Details
-
Bug
-
Resolution: Fixed
-
Critical
-
7.1.0
-
7.1.0-2071
-
Untriaged
-
Centos 64-bit
-
-
1
-
Unknown
-
KV 2022-Jan
Description
Steps to repro:
- Create a 2 node cluster(172.23.122.245, 172.23.122.246(bucket_ram_quota = 2056 MB/node), replicas=0)
- Create 100 non default collections in default scope(collection count is 101(including default collection)
- Start Loading 500k docs in each of 100 non default collections
- Drop 2 collections , recreate collections
- Change replicas to 1, Trigger rebalance
#Pause rebalance and add a node and resume rebalance - Observed Memcached aborted in NexusKVStore::getAllKeys(Vbid, DiskDocKey const&, unsigned int, std::shared_ptr<StatusCallback<DiskDocKey const&> >) const ()
Below Core found on node : 172.23.122.246
BackTrace:
(gdb) bt full
|
#0 0x00007f7c55377337 in raise () from /lib64/libc.so.6
|
No symbol table info available.
|
#1 0x00007f7c55378a28 in abort () from /lib64/libc.so.6
|
No symbol table info available.
|
#2 0x00000000006d5a32 in cb::handleError(spdlog::logger&, spdlog::level::level_enum, std::basic_string_view<char, std::char_traits<char> >, cb::ErrorHandlingMethod) () at /home/couchbase/jenkins/workspace/couchbase-server-unix/kv_engine/engines/ep/src/error_handler.cc:43
|
No locals.
|
#3 0x00000000008f1418 in handleError (msg=..., this=0x7f7c4025c780)
|
at /home/couchbase/jenkins/workspace/couchbase-server-unix/kv_engine/engines/ep/src/kvstore/nexus-kvstore/nexus-kvstore-config.h:39
|
No locals.
|
#4 NexusKVStore::getAllKeys(Vbid, DiskDocKey const&, unsigned int, std::shared_ptr<StatusCallback<DiskDocKey const&> >) const ()
|
at /home/couchbase/jenkins/workspace/couchbase-server-unix/kv_engine/engines/ep/src/kvstore/nexus-kvstore/nexus-kvstore.cc:1863
|
ss = <incomplete type>
|
msg = {static npos = 18446744073709551615,
|
_M_dataplus = {<std::allocator<char>> = {<__gnu_cxx::new_allocator<char>> = {<No data fields>}, <No data fields>},
|
_M_p = 0x7f7b8f28e1a0 <Address 0x7f7b8f28e1a0 out of bounds>}, _M_string_length = 199, {
|
_M_local_buf = "\307\000\000\000\000\000\000\000@\000\000\000\000\000\000", _M_allocated_capacity = 199}}
|
lh = {_M_device = 0x7f7c4028f600, _M_owns = true}
|
primaryCallback = {<std::__shared_ptr<NexusKVStorePrimaryGetAllKeysCallback, (__gnu_cxx::_Lock_policy)2>> = {<std::__shared_ptr_access<NexusKVStorePrimaryGetAllKeysCallback, (__gnu_cxx::_Lock_policy)2, false, false>> = {<No data fields>}, _M_ptr = <optimized out>, _M_refcount = {
|
_M_pi = 0x7f7b45355400}}, <No data fields>}
|
secondaryCallback = {<std::__shared_ptr<NexusKVStoreSecondaryGetAllKeysCallback, (__gnu_cxx::_Lock_policy)2>> = {<std::__shared_ptr_access<NexusKVStoreSecondaryGetAllKeysCallback, (__gnu_cxx::_Lock_policy)2, false, false>> = {<No data fields>}, _M_ptr = <optimized out>, _M_refcount = {
|
_M_pi = 0x7f7b8da26ec0}}, <No data fields>}
|
primaryResult = cb::success
|
secondaryResult = cb::success
|
#5 0x00000000006dc483 in FetchAllKeysTask::run() () at /opt/gcc-10.2.0/include/c++/10.2.0/ext/atomicity.h:100
|
phosphor_internal_category_enabled_84 = {_M_b = {_M_p = 0x0}, static is_always_lock_free = <optimized out>}
|
phosphor_internal_category_enabled_temp_84 = <optimized out>
|
phosphor_internal_tpi_84 = {category = 0x0, name = 0x0, type = phosphor::AsyncStart, argument_names = {_M_elems = {0x0, 0x0}},
|
argument_types = {_M_elems = {phosphor::is_bool, phosphor::is_bool}}}
|
phosphor_internal_guard_84 = {tpi = 0x10663c0 <FetchAllKeysTask::run()::phosphor_internal_tpi_84>, enabled = true, arg1 = {<No data fields>},
|
arg2 = {<No data fields>}, start = {__d = {__r = 7952034234048951}}}
|
err = <optimized out>
|
#6 0x0000000000aa6642 in GlobalTask::execute() () at /home/couchbase/jenkins/workspace/couchbase-server-unix/kv_engine/executor/globaltask.cc:68
|
guard = {previous = 0x0}
|
#7 0x0000000000aa3855 in FollyExecutorPool::TaskProxy::scheduleViaCPUPool()::{lambda()#2}::operator()() const (__closure=0x7f7c3a7c8840)
|
at /home/couchbase/jenkins/workspace/couchbase-server-unix/kv_engine/executor/folly_executorpool.cc:189
|
scheduleOverhead = <optimized out>
|
---Type <return> to continue, or q <return> to quit---
|
start = {__d = {__r = 7952034234044627}}
|
runAgain = false
|
proxy = @0x7f7c4802ce60: <error reading variable>
|
#8 0x0000000000bfa640 in operator() (this=0x7f7c3a7c8840)
|
at /home/couchbase/jenkins/workspace/cbdeps-platform-build-old/deps/packages/build/folly/folly-prefix/src/folly/folly/Function.h:416
|
fn = @0x7f7c3a7c8840: {<folly::detail::function::FunctionTraits<void()>> = {<No data fields>}, data_ = {big = 0x7f7c4802ce60, tiny = {
|
__data = "`\316\002H|\177\000\000\000\000\000\000\000\000\000\000\360\067\033T|\177\000\000\305\312\000\000\000\000\000\000\340\000\000\000\000\000\000\000\020\211|:|\177\000", __align = {<No data fields>}}},
|
call_ = 0xaa3f10 <folly::detail::function::FunctionTraits<void ()>::callSmall<FollyExecutorPool::TaskProxy::scheduleViaCPUPool()::{lambda()#2}>(folly::detail::function::Data&)>,
|
exec_ = 0xaa2660 <folly::detail::function::execSmall<FollyExecutorPool::TaskProxy::scheduleViaCPUPool()::{lambda()#2}>(folly::detail::function::Op, folly::detail::function::Data*, folly::detail::function::Data)>}
|
#9 folly::ThreadPoolExecutor::runTask(std::shared_ptr<folly::ThreadPoolExecutor::Thread> const&, folly::ThreadPoolExecutor::Task&&) (
|
this=this@entry=0x7f7c53d2a800, thread=...,
|
task=task@entry=<unknown type in /usr/lib/debug/opt/couchbase/bin/memcached-7.1.0-2071.x86_64.debug, CU 0xa37b575, DIE 0xa3ff4aa>)
|
at /home/couchbase/jenkins/workspace/cbdeps-platform-build-old/deps/packages/build/folly/folly-prefix/src/folly/folly/executors/ThreadPoolExecutor.cpp:97
|
rctx = {
|
prev_ = {<std::__shared_ptr<folly::RequestContext, (__gnu_cxx::_Lock_policy)2>> = {<std::__shared_ptr_access<folly::RequestContext, (__gnu_cxx::_Lock_policy)2, false, false>> = {<No data fields>}, _M_ptr = 0x0, _M_refcount = {_M_pi = 0x0}}, <No data fields>}}
|
startTime = {__d = {__r = 7952034234039690}}
|
stats = {expired = false, waitTime = {__r = 89136}, runTime = {__r = 0}, enqueueTime = {__d = {__r = 7952034233950554}}, requestId = 0}
|
#10 0x0000000000be23fa in folly::CPUThreadPoolExecutor::threadRun (this=0x7f7c53d2a800, thread=...)
|
at /home/couchbase/jenkins/workspace/cbdeps-platform-build-old/deps/packages/build/folly/folly-prefix/src/folly/folly/executors/CPUThreadPoolExecutor.cpp:265
|
task = {storage_ = {{emptyState = 96 '`', value = {<folly::ThreadPoolExecutor::Task> = {
|
func_ = {<folly::detail::function::FunctionTraits<void()>> = {<No data fields>}, data_ = {big = 0x7f7c4802ce60, tiny = {
|
__data = "`\316\002H|\177\000\000\000\000\000\000\000\000\000\000\360\067\033T|\177\000\000\305\312\000\000\000\000\000\000\340\000\000\000\000\000\000\000\020\211|:|\177\000", __align = {<No data fields>}}},
|
call_ = 0xaa3f10 <folly::detail::function::FunctionTraits<void ()>::callSmall<FollyExecutorPool::TaskProxy::scheduleViaCPUPool()::{lambda()#2}>(folly::detail::function::Data&)>,
|
exec_ = 0xaa2660 <folly::detail::function::execSmall<FollyExecutorPool::TaskProxy::scheduleViaCPUPool()::{lambda()#2}>(folly::detail::function::Op, folly::detail::function::Data*, folly::detail::function::Data)>}, enqueueTime_ = {__d = {__r = 7952034233950554}}, expiration_ = {
|
__r = 0}, expireCallback_ = {<folly::detail::function::FunctionTraits<void()>> = {<No data fields>}, data_ = {big = 0xcac5,
|
tiny = {
|
__data = "\305\312\000\000\000\000\000\000\353\060\243", '\000' <repeats 13 times>, "_\376\362W|\177\000\000p\352~K|\177\000\000@\226\023X|\177\000", __align = {<No data fields>}}}, call_ = 0x465dd3
|
<folly::detail::function::FunctionTraits<void ()>::uninitCall(folly::detail::function::Data&)>, exec_ = 0x0},
|
context_ = {<std::__shared_ptr<folly::RequestContext, (__gnu_cxx::_Lock_policy)2>> = {<std::__shared_ptr_access<folly::RequestContext---Type <return> to continue, or q <return> to quit---
|
, (__gnu_cxx::_Lock_policy)2, false, false>> = {<No data fields>}, _M_ptr = 0x0, _M_refcount = {_M_pi = 0x0}}, <No data fields>}}, poison = false,
|
priority_ = 0 '\000', queueObserverPayload_ = 0}}, hasValue = true}}
|
guard = {list_ = {forbid = true, prev = 0x0, curr = {name = {static npos = <optimized out>, b_ = 0xccc3eb "CPUThreadPoolExecutor",
|
e_ = 0xccc400 ""}}}}
|
#11 0x0000000000bfd5f9 in __invoke_impl<void, void (folly::ThreadPoolExecutor::*&)(std::shared_ptr<folly::ThreadPoolExecutor::Thread>), folly::ThreadPoolExecutor*&, std::shared_ptr<folly::ThreadPoolExecutor::Thread>&> (__t=<optimized out>, __f=<optimized out>)
|
at /usr/local/include/c++/7.3.0/bits/invoke.h:73
|
No locals.
|
#12 __invoke<void (folly::ThreadPoolExecutor::*&)(std::shared_ptr<folly::ThreadPoolExecutor::Thread>), folly::ThreadPoolExecutor*&, std::shared_ptr<folly::ThreadPoolExecutor::Thread>&> (__fn=<optimized out>) at /usr/local/include/c++/7.3.0/bits/invoke.h:95
|
No locals.
|
#13 __call<void, 0, 1> (__args=<optimized out>, this=<optimized out>) at /usr/local/include/c++/7.3.0/functional:467
|
No locals.
|
#14 operator()<> (this=<optimized out>) at /usr/local/include/c++/7.3.0/functional:551
|
No locals.
|
#15 folly::detail::function::FunctionTraits<void ()>::callBig<std::_Bind<void (folly::ThreadPoolExecutor::*(folly::ThreadPoolExecutor*, std::shared_ptr<folly::ThreadPoolExecutor::Thread>))(std::shared_ptr<folly::ThreadPoolExecutor::Thread>)> >(folly::detail::function::Data&) (p=...)
|
at /home/couchbase/jenkins/workspace/cbdeps-platform-build-old/deps/packages/build/folly/folly-prefix/src/folly/folly/Function.h:401
|
fn = <optimized out>
|
#16 0x0000000000aa34e4 in operator() (this=0x7f7c53cf1d40)
|
at /home/couchbase/jenkins/workspace/couchbase-server-unix/kv_engine/executor/folly_executorpool.cc:47
|
fn = @0x7f7c53cf1d40: <error reading variable>
|
#17 operator() (__closure=0x7f7c53cf1d40) at /home/couchbase/jenkins/workspace/couchbase-server-unix/kv_engine/executor/folly_executorpool.cc:47
|
threadNameOpt = {storage_ = {{emptyState = -96 '\240', value = {static npos = 18446744073709551615,
|
_M_dataplus = {<std::allocator<char>> = {<__gnu_cxx::new_allocator<char>> = {<No data fields>}, <No data fields>},
|
_M_p = 0x7f7c3a7c89a0 "ReaderPool4"}, _M_string_length = 11, {_M_local_buf = "ReaderPool4\000\000\000\000",
|
_M_allocated_capacity = 8021036716148221266}}}, hasValue = true}}
|
func = <error reading variable func (Cannot access memory at address 0x7f7c53cf1d40)>
|
#18 folly::detail::function::FunctionTraits<void ()>::callBig<CBRegisteredThreadFactory::newThread(folly::Function<void ()>&&)::{lambda()#1}>(folly::detail::function::Data&) (p=...)
|
at /home/couchbase/jenkins/workspace/couchbase-server-unix/server_build/tlm/deps/folly.exploded/include/folly/Function.h:401
|
fn = @0x7f7c53cf1d40: <error reading variable>
|
#19 0x00007f7c55cf6d40 in execute_native_thread_routine () from /opt/couchbase/bin/../lib/libstdc++.so.6
|
No symbol table info available.
|
#20 0x00007f7c57afee65 in start_thread () from /lib64/libpthread.so.0
|
No symbol table info available.
|
#21 0x00007f7c5543f88d in clone () from /lib64/libc.so.6
|
No symbol table info available.
|
QE-Test:
git fetch "https://review.couchbase.org/TAF" refs/changes/88/166488/1 && git checkout FETCH_HEAD
|
|
guides/gradlew --refresh-dependencies testrunner -P jython=/opt/jython/bin/jython -P 'args=-i /tmp/qe_r.ini -p bucket_storage=couchstore,rerun=false,bucket_eviction_policy=fullEviction,init_loading=False -t storage.magma.magma_rebalance.MagmaRebalance.test_data_load_collections_with_rebalance_out,num_items=300000,doc_size=28,nodes_init=2,nodes_out=1,standard_buckets=1,magma_buckets=0,bucket_storage=couchstore,data_load_stage=during,sdk_timeout=60,vbuckets=1024,key_size=22,replicas=0,infra_log_level=debug,log_level=debug,skip_cleaup=True,randomize_value=True,bucket_eviction_policy=fullEviction,infra_log_level=debug,log_level=debug,init_loading=False,fragmentation=50,skip_cleanup=True,autoCompactionDefined=true,iterations=1,enable_dp=True,num_collections=101,num_scopes=1,bucket_ram_quota=2056,skip_cleanup=True,sdk_client_pool=False,ops_rate=30000,doc_ops=create,create_perc=0,delete_perc=50,update_perc=50,num_collections_to_drop=50,get-cbcollect-info=True -m rest'
|