodeIndexscan.cpp:467
#14 0x0000000001b3444e in ExecEndNodeByType (node=0x7f416c650060) at execProcnode.cpp:1144
#15 0x0000000001b3493d in ExecEndNode (node=0x7f416c650060) at execProcnode.cpp:1400
#16 0x0000000001bbe30b in ExecEndLimit (node=0x7f416dbf4060) at nodeLimit.cpp:427
#17 0x0000000001b34619 in ExecEndNodeByType (node=0x7f416dbf4060) at execProcnode.cpp:1258
#18 0x0000000001b3493d in ExecEndNode (node=0x7f416dbf4060) at execProcnode.cpp:1400
#19 0x0000000001b2b46d in ExecEndPlan (planstate=0x7f416c676060, estate=0x7f416dbea060) at execMain.cpp:2048
#20 0x0000000001b28588 in standard_ExecutorEnd (queryDesc=0x7f416c365288) at execMain.cpp:821
#21 0x0000000001a8d082 in pgaudit_ExecutorEnd (queryDesc=0x7f416c365288) at auditfuncs.cpp:1934
#22 0x0000000001e89771 in ledger_ExecutorEnd (query_desc=0x7f416c365288) at blockchain.cpp:248
#23 0x0000000001ae9f06 in hypo_executorEnd_hook (queryDesc=0x7f416c365288) at hypopg_index.cpp:211
#24 0x0000000001b28400 in ExecutorEnd (queryDesc=0x7f416c365288) at execMain.cpp:768
#25 0x00000000017dae23 in PortalCleanup (portal=0x7f416dbdc060) at portalcmds.cpp:291
#26 0x00000000012b353e in AtAbort_Portals (STP_rollback=false) at portalmem.cpp:885
#27 0x00000000020212ac in AbortTransaction (PerfectRollback=false, STP_rollback=false) at xact.cpp:3920
#28 0x0000000002025694 in AbortOutOfAnyTransaction (reserve_topxact_abort=false) at xact.cpp:6073
#29 0x000000000123714f in ShutdownPostgres (code=1, arg=0) at postinit.cpp:970
#30 0x00000000023d9bfe in shmem_exit (code=1) at ipc.cpp:494
#31 0x00000000023d9473 in proc_exit_prepare (code=1) at ipc.cpp:366
#32 0x00000000023d913b in proc_exit (code=1) at ipc.cpp:274
#33 0x00000000011fdd22 in errfinish (dummy=0) at elog.cpp:779
#34 0x0000000001a5a295 in ProcessInterrupts () at postgres.cpp:6582
#35 0x0000000001f52c2a in _bt_walk_left (rel=0x7f416dd4fb08, buf=2902752) at nbtsearch.cpp:1466
#36 0x0000000001f5289d in _bt_steppage (scan=0x7f416c7b6860, dir=BackwardScanDirection) at nbtsearch.cpp:1401
#37 0x0000000001f514df in _bt_next (scan=0x7f416c7b6860, dir=BackwardScanDirection) at nbtsearch.cpp:1115
#38 0x0000000001f54142 in _bt_gettuple_internal (scan=0x7f416c7b6860, dir=BackwardScanDirection) at nbtsearch.cpp:1765
#39 0x0000000001f4ad40 in btgettuple (fcinfo=0x7f416c0c66b0) at nbtree.cpp:310
#40 0x00000000012214e8 in FunctionCall2Coll (flinfo=0x7f416c5009b0, collation=0, arg1=139918969628768, arg2=4294967295) at fmgr.cpp:1563
#41 0x0000000001f2d73e in index_getnext_tid (scan=0x7f416c7b6860, direction=BackwardScanDirection) at indexam.cpp:507
#42 0x0000000001f2e0cd in index_getnext (scan=0x7f416c7b6860, direction=BackwardScanDirection, has_cur_xact_write=0x7f416dbea1f0) at indexam.cpp:750
#43 0x000000000212cb4d in scan_handler_idx_getnext (scan=0x7f416c7b6860, direction=BackwardScanDirection, expect_partoid=0, expect_bktid=-1, has_cur_xact_write=0x7f416dbea1f0)
    at hbindex_am.cpp:644
#44 0x0000000001bb6c60 in IndexNext (node=0x7f416c650060) at nodeIndexscan.cpp:100
#45 0x0000000001b5cf7f in ExecScanFetch (node=0x7f416c650060, access_mtd=0x1bb6af0 <IndexNext(IndexScanState*)>, recheck_mtd=0x1bb6d53 <IndexRecheck(IndexScanState*, TupleTableSlot*)>)
    at execScan.cpp:83
#46 0x0000000001b5d10e in ExecScan (node=0x7f416c650060, access_mtd=0x1bb6af0 <IndexNext(IndexScanState*)>, recheck_mtd=0x1bb6d53 <IndexRecheck(IndexScanState*, TupleTableSlot*)>)
    at execScan.cpp:172
#47 0x0000000001bb6e80 in ExecIndexScan (state=0x7f416c650060) at nodeIndexscan.cpp:186
#48 0x0000000001b32a5b in ExecProcNodeFirst (node=0x7f416c650060) at execProcnode.cpp:764
#49 0x0000000001bbd74f in ExecProcNode (node=0x7f416c650060) at ../../../../src/include/executor/executor.h:279
#50 0x0000000001bbd8e5 in ExecLimit (state=0x7f416dbf4060) at nodeLimit.cpp:91
#51 0x0000000001b32a5b in ExecProcNodeFirst (node=0x7f416dbf4060) at execProcnode.cpp:764
#52 0x0000000001bf8cf2 in ExecProcNode (node=0x7f416dbf4060) at ../../../../src/include/executor/executor.h:279
#53 0x0000000001bfbb98 in ExecSetParamPlan (node=0x7f416c652fd0, econtext=0x7f416c652188) at nodeSubplan.cpp:1003
--Type <RET> for more, q to quit, c to continue without paging--
#54 0x0000000001b38005 in ExecEvalParamExec (exprstate=0x7f416c652890, econtext=0x7f416c652188, isNull=0x7f416c652bd8, isDone=0x7f416c652f88) at execQual.cpp:1374
#55 0x0000000001b34ab1 in ExecEvalExpr (state=0x7f416c652890, econtext=0x7f416c652188, isNull=0x7f416c652bd8, isDone=0x7f416c652f88) at ../../../../src/include/executor/executor.h:366
#56 0x0000000001b468e0 in ExecTargetList (targetlist=0x7f416c652f20, econtext=0x7f416c652188, values=0x7f416c652b90, isnull=0x7f416c652bd8, itemIsDone=0x7f416c652f88, isDone=0x7f416c0c6f44)
    at execQual.cpp:6900
#57 0x0000000001b4769c in ExecProjectByRecursion (projInfo=0x7f416c652c68, isDone=0x7f416c0c6f44) at execQual.cpp:7152
#58 0x0000000001b47199 in ExecProject (projInfo=0x7f416c652c68, isDone=0x7f416c0c6f44) at execQual.cpp:7056
#59 0x0000000001be25fd in ExecResult (state=0x7f416c652060) at nodeResult.cpp:191
#60 0x0000000001b32a5b in ExecProcNodeFirst (node=0x7f416c652060) at execProcnode.cpp:764
#61 0x0000000001bf8cf2 in ExecProcNode (node=0x7f416c652060) at ../../../../src/include/executor/executor.h:279
#62 0x0000000001bfbb98 in ExecSetParamPlan (node=0x7f416d1ff500, econtext=0x7f416d1fe7f8) at nodeSubplan.cpp:1003
#63 0x0000000001b38005 in ExecEvalParamExec (exprstate=0x7f416d1fe660, econtext=0x7f416d1fe7f8, isNull=0x7f416c0c714b, isDone=0x0) at execQual.cpp:1374
#64 0x0000000001bb6aee in ExecEvalExpr (state=0x7f416d1fe660, econtext=0x7f416d1fe7f8, isNull=0x7f416c0c714b, isDone=0x0) at ../../../../src/include/executor/executor.h:366
#65 0x0000000001bb712f in ExecIndexEvalRuntimeKeys (econtext=0x7f416d1fe7f8, run_time_keys=0x7f416d1fe2e8, num_run_time_keys=3) at nodeIndexscan.cpp:300
#66 0x0000000001bb6f0e in ExecReScanIndexScan (node=0x7f416c676060) at nodeIndexscan.cpp:221
#67 0x0000000001b22ed9 in ExecReScanByType (node=0x7f416c676060) at execAmi.cpp:174
#68 0x0000000001b23324 in ExecReScan (node=0x7f416c676060) at execAmi.cpp:375
#69 0x0000000001bb6e6a in ExecIndexScan (state=0x7f416c676060) at nodeIndexscan.cpp:182
#70 0x0000000001b32a5b in ExecProcNodeFirst (node=0x7f416c676060) at execProcnode.cpp:764
#71 0x0000000001b26c31 in ExecProcNode (node=0x7f416c676060) at ../../../../src/include/executor/executor.h:279
#72 0x0000000001b2bb5a in ExecutePlan (estate=0x7f416dbea060, planstate=0x7f416c676060, operation=CMD_SELECT, sendTuples=true, numberTuples=0, direction=ForwardScanDirection,
    dest=0x7f416d1e4b58, motJitContext=0x0) at execMain.cpp:2251
#73 0x0000000001b2806b in standard_ExecutorRun (queryDesc=0x7f416c365288, direction=ForwardScanDirection, count=0) at execMain.cpp:653
#74 0x000000000190054b in explain_ExecutorRun (queryDesc=0x7f416c365288, direction=ForwardScanDirection, count=0) at auto_explain.cpp:122
#75 0x0000000001b27ade in ExecutorRun (queryDesc=0x7f416c365288, direction=ForwardScanDirection, count=0) at execMain.cpp:503
#76 0x0000000001a6fc88 in PortalRunSelect (portal=0x7f416dbdc060, forward=true, count=0, dest=0x7f416d1e4b58) at pquery.cpp:1425
#77 0x0000000001a6ed94 in PortalRun (portal=0x7f416dbdc060, count=9223372036854775807, isTopLevel=true, dest=0x7f416d1e4b58, altdest=0x7f416d1e4b58, completionTag=0x7f416c0c7850 "")
    at pquery.cpp:1159
#78 0x0000000001a5772d in exec_execute_message (portal_name=0x7f416d1e4060 "", max_rows=9223372036854775807) at postgres.cpp:5354
#79 0x0000000001a62ad4 in PostgresMain (argc=1, argv=0x7f416c2e7650, dbname=0x7f416c2e61f8 "tpcc_lm", username=0x7f416c2e61b0 "lmm") at postgres.cpp:9629
#80 0x000000000199804b in BackendRun (port=0x7f416c0c9170) at postmaster.cpp:9447
#81 0x00000000019a98dd in GaussDbThreadMain<(knl_thread_role)1> (arg=0x7f4393e5a7d8) at postmaster.cpp:13976
#82 0x00000000019a4eea in InternalThreadFunc (args=0x7f4393e5a7d8) at postmaster.cpp:14607
#83 0x0000000002617785 in ThreadStarterFunc (arg=0x7f4393e5a7c8) at gs_thread.cpp:380
#84 0x00007f4f37eb7fed in ?? () from /lib64/libpthread.so.0
#85 0x00007f4f37deb18f in clone () from /lib64/libc.so.6
![输入图片说明](https://foruda.gitee.com/images/1704785551023859438/3b4de14f_10921273.png "屏幕截图")
【测试代码】:

openGauss/openGauss-server

内容风险标识

评论 (4)

openGauss/openGauss-server .gitee-modal { width: 500px !important; }

内容风险标识