From: Andrew Morton <akpm@osdl.org>
To: Lars Ellenberg <Lars.Ellenberg@linbit.com>
Cc: Neil Brown <neilb@suse.de>, Ingo Molnar <mingo@redhat.com>,
linux-raid@vger.kernel.org, Jens Axboe <jens.axboe@oracle.com>,
stable@kernel.org
Subject: Re: [patch] md: pass down BIO_RW_SYNC in raid{1,10}
Date: Mon, 8 Jan 2007 15:02:42 -0800 [thread overview]
Message-ID: <20070108150242.1b39eda2.akpm@osdl.org> (raw)
In-Reply-To: <20070108090833.GF8125@soda.linbit>
On Mon, 8 Jan 2007 10:08:34 +0100
Lars Ellenberg <Lars.Ellenberg@linbit.com> wrote:
> md raidX make_request functions strip off the BIO_RW_SYNC flag,
> thus introducing additional latency.
>
> fixing this in raid1 and raid10 seems to be straight forward enough.
>
> for our particular usage case in DRBD, passing this flag improved
> some initialization time from ~5 minutes to ~5 seconds.
That sounds like a significant fix.
This patch also applies to 2.6.19 and I have tagged it for a -stable
backport. Neil, are you OK with that?
> Acked-by: NeilBrown <neilb@suse.de>
> Signed-off-by: Lars Ellenberg <lars@linbit.com>
>
> ---
>
> diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
> index b30f74b..164b25d 100644
> --- a/drivers/md/raid1.c
> +++ b/drivers/md/raid1.c
> @@ -775,6 +775,7 @@ static int make_request(request_queue_t
> struct bio_list bl;
> struct page **behind_pages = NULL;
> const int rw = bio_data_dir(bio);
> + const int do_sync = bio_sync(bio);
> int do_barriers;
>
> /*
> @@ -835,7 +836,7 @@ static int make_request(request_queue_t
> read_bio->bi_sector = r1_bio->sector + mirror->rdev->data_offset;
> read_bio->bi_bdev = mirror->rdev->bdev;
> read_bio->bi_end_io = raid1_end_read_request;
> - read_bio->bi_rw = READ;
> + read_bio->bi_rw = READ | do_sync;
> read_bio->bi_private = r1_bio;
>
> generic_make_request(read_bio);
> @@ -906,7 +907,7 @@ #endif
> mbio->bi_sector = r1_bio->sector + conf->mirrors[i].rdev->data_offset;
> mbio->bi_bdev = conf->mirrors[i].rdev->bdev;
> mbio->bi_end_io = raid1_end_write_request;
> - mbio->bi_rw = WRITE | do_barriers;
> + mbio->bi_rw = WRITE | do_barriers | do_sync;
> mbio->bi_private = r1_bio;
>
> if (behind_pages) {
> @@ -941,6 +942,8 @@ #endif
> blk_plug_device(mddev->queue);
> spin_unlock_irqrestore(&conf->device_lock, flags);
>
> + if (do_sync)
> + md_wakeup_thread(mddev->thread);
> #if 0
> while ((bio = bio_list_pop(&bl)) != NULL)
> generic_make_request(bio);
> @@ -1541,6 +1544,7 @@ static void raid1d(mddev_t *mddev)
> * We already have a nr_pending reference on these rdevs.
> */
> int i;
> + const int do_sync = bio_sync(r1_bio->master_bio);
> clear_bit(R1BIO_BarrierRetry, &r1_bio->state);
> clear_bit(R1BIO_Barrier, &r1_bio->state);
> for (i=0; i < conf->raid_disks; i++)
> @@ -1561,7 +1565,7 @@ static void raid1d(mddev_t *mddev)
> conf->mirrors[i].rdev->data_offset;
> bio->bi_bdev = conf->mirrors[i].rdev->bdev;
> bio->bi_end_io = raid1_end_write_request;
> - bio->bi_rw = WRITE;
> + bio->bi_rw = WRITE | do_sync;
> bio->bi_private = r1_bio;
> r1_bio->bios[i] = bio;
> generic_make_request(bio);
> @@ -1593,6 +1597,7 @@ static void raid1d(mddev_t *mddev)
> (unsigned long long)r1_bio->sector);
> raid_end_bio_io(r1_bio);
> } else {
> + const int do_sync = bio_sync(r1_bio->master_bio);
> r1_bio->bios[r1_bio->read_disk] =
> mddev->ro ? IO_BLOCKED : NULL;
> r1_bio->read_disk = disk;
> @@ -1608,7 +1613,7 @@ static void raid1d(mddev_t *mddev)
> bio->bi_sector = r1_bio->sector + rdev->data_offset;
> bio->bi_bdev = rdev->bdev;
> bio->bi_end_io = raid1_end_read_request;
> - bio->bi_rw = READ;
> + bio->bi_rw = READ | do_sync;
> bio->bi_private = r1_bio;
> unplug = 1;
> generic_make_request(bio);
> diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
> index f014191..a9401c0 100644
> --- a/drivers/md/raid10.c
> +++ b/drivers/md/raid10.c
> @@ -782,6 +782,7 @@ static int make_request(request_queue_t
> int i;
> int chunk_sects = conf->chunk_mask + 1;
> const int rw = bio_data_dir(bio);
> + const int do_sync = bio_sync(bio);
> struct bio_list bl;
> unsigned long flags;
>
> @@ -863,7 +864,7 @@ static int make_request(request_queue_t
> mirror->rdev->data_offset;
> read_bio->bi_bdev = mirror->rdev->bdev;
> read_bio->bi_end_io = raid10_end_read_request;
> - read_bio->bi_rw = READ;
> + read_bio->bi_rw = READ | do_sync;
> read_bio->bi_private = r10_bio;
>
> generic_make_request(read_bio);
> @@ -909,7 +910,7 @@ static int make_request(request_queue_t
> conf->mirrors[d].rdev->data_offset;
> mbio->bi_bdev = conf->mirrors[d].rdev->bdev;
> mbio->bi_end_io = raid10_end_write_request;
> - mbio->bi_rw = WRITE;
> + mbio->bi_rw = WRITE | do_sync;
> mbio->bi_private = r10_bio;
>
> atomic_inc(&r10_bio->remaining);
> @@ -922,6 +923,9 @@ static int make_request(request_queue_t
> blk_plug_device(mddev->queue);
> spin_unlock_irqrestore(&conf->device_lock, flags);
>
> + if (do_sync)
> + md_wakeup_thread(mddev->thread);
> +
> return 0;
> }
>
> @@ -1563,6 +1567,7 @@ static void raid10d(mddev_t *mddev)
> (unsigned long long)r10_bio->sector);
> raid_end_bio_io(r10_bio);
> } else {
> + const int do_sync = bio_sync(r10_bio->master_bio);
> rdev = conf->mirrors[mirror].rdev;
> if (printk_ratelimit())
> printk(KERN_ERR "raid10: %s: redirecting sector %llu to"
> @@ -1574,7 +1579,7 @@ static void raid10d(mddev_t *mddev)
> bio->bi_sector = r10_bio->devs[r10_bio->read_slot].addr
> + rdev->data_offset;
> bio->bi_bdev = rdev->bdev;
> - bio->bi_rw = READ;
> + bio->bi_rw = READ | do_sync;
> bio->bi_private = r10_bio;
> bio->bi_end_io = raid10_end_read_request;
> unplug = 1;
> --
> : Lars Ellenberg Tel +43-1-8178292-55 :
> : LINBIT Information Technologies GmbH Fax +43-1-8178292-82 :
> : Vivenotgasse 48, A-1120 Vienna/Europe http://www.linbit.com :
next prev parent reply other threads:[~2007-01-08 23:02 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-01-08 9:08 [patch] md: pass down BIO_RW_SYNC in raid{1,10} Lars Ellenberg
2007-01-08 23:02 ` Andrew Morton [this message]
2007-01-08 23:50 ` Neil Brown
2007-01-09 7:12 ` Jens Axboe
2007-01-09 14:08 ` Lars Ellenberg
2007-01-09 16:13 ` Mike Snitzer
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=20070108150242.1b39eda2.akpm@osdl.org \
--to=akpm@osdl.org \
--cc=Lars.Ellenberg@linbit.com \
--cc=jens.axboe@oracle.com \
--cc=linux-raid@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=neilb@suse.de \
--cc=stable@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: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).