[jira] [Commented] (KAFKA-4039) Exit Strategy: using exceptions instead of inline invocation of exit/halt

[ https://issues.apache.org/jira/browse/KAFKA-4039?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15721224#comment-15721224 ] Maysam Yabandeh commented on KAFKA-4039: I am afraid I do not have much free cycle

[jira] [Commented] (KAFKA-3410) Unclean leader election and "Halting because log truncation is not allowed"

[ https://issues.apache.org/jira/browse/KAFKA-3410?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15450881#comment-15450881 ] Maysam Yabandeh commented on KAFKA-3410: [~wushujames] I do not think KAFKA-3924 i

[jira] [Commented] (KAFKA-4039) Exit Strategy: using exceptions instead of inline invocation of exit/halt

[ https://issues.apache.org/jira/browse/KAFKA-4039?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15423346#comment-15423346 ] Maysam Yabandeh commented on KAFKA-4039: Certainly. I will submit a patch soon. >

[jira] [Commented] (KAFKA-4039) Exit Strategy: using exceptions instead of inline invocation of exit/halt

[ https://issues.apache.org/jira/browse/KAFKA-4039?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15423311#comment-15423311 ] Maysam Yabandeh commented on KAFKA-4039: Revert is certainly an option but I am no

[jira] [Commented] (KAFKA-3924) Data loss due to halting when LEO is larger than leader's LEO

[ https://issues.apache.org/jira/browse/KAFKA-3924?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15420455#comment-15420455 ] Maysam Yabandeh commented on KAFKA-3924: Thanks [~ijuma]. I created KAFKA-4039 to

[jira] [Created] (KAFKA-4039) Exit Strategy: using exceptions instead of inline invocation of exit/halt

Maysam Yabandeh created KAFKA-4039: -- Summary: Exit Strategy: using exceptions instead of inline invocation of exit/halt Key: KAFKA-4039 URL: https://issues.apache.org/jira/browse/KAFKA-4039 Project:

[jira] [Commented] (KAFKA-3924) Data loss due to halting when LEO is larger than leader's LEO

[ https://issues.apache.org/jira/browse/KAFKA-3924?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15420049#comment-15420049 ] Maysam Yabandeh commented on KAFKA-3924: Thanks [~aozeritsky]. That makes sense.

[jira] [Commented] (KAFKA-3924) Data loss due to halting when LEO is larger than leader's LEO

[ https://issues.apache.org/jira/browse/KAFKA-3924?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15420026#comment-15420026 ] Maysam Yabandeh commented on KAFKA-3924: Thanks [~aozeritsky] Let me run my unders

[jira] [Commented] (KAFKA-3924) Data loss due to halting when LEO is larger than leader's LEO

[ https://issues.apache.org/jira/browse/KAFKA-3924?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15420004#comment-15420004 ] Maysam Yabandeh commented on KAFKA-3924: Thanks [~aozeritsky]. I am not sure if I

[jira] [Updated] (KAFKA-3924) Data loss due to halting when LEO is larger than leader's LEO

[ https://issues.apache.org/jira/browse/KAFKA-3924?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Maysam Yabandeh updated KAFKA-3924: --- Status: Patch Available (was: Open) Submitting a simple patch that replaces halt with exit, w

[jira] [Updated] (KAFKA-3924) Data loss due to halting when LEO is larger than leader's LEO

[ https://issues.apache.org/jira/browse/KAFKA-3924?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Maysam Yabandeh updated KAFKA-3924: --- Description: Currently the follower broker panics when its LEO is larger than its leader's LE

[jira] [Commented] (KAFKA-3693) Lost highwatermark at broker start-up

[ https://issues.apache.org/jira/browse/KAFKA-3693?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15381457#comment-15381457 ] Maysam Yabandeh commented on KAFKA-3693: Thanks [~aozeritsky]. I linked the issue.

[jira] [Updated] (KAFKA-3693) Lost highwatermark at broker start-up

[ https://issues.apache.org/jira/browse/KAFKA-3693?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Maysam Yabandeh updated KAFKA-3693: --- Summary: Lost highwatermark at broker start-up (was: Race condition between highwatermark-che

[jira] [Resolved] (KAFKA-3963) Missing messages from the controller to brokers

[ https://issues.apache.org/jira/browse/KAFKA-3963?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Maysam Yabandeh resolved KAFKA-3963. Resolution: Invalid > Missing messages from the controller to brokers >

[jira] [Commented] (KAFKA-3963) Missing messages from the controller to brokers

[ https://issues.apache.org/jira/browse/KAFKA-3963?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15376065#comment-15376065 ] Maysam Yabandeh commented on KAFKA-3963: Thanks [~ijuma]. Yeah when reading the co

[jira] [Created] (KAFKA-3964) Metadata update requests are sometimes received after LeaderAndIsrRequests

Maysam Yabandeh created KAFKA-3964: -- Summary: Metadata update requests are sometimes received after LeaderAndIsrRequests Key: KAFKA-3964 URL: https://issues.apache.org/jira/browse/KAFKA-3964 Project:

[jira] [Created] (KAFKA-3963) Missing messages from the controller to brokers

Maysam Yabandeh created KAFKA-3963: -- Summary: Missing messages from the controller to brokers Key: KAFKA-3963 URL: https://issues.apache.org/jira/browse/KAFKA-3963 Project: Kafka Issue Type:

[jira] [Commented] (KAFKA-1120) Controller could miss a broker state change

[ https://issues.apache.org/jira/browse/KAFKA-1120?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15373872#comment-15373872 ] Maysam Yabandeh commented on KAFKA-1120: [~junrao] This is currently a major pain

[jira] [Created] (KAFKA-3944) After the broker restart, fetchers stopped due to a delayed controlled shutdown message

Maysam Yabandeh created KAFKA-3944: -- Summary: After the broker restart, fetchers stopped due to a delayed controlled shutdown message Key: KAFKA-3944 URL: https://issues.apache.org/jira/browse/KAFKA-3944

[jira] [Commented] (KAFKA-3410) Unclean leader election and "Halting because log truncation is not allowed"

[ https://issues.apache.org/jira/browse/KAFKA-3410?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15362701#comment-15362701 ] Maysam Yabandeh commented on KAFKA-3410: We ran into this problem again and this t

[jira] [Created] (KAFKA-3924) Data loss due to halting when LEO is larger than leader's LEO

Maysam Yabandeh created KAFKA-3924: -- Summary: Data loss due to halting when LEO is larger than leader's LEO Key: KAFKA-3924 URL: https://issues.apache.org/jira/browse/KAFKA-3924 Project: Kafka

[jira] [Commented] (KAFKA-3861) Shrunk ISR before leader crash makes the partition unavailable

[ https://issues.apache.org/jira/browse/KAFKA-3861?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15338804#comment-15338804 ] Maysam Yabandeh commented on KAFKA-3861: Thanks [~wushujames]. I left a comment on

[jira] [Commented] (KAFKA-3410) Unclean leader election and "Halting because log truncation is not allowed"

[ https://issues.apache.org/jira/browse/KAFKA-3410?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15338801#comment-15338801 ] Maysam Yabandeh commented on KAFKA-3410: Seems that KAFKA-3861 is a slightly modif

[jira] [Updated] (KAFKA-3861) Shrunk ISR before leader crash makes the partition unavailable

[ https://issues.apache.org/jira/browse/KAFKA-3861?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Maysam Yabandeh updated KAFKA-3861: --- Description: We observed a case that the leader experienced a crash and lost its in-memory da

[jira] [Updated] (KAFKA-3861) Shrunk ISR before leader crash makes the partition unavailable

[ https://issues.apache.org/jira/browse/KAFKA-3861?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Maysam Yabandeh updated KAFKA-3861: --- Description: We observed a case that the leader experienced a crash and lost its in-memory da

[jira] [Created] (KAFKA-3861) Shrunk ISR before leader crash makes the partition unavailable

Maysam Yabandeh created KAFKA-3861: -- Summary: Shrunk ISR before leader crash makes the partition unavailable Key: KAFKA-3861 URL: https://issues.apache.org/jira/browse/KAFKA-3861 Project: Kafka

[jira] [Commented] (KAFKA-3693) Race condition between highwatermark-checkpoint thread and handleLeaderAndIsrRequest at broker start-up

[ https://issues.apache.org/jira/browse/KAFKA-3693?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15336241#comment-15336241 ] Maysam Yabandeh commented on KAFKA-3693: [~junrao] I am thinking of a panic reacti

[jira] [Commented] (KAFKA-3693) Race condition between highwatermark-checkpoint thread and handleLeaderAndIsrRequest at broker start-up

[ https://issues.apache.org/jira/browse/KAFKA-3693?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15332618#comment-15332618 ] Maysam Yabandeh commented on KAFKA-3693: Thinking more about this, the complexity

[jira] [Commented] (KAFKA-3693) Race condition between highwatermark-checkpoint thread and handleLeaderAndIsrRequest at broker start-up

[ https://issues.apache.org/jira/browse/KAFKA-3693?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15325563#comment-15325563 ] Maysam Yabandeh commented on KAFKA-3693: [~junrao] oh yeah that makes sense. Thank

[jira] [Comment Edited] (KAFKA-3693) Race condition between highwatermark-checkpoint thread and handleLeaderAndIsrRequest at broker start-up

[ https://issues.apache.org/jira/browse/KAFKA-3693?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15319273#comment-15319273 ] Maysam Yabandeh edited comment on KAFKA-3693 at 6/10/16 4:00 AM: ---

[jira] [Comment Edited] (KAFKA-3693) Race condition between highwatermark-checkpoint thread and handleLeaderAndIsrRequest at broker start-up

[ https://issues.apache.org/jira/browse/KAFKA-3693?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15316991#comment-15316991 ] Maysam Yabandeh edited comment on KAFKA-3693 at 6/10/16 3:57 AM: ---

[jira] [Comment Edited] (KAFKA-3693) Race condition between highwatermark-checkpoint thread and handleLeaderAndIsrRequest at broker start-up

[ https://issues.apache.org/jira/browse/KAFKA-3693?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15315055#comment-15315055 ] Maysam Yabandeh edited comment on KAFKA-3693 at 6/10/16 3:54 AM: ---

[jira] [Commented] (KAFKA-3693) Race condition between highwatermark-checkpoint thread and handleLeaderAndIsrRequest at broker start-up

[ https://issues.apache.org/jira/browse/KAFKA-3693?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15323801#comment-15323801 ] Maysam Yabandeh commented on KAFKA-3693: [~junrao] Yes, you seem to be right. The

[jira] [Commented] (KAFKA-3693) Race condition between highwatermark-checkpoint thread and handleLeaderAndIsrRequest at broker start-up

[ https://issues.apache.org/jira/browse/KAFKA-3693?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15319273#comment-15319273 ] Maysam Yabandeh commented on KAFKA-3693: Thanks for the grep hints [~junrao]. Acco

[jira] [Commented] (KAFKA-3693) Race condition between highwatermark-checkpoint thread and handleLeaderAndIsrRequest at broker start-up

[ https://issues.apache.org/jira/browse/KAFKA-3693?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15316991#comment-15316991 ] Maysam Yabandeh commented on KAFKA-3693: My apology. That was a copy-paste error.

[jira] [Commented] (KAFKA-3693) Race condition between highwatermark-checkpoint thread and handleLeaderAndIsrRequest at broker start-up

[ https://issues.apache.org/jira/browse/KAFKA-3693?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15315112#comment-15315112 ] Maysam Yabandeh commented on KAFKA-3693: As mentioned above: bq. We managed to rep

[jira] [Commented] (KAFKA-3693) Race condition between highwatermark-checkpoint thread and handleLeaderAndIsrRequest at broker start-up

[ https://issues.apache.org/jira/browse/KAFKA-3693?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15315055#comment-15315055 ] Maysam Yabandeh commented on KAFKA-3693: Thanks [~junrao]. My understanding is tha

[jira] [Commented] (KAFKA-3693) Race condition between highwatermark-checkpoint thread and handleLeaderAndIsrRequest at broker start-up

[ https://issues.apache.org/jira/browse/KAFKA-3693?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15313379#comment-15313379 ] Maysam Yabandeh commented on KAFKA-3693: Thanks for looking into this [~junrao] I

[jira] [Commented] (KAFKA-3693) Race condition between highwatermark-checkpoint thread and handleLeaderAndIsrRequest at broker start-up

[ https://issues.apache.org/jira/browse/KAFKA-3693?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15307932#comment-15307932 ] Maysam Yabandeh commented on KAFKA-3693: [~junrao] Any thoughts? > Race condition

[jira] [Commented] (KAFKA-3693) Race condition between highwatermark-checkpoint thread and handleLeaderAndIsrRequest at broker start-up

[ https://issues.apache.org/jira/browse/KAFKA-3693?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15280411#comment-15280411 ] Maysam Yabandeh commented on KAFKA-3693: [~junrao] based on controller logs the fo

[jira] [Commented] (KAFKA-3693) Race condition between highwatermark-checkpoint thread and handleLeaderAndIsrRequest at broker start-up

[ https://issues.apache.org/jira/browse/KAFKA-3693?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15279334#comment-15279334 ] Maysam Yabandeh commented on KAFKA-3693: Thanks [~junrao]. We managed to reproduce

[jira] [Created] (KAFKA-3693) Race condition between highwatermark-checkpoint thread and handleLeaderAndIsrRequest at broker start-up

Maysam Yabandeh created KAFKA-3693: -- Summary: Race condition between highwatermark-checkpoint thread and handleLeaderAndIsrRequest at broker start-up Key: KAFKA-3693 URL: https://issues.apache.org/jira/browse/KAF

[jira] [Commented] (KAFKA-3493) Replica fetcher load is not balanced over fetcher threads

[ https://issues.apache.org/jira/browse/KAFKA-3493?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15227557#comment-15227557 ] Maysam Yabandeh commented on KAFKA-3493: [~nehanarkhede], git suggests that you ha

[jira] [Updated] (KAFKA-3493) Replica fetcher load is not balanced over fetcher threads

[ https://issues.apache.org/jira/browse/KAFKA-3493?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Maysam Yabandeh updated KAFKA-3493: --- Description: The replicas are not evenly distributed among the fetcher threads. This has caus

[jira] [Created] (KAFKA-3493) Replica fetcher load is not balanced over fetcher threads

Maysam Yabandeh created KAFKA-3493: -- Summary: Replica fetcher load is not balanced over fetcher threads Key: KAFKA-3493 URL: https://issues.apache.org/jira/browse/KAFKA-3493 Project: Kafka I

[jira] [Updated] (KAFKA-3428) Remove metadata sync bottleneck from mirrormaker's producer

[ https://issues.apache.org/jira/browse/KAFKA-3428?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Maysam Yabandeh updated KAFKA-3428: --- Reviewer: Ismael Juma Fix Version/s: 0.10.0.0 Affects Version/s: 0.9.0.1

[jira] [Commented] (KAFKA-3428) Remove metadata sync bottleneck from mirrormaker's producer

[ https://issues.apache.org/jira/browse/KAFKA-3428?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15203615#comment-15203615 ] Maysam Yabandeh commented on KAFKA-3428: I believe volatile variable takes care of

[jira] [Commented] (KAFKA-3428) Remove metadata sync bottleneck from mirrormaker's producer

[ https://issues.apache.org/jira/browse/KAFKA-3428?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15203578#comment-15203578 ] Maysam Yabandeh commented on KAFKA-3428: Sure. Will do that. bq. By the way, what

[jira] [Commented] (KAFKA-3428) Remove metadata sync bottleneck from mirrormaker's producer

[ https://issues.apache.org/jira/browse/KAFKA-3428?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15203568#comment-15203568 ] Maysam Yabandeh commented on KAFKA-3428: The hardware spec needs an auditing proce

[jira] [Created] (KAFKA-3428) Remove metadata sync bottleneck from mirrormaker's producer

Maysam Yabandeh created KAFKA-3428: -- Summary: Remove metadata sync bottleneck from mirrormaker's producer Key: KAFKA-3428 URL: https://issues.apache.org/jira/browse/KAFKA-3428 Project: Kafka