From: John Garry <firstname.lastname@example.org> To: Ming Lei <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: Tue, 22 Oct 2019 12:19:17 +0100 [thread overview] Message-ID: <email@example.com> (raw) In-Reply-To: <20191022001613.GA32193@ming.t460p> On 22/10/2019 01:16, Ming Lei wrote: > On Mon, Oct 21, 2019 at 03:02:56PM +0100, John Garry wrote: >> On 21/10/2019 13:53, Ming Lei wrote: >>> 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. >>> >> >> Hi Ming, Hi Ming, >> >>> That check isn't correct, and each hw queue should have allowed >>> .can_queue in-flight requests. >> >> There always seems to be some confusion or disagreement on this topic. >> >> I work according to the comment in scsi_host.h: >> >> "Note: it is assumed that each hardware queue has a queue depth of >> can_queue. In other words, the total queue depth per host >> is nr_hw_queues * can_queue." >> >> So I set Scsi_host.can_queue = HISI_SAS_MAX_COMMANDS (=4096) > > I believe all current drivers set .can_queue as single hw queue's depth. > If you set .can_queue as HISI_SAS_MAX_COMMANDS which is HBA's queue > depth, the hisilicon sas driver will HISI_SAS_MAX_COMMANDS * nr_hw_queues > in-flight requests. Yeah, but the SCSI host should still limit max IOs over all queues to .can_queue: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/Documentation/scsi/scsi_mid_low_api.txt#n1083 > >> >>> >>>> >>>>> >>>>> 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. >> >> Let's discuss this when I send the patches, so we don't get sidetracked on >> this blk-mq improvement topic. > > OK, what I meant is to use correct driver to test the patches, otherwise > it might be hard to investigate. Of course. I'm working on this now, and it looks like it will turn out complicated... you'll see. BTW, I reran the test and never say the new WARN trigger (while SCSI timeouts did occur). Thanks again, John > > > Thanks, > Ming > > . >
next prev parent reply other threads:[~2019-10-22 11:19 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 2019-10-21 14:02 ` John Garry 2019-10-22 0:16 ` Ming Lei 2019-10-22 11:19 ` John Garry [this message] 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 \ --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 \ --firstname.lastname@example.org \ --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).