From: Ming Lei <firstname.lastname@example.org> To: John Garry <email@example.com> Cc: Jens Axboe <firstname.lastname@example.org>, email@example.com, Bart Van Assche <firstname.lastname@example.org>, Hannes Reinecke <email@example.com>, Christoph Hellwig <firstname.lastname@example.org>, Thomas Gleixner <email@example.com>, Keith Busch <firstname.lastname@example.org> Subject: Re: [PATCH V4 0/5] blk-mq: improvement on handling IO during CPU hotplug Date: Mon, 21 Oct 2019 20:53:28 +0800 [thread overview] Message-ID: <20191021125327.GA25864@ming.t460p> (raw) In-Reply-To: <email@example.com> On Mon, Oct 21, 2019 at 12:49:53PM +0100, John Garry wrote: > > > > > > > > > > Yes, we share tags among all queues, but we generate the tag - known as IPTT > > > - in the LLDD now, as we can no longer use the request tag (as it is not > > > unique per all queues): > > > > > > https://github.com/hisilicon/kernel-dev/commit/087b95af374be6965583c1673032fb33bc8127e8#diff-f5d8fff19bc539a7387af5230d4e5771R188 > > > > > > As I said, the branch is messy and I did have to fix 087b95af374. > > > > Firstly this way may waste lots of memory, especially the queue depth is > > big, such as, hisilicon V3's queue depth is 4096. > > > > Secondly, you have to deal with queue busy efficiently and correctly, > > for example, your real hw tags(IPTT) can be used up easily, and how > > will you handle these dispatched request? > > I have not seen scenario of exhausted IPTT. And IPTT count is same as SCSI > host.can_queue, so SCSI midlayer should ensure that this does not occur. That check isn't correct, and each hw queue should have allowed .can_queue in-flight requests. > > > > > Finally, you have to evaluate the performance effect, this is highly > > related with how to deal with out-of-IPTT. > > Some figures from our previous testing: > > Managed interrupt without exposing multiple queues: 3M IOPs > Managed interrupt with exposing multiple queues: 2.6M IOPs Then you see the performance regression. Thanks, Ming
next prev parent reply other threads:[~2019-10-21 12:53 UTC|newest] Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top 2019-10-14 1:50 Ming Lei 2019-10-14 1:50 ` [PATCH V4 1/5] blk-mq: add new state of BLK_MQ_S_INTERNAL_STOPPED Ming Lei 2019-10-14 1:50 ` [PATCH V4 2/5] blk-mq: prepare for draining IO when hctx's all CPUs are offline Ming Lei 2019-10-14 1:50 ` [PATCH V4 3/5] blk-mq: stop to handle IO and drain IO before hctx becomes dead Ming Lei 2019-11-28 9:29 ` John Garry 2019-10-14 1:50 ` [PATCH V4 4/5] blk-mq: re-submit IO in case that hctx is dead Ming Lei 2019-10-14 1:50 ` [PATCH V4 5/5] blk-mq: handle requests dispatched from IO scheduler " Ming Lei 2019-10-16 8:58 ` [PATCH V4 0/5] blk-mq: improvement on handling IO during CPU hotplug John Garry 2019-10-16 12:07 ` Ming Lei 2019-10-16 16:19 ` John Garry [not found] ` <firstname.lastname@example.org> 2019-10-20 10:14 ` Ming Lei 2019-10-21 9:19 ` John Garry 2019-10-21 9:34 ` Ming Lei 2019-10-21 9:47 ` John Garry 2019-10-21 10:24 ` Ming Lei 2019-10-21 11:49 ` John Garry 2019-10-21 12:53 ` Ming Lei [this message] 2019-10-21 14:02 ` John Garry 2019-10-22 0:16 ` Ming Lei 2019-10-22 11:19 ` John Garry 2019-10-22 13:45 ` Ming Lei 2019-10-25 16:33 ` John Garry 2019-10-28 10:42 ` Ming Lei 2019-10-28 11:55 ` John Garry 2019-10-29 1:50 ` Ming Lei 2019-10-29 9:22 ` John Garry 2019-10-29 10:05 ` Ming Lei 2019-10-29 17:54 ` John Garry 2019-10-31 16:28 ` John Garry 2019-11-28 1:09 ` chenxiang (M) 2019-11-28 2:02 ` Ming Lei 2019-11-28 10:45 ` John Garry
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=20191021125327.GA25864@ming.t460p \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --firstname.lastname@example.org \ --email@example.com \ --subject='Re: [PATCH V4 0/5] blk-mq: improvement on handling IO during CPU hotplug' \ /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
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).