From: brookxu <brookxu.cn@gmail.com> To: Tejun Heo <tj@kernel.org> Cc: axboe@kernel.dk, cgroups@vger.kernel.org, linux-block@vger.kernel.org, linux-kernel@vger.kernel.org Subject: Re: [PATCH] blk-throtl: optimize IOPS throttle for large IO scenarios Date: Wed, 28 Jul 2021 10:33:20 +0800 [thread overview] Message-ID: <fab343e8-5929-fb30-90e3-b5b6bd34702a@gmail.com> (raw) In-Reply-To: <YQAydzEhZfPUpzWI@mtj.duckdns.org> Thanks for your time. Tejun Heo wrote on 2021/7/28 12:21 上午: > Hello, > > On Tue, Jul 27, 2021 at 11:06:18AM +0800, brookxu wrote: >> Make blk-throttle use rq-qos may be more elegant. But I found that there may be at least >> one problem that is difficult to solve. blk-throttle supports separate throttle for read >> and write IOs, which means that we cannot suspend tasks during throttle, but rq-qos >> throttle IOs by suspending tasks. > > Ah, right, I forgot about that. > >> We may be able to relocate the blk-throttle hooks to the rq-qos hooks. Since we may not >> be able to replace the throttle hook, in this case, if we register a rq-qos to the system, >> part of the blk-throttle hooks is in rq-qos and part hooks not, which feels a bit confusing. >> In addition, we may need to implement more hooks, such as IO merge hook. > > Would it be possible to just move the blk-throtl throttling hook right next > to the rq-qos hook so that it gets throttled after splitting? If we do this, I think we will encounter some problems, as follows: 1. blk-throttle is now at the top of the IO stack. Changing the position of the throttle hook will make this mechanism invalid for some devices. 2. We may also need to add a new hook to handle back-merge, otherwise I think the isolation effect will be worse in the sequential IO scene. 3. Since bio has entered the IO stack, if it is suspended and resubmitted by blk-throttle, then there is an IO stack reentry problem, which I think may cause many small problems. > Thanks. >
WARNING: multiple messages have this Message-ID (diff)
From: brookxu <brookxu.cn-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org> To: Tejun Heo <tj-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org> Cc: axboe-tSWWG44O7X1aa/9Udqfwiw@public.gmane.org, cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-block-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org Subject: Re: [PATCH] blk-throtl: optimize IOPS throttle for large IO scenarios Date: Wed, 28 Jul 2021 10:33:20 +0800 [thread overview] Message-ID: <fab343e8-5929-fb30-90e3-b5b6bd34702a@gmail.com> (raw) In-Reply-To: <YQAydzEhZfPUpzWI-qYNAdHglDFBN0TnZuCh8vA@public.gmane.org> Thanks for your time. Tejun Heo wrote on 2021/7/28 12:21 上午: > Hello, > > On Tue, Jul 27, 2021 at 11:06:18AM +0800, brookxu wrote: >> Make blk-throttle use rq-qos may be more elegant. But I found that there may be at least >> one problem that is difficult to solve. blk-throttle supports separate throttle for read >> and write IOs, which means that we cannot suspend tasks during throttle, but rq-qos >> throttle IOs by suspending tasks. > > Ah, right, I forgot about that. > >> We may be able to relocate the blk-throttle hooks to the rq-qos hooks. Since we may not >> be able to replace the throttle hook, in this case, if we register a rq-qos to the system, >> part of the blk-throttle hooks is in rq-qos and part hooks not, which feels a bit confusing. >> In addition, we may need to implement more hooks, such as IO merge hook. > > Would it be possible to just move the blk-throtl throttling hook right next > to the rq-qos hook so that it gets throttled after splitting? If we do this, I think we will encounter some problems, as follows: 1. blk-throttle is now at the top of the IO stack. Changing the position of the throttle hook will make this mechanism invalid for some devices. 2. We may also need to add a new hook to handle back-merge, otherwise I think the isolation effect will be worse in the sequential IO scene. 3. Since bio has entered the IO stack, if it is suspended and resubmitted by blk-throttle, then there is an IO stack reentry problem, which I think may cause many small problems. > Thanks. >
next prev parent reply other threads:[~2021-07-28 2:33 UTC|newest] Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top 2021-07-16 6:22 [PATCH] blk-throtl: optimize IOPS throttle for large IO scenarios brookxu 2021-07-16 16:09 ` Tejun Heo 2021-07-16 16:09 ` Tejun Heo 2021-07-16 23:07 ` brookxu 2021-07-19 16:35 ` brookxu 2021-07-19 16:35 ` brookxu 2021-07-26 21:46 ` Tejun Heo 2021-07-26 21:46 ` Tejun Heo 2021-07-27 3:06 ` brookxu 2021-07-27 3:06 ` brookxu 2021-07-27 16:21 ` Tejun Heo 2021-07-27 16:21 ` Tejun Heo 2021-07-28 2:33 ` brookxu [this message] 2021-07-28 2:33 ` brookxu 2021-07-28 7:48 ` Tejun Heo 2021-07-28 7:48 ` Tejun Heo
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=fab343e8-5929-fb30-90e3-b5b6bd34702a@gmail.com \ --to=brookxu.cn@gmail.com \ --cc=axboe@kernel.dk \ --cc=cgroups@vger.kernel.org \ --cc=linux-block@vger.kernel.org \ --cc=linux-kernel@vger.kernel.org \ --cc=tj@kernel.org \ /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: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.