From: Christian Ehrhardt <christian.ehrhardt@canonical.com>
To: "Morten Brørup" <mb@smartsharesystems.com>
Cc: "dpdk stable" <stable@dpdk.org>,
"Konstantin Ananyev" <konstantin.ananyev@intel.com>,
"Konstantin Ananyev" <konstantin.v.ananyev@yandex.ru>,
"Kumara Parameshwaran" <kumaraparamesh92@gmail.com>,
"Lijun Ou" <oulijun@huawei.com>,
"Lior Margalit" <lmargalit@nvidia.com>,
"Long Li" <longli@microsoft.com>,
"Long Wu" <long.wu@corigine.com>,
"Mah Yock Gen" <yock.gen.mah@intel.com>,
"Mao YingMing" <maoyingming@baidu.com>,
"Matan Azrad" <matan@mellanox.com>,
"Matan Azrad" <matan@nvidia.com>,
"Mattias Rönnblom" <mattias.ronnblom@ericsson.com>,
"Maxime Coquelin" <maxime.coquelin@redhat.com>,
"Min Hu (Connor)" <humin29@huawei.com>,
"Nikhil Rao" <nikhil.rao@intel.com>,
"Niklas Soderlund" <niklas.soderlund@corigine.com>,
"Nithin Dabilpuram" <ndabilpuram@marvell.com>,
"Olivier Matz" <olivier.matz@6wind.com>,
"Ori Kam" <orika@nvidia.com>,
"Pablo de Lara" <pablo.de.lara.guarch@intel.com>,
"Paul M Stillwell Jr" <paul.m.stillwell.jr@intel.com>,
"Pavan Nikhilesh" <pbhagavatula@marvell.com>,
"Peng Zhang" <peng.zhang@corigine.com>,
"Qiming Yang" <qiming.yang@intel.com>,
"Qi Zhang" <qi.z.zhang@intel.com>,
"Radu Nicolau" <radu.nicolau@intel.com>,
"Raja Zidane" <rzidane@nvidia.com>,
"Remy Horton" <remy.horton@intel.com>,
"Rolf Neugebauer" <rolf.neugebauer@netronome.com>,
"Shahaf Shuler" <shahafs@mellanox.com>,
"Shally Verma" <shally.verma@caviumnetworks.com>,
"Shijith Thotton" <sthotton@marvell.com>,
"Shiqi Liu" <835703180@qq.com>, "Simei Su" <simei.su@intel.com>,
"Somnath Kotur" <somnath.kotur@broadcom.com>,
"Suanming Mou" <suanmingm@mellanox.com>,
"Sunila Sahu" <sunila.sahu@caviumnetworks.com>,
"Taripin Samuel" <samuel.taripin@intel.com>,
"Umesh Kartha" <umesh.kartha@caviumnetworks.com>,
"Usman Tanveer" <usman.tanveer@emumba.com>,
"Viacheslav Ovsiienko" <viacheslavo@nvidia.com>,
"Vladimir Medvedkin" <vladimir.medvedkin@intel.com>,
"Wei Hu (Xavier)" <xavier.huwei@huawei.com>,
"Wei Ling" <weix.ling@intel.com>,
"Wenwu Ma" <wenwux.ma@intel.com>,
"Wenzhuo Lu" <wenzhuo.lu@intel.com>,
"Yiding Zhou" <yidingx.zhou@intel.com>,
"Yisen Zhuang" <yisen.zhuang@huawei.com>,
"Yongseok Koh" <yskoh@mellanox.com>,
"Yuan Wang" <yuanx.wang@intel.com>
Subject: Re: please help backporting some patches to stable release 19.11.14
Date: Thu, 17 Nov 2022 07:27:29 +0100 [thread overview]
Message-ID: <CAATJJ0LW_E+ETWKw+xig0cnjoN0Q_kUHzrNPp_vYW6sLM674Bw@mail.gmail.com> (raw)
In-Reply-To: <98CBD80474FA8B44BF855DF32C47DC35D874C6@smartserver.smartshare.dk>
On Wed, Nov 16, 2022 at 11:45 AM Morten Brørup <mb@smartsharesystems.com> wrote:
>
> > From: christian.ehrhardt@canonical.com
> > Sent: Friday, 11 November 2022 12.48
>
> [...]
>
> > 459531c958 Morten Brørup mempool: fix cache flushing algorithm
> > a2833ecc5e Morten Brørup mempool: fix get objects from mempool with
> > cache
>
> These two patches fixes some performance issues for certain use cases. The affected use cases work without the patches, but don't get the improved performance.
>
> However, these patches change the inner workings of the mempool cache.
>
> And since some PMDs bypass the mempool API and interact directly with the mempool caches, there is a risk that applications do the same.
>
> Although these patches are relevant for the performance of the affected use cases, I fear that backporting them would introduce an unwanted risk of breaking PMDs and/or applications (generally, not just for the affected use cases).
Thanks for your thoughts, I completely agree.
Let us now backport them and keep -stable stable.
> For the common good, I prefer not backporting them. Anyone feel free to speak up if you disagree.
>
> We have a policy of not backporting performance improvements, and fixing a lack of performance could be interpreted as falling under this policy.
>
--
Christian Ehrhardt
Senior Staff Engineer, Ubuntu Server
Canonical Ltd
next prev parent reply other threads:[~2022-11-17 6:28 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20221111114814.1553136-1-christian.ehrhardt@canonical.com>
2022-11-14 9:57 ` Nicolau, Radu
2022-11-17 8:17 ` 答复: " Mao,Yingming
2022-11-17 8:19 ` Christian Ehrhardt
2022-11-16 10:45 ` Morten Brørup
2022-11-17 6:27 ` Christian Ehrhardt [this message]
2022-11-17 7:25 ` Christian Ehrhardt
2022-11-16 23:23 ` Mah, Yock Gen
2022-11-17 8:49 ` Christian Ehrhardt
2022-11-17 14:33 ` Niklas Soderlund
[not found] <20221116104124.2975325-1-christian.ehrhardt@canonical.com>
2022-11-22 10:57 ` Mattias Rönnblom
2022-11-22 11:35 ` Christian Ehrhardt
[not found] <20221111114803.1553104-1-christian.ehrhardt@canonical.com>
2022-12-01 4:11 ` lihuisong (C)
2022-12-01 6:36 ` Christian Ehrhardt
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=CAATJJ0LW_E+ETWKw+xig0cnjoN0Q_kUHzrNPp_vYW6sLM674Bw@mail.gmail.com \
--to=christian.ehrhardt@canonical.com \
--cc=835703180@qq.com \
--cc=humin29@huawei.com \
--cc=konstantin.ananyev@intel.com \
--cc=konstantin.v.ananyev@yandex.ru \
--cc=kumaraparamesh92@gmail.com \
--cc=lmargalit@nvidia.com \
--cc=long.wu@corigine.com \
--cc=longli@microsoft.com \
--cc=maoyingming@baidu.com \
--cc=matan@mellanox.com \
--cc=matan@nvidia.com \
--cc=mattias.ronnblom@ericsson.com \
--cc=maxime.coquelin@redhat.com \
--cc=mb@smartsharesystems.com \
--cc=ndabilpuram@marvell.com \
--cc=nikhil.rao@intel.com \
--cc=niklas.soderlund@corigine.com \
--cc=olivier.matz@6wind.com \
--cc=orika@nvidia.com \
--cc=oulijun@huawei.com \
--cc=pablo.de.lara.guarch@intel.com \
--cc=paul.m.stillwell.jr@intel.com \
--cc=pbhagavatula@marvell.com \
--cc=peng.zhang@corigine.com \
--cc=qi.z.zhang@intel.com \
--cc=qiming.yang@intel.com \
--cc=radu.nicolau@intel.com \
--cc=remy.horton@intel.com \
--cc=rolf.neugebauer@netronome.com \
--cc=rzidane@nvidia.com \
--cc=samuel.taripin@intel.com \
--cc=shahafs@mellanox.com \
--cc=shally.verma@caviumnetworks.com \
--cc=simei.su@intel.com \
--cc=somnath.kotur@broadcom.com \
--cc=stable@dpdk.org \
--cc=sthotton@marvell.com \
--cc=suanmingm@mellanox.com \
--cc=sunila.sahu@caviumnetworks.com \
--cc=umesh.kartha@caviumnetworks.com \
--cc=usman.tanveer@emumba.com \
--cc=viacheslavo@nvidia.com \
--cc=vladimir.medvedkin@intel.com \
--cc=weix.ling@intel.com \
--cc=wenwux.ma@intel.com \
--cc=wenzhuo.lu@intel.com \
--cc=xavier.huwei@huawei.com \
--cc=yidingx.zhou@intel.com \
--cc=yisen.zhuang@huawei.com \
--cc=yock.gen.mah@intel.com \
--cc=yskoh@mellanox.com \
--cc=yuanx.wang@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).