[
https://issues.apache.org/jira/browse/SLIDER-1034?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15117694#comment-15117694
]
Steve Loughran commented on SLIDER-1034:
----------------------------------------
Seen again, locally.
{code}
Failed tests:
TestAgentAAEcho.testAgentEcho:88->postLaunchActions:186 assert
cd.getRoleOptInt(rolename, RoleKeys.ROLE_PENDING_AA_INSTANCES, -1) == 0
| | | | |
| 49 echo role.pending.aa.instances false
{
"version" : "1.0",
"name" : "testagentaaecho",
"type" : "agent",
"state" : 3,
"createTime" : 1453828499575,
"updateTime" : 1453828520462,
"originConfigurationPath" :
"file:/Users/stevel/.slider/cluster/testagentaaecho/snapshot",
"generatedConfigurationPath" :
"file:/Users/stevel/.slider/cluster/testagentaaecho/generated",
"dataPath" :
"file:/Users/stevel/.slider/cluster/testagentaaecho/database",
"options" : {
"site.global.security_enabled" : "false",
"internal.appdef.dir.path" :
"file:/Users/stevel/.slider/cluster/testagentaaecho/tmp/appdef",
"internal.application.home" : "/",
"agent.package.root" :
"/Users/stevel/Projects/Hortonworks/Projects/slider/slider-core/./src/test/python",
"slider.cluster.directory.permissions" : "0770",
"application.name" : "testagentaaecho",
"internal.addons.dir.path" :
"file:/Users/stevel/.slider/cluster/testagentaaecho/tmp/addons",
"internal.tmp.dir" :
"file:/Users/stevel/.slider/cluster/testagentaaecho/tmp",
"internal.snapshot.conf.path" :
"file:/Users/stevel/.slider/cluster/testagentaaecho/snapshot",
"env.MALLOC_ARENA_MAX" : "4",
"zookeeper.path" : "/services/slider/users/stevel/testagentaaecho",
"internal.container.failure.shortlife" : "60000",
"internal.application.image.path" : null,
"internal.generated.conf.path" :
"file:/Users/stevel/.slider/cluster/testagentaaecho/generated",
"site.fs.default.name" : "file:///",
"agent.version" :
"file:/Users/stevel/Projects/Hortonworks/Projects/slider/slider-core/./src/test/python/version",
"agent.conf" :
"file:/Users/stevel/Projects/Hortonworks/Projects/slider/slider-core/./src/test/python/agent.ini",
"zookeeper.hosts" : "localhost",
"internal.provider.name" : "agent",
"internal.data.dir.path" :
"file:/Users/stevel/.slider/cluster/testagentaaecho/database",
"site.fs.defaultFS" : "file:///",
"slider.data.directory.permissions" : "0770",
"zookeeper.quorum" : "localhost:63451",
"internal.am.tmp.dir" :
"file:/Users/stevel/.slider/cluster/testagentaaecho/tmp/appmaster",
"internal.container.failure.threshold" : "5",
"application.def" :
"file:/private/var/folders/57/xyts0qt105z1f1k0twk6rd8m0000gq/T/junit8871531317671442911/testpkg/appdef_1.zip"
},
"info" : {
"info.am.container.id" : "container_1453828488505_0001_01_000001",
"info.am.rpc.port" : "1026",
"info.am.attempt.id" : "appattempt_1453828488505_0001_000001",
"yarn.memory" : "8192",
"info.am.web.port" : "1027",
"info.am.web.url" : "http://stevel-2.local:1027/";,
"info.am.app.id" : "application_1453828488505_0001",
"yarn.vcores" : "1",
"info.am.hostname" : "stevel-2.local",
"status.application.build.info" : "Slider
Core-0.90.0-incubating-SNAPSHOT Built against commit# 20198e2228 on Java
1.7.0_75 by stevel",
"status.hadoop.build.info" : "2.6.0",
"status.hadoop.deployed.info" : "branch-2.6.0
@18e43357c8f927c0695f1e9522859d6a",
"live.time" : "26 Jan 2016 17:14:59 GMT",
"live.time.millis" : "1453828499575",
"create.time" : "26 Jan 2016 17:14:59 GMT",
"create.time.millis" : "1453828499575",
"containers.at.am-restart" : "0",
"status.time" : "26 Jan 2016 17:15:20 GMT",
"status.time.millis" : "1453828520462",
"info.am.agent.status.url" : "https://stevel-2.local:63496/";,
"info.am.agent.status.port" : "63496",
"info.am.agent.ops.url" : "https://stevel-2.local:63497/";,
"info.am.agent.ops.port" : "63497"
},
"statistics" : {
"slider-appmaster" : {
"containers.unknown.completed" : 0,
"containers.start.started" : 1,
"containers.live" : 2,
"containers.start.failed" : 0,
"containers.failed" : 0,
"containers.completed" : 0,
"containers.surplus" : 0
},
"echo" : {
"containers.failed.node" : 0,
"containers.start.started" : 0,
"containers.live" : 1,
"containers.start.failed" : 0,
"containers.failed.preempted" : 0,
"containers.active.requests" : 0,
"containers.failed.recently" : 0,
"containers.failed" : 0,
"containers.completed" : 0,
"containers.anti-affine.pending" : 49,
"containers.desired" : 1,
"containers.requested" : 1
}
},
"instances" : {
"slider-appmaster" : [ "container_1453828488505_0001_01_000001" ],
"echo" : [ "container_1453828488505_0001_01_000002" ]
},
"roles" : {
"slider-appmaster" : {
"role.failed.recently.instances" : "0",
"yarn.memory" : "1024",
"role.requested.instances" : "0",
"role.failed.starting.instances" : "0",
"role.actual.instances" : "1",
"yarn.vcores" : "1",
"yarn.component.instances" : "1",
"role.releasing.instances" : "0",
"role.failed.node.instances" : "0",
"role.failed.instances" : "0",
"role.failed.preempted.instances" : "0"
},
"echo" : {
"role.failed.recently.instances" : "0",
"yarn.component.placement.policy" : "4",
"role.requested.instances" : "0",
"test.relax.validation" : "true",
"role.failed.starting.instances" : "0",
"role.failed.node.instances" : "0",
"role.failed.preempted.instances" : "0",
"app.name" : "Agent",
"yarn.role.priority" : "1",
"role.actual.instances" : "1",
"agent.script" : "echo.py",
"yarn.component.instances" : "1",
"role.releasing.instances" : "0",
"role.failed.instances" : "0",
"role.pending.aa.instances" : "49"
}
},
"clientProperties" : { },
"status" : {
"live" : {
"slider-appmaster" : {
"container_1453828488505_0001_01_000001" : {
"name" : "container_1453828488505_0001_01_000001",
"role" : "slider-appmaster",
"roleId" : 0,
"createTime" : 1453828499591,
"startTime" : 1453828499591,
"released" : false,
"host" : "stevel-2.local",
"hostUrl" : "http://stevel-2.local:1027";,
"state" : 3,
"exitCode" : 0
}
},
"echo" : {
"container_1453828488505_0001_01_000002" : {
"name" : "container_1453828488505_0001_01_000002",
"role" : "echo",
"roleId" : 1,
"createTime" : 1453828502297,
"startTime" : 1453828502350,
"released" : false,
"host" : "192.168.1.85",
"hostUrl" : "http://192.168.1.85:63466";,
"state" : 3,
"exitCode" : 0,
"command" : "python
/Users/stevel/Projects/Hortonworks/Projects/slider/slider-core/./src/test/python/agent/main.py
--label container_1453828488505_0001_01_000002___echo --zk-quorum
localhost:63451 --zk-reg-path
/registry/users/stevel/services/org-apache-slider/testagentaaecho >
<LOG_DIR>/slider-agent.out 2>&1 ; ",
"environment" : [ "LANGUAGE=\"en_US.UTF-8\"",
"AGENT_WORK_ROOT=\"$PWD\"", "HADOOP_USER_NAME=\"stevel\"",
"AGENT_LOG_ROOT=\"<LOG_DIR>\"", "PYTHONPATH=\"./infra/agent/slider-agent/\"",
"LC_ALL=\"en_US.UTF-8\"",
"SLIDER_PASSPHRASE=\"rA3VdXwqjKGvKhr10XhjIj3k1uNDFroQbicQvlQi5d39aEe8UQ\"",
"MALLOC_ARENA_MAX=\"4\"", "LANG=\"en_US.UTF-8\"" ]
}
}
}
},
"liveness" : {
"allRequestsSatisfied" : true,
"requestsOutstanding" : 0,
"activeRequests" : 0
}
}
{code}
> TestAgentAAEcho failed with #of pending instances == 49
> -------------------------------------------------------
>
> Key: SLIDER-1034
> URL: https://issues.apache.org/jira/browse/SLIDER-1034
> Project: Slider
> Issue Type: Bug
> Components: appmaster, test
> Affects Versions: Slider 0.90.2
> Environment: Jenkins
> Reporter: Steve Loughran
> Assignee: Steve Loughran
> Fix For: Slider 0.91
>
> Attachments: jenkins.txt
>
>
> A transient jenkins failure had an as
> {code}
> ssert cd.getRoleOptInt(rolename, RoleKeys.ROLE_PENDING_AA_INSTANCES, -1) == 0
> | | | | |
> | 49 echo role.pending.aa.instances
> false
> {code}
> And yes, that's what is in the JSON
> {code}
> "role.pending.aa.instances" : "49"
> {code}
> This hints at some race condition in the test, reporting, or appstate
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
