[
https://issues.apache.org/jira/browse/HDDS-5756?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Ritesh H Shukla updated HDDS-5756:
----------------------------------
Description:
During load testing, the following crash was observed.
bq. Current thread (0x00007f4e7b083800): JavaThread
"grpc-default-executor-1243" daemon [_thread_in_native, id=30646,
stack(0x00007f4de67b6000,0x00007f4de68b7000)]
bq.
bq. Stack: [0x00007f4de67b6000,0x00007f4de68b7000], sp=0x00007f4de68b4c90,
free space=1019k
bq. Native frames: (J=compiled Java code, A=aot compiled Java code,
j=interpreted, Vv=VM code, C=native code)
bq. C [librocksdbjni7210046854294290562.so+0x470f9e]
rocksdb::ReadFileToString(rocksdb::FileSystem*, std::string const&,
std::string*)+0x8e
bq. C [librocksdbjni7210046854294290562.so+0x41a500]
rocksdb::VersionSet::GetCurrentManifestPath(std::string const&,
rocksdb::FileSystem*, std::string*, unsigned long*)+0x60
bq. C [librocksdbjni7210046854294290562.so+0x431776]
rocksdb::VersionSet::ListColumnFamilies(std::vector<std::string,
std::allocator<std::string> >*, std::string const&, rocksdb::FileSystem*)+0x96
bq. C [librocksdbjni7210046854294290562.so+0x300d90]
rocksdb::DB::ListColumnFamilies(rocksdb::DBOptions const&, std::string const&,
std::vector<std::string, std::allocator<std::string> >*)+0x30
bq. C [librocksdbjni7210046854294290562.so+0x241e49]
Java_org_rocksdb_RocksDB_listColumnFamilies+0x89
bq. J 4802 org.rocksdb.RocksDB.listColumnFamilies(JLjava/lang/String;)[[B (0
bytes) @ 0x00007f4e8485dda2 [0x00007f4e8485dcc0+0x00000000000000e2]
bq. J 13730 c2
org.apache.hadoop.hdds.utils.db.RDBStore.<init>(Ljava/io/File;Lorg/rocksdb/DBOptions;Lorg/rocksdb/WriteOptions;Ljava/util/Set;Lorg/apache/hadoop/hdds/utils/db/CodecRegistry;Z)V
(717 bytes) @ 0x00007f4e85557484 [0x00007f4e85556b80+0x0000000000000904]
bq. J 14818 c2
org.apache.hadoop.ozone.container.keyvalue.helpers.BlockUtils.getUncachedDatanodeStore(JLjava/lang/String;Ljava/lang/String;Lorg/apache/hadoop/hdds/conf/ConfigurationSource;Z)Lorg/apache/hadoop/ozone/container/metadata/DatanodeStore;
(84 bytes) @ 0x00007f4e8530cbac [0x00007f4e85309960+0x000000000000324c]
bq. J 21714 c2
org.apache.hadoop.ozone.container.common.utils.ContainerCache.getDB(JLjava/lang/String;Ljava/lang/String;Ljava/lang/String;Lorg/apache/hadoop/hdds/conf/ConfigurationSource;)Lorg/apache/hadoop/ozone/container/common/utils/ReferenceCountedDB;
(339 bytes) @ 0x00007f4e85f200fc [0x00007f4e85f1ec00+0x00000000000014fc]
bq. J 21274 c2
org.apache.hadoop.ozone.container.keyvalue.impl.BlockManagerImpl.getBlock(Lorg/apache/hadoop/ozone/container/common/interfaces/Container;Lorg/apache/hadoop/hdds/client/BlockID;)Lorg/apache/hadoop/ozone/container/common/helpers/BlockData;
(299 bytes) @ 0x00007f4e85d95cf8 [0x00007f4e85d95b80+0x0000000000000178]
bq. J 21490 c2
org.apache.hadoop.ozone.container.common.impl.HddsDispatcher.dispatchRequest(Lorg/apache/hadoop/hdds/protocol/datanode/proto/ContainerProtos$ContainerCommandRequestProto;Lorg/apache/hadoop/ozone/container/common/transport/server/ratis/DispatcherContext;)Lorg/apache/hadoop/hdds/protocol/datanode/proto/ContainerProtos$ContainerCommandResponseProto;
(1105 bytes) @ 0x00007f4e85ebb89c [0x00007f4e85eb9100+0x000000000000279c]
bq. J 20711 c2
org.apache.hadoop.ozone.container.common.impl.HddsDispatcher.dispatch(Lorg/apache/hadoop/hdds/protocol/datanode/proto/ContainerProtos$ContainerCommandRequestProto;Lorg/apache/hadoop/ozone/container/common/transport/server/ratis/DispatcherContext;)Lorg/apache/hadoop/hdds/protocol/datanode/proto/ContainerProtos$ContainerCommandResponseProto;
(38 bytes) @ 0x00007f4e85bacf00 [0x00007f4e85baccc0+0x0000000000000240]
bq. J 20718 c2
org.apache.hadoop.ozone.container.common.transport.server.GrpcXceiverService$1.onNext(Lorg/apache/hadoop/hdds/protocol/datanode/proto/ContainerProtos$ContainerCommandRequestProto;)V
(52 bytes) @ 0x00007f4e85bb71c8 [0x00007f4e85bb7160+0x0000000000000068]
bq. J 20363 c2
org.apache.ratis.thirdparty.io.grpc.internal.ServerImpl$JumpToApplicationThreadServerStreamListener$1MessagesAvailable.runInContext()V
(77 bytes) @ 0x00007f4e8583e290 [0x00007f4e8583cda0+0x00000000000014f0]
bq. J 16086 c2
org.apache.ratis.thirdparty.io.grpc.internal.ContextRunnable.run()V (35 bytes)
@ 0x00007f4e855d0fb0 [0x00007f4e855d0b00+0x00000000000004b0]
bq. J 21355 c2
org.apache.ratis.thirdparty.io.grpc.internal.SerializingExecutor.run()V (99
bytes) @ 0x00007f4e85e7469c [0x00007f4e85e745a0+0x00000000000000fc]
bq. J 20042 c2
java.util.concurrent.ThreadPoolExecutor.runWorker(Ljava/util/concurrent/ThreadPoolExecutor$Worker;)V
[email protected] (187 bytes) @ 0x00007f4e855b7780
[0x00007f4e855b75a0+0x00000000000001e0]
bq. J 17003 c1 java.util.concurrent.ThreadPoolExecutor$Worker.run()V
[email protected] (9 bytes) @ 0x00007f4e7d27e9e4
[0x00007f4e7d27e940+0x00000000000000a4]
bq. J 11466 c1 java.lang.Thread.run()V [email protected] (17 bytes) @
0x00007f4e7e77fcd4 [0x00007f4e7e77fb60+0x0000000000000174]
bq. v ~StubRoutines::call_stub
bq. V [libjvm.so+0x885ac9] JavaCalls::call_helper(JavaValue*, methodHandle
const&, JavaCallArguments*, Thread*)+0x3b9
bq. V [libjvm.so+0x883a6d] JavaCalls::call_virtual(JavaValue*, Handle,
Klass*, Symbol*, Symbol*, Thread*)+0x1ed
bq. V [libjvm.so+0x92cd4c] thread_entry(JavaThread*, Thread*)+0x6c
bq. V [libjvm.so+0xdbea53] JavaThread::thread_main_inner()+0x103
bq. V [libjvm.so+0xdbed25] JavaThread::run()+0x2a5
bq. V [libjvm.so+0xdbaa3a] Thread::call_run()+0x13a
bq. V [libjvm.so+0xc0ad2e] thread_native_entry(Thread*)+0xee
was:
During load testing, the following crash was observed.
Current thread (0x00007f4e7b083800): JavaThread "grpc-default-executor-1243"
daemon [_thread_in_native, id=30646,
stack(0x00007f4de67b6000,0x00007f4de68b7000)]
Stack: [0x00007f4de67b6000,0x00007f4de68b7000], sp=0x00007f4de68b4c90, free
space=1019k
Native frames: (J=compiled Java code, A=aot compiled Java code, j=interpreted,
Vv=VM code, C=native code)
C [librocksdbjni7210046854294290562.so+0x470f9e]
rocksdb::ReadFileToString(rocksdb::FileSystem*, std::string const&,
std::string*)+0x8e
C [librocksdbjni7210046854294290562.so+0x41a500]
rocksdb::VersionSet::GetCurrentManifestPath(std::string const&,
rocksdb::FileSystem*, std::string*, unsigned long*)+0x60
C [librocksdbjni7210046854294290562.so+0x431776]
rocksdb::VersionSet::ListColumnFamilies(std::vector<std::string,
std::allocator<std::string> >*, std::string const&, rocksdb::FileSystem*)+0x96
C [librocksdbjni7210046854294290562.so+0x300d90]
rocksdb::DB::ListColumnFamilies(rocksdb::DBOptions const&, std::string const&,
std::vector<std::string, std::allocator<std::string> >*)+0x30
C [librocksdbjni7210046854294290562.so+0x241e49]
Java_org_rocksdb_RocksDB_listColumnFamilies+0x89
J 4802 org.rocksdb.RocksDB.listColumnFamilies(JLjava/lang/String;)[[B (0
bytes) @ 0x00007f4e8485dda2 [0x00007f4e8485dcc0+0x00000000000000e2]
J 13730 c2
org.apache.hadoop.hdds.utils.db.RDBStore.<init>(Ljava/io/File;Lorg/rocksdb/DBOptions;Lorg/rocksdb/WriteOptions;Ljava/util/Set;Lorg/apache/hadoop/hdds/utils/db/CodecRegistry;Z)V
(717 bytes) @ 0x00007f4e85557484 [0x00007f4e85556b80+0x0000000000000904]
J 14818 c2
org.apache.hadoop.ozone.container.keyvalue.helpers.BlockUtils.getUncachedDatanodeStore(JLjava/lang/String;Ljava/lang/String;Lorg/apache/hadoop/hdds/conf/ConfigurationSource;Z)Lorg/apache/hadoop/ozone/container/metadata/DatanodeStore;
(84 bytes) @ 0x00007f4e8530cbac [0x00007f4e85309960+0x000000000000324c]
J 21714 c2
org.apache.hadoop.ozone.container.common.utils.ContainerCache.getDB(JLjava/lang/String;Ljava/lang/String;Ljava/lang/String;Lorg/apache/hadoop/hdds/conf/ConfigurationSource;)Lorg/apache/hadoop/ozone/container/common/utils/ReferenceCountedDB;
(339 bytes) @ 0x00007f4e85f200fc [0x00007f4e85f1ec00+0x00000000000014fc]
J 21274 c2
org.apache.hadoop.ozone.container.keyvalue.impl.BlockManagerImpl.getBlock(Lorg/apache/hadoop/ozone/container/common/interfaces/Container;Lorg/apache/hadoop/hdds/client/BlockID;)Lorg/apache/hadoop/ozone/container/common/helpers/BlockData;
(299 bytes) @ 0x00007f4e85d95cf8 [0x00007f4e85d95b80+0x0000000000000178]
J 21490 c2
org.apache.hadoop.ozone.container.common.impl.HddsDispatcher.dispatchRequest(Lorg/apache/hadoop/hdds/protocol/datanode/proto/ContainerProtos$ContainerCommandRequestProto;Lorg/apache/hadoop/ozone/container/common/transport/server/ratis/DispatcherContext;)Lorg/apache/hadoop/hdds/protocol/datanode/proto/ContainerProtos$ContainerCommandResponseProto;
(1105 bytes) @ 0x00007f4e85ebb89c [0x00007f4e85eb9100+0x000000000000279c]
J 20711 c2
org.apache.hadoop.ozone.container.common.impl.HddsDispatcher.dispatch(Lorg/apache/hadoop/hdds/protocol/datanode/proto/ContainerProtos$ContainerCommandRequestProto;Lorg/apache/hadoop/ozone/container/common/transport/server/ratis/DispatcherContext;)Lorg/apache/hadoop/hdds/protocol/datanode/proto/ContainerProtos$ContainerCommandResponseProto;
(38 bytes) @ 0x00007f4e85bacf00 [0x00007f4e85baccc0+0x0000000000000240]
J 20718 c2
org.apache.hadoop.ozone.container.common.transport.server.GrpcXceiverService$1.onNext(Lorg/apache/hadoop/hdds/protocol/datanode/proto/ContainerProtos$ContainerCommandRequestProto;)V
(52 bytes) @ 0x00007f4e85bb71c8 [0x00007f4e85bb7160+0x0000000000000068]
J 20363 c2
org.apache.ratis.thirdparty.io.grpc.internal.ServerImpl$JumpToApplicationThreadServerStreamListener$1MessagesAvailable.runInContext()V
(77 bytes) @ 0x00007f4e8583e290 [0x00007f4e8583cda0+0x00000000000014f0]
J 16086 c2 org.apache.ratis.thirdparty.io.grpc.internal.ContextRunnable.run()V
(35 bytes) @ 0x00007f4e855d0fb0 [0x00007f4e855d0b00+0x00000000000004b0]
J 21355 c2
org.apache.ratis.thirdparty.io.grpc.internal.SerializingExecutor.run()V (99
bytes) @ 0x00007f4e85e7469c [0x00007f4e85e745a0+0x00000000000000fc]
J 20042 c2
java.util.concurrent.ThreadPoolExecutor.runWorker(Ljava/util/concurrent/ThreadPoolExecutor$Worker;)V
[email protected] (187 bytes) @ 0x00007f4e855b7780
[0x00007f4e855b75a0+0x00000000000001e0]
J 17003 c1 java.util.concurrent.ThreadPoolExecutor$Worker.run()V
[email protected] (9 bytes) @ 0x00007f4e7d27e9e4
[0x00007f4e7d27e940+0x00000000000000a4]
J 11466 c1 java.lang.Thread.run()V [email protected] (17 bytes) @
0x00007f4e7e77fcd4 [0x00007f4e7e77fb60+0x0000000000000174]
v ~StubRoutines::call_stub
V [libjvm.so+0x885ac9] JavaCalls::call_helper(JavaValue*, methodHandle
const&, JavaCallArguments*, Thread*)+0x3b9
V [libjvm.so+0x883a6d] JavaCalls::call_virtual(JavaValue*, Handle, Klass*,
Symbol*, Symbol*, Thread*)+0x1ed
V [libjvm.so+0x92cd4c] thread_entry(JavaThread*, Thread*)+0x6c
V [libjvm.so+0xdbea53] JavaThread::thread_main_inner()+0x103
V [libjvm.so+0xdbed25] JavaThread::run()+0x2a5
V [libjvm.so+0xdbaa3a] Thread::call_run()+0x13a
V [libjvm.so+0xc0ad2e] thread_native_entry(Thread*)+0xee
> SIGSEGV RocksDB crash in Datanode
> ---------------------------------
>
> Key: HDDS-5756
> URL: https://issues.apache.org/jira/browse/HDDS-5756
> Project: Apache Ozone
> Issue Type: Bug
> Components: Ozone Datanode
> Reporter: Ritesh H Shukla
> Assignee: Ritesh H Shukla
> Priority: Major
>
> During load testing, the following crash was observed.
> bq. Current thread (0x00007f4e7b083800): JavaThread
> "grpc-default-executor-1243" daemon [_thread_in_native, id=30646,
> stack(0x00007f4de67b6000,0x00007f4de68b7000)]
> bq.
> bq. Stack: [0x00007f4de67b6000,0x00007f4de68b7000], sp=0x00007f4de68b4c90,
> free space=1019k
> bq. Native frames: (J=compiled Java code, A=aot compiled Java code,
> j=interpreted, Vv=VM code, C=native code)
> bq. C [librocksdbjni7210046854294290562.so+0x470f9e]
> rocksdb::ReadFileToString(rocksdb::FileSystem*, std::string const&,
> std::string*)+0x8e
> bq. C [librocksdbjni7210046854294290562.so+0x41a500]
> rocksdb::VersionSet::GetCurrentManifestPath(std::string const&,
> rocksdb::FileSystem*, std::string*, unsigned long*)+0x60
> bq. C [librocksdbjni7210046854294290562.so+0x431776]
> rocksdb::VersionSet::ListColumnFamilies(std::vector<std::string,
> std::allocator<std::string> >*, std::string const&, rocksdb::FileSystem*)+0x96
> bq. C [librocksdbjni7210046854294290562.so+0x300d90]
> rocksdb::DB::ListColumnFamilies(rocksdb::DBOptions const&, std::string
> const&, std::vector<std::string, std::allocator<std::string> >*)+0x30
> bq. C [librocksdbjni7210046854294290562.so+0x241e49]
> Java_org_rocksdb_RocksDB_listColumnFamilies+0x89
> bq. J 4802 org.rocksdb.RocksDB.listColumnFamilies(JLjava/lang/String;)[[B (0
> bytes) @ 0x00007f4e8485dda2 [0x00007f4e8485dcc0+0x00000000000000e2]
> bq. J 13730 c2
> org.apache.hadoop.hdds.utils.db.RDBStore.<init>(Ljava/io/File;Lorg/rocksdb/DBOptions;Lorg/rocksdb/WriteOptions;Ljava/util/Set;Lorg/apache/hadoop/hdds/utils/db/CodecRegistry;Z)V
> (717 bytes) @ 0x00007f4e85557484 [0x00007f4e85556b80+0x0000000000000904]
> bq. J 14818 c2
> org.apache.hadoop.ozone.container.keyvalue.helpers.BlockUtils.getUncachedDatanodeStore(JLjava/lang/String;Ljava/lang/String;Lorg/apache/hadoop/hdds/conf/ConfigurationSource;Z)Lorg/apache/hadoop/ozone/container/metadata/DatanodeStore;
> (84 bytes) @ 0x00007f4e8530cbac [0x00007f4e85309960+0x000000000000324c]
> bq. J 21714 c2
> org.apache.hadoop.ozone.container.common.utils.ContainerCache.getDB(JLjava/lang/String;Ljava/lang/String;Ljava/lang/String;Lorg/apache/hadoop/hdds/conf/ConfigurationSource;)Lorg/apache/hadoop/ozone/container/common/utils/ReferenceCountedDB;
> (339 bytes) @ 0x00007f4e85f200fc [0x00007f4e85f1ec00+0x00000000000014fc]
> bq. J 21274 c2
> org.apache.hadoop.ozone.container.keyvalue.impl.BlockManagerImpl.getBlock(Lorg/apache/hadoop/ozone/container/common/interfaces/Container;Lorg/apache/hadoop/hdds/client/BlockID;)Lorg/apache/hadoop/ozone/container/common/helpers/BlockData;
> (299 bytes) @ 0x00007f4e85d95cf8 [0x00007f4e85d95b80+0x0000000000000178]
> bq. J 21490 c2
> org.apache.hadoop.ozone.container.common.impl.HddsDispatcher.dispatchRequest(Lorg/apache/hadoop/hdds/protocol/datanode/proto/ContainerProtos$ContainerCommandRequestProto;Lorg/apache/hadoop/ozone/container/common/transport/server/ratis/DispatcherContext;)Lorg/apache/hadoop/hdds/protocol/datanode/proto/ContainerProtos$ContainerCommandResponseProto;
> (1105 bytes) @ 0x00007f4e85ebb89c [0x00007f4e85eb9100+0x000000000000279c]
> bq. J 20711 c2
> org.apache.hadoop.ozone.container.common.impl.HddsDispatcher.dispatch(Lorg/apache/hadoop/hdds/protocol/datanode/proto/ContainerProtos$ContainerCommandRequestProto;Lorg/apache/hadoop/ozone/container/common/transport/server/ratis/DispatcherContext;)Lorg/apache/hadoop/hdds/protocol/datanode/proto/ContainerProtos$ContainerCommandResponseProto;
> (38 bytes) @ 0x00007f4e85bacf00 [0x00007f4e85baccc0+0x0000000000000240]
> bq. J 20718 c2
> org.apache.hadoop.ozone.container.common.transport.server.GrpcXceiverService$1.onNext(Lorg/apache/hadoop/hdds/protocol/datanode/proto/ContainerProtos$ContainerCommandRequestProto;)V
> (52 bytes) @ 0x00007f4e85bb71c8 [0x00007f4e85bb7160+0x0000000000000068]
> bq. J 20363 c2
> org.apache.ratis.thirdparty.io.grpc.internal.ServerImpl$JumpToApplicationThreadServerStreamListener$1MessagesAvailable.runInContext()V
> (77 bytes) @ 0x00007f4e8583e290 [0x00007f4e8583cda0+0x00000000000014f0]
> bq. J 16086 c2
> org.apache.ratis.thirdparty.io.grpc.internal.ContextRunnable.run()V (35
> bytes) @ 0x00007f4e855d0fb0 [0x00007f4e855d0b00+0x00000000000004b0]
> bq. J 21355 c2
> org.apache.ratis.thirdparty.io.grpc.internal.SerializingExecutor.run()V (99
> bytes) @ 0x00007f4e85e7469c [0x00007f4e85e745a0+0x00000000000000fc]
> bq. J 20042 c2
> java.util.concurrent.ThreadPoolExecutor.runWorker(Ljava/util/concurrent/ThreadPoolExecutor$Worker;)V
> [email protected] (187 bytes) @ 0x00007f4e855b7780
> [0x00007f4e855b75a0+0x00000000000001e0]
> bq. J 17003 c1 java.util.concurrent.ThreadPoolExecutor$Worker.run()V
> [email protected] (9 bytes) @ 0x00007f4e7d27e9e4
> [0x00007f4e7d27e940+0x00000000000000a4]
> bq. J 11466 c1 java.lang.Thread.run()V [email protected] (17 bytes) @
> 0x00007f4e7e77fcd4 [0x00007f4e7e77fb60+0x0000000000000174]
> bq. v ~StubRoutines::call_stub
> bq. V [libjvm.so+0x885ac9] JavaCalls::call_helper(JavaValue*, methodHandle
> const&, JavaCallArguments*, Thread*)+0x3b9
> bq. V [libjvm.so+0x883a6d] JavaCalls::call_virtual(JavaValue*, Handle,
> Klass*, Symbol*, Symbol*, Thread*)+0x1ed
> bq. V [libjvm.so+0x92cd4c] thread_entry(JavaThread*, Thread*)+0x6c
> bq. V [libjvm.so+0xdbea53] JavaThread::thread_main_inner()+0x103
> bq. V [libjvm.so+0xdbed25] JavaThread::run()+0x2a5
> bq. V [libjvm.so+0xdbaa3a] Thread::call_run()+0x13a
> bq. V [libjvm.so+0xc0ad2e] thread_native_entry(Thread*)+0xee
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]