bingfeng2004 opened a new issue #4967:
URL: https://github.com/apache/incubator-doris/issues/4967
Hi,I have three be node,but it have been too many outages recently in three
days.Please help me to analyze the reason.
**1.be.out:**
start time: 2020年 11月 20日 星期五 15:49:53 CST
*** Aborted at 1606117421 (unix time) try "date -d @1606117421" if you are
using GNU date ***
PC: @ 0x7f43239e06e6 __memcpy_ssse3_back
*** SIGSEGV (@0x0) received by PID 17175 (TID 0x7f42d8b6c700) from PID 0;
stack trace: ***
@ 0x7f43238c1280 (unknown)
@ 0x7f43239e06e6 __memcpy_ssse3_back
@ 0x108ab08 doris::Tuple::materialize_exprs<>()
@ 0x14b56a1 doris::TopNNode::insert_tuple_row()
@ 0x14b71f7 doris::TopNNode::open()
@ 0x10727b3 doris::PlanFragmentExecutor::open_internal()
@ 0x1072fac doris::PlanFragmentExecutor::open()
@ 0xff6c5b doris::FragmentExecState::execute()
@ 0xff8ee6 doris::FragmentMgr::exec_actual()
@ 0xffe34c std::_Function_handler<>::_M_invoke()
@ 0x117ced2 doris::ThreadPool::dispatch_thread()
@ 0x118f5e8 doris::Thread::supervise_thread()
@ 0x7f4323676dd5 start_thread
@ 0x7f4323988ead __clone
start time: 2020年 11月 23日 星期一 17:05:09 CST
start time: 2020年 11月 24日 星期二 12:42:47 CST
tcmalloc: large alloc 18014398509481984 bytes == (nil) @ 0x25b0d53
0x271b74b 0x271ba9a 0x10c268b 0x1060ae4 0xfe487b 0xfe6525 0x108ab08 0x14b56a1
0x14b71f7 0x10727b3 0x1072fac 0xff6c5b 0xff8ee6 0xffe34c 0x117ced2 0x118f5e8
0x7f2fd85f2dd5
*** Aborted at 1606198096 (unix time) try "date -d @1606198096" if you are
using GNU date ***
PC: @ 0x7f2fd895c6e6 __memcpy_ssse3_back
*** SIGSEGV (@0x0) received by PID 8016 (TID 0x7f2f8e16d700) from PID 0;
stack trace: ***
@ 0x7f2fd883d280 (unknown)
@ 0x7f2fd895c6e6 __memcpy_ssse3_back
@ 0x108ab08 doris::Tuple::materialize_exprs<>()
@ 0x14b56a1 doris::TopNNode::insert_tuple_row()
@ 0x14b71f7 doris::TopNNode::open()
@ 0x10727b3 doris::PlanFragmentExecutor::open_internal()
@ 0x1072fac doris::PlanFragmentExecutor::open()
**2.be.warnning**
E1126 11:39:17.004621 11395 cgroups_mgr.cpp:350] Could not find a valid
cgroups path for resource isolation,current value is
W1126 11:39:17.038318 11659 utils.cpp:101] fail to get master client from
cache. host=, port=0, code=7
W1126 11:39:17.043932 11659 task_worker_pool.cpp:1059] finish report task
failed. status:-1, master host:port:0
W1126 11:50:13.609467 11597 fragment_mgr.cpp:353] Retrying ReportExecStatus:
write() send(): Broken pipe
W1126 11:50:13.665206 11597 fragment_mgr.cpp:220] Got error while opening
fragment 7edb9a8245bf474b-b6eb5625e6b7c37f: Cancelled: Cancelled
W1126 12:38:37.382897 11597 fragment_mgr.cpp:353] Retrying ReportExecStatus:
write() send(): Broken pipe
W1126 12:38:37.386775 11597 fragment_mgr.cpp:220] Got error while opening
fragment 51537a88f7614c2a-a256ba81ab16c911: Cancelled: Cancelled
W1126 15:25:32.288538 11595 thrift_rpc_helper.cpp:72] retrying call frontend
service after 1000 ms, address=TNetworkAddress(hostname=192.168.1.92,
port=19020), reason=No more data to read.
W1126 20:12:27.589342 11597 thrift_rpc_helper.cpp:72] retrying call frontend
service after 1000 ms, address=TNetworkAddress(hostname=192.168.1.92,
port=19020), reason=No more data to read.
W1126 20:13:23.924654 11597 thrift_rpc_helper.cpp:72] retrying call frontend
service after 1000 ms, address=TNetworkAddress(hostname=192.168.1.92,
port=19020), reason=No more data to read.
W1126 20:18:25.652693 11596 thrift_rpc_helper.cpp:72] retrying call frontend
service after 1000 ms, address=TNetworkAddress(hostname=192.168.1.92,
port=19020), reason=No more data to read.
W1126 20:26:04.607511 11597 thrift_rpc_helper.cpp:72] retrying call frontend
service after 1000 ms, address=TNetworkAddress(hostname=192.168.1.92,
port=19020), reason=No more data to read.
W1126 20:36:45.105013 11595 thrift_rpc_helper.cpp:72] retrying call frontend
service after 1000 ms, address=TNetworkAddress(hostname=192.168.1.92,
port=19020), reason=No more data to read.
E1126 20:36:49.262317 11595 system_allocator.cpp:59] fail to allocate mem
via posix_memalign, res=12, errmsg=**_Cannot allocate memory_**
**_Cannot allocate memory_** is the root cause?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@doris.apache.org
For additional commands, e-mail: commits-h...@doris.apache.org
