[
https://issues.apache.org/jira/browse/KAFKA-1194?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16005392#comment-16005392
]
Jose Alberto Gutierrez commented on KAFKA-1194:
-----------------------------------------------
Still a problem.
Kafka : kafka_2.12-0.10.2.0
Config:
advertised.host.name = 192.168.2.202
advertised.listeners = null
advertised.port = null
authorizer.class.name =
auto.create.topics.enable = true
auto.leader.rebalance.enable = true
background.threads = 10
broker.id = 6202
broker.id.generation.enable = true
broker.rack = null
compression.type = producer
connections.max.idle.ms = 600000
controlled.shutdown.enable = true
controlled.shutdown.max.retries = 3
controlled.shutdown.retry.backoff.ms = 5000
controller.socket.timeout.ms = 30000
create.topic.policy.class.name = null
default.replication.factor = 1
delete.topic.enable = false
fetch.purgatory.purge.interval.requests = 1000
group.max.session.timeout.ms = 300000
group.min.session.timeout.ms = 6000
host.name =
inter.broker.listener.name = null
inter.broker.protocol.version = 0.8.2.2
leader.imbalance.check.interval.seconds = 300
leader.imbalance.per.broker.percentage = 10
listener.security.protocol.map =
SSL:SSL,SASL_PLAINTEXT:SASL_PLAINTEXT,TRACE:TRACE,SASL_SSL:SASL_SSL,PLAINTEXT:PLAINTEXT
listeners = null
log.cleaner.backoff.ms = 15000
log.cleaner.dedupe.buffer.size = 134217728
log.cleaner.delete.retention.ms = 86400000
log.cleaner.enable = true
log.cleaner.io.buffer.load.factor = 0.9
log.cleaner.io.buffer.size = 524288
log.cleaner.io.max.bytes.per.second = 1.7976931348623157E308
log.cleaner.min.cleanable.ratio = 0.5
log.cleaner.min.compaction.lag.ms = 0
log.cleaner.threads = 1
log.cleanup.policy = [delete]
log.dir = /tmp/kafka-logs
log.dirs = /tmp/kafka-logs
log.flush.interval.messages = 9223372036854775807
log.flush.interval.ms = null
log.flush.offset.checkpoint.interval.ms = 60000
log.flush.scheduler.interval.ms = 9223372036854775807
log.index.interval.bytes = 4096
log.index.size.max.bytes = 10485760
log.message.format.version = 0.8.2.2
log.message.timestamp.difference.max.ms = 9223372036854775807
log.message.timestamp.type = CreateTime
log.preallocate = false
log.retention.bytes = -1
log.retention.check.interval.ms = 300000
log.retention.hours = 168
log.retention.minutes = null
log.retention.ms = null
log.roll.hours = 168
log.roll.jitter.hours = 0
log.roll.jitter.ms = null
log.roll.ms = null
log.segment.bytes = 1073741824
log.segment.delete.delay.ms = 60000
max.connections.per.ip = 2147483647
max.connections.per.ip.overrides =
message.max.bytes = 1000012
metric.reporters = []
metrics.num.samples = 2
metrics.recording.level = INFO
metrics.sample.window.ms = 30000
min.insync.replicas = 1
num.io.threads = 8
num.network.threads = 3
num.partitions = 10
num.recovery.threads.per.data.dir = 1
num.replica.fetchers = 1
offset.metadata.max.bytes = 4096
offsets.commit.required.acks = -1
offsets.commit.timeout.ms = 5000
offsets.load.buffer.size = 5242880
offsets.retention.check.interval.ms = 600000
offsets.retention.minutes = 1440
offsets.topic.compression.codec = 0
offsets.topic.num.partitions = 50
offsets.topic.replication.factor = 3
offsets.topic.segment.bytes = 104857600
port = 9092
principal.builder.class = class
org.apache.kafka.common.security.auth.DefaultPrincipalBuilder
producer.purgatory.purge.interval.requests = 1000
queued.max.requests = 500
quota.consumer.default = 9223372036854775807
quota.producer.default = 9223372036854775807
quota.window.num = 11
quota.window.size.seconds = 1
replica.fetch.backoff.ms = 1000
replica.fetch.max.bytes = 1048576
replica.fetch.min.bytes = 1
replica.fetch.response.max.bytes = 10485760
replica.fetch.wait.max.ms = 500
replica.high.watermark.checkpoint.interval.ms = 5000
replica.lag.time.max.ms = 10000
replica.socket.receive.buffer.bytes = 65536
replica.socket.timeout.ms = 30000
replication.quota.window.num = 11
replication.quota.window.size.seconds = 1
request.timeout.ms = 30000
reserved.broker.max.id = 1000
sasl.enabled.mechanisms = [GSSAPI]
sasl.kerberos.kinit.cmd = /usr/bin/kinit
sasl.kerberos.min.time.before.relogin = 60000
sasl.kerberos.principal.to.local.rules = [DEFAULT]
sasl.kerberos.service.name = null
sasl.kerberos.ticket.renew.jitter = 0.05
sasl.kerberos.ticket.renew.window.factor = 0.8
sasl.mechanism.inter.broker.protocol = GSSAPI
security.inter.broker.protocol = PLAINTEXT
socket.receive.buffer.bytes = 102400
socket.request.max.bytes = 104857600
socket.send.buffer.bytes = 102400
ssl.cipher.suites = null
ssl.client.auth = none
ssl.enabled.protocols = [TLSv1.2, TLSv1.1, TLSv1]
ssl.endpoint.identification.algorithm = null
ssl.key.password = null
ssl.keymanager.algorithm = SunX509
ssl.keystore.location = null
ssl.keystore.password = null
ssl.keystore.type = JKS
ssl.protocol = TLS
ssl.provider = null
ssl.secure.random.implementation = null
ssl.trustmanager.algorithm = PKIX
ssl.truststore.location = null
ssl.truststore.password = null
ssl.truststore.type = JKS
unclean.leader.election.enable = true
zookeeper.connect =
192.168.2.203:2181,192.168.2.150:2181,192.168.2.202:2181
zookeeper.connection.timeout.ms = 6000
zookeeper.session.timeout.ms = 6000
zookeeper.set.acl = false
zookeeper.sync.time.ms = 2000
On:
Windows 2012 Server
Java version : 1.8.0_121
Log:
[2017-05-10 17:40:19,981] INFO Rolled new log segment for 'lt_backend_n-8' in 2
ms. (kafka.log.Log)
[2017-05-10 17:40:19,982] INFO Scheduling log segment 352 for log
lt_backend_n-8 for deletion. (kafka.log.Log)
[2017-05-10 17:40:19,982] ERROR Uncaught exception in scheduled task
'kafka-log-retention' (kafka.utils.KafkaScheduler)
kafka.common.KafkaStorageException: Failed to change the log file suffix from
to .deleted for log segment 352
at kafka.log.LogSegment.kafkaStorageException$1(LogSegment.scala:340)
at kafka.log.LogSegment.changeFileSuffixes(LogSegment.scala:344)
at kafka.log.Log.asyncDeleteSegment(Log.scala:981)
at kafka.log.Log.deleteSegment(Log.scala:971)
at kafka.log.Log.$anonfun$deleteOldSegments$1(Log.scala:673)
at kafka.log.Log.$anonfun$deleteOldSegments$1$adapted(Log.scala:673)
at scala.collection.immutable.List.foreach(List.scala:378)
at kafka.log.Log.deleteOldSegments(Log.scala:673)
at kafka.log.Log.deleteRetenionMsBreachedSegments(Log.scala:703)
at kafka.log.Log.deleteOldSegments(Log.scala:697)
at kafka.log.LogManager.$anonfun$cleanupLogs$3(LogManager.scala:474)
at
kafka.log.LogManager.$anonfun$cleanupLogs$3$adapted(LogManager.scala:472)
at
scala.collection.TraversableLike$WithFilter.$anonfun$foreach$1(TraversableLike.scala:789)
at scala.collection.Iterator.foreach(Iterator.scala:929)
at scala.collection.Iterator.foreach$(Iterator.scala:929)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1406)
at scala.collection.IterableLike.foreach(IterableLike.scala:71)
at scala.collection.IterableLike.foreach$(IterableLike.scala:70)
at scala.collection.AbstractIterable.foreach(Iterable.scala:54)
at
scala.collection.TraversableLike$WithFilter.foreach(TraversableLike.scala:788)
at kafka.log.LogManager.cleanupLogs(LogManager.scala:472)
at kafka.log.LogManager.$anonfun$startup$2(LogManager.scala:200)
at
kafka.utils.KafkaScheduler.$anonfun$schedule$2(KafkaScheduler.scala:110)
at kafka.utils.CoreUtils$$anon$1.run(CoreUtils.scala:57)
at java.util.concurrent.Executors$RunnableAdapter.call(Unknown Source)
at java.util.concurrent.FutureTask.runAndReset(Unknown Source)
at
java.util.concurrent.ScheduledThreadPoolExecutor$ScheduledFutureTask.access$301(Unknown
Source)
at
java.util.concurrent.ScheduledThreadPoolExecutor$ScheduledFutureTask.run(Unknown
Source)
at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.lang.Thread.run(Unknown Source)
Caused by: java.nio.file.FileSystemException:
\tmp\kafka-logs\lt_backend_n-8\00000000000000000352.log ->
\tmp\kafka-logs\lt_backend_n-8\00000000000000000352.log.deleted: The process
cannot access the file because it is being used by another process.
at sun.nio.fs.WindowsException.translateToIOException(Unknown Source)
at sun.nio.fs.WindowsException.rethrowAsIOException(Unknown Source)
at sun.nio.fs.WindowsFileCopy.move(Unknown Source)
at sun.nio.fs.WindowsFileSystemProvider.move(Unknown Source)
at java.nio.file.Files.move(Unknown Source)
at
org.apache.kafka.common.utils.Utils.atomicMoveWithFallback(Utils.java:711)
at
org.apache.kafka.common.record.FileRecords.renameTo(FileRecords.java:210)
at kafka.log.LogSegment.changeFileSuffixes(LogSegment.scala:342)
... 29 more
Suppressed: java.nio.file.FileSystemException:
\tmp\kafka-logs\lt_backend_n-8\00000000000000000352.log ->
\tmp\kafka-logs\lt_backend_n-8\00000000000000000352.log.deleted: The process
cannot access the file because it is being used by another process.
at sun.nio.fs.WindowsException.translateToIOException(Unknown
Source)
at sun.nio.fs.WindowsException.rethrowAsIOException(Unknown
Source)
at sun.nio.fs.WindowsFileCopy.move(Unknown Source)
at sun.nio.fs.WindowsFileSystemProvider.move(Unknown Source)
at java.nio.file.Files.move(Unknown Source)
at
org.apache.kafka.common.utils.Utils.atomicMoveWithFallback(Utils.java:708)
... 31 more
> The kafka broker cannot delete the old log files after the configured time
> --------------------------------------------------------------------------
>
> Key: KAFKA-1194
> URL: https://issues.apache.org/jira/browse/KAFKA-1194
> Project: Kafka
> Issue Type: Bug
> Components: log
> Affects Versions: 0.8.1
> Environment: window
> Reporter: Tao Qin
> Priority: Critical
> Labels: features, patch
> Attachments: KAFKA-1194.patch, kafka-1194-v1.patch,
> kafka-1194-v2.patch, screenshot-1.png, Untitled.jpg
>
> Original Estimate: 72h
> Remaining Estimate: 72h
>
> We tested it in windows environment, and set the log.retention.hours to 24
> hours.
> # The minimum age of a log file to be eligible for deletion
> log.retention.hours=24
> After several days, the kafka broker still cannot delete the old log file.
> And we get the following exceptions:
> [2013-12-19 01:57:38,528] ERROR Uncaught exception in scheduled task
> 'kafka-log-retention' (kafka.utils.KafkaScheduler)
> kafka.common.KafkaStorageException: Failed to change the log file suffix from
> to .deleted for log segment 1516723
> at kafka.log.LogSegment.changeFileSuffixes(LogSegment.scala:249)
> at kafka.log.Log.kafka$log$Log$$asyncDeleteSegment(Log.scala:638)
> at kafka.log.Log.kafka$log$Log$$deleteSegment(Log.scala:629)
> at kafka.log.Log$$anonfun$deleteOldSegments$1.apply(Log.scala:418)
> at kafka.log.Log$$anonfun$deleteOldSegments$1.apply(Log.scala:418)
> at
> scala.collection.LinearSeqOptimized$class.foreach(LinearSeqOptimized.scala:59)
> at scala.collection.immutable.List.foreach(List.scala:76)
> at kafka.log.Log.deleteOldSegments(Log.scala:418)
> at
> kafka.log.LogManager.kafka$log$LogManager$$cleanupExpiredSegments(LogManager.scala:284)
> at
> kafka.log.LogManager$$anonfun$cleanupLogs$3.apply(LogManager.scala:316)
> at
> kafka.log.LogManager$$anonfun$cleanupLogs$3.apply(LogManager.scala:314)
> at
> scala.collection.TraversableLike$WithFilter$$anonfun$foreach$1.apply(TraversableLike.scala:743)
> at scala.collection.Iterator$class.foreach(Iterator.scala:772)
> at
> scala.collection.JavaConversions$JIteratorWrapper.foreach(JavaConversions.scala:573)
> at scala.collection.IterableLike$class.foreach(IterableLike.scala:73)
> at
> scala.collection.JavaConversions$JListWrapper.foreach(JavaConversions.scala:615)
> at
> scala.collection.TraversableLike$WithFilter.foreach(TraversableLike.scala:742)
> at kafka.log.LogManager.cleanupLogs(LogManager.scala:314)
> at
> kafka.log.LogManager$$anonfun$startup$1.apply$mcV$sp(LogManager.scala:143)
> at kafka.utils.KafkaScheduler$$anon$1.run(KafkaScheduler.scala:100)
> at
> java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471)
> at java.util.concurrent.FutureTask.runAndReset(FutureTask.java:304)
> at
> java.util.concurrent.ScheduledThreadPoolExecutor$ScheduledFutureTask.access$301(ScheduledThreadPoolExecutor.java:178)
> at
> java.util.concurrent.ScheduledThreadPoolExecutor$ScheduledFutureTask.run(ScheduledThreadPoolExecutor.java:293)
> at
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:724)
> I think this error happens because kafka tries to rename the log file when it
> is still opened. So we should close the file first before rename.
> The index file uses a special data structure, the MappedByteBuffer. Javadoc
> describes it as:
> A mapped byte buffer and the file mapping that it represents remain valid
> until the buffer itself is garbage-collected.
> Fortunately, I find a forceUnmap function in kafka code, and perhaps it can
> be used to free the MappedByteBuffer.
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
