Zhanxiang (Patrick) Huang created KAFKA-8921:
Summary: Avoid excessive info logs in the client side for
incremental fetch
Key: KAFKA-8921
URL: https://issues.apache.org/jira/browse/KAFKA-8921
Zhanxiang (Patrick) Huang created KAFKA-8668:
Summary: Improve broker shutdown time
Key: KAFKA-8668
URL: https://issues.apache.org/jira/browse/KAFKA-8668
Project: Kafka
Issue
Zhanxiang (Patrick) Huang created KAFKA-8667:
Summary: Improve leadership transition time
Key: KAFKA-8667
URL: https://issues.apache.org/jira/browse/KAFKA-8667
Project: Kafka
Zhanxiang (Patrick) Huang created KAFKA-8571:
Summary: Not complete delayed produce requests when processing
StopReplicaRequest causing high produce latency for acks=all
Key: KAFKA-8571
URL: https
Zhanxiang (Patrick) Huang created KAFKA-8069:
Summary: Committed offsets get cleaned up right after the
coordinator loading them back from __consumer_offsets in broker with old
inter-broker protocol version (<
Zhanxiang (Patrick) Huang created KAFKA-8066:
Summary: ReplicaFetcherThread fails to startup because of failing
to register the metric.
Key: KAFKA-8066
URL: https://issues.apache.org/jira/browse/KAFKA
Zhanxiang (Patrick) Huang created KAFKA-7854:
Summary: Behavior change in controller picking up partition
reassignment tasks since 1.1.0
Key: KAFKA-7854
URL: https://issues.apache.org/jira/browse
Count
are very specific to one type of request and we should make the pre-define
info more generic if we choose to go for this route.
Best,
Zhanxiang (Patrick) Huang
From: Dong Lin
Sent: Saturday, November 17, 2018 18:37
To: dev
Subject: Re: [DISCUSS] KIP-388 Add obs
,
Zhanxiang (Patrick) Huang
From: Becket Qin
Sent: Monday, November 12, 2018 21:56
To: Dong Lin
Cc: dev
Subject: Re: [DISCUSS] KIP-380: Detect outdated control requests and bounced
brokers using broker generation
Hi Dong,
That is a good point. But I think the
[
https://issues.apache.org/jira/browse/KAFKA-7452?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Zhanxiang (Patrick) Huang resolved KAFKA-7452.
--
Resolution: Duplicate
KAFKA-7557 fixed this.
> Deleting snaps
need and will not do anything
for STALE_BROKER_EPOCH response. Thanks for pointing it out.
Thanks,
Zhanxiang (Patrick) Huang
From: Becket Qin
Sent: Monday, November 12, 2018 6:46
To: dev
Subject: Re: [DISCUSS] KIP-380: Detect outdated control requests and bounced
as public interface change, I
have updated the original KIP accordingly to include this change. Feel free to
comment if there is any concern.
Thanks,
Zhanxiang (Patrick) Huang
____
From: Patrick Huang
Sent: Tuesday, October 23, 2018 6:20
To: Jun Rao; dev@kafka.
all!
Best,
Zhanxiang (Patrick) Huang
From: Harsha Chintalapani
Sent: Tuesday, October 30, 2018 16:10
To: Patrick Huang; dev@kafka.apache.org
Cc: dev@kafka.apache.org
Subject: Re: [VOTE] KIP-380: Detect outdated control requests and bounced
brokers using broker
Hi Jun,
Sure. I already updated the KIP. Thanks!
Best,
Zhanxiang (Patrick) Huang
From: Jun Rao
Sent: Wednesday, October 24, 2018 14:17
To: dev
Subject: Re: [VOTE] KIP-380: Detect outdated control requests and bounced
brokers using broker generation
Hi
Zhanxiang (Patrick) Huang created KAFKA-7537:
Summary: Only include live brokers in the UpdateMetadataRequest
sent to existing brokers if there is no change in the partition states
Key: KAFKA-7537
URL
@%3Cdev.kafka.apache.org%3E
Best,
Zhanxiang (Patrick) Huang
From: Jun Rao
Sent: Monday, October 22, 2018 21:31
To: dev@kafka.apache.org
Subject: Re: [DISCUSS] KIP-380: Detect outdated control requests and bounced
brokers using broker generation
Hi, Patrick,
Yes
,
Zhanxiang (Patrick) Huang
From: Jun Rao
Sent: Monday, October 22, 2018 14:45
To: dev
Subject: Re: [DISCUSS] KIP-380: Detect outdated control requests and bounced
brokers using broker generation
Hi, Patrick,
There is another thing that may be worth considering
o-have optimization because the memory
footprint for the control requests hinders the controller from scaling up if we
have many topics with large partition counts.
cwiki.apache.org
Thanks,
Zhanxiang (Patrick) Huang
ted broker from receiving a
> partial replica list on the first LeaderAndIsr request because of this.
>
> Thanks,
>
> Jun
>
> On Wed, Oct 10, 2018 at 12:51 PM, Patrick Huang
> wrote:
>
> > Hey Stanislav,
> >
> > Sure. Thanks for your interest in this K
mize the flow by avoiding sending requests to a broker
if its broker generation is larger than the one in the controller context.
I will also update the KIP to clarify how it works for BrokerChangeEvent
processing in more detail.
Best,
Zhanxiang (Patrick) Huang
___
at I answer your questions. Feel free to follow up if I am missing
something.
Thanks,
Zhanxiang (Patrick) Huang
From: Stanislav Kozlovski
Sent: Wednesday, October 10, 2018 7:22
To: dev@kafka.apache.org
Subject: Re: [DISCUSS] KIP-380: Detect outdated control requests
+and+bounced+brokers+using+broker+generation
All comments are appreciated.
Best,
Zhanxiang (Patrick) Huang
Zhanxiang (Patrick) Huang created KAFKA-7464:
Summary: Fail to shutdown ReplicaManager during broker cleaned
shutdown
Key: KAFKA-7464
URL: https://issues.apache.org/jira/browse/KAFKA-7464
Zhanxiang (Patrick) Huang created KAFKA-7459:
Summary: Concurrency bug in updating RequestsPerSec metric
Key: KAFKA-7459
URL: https://issues.apache.org/jira/browse/KAFKA-7459
Project
Zhanxiang (Patrick) Huang created KAFKA-7452:
Summary: Deleting snapshot files after check-pointing log recovery
offsets can slow down replication when truncation happens
Key: KAFKA-7452
URL: https
Zhanxiang (Patrick) Huang created KAFKA-7283:
Summary: mmap indexes lazily and skip sanity check for segments
below recovery point
Key: KAFKA-7283
URL: https://issues.apache.org/jira/browse/KAFKA-7283
scenario, I think
it is safe to skip the sanity checks for segments below the recovery point to
speed up broker restart.
Best,
Zhanxiang (Patrick) Huang
From: Dong Lin
Sent: Saturday, July 21, 2018 3:45
To: dev
Subject: Re: [DISCUSS] KIP-263: Allow broker to
Zhanxiang (Patrick) Huang created KAFKA-7186:
Summary: Controller uses too much memory when sending out
UpdateMetadataRequest that can cause OutOfMemoryError
Key: KAFKA-7186
URL: https
28 matches
Mail list logo
