You are viewing a plain text version of this content. The canonical link for it is here.
Posted to hdfs-dev@hadoop.apache.org by "郑锴(铁杰)" <zh...@alibaba-inc.com> on 2018/02/09 01:47:18 UTC
回复：[DISCUSS] Meetup for HDFS tests and build infra
Thanks Chris for driving on this.
>>I'm looking at you, TestDFSStripedOutputStreamWithFailure ...AFAIK and IMO, it's pretty hard to get all the test cases stably running given the limitation of MiniDFSCluster, and if we'd agree on that, we could remove these cases as unit tests and cover them in integration tests instead using a true cluster, like based on k8s infra. We're lacking basic facility infra env and tools to get most of the complicated functionalities well tested and covered, so let's avoid too much complicated tests. Fixing of such tests should definitely help and be appreciated.
Regards,Kai
------------------------------------------------------------------发件人：Chris Douglas <cd...@apache.org>发送时间：2018年2月8日(星期四) 08:39收件人：Hdfs-dev <hd...@hadoop.apache.org>主 题：Re: [DISCUSS] Meetup for HDFS tests and build infra
Created a poll [1] to inform scheduling. -C
[1]: https://doodle.com/poll/r22znitzae9apfbf
On Tue, Feb 6, 2018 at 3:09 PM, Chris Douglas <cd...@apache.org> wrote:
> The HDFS build is not healthy. Many of the unit tests aren't actually
> run in Jenkins due to resource exhaustion, haven't been updated since
> build/test/data was the test temp dir, or are chronically unstable
> (I'm looking at you, TestDFSStripedOutputStreamWithFailure). The
> situation has deteriorated slowly, but we can't confidently merge
> patches, let alone significant features, when our CI infra is in this
> state.
>
> How would folks feel about a half to full-day meetup to work through
> patches improving this, specifically? We can improve tests,
> troubleshoot the build, and rev/commit existing patches. It would
> require some preparation, so the simultaneous attention is productive
> and not a coordination bottleneck. I started a wiki page for this [1],
> please add to it.
>
> If enough people can make time for this, say in 2-3 weeks, the project
> would certainly benefit. -C
>
> [1]: https://s.apache.org/ng3C
---------------------------------------------------------------------
To unsubscribe, e-mail: hdfs-dev-unsubscribe@hadoop.apache.org
For additional commands, e-mail: hdfs-dev-help@hadoop.apache.org
Re: [DISCUSS] Meetup for HDFS tests and build infra
Posted by Chris Douglas <cd...@apache.org>.
Correction: 3/12 or 3/13, as in March 12 or 13th. -C
On Tue, Feb 20, 2018 at 3:59 PM, Chris Douglas <cd...@apache.org> wrote:
> Looking at the poll [1], it looks like 12/12 or 12/13 would be the
> best day to do this. If you haven't posted your availability and would
> like to participate, please fill this out soon.
>
> We'll work on some common space in the bay area, but we'll also open a
> channel for folks who can't attend in-person. -C
>
> [1]: https://doodle.com/poll/r22znitzae9apfbf
>
>
> On Fri, Feb 9, 2018 at 1:45 PM, Chris Douglas <cd...@apache.org> wrote:
>> On Thu, Feb 8, 2018 at 5:47 PM, 郑锴(铁杰) <zh...@alibaba-inc.com> wrote:
>>>>>I'm looking at you, TestDFSStripedOutputStreamWithFailure ...
>>> AFAIK and IMO, it's pretty hard to get all the test cases stably running
>>> given the limitation of MiniDFSCluster, and if we'd agree on that, we could
>>> remove these cases as unit tests and cover them in integration tests instead
>>> using a true cluster, like based on k8s infra.
>>
>> Since its inception, the Mini*Clusters have made it much easier to
>> write unit tests (good!), but these tests take more time and resources
>> than fine-grained tests (unfortunate) and they're often unreliable
>> (bad). As we see in issues like HDFS-12711, the resource problem seems
>> to harm reliability across the entire suite of tests (dire).
>>
>> Running integration tests with our CI is helpful, but perhaps we
>> should separate the Mini*Cluster tests and/or press contributors to
>> write lighter unit tests for new functionality. -C
>>
>>> We're lacking basic facility
>>> infra env and tools to get most of the complicated functionalities well
>>> tested and covered, so let's avoid too much complicated tests. Fixing of
>>> such tests should definitely help and be appreciated.
>>>
>>> Regards,
>>> Kai
>>>
>>> ------------------------------------------------------------------
>>> 发件人：Chris Douglas <cd...@apache.org>
>>> 发送时间：2018年2月8日(星期四) 08:39
>>> 收件人：Hdfs-dev <hd...@hadoop.apache.org>
>>> 主 题：Re: [DISCUSS] Meetup for HDFS tests and build infra
>>>
>>> Created a poll [1] to inform scheduling. -C
>>>
>>> [1]: https://doodle.com/poll/r22znitzae9apfbf
>>>
>>> On Tue, Feb 6, 2018 at 3:09 PM, Chris Douglas <cd...@apache.org> wrote:
>>>> The HDFS build is not healthy. Many of the unit tests aren't actually
>>>> run in Jenkins due to resource exhaustion, haven't been updated since
>>>> build/test/data was the test temp dir, or are chronically unstable
>>>> (I'm looking at you, TestDFSStripedOutputStreamWithFailure). The
>>>> situation has deteriorated slowly, but we can't confidently merge
>>>> patches, let alone significant features, when our CI infra is in this
>>>> state.
>>>>
>>>> How would folks feel about a half to full-day meetup to work through
>>>> patches improving this, specifically? We can improve tests,
>>>> troubleshoot the build, and rev/commit existing patches. It would
>>>> require some preparation, so the simultaneous attention is productive
>>>> and not a coordination bottleneck. I started a wiki page for this [1],
>>>> please add to it.
>>>>
>>>> If enough people can make time for this, say in 2-3 weeks, the project
>>>> would certainly benefit. -C
>>>>
>>>> [1]: https://s.apache.org/ng3C
>>>
>>> ---------------------------------------------------------------------
>>> To unsubscribe, e-mail: hdfs-dev-unsubscribe@hadoop.apache.org
>>> For additional commands, e-mail: hdfs-dev-help@hadoop.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: hdfs-dev-unsubscribe@hadoop.apache.org
For additional commands, e-mail: hdfs-dev-help@hadoop.apache.org
Re: [DISCUSS] Meetup for HDFS tests and build infra
Posted by Chris Douglas <cd...@apache.org>.
Looking at the poll [1], it looks like 12/12 or 12/13 would be the
best day to do this. If you haven't posted your availability and would
like to participate, please fill this out soon.
We'll work on some common space in the bay area, but we'll also open a
channel for folks who can't attend in-person. -C
[1]: https://doodle.com/poll/r22znitzae9apfbf
On Fri, Feb 9, 2018 at 1:45 PM, Chris Douglas <cd...@apache.org> wrote:
> On Thu, Feb 8, 2018 at 5:47 PM, 郑锴(铁杰) <zh...@alibaba-inc.com> wrote:
>>>>I'm looking at you, TestDFSStripedOutputStreamWithFailure ...
>> AFAIK and IMO, it's pretty hard to get all the test cases stably running
>> given the limitation of MiniDFSCluster, and if we'd agree on that, we could
>> remove these cases as unit tests and cover them in integration tests instead
>> using a true cluster, like based on k8s infra.
>
> Since its inception, the Mini*Clusters have made it much easier to
> write unit tests (good!), but these tests take more time and resources
> than fine-grained tests (unfortunate) and they're often unreliable
> (bad). As we see in issues like HDFS-12711, the resource problem seems
> to harm reliability across the entire suite of tests (dire).
>
> Running integration tests with our CI is helpful, but perhaps we
> should separate the Mini*Cluster tests and/or press contributors to
> write lighter unit tests for new functionality. -C
>
>> We're lacking basic facility
>> infra env and tools to get most of the complicated functionalities well
>> tested and covered, so let's avoid too much complicated tests. Fixing of
>> such tests should definitely help and be appreciated.
>>
>> Regards,
>> Kai
>>
>> ------------------------------------------------------------------
>> 发件人：Chris Douglas <cd...@apache.org>
>> 发送时间：2018年2月8日(星期四) 08:39
>> 收件人：Hdfs-dev <hd...@hadoop.apache.org>
>> 主 题：Re: [DISCUSS] Meetup for HDFS tests and build infra
>>
>> Created a poll [1] to inform scheduling. -C
>>
>> [1]: https://doodle.com/poll/r22znitzae9apfbf
>>
>> On Tue, Feb 6, 2018 at 3:09 PM, Chris Douglas <cd...@apache.org> wrote:
>>> The HDFS build is not healthy. Many of the unit tests aren't actually
>>> run in Jenkins due to resource exhaustion, haven't been updated since
>>> build/test/data was the test temp dir, or are chronically unstable
>>> (I'm looking at you, TestDFSStripedOutputStreamWithFailure). The
>>> situation has deteriorated slowly, but we can't confidently merge
>>> patches, let alone significant features, when our CI infra is in this
>>> state.
>>>
>>> How would folks feel about a half to full-day meetup to work through
>>> patches improving this, specifically? We can improve tests,
>>> troubleshoot the build, and rev/commit existing patches. It would
>>> require some preparation, so the simultaneous attention is productive
>>> and not a coordination bottleneck. I started a wiki page for this [1],
>>> please add to it.
>>>
>>> If enough people can make time for this, say in 2-3 weeks, the project
>>> would certainly benefit. -C
>>>
>>> [1]: https://s.apache.org/ng3C
>>
>> ---------------------------------------------------------------------
>> To unsubscribe, e-mail: hdfs-dev-unsubscribe@hadoop.apache.org
>> For additional commands, e-mail: hdfs-dev-help@hadoop.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: hdfs-dev-unsubscribe@hadoop.apache.org
For additional commands, e-mail: hdfs-dev-help@hadoop.apache.org
Re: [DISCUSS] Meetup for HDFS tests and build infra
Posted by Chris Douglas <cd...@apache.org>.
On Thu, Feb 8, 2018 at 5:47 PM, 郑锴(铁杰) <zh...@alibaba-inc.com> wrote:
>>>I'm looking at you, TestDFSStripedOutputStreamWithFailure ...
> AFAIK and IMO, it's pretty hard to get all the test cases stably running
> given the limitation of MiniDFSCluster, and if we'd agree on that, we could
> remove these cases as unit tests and cover them in integration tests instead
> using a true cluster, like based on k8s infra.
Since its inception, the Mini*Clusters have made it much easier to
write unit tests (good!), but these tests take more time and resources
than fine-grained tests (unfortunate) and they're often unreliable
(bad). As we see in issues like HDFS-12711, the resource problem seems
to harm reliability across the entire suite of tests (dire).
Running integration tests with our CI is helpful, but perhaps we
should separate the Mini*Cluster tests and/or press contributors to
write lighter unit tests for new functionality. -C
> We're lacking basic facility
> infra env and tools to get most of the complicated functionalities well
> tested and covered, so let's avoid too much complicated tests. Fixing of
> such tests should definitely help and be appreciated.
>
> Regards,
> Kai
>
> ------------------------------------------------------------------
> 发件人：Chris Douglas <cd...@apache.org>
> 发送时间：2018年2月8日(星期四) 08:39
> 收件人：Hdfs-dev <hd...@hadoop.apache.org>
> 主 题：Re: [DISCUSS] Meetup for HDFS tests and build infra
>
> Created a poll [1] to inform scheduling. -C
>
> [1]: https://doodle.com/poll/r22znitzae9apfbf
>
> On Tue, Feb 6, 2018 at 3:09 PM, Chris Douglas <cd...@apache.org> wrote:
>> The HDFS build is not healthy. Many of the unit tests aren't actually
>> run in Jenkins due to resource exhaustion, haven't been updated since
>> build/test/data was the test temp dir, or are chronically unstable
>> (I'm looking at you, TestDFSStripedOutputStreamWithFailure). The
>> situation has deteriorated slowly, but we can't confidently merge
>> patches, let alone significant features, when our CI infra is in this
>> state.
>>
>> How would folks feel about a half to full-day meetup to work through
>> patches improving this, specifically? We can improve tests,
>> troubleshoot the build, and rev/commit existing patches. It would
>> require some preparation, so the simultaneous attention is productive
>> and not a coordination bottleneck. I started a wiki page for this [1],
>> please add to it.
>>
>> If enough people can make time for this, say in 2-3 weeks, the project
>> would certainly benefit. -C
>>
>> [1]: https://s.apache.org/ng3C
>
> ---------------------------------------------------------------------
> To unsubscribe, e-mail: hdfs-dev-unsubscribe@hadoop.apache.org
> For additional commands, e-mail: hdfs-dev-help@hadoop.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: hdfs-dev-unsubscribe@hadoop.apache.org
For additional commands, e-mail: hdfs-dev-help@hadoop.apache.org