From: Chao Leng <lengchao@huawei.com> To: Ming Lei <ming.lei@redhat.com> Cc: Sagi Grimberg <sagi@grimberg.me>, Keith Busch <kbusch@kernel.org>, <paulmck@kernel.org>, Christoph Hellwig <hch@lst.de>, Jens Axboe <axboe@kernel.dk>, <linux-nvme@lists.infradead.org>, <linux-block@vger.kernel.org>, Ming Lin <mlin@kernel.org> Subject: Re: [PATCH v5 1/2] blk-mq: add tagset quiesce interface Date: Fri, 7 Aug 2020 17:35:54 +0800 [thread overview] Message-ID: <e6b4032e-a5c6-0038-33b8-04a15ae75a0e@huawei.com> (raw) In-Reply-To: <20200807092457.GA2112310@T590> On 2020/8/7 17:24, Ming Lei wrote: > On Fri, Aug 07, 2020 at 05:04:38PM +0800, Chao Leng wrote: >> >> >> On 2020/7/29 12:39, Sagi Grimberg wrote: >>> >>>>>>> Dynamically allocating each one is possible but not very scalable. >>>>>>> >>>>>>> The question is if there is some way, we can do this with on-stack >>>>>>> or a single on-heap rcu_head or equivalent that can achieve the same >>>>>>> effect. >>>>>> >>>>>> If the hctx structures are guaranteed to stay put, you could count >>>>>> them and then do a single allocation of an array of rcu_head structures >>>>>> (or some larger structure containing an rcu_head structure, if needed). >>>>>> You could then sequence through this array, consuming one rcu_head per >>>>>> hctx as you processed it. Once all the callbacks had been invoked, >>>>>> it would be safe to free the array. >>>>>> >>>>>> Sounds too simple, though. So what am I missing? >>>>> >>>>> We don't want higher-order allocations... >>>> >>>> So: >>>> >>>> (1) We don't want to embed the struct in the hctx because we allocate >>>> so many of them that this is non-negligable to add for something we >>>> typically never use. >>>> >>>> (2) We don't want to allocate dynamically because it's potentially >>>> huge. >>>> >>>> As long as we're using srcu for blocking hctx's, I think it's "pick your >>>> poison". >>>> >>>> Alternatively, Ming's percpu_ref patch(*) may be worth a look. >>>> >>>> * https://www.spinics.net/lists/linux-block/msg56976.html1 >>> I'm not opposed to having this. Will require some more testing >>> as this affects pretty much every driver out there.. >>> >>> If we are going with a lightweight percpu_ref, can we just do >>> it also for non-blocking hctx and have a single code-path? >>> . >> I tried to optimize the patch,support for non blocking queue and >> blocking queue. >> See next email. > > Please see the following thread: > > https://lore.kernel.org/linux-block/05f75e89-b6f7-de49-eb9f-a08aa4e0ba4f@kernel.dk/ > > Both Keith and Jens didn't think it is a good idea. If we can support nonblocking queue and blocking queue simplely, this may be a good choice. Please review the patch first. > > > > Thanks, > Ming > > . >
WARNING: multiple messages have this Message-ID (diff)
From: Chao Leng <lengchao@huawei.com> To: Ming Lei <ming.lei@redhat.com> Cc: Jens Axboe <axboe@kernel.dk>, Sagi Grimberg <sagi@grimberg.me>, paulmck@kernel.org, linux-nvme@lists.infradead.org, linux-block@vger.kernel.org, Keith Busch <kbusch@kernel.org>, Ming Lin <mlin@kernel.org>, Christoph Hellwig <hch@lst.de> Subject: Re: [PATCH v5 1/2] blk-mq: add tagset quiesce interface Date: Fri, 7 Aug 2020 17:35:54 +0800 [thread overview] Message-ID: <e6b4032e-a5c6-0038-33b8-04a15ae75a0e@huawei.com> (raw) In-Reply-To: <20200807092457.GA2112310@T590> On 2020/8/7 17:24, Ming Lei wrote: > On Fri, Aug 07, 2020 at 05:04:38PM +0800, Chao Leng wrote: >> >> >> On 2020/7/29 12:39, Sagi Grimberg wrote: >>> >>>>>>> Dynamically allocating each one is possible but not very scalable. >>>>>>> >>>>>>> The question is if there is some way, we can do this with on-stack >>>>>>> or a single on-heap rcu_head or equivalent that can achieve the same >>>>>>> effect. >>>>>> >>>>>> If the hctx structures are guaranteed to stay put, you could count >>>>>> them and then do a single allocation of an array of rcu_head structures >>>>>> (or some larger structure containing an rcu_head structure, if needed). >>>>>> You could then sequence through this array, consuming one rcu_head per >>>>>> hctx as you processed it. Once all the callbacks had been invoked, >>>>>> it would be safe to free the array. >>>>>> >>>>>> Sounds too simple, though. So what am I missing? >>>>> >>>>> We don't want higher-order allocations... >>>> >>>> So: >>>> >>>> (1) We don't want to embed the struct in the hctx because we allocate >>>> so many of them that this is non-negligable to add for something we >>>> typically never use. >>>> >>>> (2) We don't want to allocate dynamically because it's potentially >>>> huge. >>>> >>>> As long as we're using srcu for blocking hctx's, I think it's "pick your >>>> poison". >>>> >>>> Alternatively, Ming's percpu_ref patch(*) may be worth a look. >>>> >>>> * https://www.spinics.net/lists/linux-block/msg56976.html1 >>> I'm not opposed to having this. Will require some more testing >>> as this affects pretty much every driver out there.. >>> >>> If we are going with a lightweight percpu_ref, can we just do >>> it also for non-blocking hctx and have a single code-path? >>> . >> I tried to optimize the patch,support for non blocking queue and >> blocking queue. >> See next email. > > Please see the following thread: > > https://lore.kernel.org/linux-block/05f75e89-b6f7-de49-eb9f-a08aa4e0ba4f@kernel.dk/ > > Both Keith and Jens didn't think it is a good idea. If we can support nonblocking queue and blocking queue simplely, this may be a good choice. Please review the patch first. > > > > Thanks, > Ming > > . > _______________________________________________ Linux-nvme mailing list Linux-nvme@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-nvme
next prev parent reply other threads:[~2020-08-07 9:36 UTC|newest] Thread overview: 80+ messages / expand[flat|nested] mbox.gz Atom feed top 2020-07-27 23:10 [PATCH v5 0/2] improve nvme quiesce time for large amount of namespaces Sagi Grimberg 2020-07-27 23:10 ` Sagi Grimberg 2020-07-27 23:10 ` [PATCH v5 1/2] blk-mq: add tagset quiesce interface Sagi Grimberg 2020-07-27 23:10 ` Sagi Grimberg 2020-07-27 23:32 ` Keith Busch 2020-07-27 23:32 ` Keith Busch 2020-07-28 0:12 ` Sagi Grimberg 2020-07-28 0:12 ` Sagi Grimberg 2020-07-28 1:40 ` Ming Lei 2020-07-28 1:40 ` Ming Lei 2020-07-28 1:51 ` Jens Axboe 2020-07-28 1:51 ` Jens Axboe 2020-07-28 2:17 ` Ming Lei 2020-07-28 2:17 ` Ming Lei 2020-07-28 2:23 ` Jens Axboe 2020-07-28 2:23 ` Jens Axboe 2020-07-28 2:28 ` Ming Lei 2020-07-28 2:28 ` Ming Lei 2020-07-28 2:32 ` Jens Axboe 2020-07-28 2:32 ` Jens Axboe 2020-07-28 3:29 ` Sagi Grimberg 2020-07-28 3:29 ` Sagi Grimberg 2020-07-28 3:25 ` Sagi Grimberg 2020-07-28 3:25 ` Sagi Grimberg 2020-07-28 7:18 ` Christoph Hellwig 2020-07-28 7:18 ` Christoph Hellwig 2020-07-28 7:48 ` Sagi Grimberg 2020-07-28 7:48 ` Sagi Grimberg 2020-07-28 9:16 ` Ming Lei 2020-07-28 9:16 ` Ming Lei 2020-07-28 9:24 ` Sagi Grimberg 2020-07-28 9:24 ` Sagi Grimberg 2020-07-28 9:33 ` Ming Lei 2020-07-28 9:33 ` Ming Lei 2020-07-28 9:37 ` Sagi Grimberg 2020-07-28 9:37 ` Sagi Grimberg 2020-07-28 9:43 ` Sagi Grimberg 2020-07-28 9:43 ` Sagi Grimberg 2020-07-28 10:10 ` Ming Lei 2020-07-28 10:10 ` Ming Lei 2020-07-28 10:57 ` Christoph Hellwig 2020-07-28 10:57 ` Christoph Hellwig 2020-07-28 14:13 ` Paul E. McKenney 2020-07-28 14:13 ` Paul E. McKenney 2020-07-28 10:58 ` Christoph Hellwig 2020-07-28 10:58 ` Christoph Hellwig 2020-07-28 16:25 ` Sagi Grimberg 2020-07-28 16:25 ` Sagi Grimberg 2020-07-28 13:54 ` Paul E. McKenney 2020-07-28 13:54 ` Paul E. McKenney 2020-07-28 23:46 ` Sagi Grimberg 2020-07-28 23:46 ` Sagi Grimberg 2020-07-29 0:31 ` Paul E. McKenney 2020-07-29 0:31 ` Paul E. McKenney 2020-07-29 0:43 ` Sagi Grimberg 2020-07-29 0:43 ` Sagi Grimberg 2020-07-29 0:59 ` Keith Busch 2020-07-29 0:59 ` Keith Busch 2020-07-29 4:39 ` Sagi Grimberg 2020-07-29 4:39 ` Sagi Grimberg 2020-08-07 9:04 ` Chao Leng 2020-08-07 9:04 ` Chao Leng 2020-08-07 9:24 ` Ming Lei 2020-08-07 9:24 ` Ming Lei 2020-08-07 9:35 ` Chao Leng [this message] 2020-08-07 9:35 ` Chao Leng 2020-07-29 4:10 ` Paul E. McKenney 2020-07-29 4:10 ` Paul E. McKenney 2020-07-29 4:37 ` Sagi Grimberg 2020-07-29 4:37 ` Sagi Grimberg 2020-07-27 23:10 ` [PATCH v5 2/2] nvme: use blk_mq_[un]quiesce_tagset Sagi Grimberg 2020-07-27 23:10 ` Sagi Grimberg 2020-07-28 0:54 ` Sagi Grimberg 2020-07-28 0:54 ` Sagi Grimberg 2020-07-28 3:21 ` Chao Leng 2020-07-28 3:21 ` Chao Leng 2020-07-28 3:34 ` Sagi Grimberg 2020-07-28 3:34 ` Sagi Grimberg 2020-07-28 3:51 ` Chao Leng 2020-07-28 3:51 ` Chao Leng
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=e6b4032e-a5c6-0038-33b8-04a15ae75a0e@huawei.com \ --to=lengchao@huawei.com \ --cc=axboe@kernel.dk \ --cc=hch@lst.de \ --cc=kbusch@kernel.org \ --cc=linux-block@vger.kernel.org \ --cc=linux-nvme@lists.infradead.org \ --cc=ming.lei@redhat.com \ --cc=mlin@kernel.org \ --cc=paulmck@kernel.org \ --cc=sagi@grimberg.me \ /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.