[
https://issues.apache.org/jira/browse/IGNITE-6967?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Alexandr Kuramshin updated IGNITE-6967:
---------------------------------------
Description:
With a service deployment when topology change occurs the discovery event
listener calls {{GridServiceProcessor.reassign()}} causing to acquire a lock on
utility cache (where the GridServiceAssignments stored) which prevents PME from
completion.
Stack traces:
{noformat}
Thread [name="test-runner-#186%service.IgniteServiceDynamicCachesSelfTest%",
id=232, state=WAITING, blockCnt=0, waitCnt=8]
at sun.misc.Unsafe.park(Native Method)
at java.util.concurrent.locks.LockSupport.park(LockSupport.java:304)
at
o.a.i.i.util.future.GridFutureAdapter.get0(GridFutureAdapter.java:177)
at o.a.i.i.util.future.GridFutureAdapter.get(GridFutureAdapter.java:140)
at o.a.i.i.IgniteKernal.createCache(IgniteKernal.java:2841)
at
o.a.i.i.processors.service.IgniteServiceDynamicCachesSelfTest.testDeployCalledBeforeCacheStart(IgniteServiceDynamicCachesSelfTest.java:140)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at junit.framework.TestCase.runTest(TestCase.java:176)
at
o.a.i.testframework.junits.GridAbstractTest.runTestInternal(GridAbstractTest.java:2000)
at
o.a.i.testframework.junits.GridAbstractTest.access$000(GridAbstractTest.java:132)
at
o.a.i.testframework.junits.GridAbstractTest$5.run(GridAbstractTest.java:1915)
at java.lang.Thread.run(Thread.java:748)
Thread [name="srvc-deploy-#38%service.IgniteServiceDynamicCachesSelfTest0%",
id=56, state=WAITING, blockCnt=5, waitCnt=9]
at sun.misc.Unsafe.park(Native Method)
at java.util.concurrent.locks.LockSupport.park(LockSupport.java:304)
at
o.a.i.i.util.future.GridFutureAdapter.get0(GridFutureAdapter.java:177)
at o.a.i.i.util.future.GridFutureAdapter.get(GridFutureAdapter.java:140)
at
o.a.i.i.processors.cache.GridCacheContext.awaitStarted(GridCacheContext.java:443)
at
o.a.i.i.processors.affinity.GridAffinityProcessor.affinityCache(GridAffinityProcessor.java:373)
at
o.a.i.i.processors.affinity.GridAffinityProcessor.keysToNodes(GridAffinityProcessor.java:347)
at
o.a.i.i.processors.affinity.GridAffinityProcessor.mapKeyToNode(GridAffinityProcessor.java:259)
at
o.a.i.i.processors.service.GridServiceProcessor.reassign(GridServiceProcessor.java:1163)
at
o.a.i.i.processors.service.GridServiceProcessor.access$2400(GridServiceProcessor.java:123)
at
o.a.i.i.processors.service.GridServiceProcessor$TopologyListener$1.run0(GridServiceProcessor.java:1763)
at
o.a.i.i.processors.service.GridServiceProcessor$DepRunnable.run(GridServiceProcessor.java:1976)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:748)
Locked synchronizers:
java.util.concurrent.ThreadPoolExecutor$Worker@27f723
{noformat}
Problematic code:
{noformat}
org.apache.ignite.internal.processors.service.GridServiceProcessor#reassign
try (GridNearTxLocal tx = cache.txStartEx(PESSIMISTIC,
REPEATABLE_READ)) {
GridServiceAssignmentsKey key = new
GridServiceAssignmentsKey(cfg.getName());
GridServiceAssignments oldAssigns =
(GridServiceAssignments)cache.get(key);
Map<UUID, Integer> cnts = new HashMap<>();
if (affKey != null) {
ClusterNode n = ctx.affinity().mapKeyToNode(cacheName,
affKey, topVer);
// WAIT HERE UNTIL PME FINISHED (INFINITELY)
{noformat}
was:
With a service deployment when topology change occurs the discovery event
listener calls {{GridServiceProcessor.reassign()}} causing to acquire a lock on
utility cache (where the GridServiceAssignments stored) which prevents PME from
completion.
Stack traces:
{{noformat}}
Thread [name="test-runner-#186%service.IgniteServiceDynamicCachesSelfTest%",
id=232, state=WAITING, blockCnt=0, waitCnt=8]
at sun.misc.Unsafe.park(Native Method)
at java.util.concurrent.locks.LockSupport.park(LockSupport.java:304)
at
o.a.i.i.util.future.GridFutureAdapter.get0(GridFutureAdapter.java:177)
at o.a.i.i.util.future.GridFutureAdapter.get(GridFutureAdapter.java:140)
at o.a.i.i.IgniteKernal.createCache(IgniteKernal.java:2841)
at
o.a.i.i.processors.service.IgniteServiceDynamicCachesSelfTest.testDeployCalledBeforeCacheStart(IgniteServiceDynamicCachesSelfTest.java:140)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at junit.framework.TestCase.runTest(TestCase.java:176)
at
o.a.i.testframework.junits.GridAbstractTest.runTestInternal(GridAbstractTest.java:2000)
at
o.a.i.testframework.junits.GridAbstractTest.access$000(GridAbstractTest.java:132)
at
o.a.i.testframework.junits.GridAbstractTest$5.run(GridAbstractTest.java:1915)
at java.lang.Thread.run(Thread.java:748)
Thread [name="srvc-deploy-#38%service.IgniteServiceDynamicCachesSelfTest0%",
id=56, state=WAITING, blockCnt=5, waitCnt=9]
at sun.misc.Unsafe.park(Native Method)
at java.util.concurrent.locks.LockSupport.park(LockSupport.java:304)
at
o.a.i.i.util.future.GridFutureAdapter.get0(GridFutureAdapter.java:177)
at o.a.i.i.util.future.GridFutureAdapter.get(GridFutureAdapter.java:140)
at
o.a.i.i.processors.cache.GridCacheContext.awaitStarted(GridCacheContext.java:443)
at
o.a.i.i.processors.affinity.GridAffinityProcessor.affinityCache(GridAffinityProcessor.java:373)
at
o.a.i.i.processors.affinity.GridAffinityProcessor.keysToNodes(GridAffinityProcessor.java:347)
at
o.a.i.i.processors.affinity.GridAffinityProcessor.mapKeyToNode(GridAffinityProcessor.java:259)
at
o.a.i.i.processors.service.GridServiceProcessor.reassign(GridServiceProcessor.java:1163)
at
o.a.i.i.processors.service.GridServiceProcessor.access$2400(GridServiceProcessor.java:123)
at
o.a.i.i.processors.service.GridServiceProcessor$TopologyListener$1.run0(GridServiceProcessor.java:1763)
at
o.a.i.i.processors.service.GridServiceProcessor$DepRunnable.run(GridServiceProcessor.java:1976)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:748)
Locked synchronizers:
java.util.concurrent.ThreadPoolExecutor$Worker@27f723
{{noformat}}
Problematic code:
{{noformat}}
org.apache.ignite.internal.processors.service.GridServiceProcessor#reassign
try (GridNearTxLocal tx = cache.txStartEx(PESSIMISTIC,
REPEATABLE_READ)) {
GridServiceAssignmentsKey key = new
GridServiceAssignmentsKey(cfg.getName());
GridServiceAssignments oldAssigns =
(GridServiceAssignments)cache.get(key);
Map<UUID, Integer> cnts = new HashMap<>();
if (affKey != null) {
ClusterNode n = ctx.affinity().mapKeyToNode(cacheName,
affKey, topVer);
// WAIT HERE UNTIL PME FINISHED (INFINITELY)
{{noformat}}
> PME deadlock on reassigning service deployment
> ----------------------------------------------
>
> Key: IGNITE-6967
> URL: https://issues.apache.org/jira/browse/IGNITE-6967
> Project: Ignite
> Issue Type: Bug
> Components: general
> Affects Versions: 2.3
> Reporter: Alexandr Kuramshin
>
> With a service deployment when topology change occurs the discovery event
> listener calls {{GridServiceProcessor.reassign()}} causing to acquire a lock
> on utility cache (where the GridServiceAssignments stored) which prevents PME
> from completion.
> Stack traces:
> {noformat}
> Thread [name="test-runner-#186%service.IgniteServiceDynamicCachesSelfTest%",
> id=232, state=WAITING, blockCnt=0, waitCnt=8]
> at sun.misc.Unsafe.park(Native Method)
> at java.util.concurrent.locks.LockSupport.park(LockSupport.java:304)
> at
> o.a.i.i.util.future.GridFutureAdapter.get0(GridFutureAdapter.java:177)
> at
> o.a.i.i.util.future.GridFutureAdapter.get(GridFutureAdapter.java:140)
> at o.a.i.i.IgniteKernal.createCache(IgniteKernal.java:2841)
> at
> o.a.i.i.processors.service.IgniteServiceDynamicCachesSelfTest.testDeployCalledBeforeCacheStart(IgniteServiceDynamicCachesSelfTest.java:140)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:498)
> at junit.framework.TestCase.runTest(TestCase.java:176)
> at
> o.a.i.testframework.junits.GridAbstractTest.runTestInternal(GridAbstractTest.java:2000)
> at
> o.a.i.testframework.junits.GridAbstractTest.access$000(GridAbstractTest.java:132)
> at
> o.a.i.testframework.junits.GridAbstractTest$5.run(GridAbstractTest.java:1915)
> at java.lang.Thread.run(Thread.java:748)
> Thread [name="srvc-deploy-#38%service.IgniteServiceDynamicCachesSelfTest0%",
> id=56, state=WAITING, blockCnt=5, waitCnt=9]
> at sun.misc.Unsafe.park(Native Method)
> at java.util.concurrent.locks.LockSupport.park(LockSupport.java:304)
> at
> o.a.i.i.util.future.GridFutureAdapter.get0(GridFutureAdapter.java:177)
> at
> o.a.i.i.util.future.GridFutureAdapter.get(GridFutureAdapter.java:140)
> at
> o.a.i.i.processors.cache.GridCacheContext.awaitStarted(GridCacheContext.java:443)
> at
> o.a.i.i.processors.affinity.GridAffinityProcessor.affinityCache(GridAffinityProcessor.java:373)
> at
> o.a.i.i.processors.affinity.GridAffinityProcessor.keysToNodes(GridAffinityProcessor.java:347)
> at
> o.a.i.i.processors.affinity.GridAffinityProcessor.mapKeyToNode(GridAffinityProcessor.java:259)
> at
> o.a.i.i.processors.service.GridServiceProcessor.reassign(GridServiceProcessor.java:1163)
> at
> o.a.i.i.processors.service.GridServiceProcessor.access$2400(GridServiceProcessor.java:123)
> at
> o.a.i.i.processors.service.GridServiceProcessor$TopologyListener$1.run0(GridServiceProcessor.java:1763)
> at
> o.a.i.i.processors.service.GridServiceProcessor$DepRunnable.run(GridServiceProcessor.java:1976)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> at java.lang.Thread.run(Thread.java:748)
> Locked synchronizers:
> java.util.concurrent.ThreadPoolExecutor$Worker@27f723
> {noformat}
> Problematic code:
> {noformat}
> org.apache.ignite.internal.processors.service.GridServiceProcessor#reassign
> try (GridNearTxLocal tx = cache.txStartEx(PESSIMISTIC,
> REPEATABLE_READ)) {
> GridServiceAssignmentsKey key = new
> GridServiceAssignmentsKey(cfg.getName());
> GridServiceAssignments oldAssigns =
> (GridServiceAssignments)cache.get(key);
> Map<UUID, Integer> cnts = new HashMap<>();
> if (affKey != null) {
> ClusterNode n = ctx.affinity().mapKeyToNode(cacheName,
> affKey, topVer);
> // WAIT HERE UNTIL PME FINISHED (INFINITELY)
> {noformat}
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)