From: Goldwyn Rodrigues <rgoldwyn@suse.de> To: Jens Axboe <axboe@kernel.dk>, linux-fsdevel@vger.kernel.org Cc: jack@suse.com, hch@infradead.org, linux-block@vger.kernel.org, linux-btrfs@vger.kernel.org, linux-ext4@vger.kernel.org, linux-xfs@vger.kernel.org, sagi@grimberg.me, avi@scylladb.com, linux-api@vger.kernel.org, willy@infradead.org, Goldwyn Rodrigues <rgoldwyn@suse.com> Subject: Re: [PATCH 5/8] nowait aio: return on congested block device Date: Fri, 24 Mar 2017 06:32:11 -0500 [thread overview] Message-ID: <47d742e9-1343-ef5b-f7d4-29a6e22bef84@suse.de> (raw) In-Reply-To: <eee4683d-9f44-434f-b97f-b0b24c7b3dab@kernel.dk> On 03/16/2017 09:33 AM, Jens Axboe wrote: > On 03/15/2017 03:51 PM, Goldwyn Rodrigues wrote: >> diff --git a/block/blk-core.c b/block/blk-core.c >> index 0eeb99e..2e5cba2 100644 >> --- a/block/blk-core.c >> +++ b/block/blk-core.c >> @@ -2014,7 +2019,7 @@ blk_qc_t generic_make_request(struct bio *bio) >> do { >> struct request_queue *q = bdev_get_queue(bio->bi_bdev); >> >> - if (likely(blk_queue_enter(q, false) == 0)) { >> + if (likely(blk_queue_enter(q, bio_flagged(bio, BIO_NOWAIT)) == 0)) { >> struct bio_list hold; >> struct bio_list lower, same; >> >> @@ -2040,7 +2045,10 @@ blk_qc_t generic_make_request(struct bio *bio) >> bio_list_merge(&bio_list_on_stack, &same); >> bio_list_merge(&bio_list_on_stack, &hold); >> } else { >> - bio_io_error(bio); >> + if (unlikely(bio_flagged(bio, BIO_NOWAIT))) >> + bio_wouldblock_error(bio); >> + else >> + bio_io_error(bio); > > This doesn't look right. What if the queue is dying, and BIO_NOWAIT just > happened to be set? > Yes, I need to add a condition here to check for blk_queue_dying(). Thanks. > And you're missing wbt_wait() as well as a blocking point. Ditto in > blk-mq. wbt_wait() does not apply to WRITE_ODIRECT > >> diff --git a/block/blk-mq.c b/block/blk-mq.c >> index 159187a..942ce8c 100644 >> --- a/block/blk-mq.c >> +++ b/block/blk-mq.c >> @@ -1518,6 +1518,8 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) >> rq = blk_mq_sched_get_request(q, bio, bio->bi_opf, &data); >> if (unlikely(!rq)) { >> __wbt_done(q->rq_wb, wb_acct); >> + if (bio && bio_flagged(bio, BIO_NOWAIT)) >> + bio_wouldblock_error(bio); >> return BLK_QC_T_NONE; >> } >> > > This seems a little fragile now, since not both paths free the bio. > Direct I/O should free the bios in bio_dio_complete(). I am not sure why it would not free bio here originally, but IIRC, this path is for bio==NULL only. So, with this patch we would get a rq==NULL here and hence the bio_wouldblock_error() call. -- Goldwyn
WARNING: multiple messages have this Message-ID (diff)
From: Goldwyn Rodrigues <rgoldwyn-l3A5Bk7waGM@public.gmane.org> To: Jens Axboe <axboe-tSWWG44O7X1aa/9Udqfwiw@public.gmane.org>, linux-fsdevel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org Cc: jack-IBi9RG/b67k@public.gmane.org, hch-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org, linux-block-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-btrfs-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-ext4-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-xfs-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, sagi-NQWnxTmZq1alnMjI0IkVqw@public.gmane.org, avi-VrcmuVmyx1hWk0Htik3J/w@public.gmane.org, linux-api-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, willy-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org, Goldwyn Rodrigues <rgoldwyn-IBi9RG/b67k@public.gmane.org> Subject: Re: [PATCH 5/8] nowait aio: return on congested block device Date: Fri, 24 Mar 2017 06:32:11 -0500 [thread overview] Message-ID: <47d742e9-1343-ef5b-f7d4-29a6e22bef84@suse.de> (raw) In-Reply-To: <eee4683d-9f44-434f-b97f-b0b24c7b3dab-tSWWG44O7X1aa/9Udqfwiw@public.gmane.org> On 03/16/2017 09:33 AM, Jens Axboe wrote: > On 03/15/2017 03:51 PM, Goldwyn Rodrigues wrote: >> diff --git a/block/blk-core.c b/block/blk-core.c >> index 0eeb99e..2e5cba2 100644 >> --- a/block/blk-core.c >> +++ b/block/blk-core.c >> @@ -2014,7 +2019,7 @@ blk_qc_t generic_make_request(struct bio *bio) >> do { >> struct request_queue *q = bdev_get_queue(bio->bi_bdev); >> >> - if (likely(blk_queue_enter(q, false) == 0)) { >> + if (likely(blk_queue_enter(q, bio_flagged(bio, BIO_NOWAIT)) == 0)) { >> struct bio_list hold; >> struct bio_list lower, same; >> >> @@ -2040,7 +2045,10 @@ blk_qc_t generic_make_request(struct bio *bio) >> bio_list_merge(&bio_list_on_stack, &same); >> bio_list_merge(&bio_list_on_stack, &hold); >> } else { >> - bio_io_error(bio); >> + if (unlikely(bio_flagged(bio, BIO_NOWAIT))) >> + bio_wouldblock_error(bio); >> + else >> + bio_io_error(bio); > > This doesn't look right. What if the queue is dying, and BIO_NOWAIT just > happened to be set? > Yes, I need to add a condition here to check for blk_queue_dying(). Thanks. > And you're missing wbt_wait() as well as a blocking point. Ditto in > blk-mq. wbt_wait() does not apply to WRITE_ODIRECT > >> diff --git a/block/blk-mq.c b/block/blk-mq.c >> index 159187a..942ce8c 100644 >> --- a/block/blk-mq.c >> +++ b/block/blk-mq.c >> @@ -1518,6 +1518,8 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) >> rq = blk_mq_sched_get_request(q, bio, bio->bi_opf, &data); >> if (unlikely(!rq)) { >> __wbt_done(q->rq_wb, wb_acct); >> + if (bio && bio_flagged(bio, BIO_NOWAIT)) >> + bio_wouldblock_error(bio); >> return BLK_QC_T_NONE; >> } >> > > This seems a little fragile now, since not both paths free the bio. > Direct I/O should free the bios in bio_dio_complete(). I am not sure why it would not free bio here originally, but IIRC, this path is for bio==NULL only. So, with this patch we would get a rq==NULL here and hence the bio_wouldblock_error() call. -- Goldwyn
next prev parent reply other threads:[~2017-03-24 11:32 UTC|newest] Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top 2017-03-15 21:50 [PATCH 0/8 v3] No wait AIO Goldwyn Rodrigues 2017-03-15 21:50 ` Goldwyn Rodrigues 2017-03-15 21:51 ` [PATCH 1/8] nowait aio: Introduce IOCB_RW_FLAG_NOWAIT Goldwyn Rodrigues 2017-03-15 21:51 ` [PATCH 2/8] nowait aio: Return if cannot get hold of i_rwsem Goldwyn Rodrigues 2017-03-15 21:51 ` [PATCH 3/8] nowait aio: return if direct write will trigger writeback Goldwyn Rodrigues 2017-03-16 13:08 ` Matthew Wilcox 2017-03-16 13:46 ` Goldwyn Rodrigues 2017-03-16 13:20 ` Matthew Wilcox 2017-03-16 13:46 ` Goldwyn Rodrigues 2017-03-16 13:46 ` Goldwyn Rodrigues 2017-03-15 21:51 ` [PATCH 4/8] nowait-aio: Introduce IOMAP_NOWAIT Goldwyn Rodrigues 2017-03-15 21:51 ` [PATCH 5/8] nowait aio: return on congested block device Goldwyn Rodrigues 2017-03-16 14:33 ` Jens Axboe 2017-03-16 14:33 ` Jens Axboe 2017-03-17 2:03 ` Ming Lei 2017-03-17 12:23 ` Goldwyn Rodrigues 2017-03-24 11:32 ` Goldwyn Rodrigues [this message] 2017-03-24 11:32 ` Goldwyn Rodrigues 2017-03-24 14:39 ` Jens Axboe 2017-03-16 21:31 ` Dave Chinner 2017-03-16 21:31 ` Dave Chinner 2017-03-17 12:23 ` Goldwyn Rodrigues 2017-03-20 17:33 ` Jan Kara 2017-03-15 21:51 ` [PATCH 6/8] nowait aio: ext4 Goldwyn Rodrigues 2017-03-15 21:51 ` [PATCH 7/8] nowait aio: xfs Goldwyn Rodrigues 2017-03-15 21:51 ` [PATCH 8/8] nowait aio: btrfs Goldwyn Rodrigues -- strict thread matches above, loose matches on Subject: below -- 2017-05-09 12:22 [PATCH 0/8 v7] No wait AIO Goldwyn Rodrigues 2017-05-09 12:22 ` [PATCH 5/8] nowait aio: return on congested block device Goldwyn Rodrigues 2017-05-11 7:44 ` Christoph Hellwig 2017-05-11 18:16 ` Goldwyn Rodrigues 2017-05-11 18:16 ` Goldwyn Rodrigues 2017-04-14 12:02 [PATCH 0/8 v6] No wait AIO Goldwyn Rodrigues 2017-04-14 12:02 ` [PATCH 5/8] nowait aio: return on congested block device Goldwyn Rodrigues 2017-04-19 6:45 ` Christoph Hellwig 2017-04-19 15:21 ` Goldwyn Rodrigues 2017-04-20 13:43 ` Jan Kara 2017-04-24 21:10 ` Goldwyn Rodrigues 2017-04-25 2:28 ` Jens Axboe 2017-04-03 18:52 [PATCH 0/8 v4] No wait AIO Goldwyn Rodrigues 2017-04-03 18:53 ` [PATCH 5/8] nowait aio: return on congested block device Goldwyn Rodrigues 2017-04-04 6:49 ` Christoph Hellwig 2017-02-28 23:36 [PATCH 0/8 v2] Non-blocking AIO Goldwyn Rodrigues 2017-02-28 23:36 ` [PATCH 5/8] nowait aio: return on congested block device Goldwyn Rodrigues 2017-03-08 7:03 ` Sagi Grimberg 2017-03-08 15:00 ` Goldwyn Rodrigues 2017-03-08 15:28 ` Jan Kara 2017-03-08 15:51 ` Christoph Hellwig 2017-03-08 16:17 ` Jens Axboe 2017-03-09 2:18 ` Goldwyn Rodrigues
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=47d742e9-1343-ef5b-f7d4-29a6e22bef84@suse.de \ --to=rgoldwyn@suse.de \ --cc=avi@scylladb.com \ --cc=axboe@kernel.dk \ --cc=hch@infradead.org \ --cc=jack@suse.com \ --cc=linux-api@vger.kernel.org \ --cc=linux-block@vger.kernel.org \ --cc=linux-btrfs@vger.kernel.org \ --cc=linux-ext4@vger.kernel.org \ --cc=linux-fsdevel@vger.kernel.org \ --cc=linux-xfs@vger.kernel.org \ --cc=rgoldwyn@suse.com \ --cc=sagi@grimberg.me \ --cc=willy@infradead.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.