From: Dan Williams <dan.j.williams@intel.com>
To: linux-kernel@vger.kernel.org, linux-raid@vger.kernel.org
Cc: neilb@suse.de, akpm@linux-foundation.org, davem@davemloft.net,
christopher.leech@intel.com, shannon.nelson@intel.com,
herbert@gondor.apana.org.au, jeff@garzik.org
Subject: [md-accel PATCH 12/19] md: handle_stripe5 - add request/completion logic for async read ops
Date: Tue, 26 Jun 2007 18:51:35 -0700 [thread overview]
Message-ID: <20070627015135.18962.52646.stgit@dwillia2-linux.ch.intel.com> (raw)
In-Reply-To: <20070627014823.18962.96398.stgit@dwillia2-linux.ch.intel.com>
When a read bio is attached to the stripe and the corresponding block is
marked R5_UPTODATE, then a read (biofill) operation is scheduled to copy
the data from the stripe cache to the bio buffer. handle_stripe flags the
blocks to be operated on with the R5_Wantfill flag. If new read requests
arrive while raid5_run_ops is running they will not be handled until
handle_stripe is scheduled to run again.
Changelog:
* cleanup to_read and to_fill accounting
* do not fail reads that have reached the cache
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Acked-By: NeilBrown <neilb@suse.de>
---
drivers/md/raid5.c | 53 +++++++++++++++++++++-----------------------
include/linux/raid/raid5.h | 2 +-
2 files changed, 26 insertions(+), 29 deletions(-)
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 89d3890..3d0dca9 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2042,9 +2042,12 @@ handle_requests_to_failed_array(raid5_conf_t *conf, struct stripe_head *sh,
bi = bi2;
}
- /* fail any reads if this device is non-operational */
- if (!test_bit(R5_Insync, &sh->dev[i].flags) ||
- test_bit(R5_ReadError, &sh->dev[i].flags)) {
+ /* fail any reads if this device is non-operational and
+ * the data has not reached the cache yet.
+ */
+ if (!test_bit(R5_Wantfill, &sh->dev[i].flags) &&
+ (!test_bit(R5_Insync, &sh->dev[i].flags) ||
+ test_bit(R5_ReadError, &sh->dev[i].flags))) {
bi = sh->dev[i].toread;
sh->dev[i].toread = NULL;
if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
@@ -2733,37 +2736,27 @@ static void handle_stripe5(struct stripe_head *sh)
struct r5dev *dev = &sh->dev[i];
clear_bit(R5_Insync, &dev->flags);
- pr_debug("check %d: state 0x%lx read %p write %p written %p\n",
- i, dev->flags, dev->toread, dev->towrite, dev->written);
- /* maybe we can reply to a read */
- if (test_bit(R5_UPTODATE, &dev->flags) && dev->toread) {
- struct bio *rbi, *rbi2;
- pr_debug("Return read for disc %d\n", i);
- spin_lock_irq(&conf->device_lock);
- rbi = dev->toread;
- dev->toread = NULL;
- if (test_and_clear_bit(R5_Overlap, &dev->flags))
- wake_up(&conf->wait_for_overlap);
- spin_unlock_irq(&conf->device_lock);
- while (rbi && rbi->bi_sector < dev->sector + STRIPE_SECTORS) {
- copy_data(0, rbi, dev->page, dev->sector);
- rbi2 = r5_next_bio(rbi, dev->sector);
- spin_lock_irq(&conf->device_lock);
- if (--rbi->bi_phys_segments == 0) {
- rbi->bi_next = return_bi;
- return_bi = rbi;
- }
- spin_unlock_irq(&conf->device_lock);
- rbi = rbi2;
- }
- }
+ pr_debug("check %d: state 0x%lx toread %p read %p write %p "
+ "written %p\n", i, dev->flags, dev->toread, dev->read,
+ dev->towrite, dev->written);
+
+ /* maybe we can request a biofill operation
+ *
+ * new wantfill requests are only permitted while
+ * STRIPE_OP_BIOFILL is clear
+ */
+ if (test_bit(R5_UPTODATE, &dev->flags) && dev->toread &&
+ !test_bit(STRIPE_OP_BIOFILL, &sh->ops.pending))
+ set_bit(R5_Wantfill, &dev->flags);
/* now count some things */
if (test_bit(R5_LOCKED, &dev->flags)) s.locked++;
if (test_bit(R5_UPTODATE, &dev->flags)) s.uptodate++;
if (test_bit(R5_Wantcompute, &dev->flags)) s.compute++;
- if (dev->toread)
+ if (test_bit(R5_Wantfill, &dev->flags))
+ s.to_fill++;
+ else if (dev->toread)
s.to_read++;
if (dev->towrite) {
s.to_write++;
@@ -2786,6 +2779,10 @@ static void handle_stripe5(struct stripe_head *sh)
set_bit(R5_Insync, &dev->flags);
}
rcu_read_unlock();
+
+ if (s.to_fill && !test_and_set_bit(STRIPE_OP_BIOFILL, &sh->ops.pending))
+ sh->ops.count++;
+
pr_debug("locked=%d uptodate=%d to_read=%d"
" to_write=%d failed=%d failed_num=%d\n",
s.locked, s.uptodate, s.to_read, s.to_write,
diff --git a/include/linux/raid/raid5.h b/include/linux/raid/raid5.h
index 2d45eba..e9dfb2d 100644
--- a/include/linux/raid/raid5.h
+++ b/include/linux/raid/raid5.h
@@ -200,7 +200,7 @@ struct stripe_head {
struct stripe_head_state {
int syncing, expanding, expanded;
int locked, uptodate, to_read, to_write, failed, written;
- int compute, req_compute, non_overwrite, dirty;
+ int to_fill, compute, req_compute, non_overwrite, dirty;
int failed_num;
};
next prev parent reply other threads:[~2007-06-27 1:51 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-06-27 1:50 [md-accel PATCH 00/19] md raid acceleration and the async_tx api Dan Williams
2007-06-27 1:50 ` [md-accel PATCH 01/19] dmaengine: refactor dmaengine around dma_async_tx_descriptor Dan Williams
2007-06-27 1:50 ` [md-accel PATCH 02/19] dmaengine: make clients responsible for managing channels Dan Williams
2007-06-27 1:50 ` [md-accel PATCH 03/19] xor: make 'xor_blocks' a library routine for use with async_tx Dan Williams
2007-06-27 6:39 ` Satyam Sharma
2007-06-27 16:13 ` Dan Williams
2007-06-27 16:22 ` Herbert Xu
2007-06-27 1:50 ` [md-accel PATCH 04/19] async_tx: add the async_tx api Dan Williams
2007-06-27 1:51 ` [md-accel PATCH 05/19] raid5: refactor handle_stripe5 and handle_stripe6 (v2) Dan Williams
2007-06-27 1:51 ` [md-accel PATCH 06/19] raid5: replace custom debug PRINTKs with standard pr_debug Dan Williams
2007-06-27 1:51 ` [md-accel PATCH 07/19] md: raid5_run_ops - run stripe operations outside sh->lock Dan Williams
2007-06-27 1:51 ` [md-accel PATCH 08/19] md: common infrastructure for running operations with raid5_run_ops Dan Williams
2007-06-27 1:51 ` [md-accel PATCH 09/19] md: handle_stripe5 - add request/completion logic for async write ops Dan Williams
2007-06-27 1:51 ` [md-accel PATCH 10/19] md: handle_stripe5 - add request/completion logic for async compute ops Dan Williams
2007-06-27 1:51 ` [md-accel PATCH 11/19] md: handle_stripe5 - add request/completion logic for async check ops Dan Williams
2007-06-27 1:51 ` Dan Williams [this message]
2007-06-27 1:51 ` [md-accel PATCH 13/19] md: handle_stripe5 - add request/completion logic for async expand ops Dan Williams
2007-06-27 1:51 ` [md-accel PATCH 14/19] md: handle_stripe5 - request io processing in raid5_run_ops Dan Williams
2007-06-27 1:51 ` [md-accel PATCH 15/19] md: remove raid5 compute_block and compute_parity5 Dan Williams
2007-06-27 1:51 ` [md-accel PATCH 16/19] dmaengine: driver for the iop32x, iop33x, and iop13xx raid engines Dan Williams
2007-08-27 13:11 ` saeed bishara
2007-08-27 13:14 ` saeed bishara
2007-08-27 19:31 ` Williams, Dan J
2007-08-30 18:43 ` saeed bishara
2007-08-30 20:41 ` Dan Williams
2007-06-27 1:52 ` [md-accel PATCH 17/19] iop13xx: surface the iop13xx adma units to the iop-adma driver Dan Williams
2007-06-27 1:52 ` [md-accel PATCH 18/19] iop3xx: surface the iop3xx DMA and AAU " Dan Williams
2007-06-27 1:52 ` [md-accel PATCH 19/19] ARM: Add drivers/dma to arch/arm/Kconfig Dan Williams
2007-06-27 3:49 ` [md-accel PATCH 00/19] md raid acceleration and the async_tx api Mr. James W. Laferriere
2007-06-27 4:02 ` Dan Williams
2007-06-27 16:45 ` Bill Davidsen
2007-06-27 17:09 ` Williams, Dan J
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=20070627015135.18962.52646.stgit@dwillia2-linux.ch.intel.com \
--to=dan.j.williams@intel.com \
--cc=akpm@linux-foundation.org \
--cc=christopher.leech@intel.com \
--cc=davem@davemloft.net \
--cc=herbert@gondor.apana.org.au \
--cc=jeff@garzik.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-raid@vger.kernel.org \
--cc=neilb@suse.de \
--cc=shannon.nelson@intel.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;
as well as URLs for NNTP newsgroup(s).