From: Christoph Hellwig <hch@lst.de>
To: "Jens Axboe" <axboe@kernel.dk>,
"Mike Snitzer" <snitzer@kernel.org>,
"Mikulas Patocka" <mpatocka@redhat.com>,
"Song Liu" <song@kernel.org>, "Yu Kuai" <yukuai3@huawei.com>,
"Philipp Reisner" <philipp.reisner@linbit.com>,
"Lars Ellenberg" <lars.ellenberg@linbit.com>,
"Christoph Böhmwalder" <christoph.boehmwalder@linbit.com>
Cc: dm-devel@lists.linux.dev, linux-block@vger.kernel.org,
linux-raid@vger.kernel.org, drbd-dev@lists.linbit.com
Subject: [PATCH 08/16] md/raid5: use the atomic queue limit update APIs
Date: Mon, 26 Feb 2024 11:29:56 +0100 [thread overview]
Message-ID: <20240226103004.281412-9-hch@lst.de> (raw)
In-Reply-To: <20240226103004.281412-1-hch@lst.de>
Build the queue limits outside the queue and apply them using
queue_limits_set. Also remove the bogus ->gendisk and ->queue NULL
checks in the are while touching it.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
drivers/md/raid5.c | 123 +++++++++++++++++++++------------------------
1 file changed, 56 insertions(+), 67 deletions(-)
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 14f2cf75abbd72..3dd7c05d3ba2ab 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -7682,12 +7682,6 @@ static int only_parity(int raid_disk, int algo, int raid_disks, int max_degraded
return 0;
}
-static void raid5_set_io_opt(struct r5conf *conf)
-{
- blk_queue_io_opt(conf->mddev->queue, (conf->chunk_sectors << 9) *
- (conf->raid_disks - conf->max_degraded));
-}
-
static int raid5_run(struct mddev *mddev)
{
struct r5conf *conf;
@@ -7695,9 +7689,12 @@ static int raid5_run(struct mddev *mddev)
struct md_rdev *rdev;
struct md_rdev *journal_dev = NULL;
sector_t reshape_offset = 0;
+ struct queue_limits lim;
int i;
long long min_offset_diff = 0;
int first = 1;
+ int data_disks, stripe;
+ int ret = -EIO;
if (mddev->recovery_cp != MaxSector)
pr_notice("md/raid:%s: not clean -- starting background reconstruction\n",
@@ -7950,67 +7947,59 @@ static int raid5_run(struct mddev *mddev)
mdname(mddev));
md_set_array_sectors(mddev, raid5_size(mddev, 0, 0));
- if (mddev->queue) {
- int chunk_size;
- /* read-ahead size must cover two whole stripes, which
- * is 2 * (datadisks) * chunksize where 'n' is the
- * number of raid devices
- */
- int data_disks = conf->previous_raid_disks - conf->max_degraded;
- int stripe = data_disks *
- ((mddev->chunk_sectors << 9) / PAGE_SIZE);
-
- chunk_size = mddev->chunk_sectors << 9;
- blk_queue_io_min(mddev->queue, chunk_size);
- raid5_set_io_opt(conf);
- mddev->queue->limits.raid_partial_stripes_expensive = 1;
- /*
- * We can only discard a whole stripe. It doesn't make sense to
- * discard data disk but write parity disk
- */
- stripe = stripe * PAGE_SIZE;
- stripe = roundup_pow_of_two(stripe);
- mddev->queue->limits.discard_granularity = stripe;
-
- blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
-
- rdev_for_each(rdev, mddev) {
- disk_stack_limits(mddev->gendisk, rdev->bdev,
- rdev->data_offset << 9);
- disk_stack_limits(mddev->gendisk, rdev->bdev,
- rdev->new_data_offset << 9);
- }
+ /*
+ * The read-ahead size must cover two whole stripes, which is
+ * 2 * (datadisks) * chunksize where 'n' is the number of raid devices.
+ */
+ data_disks = conf->previous_raid_disks - conf->max_degraded;
+ /*
+ * We can only discard a whole stripe. It doesn't make sense to
+ * discard data disk but write parity disk
+ */
+ stripe = roundup_pow_of_two(data_disks * (mddev->chunk_sectors << 9));
+
+ blk_set_stacking_limits(&lim);
+ lim.io_min = mddev->chunk_sectors << 9;
+ lim.io_opt = lim.io_min * (conf->raid_disks - conf->max_degraded);
+ lim.raid_partial_stripes_expensive = 1;
+ lim.discard_granularity = stripe;
+ lim.max_write_zeroes_sectors = 0;
+ mddev_stack_rdev_limits(mddev, &lim);
+ rdev_for_each(rdev, mddev) {
+ queue_limits_stack_bdev(&lim, rdev->bdev, rdev->new_data_offset,
+ mddev->gendisk->disk_name);
+ }
- /*
- * zeroing is required, otherwise data
- * could be lost. Consider a scenario: discard a stripe
- * (the stripe could be inconsistent if
- * discard_zeroes_data is 0); write one disk of the
- * stripe (the stripe could be inconsistent again
- * depending on which disks are used to calculate
- * parity); the disk is broken; The stripe data of this
- * disk is lost.
- *
- * We only allow DISCARD if the sysadmin has confirmed that
- * only safe devices are in use by setting a module parameter.
- * A better idea might be to turn DISCARD into WRITE_ZEROES
- * requests, as that is required to be safe.
- */
- if (!devices_handle_discard_safely ||
- mddev->queue->limits.max_discard_sectors < (stripe >> 9) ||
- mddev->queue->limits.discard_granularity < stripe)
- blk_queue_max_discard_sectors(mddev->queue, 0);
+ /*
+ * Zeroing is required for discard, otherwise data could be lost.
+ *
+ * Consider a scenario: discard a stripe (the stripe could be
+ * inconsistent if discard_zeroes_data is 0); write one disk of the
+ * stripe (the stripe could be inconsistent again depending on which
+ * disks are used to calculate parity); the disk is broken; The stripe
+ * data of this disk is lost.
+ *
+ * We only allow DISCARD if the sysadmin has confirmed that only safe
+ * devices are in use by setting a module parameter. A better idea
+ * might be to turn DISCARD into WRITE_ZEROES requests, as that is
+ * required to be safe.
+ */
+ if (!devices_handle_discard_safely ||
+ lim.max_discard_sectors < (stripe >> 9) ||
+ lim.discard_granularity < stripe)
+ lim.max_hw_discard_sectors = 0;
- /*
- * Requests require having a bitmap for each stripe.
- * Limit the max sectors based on this.
- */
- blk_queue_max_hw_sectors(mddev->queue,
- RAID5_MAX_REQ_STRIPES << RAID5_STRIPE_SHIFT(conf));
+ /*
+ * Requests require having a bitmap for each stripe.
+ * Limit the max sectors based on this.
+ */
+ lim.max_hw_sectors = RAID5_MAX_REQ_STRIPES << RAID5_STRIPE_SHIFT(conf);
- /* No restrictions on the number of segments in the request */
- blk_queue_max_segments(mddev->queue, USHRT_MAX);
- }
+ /* No restrictions on the number of segments in the request */
+ lim.max_segments = USHRT_MAX;
+ ret = queue_limits_set(mddev->queue, &lim);
+ if (ret)
+ goto abort;
if (log_init(conf, journal_dev, raid5_has_ppl(conf)))
goto abort;
@@ -8022,7 +8011,7 @@ static int raid5_run(struct mddev *mddev)
free_conf(conf);
mddev->private = NULL;
pr_warn("md/raid:%s: failed to run raid set.\n", mdname(mddev));
- return -EIO;
+ return ret;
}
static void raid5_free(struct mddev *mddev, void *priv)
@@ -8554,8 +8543,8 @@ static void end_reshape(struct r5conf *conf)
spin_unlock_irq(&conf->device_lock);
wake_up(&conf->wait_for_overlap);
- if (conf->mddev->queue)
- raid5_set_io_opt(conf);
+ mddev_update_io_opt(conf->mddev,
+ conf->raid_disks - conf->max_degraded);
}
}
--
2.39.2
next prev parent reply other threads:[~2024-02-26 11:34 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-02-26 10:29 atomic queue limit updates for stackable devices v2 Christoph Hellwig
2024-02-26 10:29 ` [PATCH 01/16] block: add a queue_limits_set helper Christoph Hellwig
2024-02-26 10:29 ` [PATCH 02/16] block: add a queue_limits_stack_bdev helper Christoph Hellwig
2024-02-26 10:29 ` [PATCH 03/16] dm: use queue_limits_set Christoph Hellwig
2024-02-26 10:29 ` [PATCH 04/16] md: add queue limit helpers Christoph Hellwig
2024-02-26 11:38 ` Yu Kuai
2024-02-27 14:36 ` Christoph Hellwig
2024-02-28 1:38 ` Yu Kuai
2024-02-26 10:29 ` [PATCH 05/16] md/raid0: use the atomic queue limit update APIs Christoph Hellwig
2024-02-26 10:29 ` [PATCH 06/16] md/raid1: " Christoph Hellwig
2024-02-26 11:29 ` Yu Kuai
2024-02-27 15:26 ` Christoph Hellwig
2024-02-27 21:54 ` Song Liu
2024-02-28 1:42 ` Yu Kuai
2024-02-26 10:29 ` [PATCH 07/16] md/raid10: " Christoph Hellwig
2024-02-26 10:29 ` Christoph Hellwig [this message]
2024-02-26 10:29 ` [PATCH 09/16] block: remove disk_stack_limits Christoph Hellwig
2024-02-26 10:29 ` [PATCH 10/16] drbd: pass the max_hw_sectors limit to blk_alloc_disk Christoph Hellwig
2024-03-03 15:14 ` drbd queue limits conversion ping Christoph Hellwig
2024-03-04 15:31 ` Philipp Reisner
2024-03-05 9:39 ` Philipp Reisner
2024-03-05 13:38 ` Christoph Hellwig
2024-02-26 10:29 ` [PATCH 11/16] drbd: refactor drbd_reconsider_queue_parameters Christoph Hellwig
2024-02-26 10:30 ` [PATCH 12/16] drbd: refactor the backing dev max_segments calculation Christoph Hellwig
2024-02-26 10:30 ` [PATCH 13/16] drbd: merge drbd_setup_queue_param into drbd_reconsider_queue_parameters Christoph Hellwig
2024-02-26 10:30 ` [PATCH 14/16] drbd: don't set max_write_zeroes_sectors in decide_on_discard_support Christoph Hellwig
2024-02-26 10:30 ` [PATCH 15/16] drbd: split out a drbd_discard_supported helper Christoph Hellwig
2024-02-26 10:30 ` [PATCH 16/16] drbd: atomically update queue limits in drbd_reconsider_queue_parameters Christoph Hellwig
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=20240226103004.281412-9-hch@lst.de \
--to=hch@lst.de \
--cc=axboe@kernel.dk \
--cc=christoph.boehmwalder@linbit.com \
--cc=dm-devel@lists.linux.dev \
--cc=drbd-dev@lists.linbit.com \
--cc=lars.ellenberg@linbit.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-raid@vger.kernel.org \
--cc=mpatocka@redhat.com \
--cc=philipp.reisner@linbit.com \
--cc=snitzer@kernel.org \
--cc=song@kernel.org \
--cc=yukuai3@huawei.com \
/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