LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Dan Williams <dan.j.williams@intel.com>
To: neilb@suse.de, linux-raid@vger.kernel.org
Cc: akpm@osdl.org, linux-kernel@vger.kernel.org, christopher.leech@intel.com
Subject: [PATCH 05/19] raid5: move read completion copies to a workqueue
Date: Mon, 11 Sep 2006 16:18:02 -0700	[thread overview]
Message-ID: <20060911231801.4737.12584.stgit@dwillia2-linux.ch.intel.com> (raw)
In-Reply-To: <1158015632.4241.31.camel@dwillia2-linux.ch.intel.com>

From: Dan Williams <dan.j.williams@intel.com>

Enable handle_stripe5 to hand off the memory copy operations that satisfy
read requests to raid5_do_soft_blocks_ops, formerly this was handled in
line within handle_stripe5.

It adds a 'read' (past tense) pointer to the r5dev structure
to to track reads that have been offloaded to the workqueue.  When the copy
operation is complete the 'read' pointer is reused as the return_bi for the
bi_end_io() call.

Changelog:
* dev->read only holds reads that have been satisfied, previously it
doubled as a request queue to the operations routine
* added R5_ReadReq to mark the blocks that belong to a given bio fill
operation
* requested reads no longer count towards the 'to_read' count, 'to_fill'
tracks the number of requested reads

Signed-off-by: Dan Williams <dan.j.willams@intel.com>
---

 drivers/md/raid5.c |   67 +++++++++++++++++++++++++++++-----------------------
 1 files changed, 38 insertions(+), 29 deletions(-)

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 0c39203..1a8dfd2 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -240,11 +240,11 @@ static void init_stripe(struct stripe_he
 	for (i = sh->disks; i--; ) {
 		struct r5dev *dev = &sh->dev[i];
 
-		if (dev->toread || dev->towrite || dev->written ||
+		if (dev->toread || dev->read || dev->towrite || dev->written ||
 		    test_bit(R5_LOCKED, &dev->flags)) {
-			printk("sector=%llx i=%d %p %p %p %d\n",
+			printk("sector=%llx i=%d %p %p %p %p %d\n",
 			       (unsigned long long)sh->sector, i, dev->toread,
-			       dev->towrite, dev->written,
+			       dev->read, dev->towrite, dev->written,
 			       test_bit(R5_LOCKED, &dev->flags));
 			BUG();
 		}
@@ -1749,7 +1749,7 @@ static void handle_stripe5(struct stripe
 	struct bio *bi;
 	int i;
 	int syncing, expanding, expanded;
-	int locked=0, uptodate=0, to_read=0, to_write=0, failed=0, written=0;
+	int locked=0, uptodate=0, to_read=0, to_write=0, failed=0, written=0, to_fill=0;
 	int compute=0, non_overwrite=0, write_complete=0;
 	int failed_num=0;
 	struct r5dev *dev;
@@ -1765,44 +1765,47 @@ static void handle_stripe5(struct stripe
 	syncing = test_bit(STRIPE_SYNCING, &sh->state);
 	expanding = test_bit(STRIPE_EXPAND_SOURCE, &sh->state);
 	expanded = test_bit(STRIPE_EXPAND_READY, &sh->state);
-	/* Now to look around and see what can be done */
 
+	if (test_bit(STRIPE_OP_BIOFILL, &sh->state) &&
+		test_bit(STRIPE_OP_BIOFILL_Done, &sh->ops.state)) {
+		clear_bit(STRIPE_OP_BIOFILL, &sh->state);
+		clear_bit(STRIPE_OP_BIOFILL_Done, &sh->ops.state);
+	}
+
+	/* Now to look around and see what can be done */
 	rcu_read_lock();
 	for (i=disks; i--; ) {
 		mdk_rdev_t *rdev;
 		dev = &sh->dev[i];
 		clear_bit(R5_Insync, &dev->flags);
 
-		PRINTK("check %d: state 0x%lx read %p write %p written %p\n",
-			i, dev->flags, dev->toread, dev->towrite, dev->written);
+		PRINTK("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 acknowledge completion of a biofill operation */
+		if (test_bit(R5_ReadReq, &dev->flags) && !dev->toread)
+			clear_bit(R5_ReadReq, &dev->flags);
+
 		/* maybe we can reply to a read */
+		if (dev->read && !test_bit(R5_ReadReq, &dev->flags) &&
+			!test_bit(STRIPE_OP_BIOFILL, &sh->state)) {
+			return_bi = dev->read;
+			dev->read = NULL;
+		}
+
+		/* maybe we can start a biofill operation */
 		if (test_bit(R5_UPTODATE, &dev->flags) && dev->toread) {
-			struct bio *rbi, *rbi2;
-			PRINTK("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;
-			}
+			to_read--;
+			if (!test_bit(STRIPE_OP_BIOFILL, &sh->state))
+				set_bit(R5_ReadReq, &dev->flags);
 		}
 
 		/* now count some things */
 		if (test_bit(R5_LOCKED, &dev->flags)) locked++;
 		if (test_bit(R5_UPTODATE, &dev->flags)) uptodate++;
+		if (test_bit(R5_ReadReq, &dev->flags)) to_fill++;
 		if (test_bit(R5_ComputeReq, &dev->flags)) BUG_ON(++compute > 1);
-		
+
 		if (dev->toread) to_read++;
 		if (dev->towrite) {
 			to_write++;
@@ -1824,9 +1827,15 @@ static void handle_stripe5(struct stripe
 			set_bit(R5_Insync, &dev->flags);
 	}
 	rcu_read_unlock();
+
+	if (to_fill && !test_bit(STRIPE_OP_BIOFILL, &sh->state)) {
+		set_bit(STRIPE_OP_BIOFILL, &sh->state);
+		sh->ops.pending++;
+	}
+
 	PRINTK("locked=%d uptodate=%d to_read=%d"
-		" to_write=%d failed=%d failed_num=%d\n",
-		locked, uptodate, to_read, to_write, failed, failed_num);
+		" to_write=%d to_fill=%d failed=%d failed_num=%d\n",
+		locked, uptodate, to_read, to_write, to_fill, failed, failed_num);
 	/* check if the array has lost two devices and, if so, some requests might
 	 * need to be failed
 	 */

  parent reply	other threads:[~2006-09-11 23:18 UTC|newest]

Thread overview: 55+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-09-11 23:00 [PATCH 00/19] Hardware Accelerated MD RAID5: Introduction Dan Williams
2006-09-11 23:17 ` [PATCH 01/19] raid5: raid5_do_soft_block_ops Dan Williams
2006-09-11 23:34   ` Jeff Garzik
2006-09-11 23:17 ` [PATCH 02/19] raid5: move write operations to a workqueue Dan Williams
2006-09-11 23:36   ` Jeff Garzik
2006-09-11 23:17 ` [PATCH 03/19] raid5: move check parity " Dan Williams
2006-09-11 23:17 ` [PATCH 04/19] raid5: move compute block " Dan Williams
2006-09-11 23:18 ` Dan Williams [this message]
2006-09-11 23:18 ` [PATCH 06/19] raid5: move the reconstruct write expansion operation " Dan Williams
2006-09-11 23:18 ` [PATCH 07/19] raid5: remove compute_block and compute_parity5 Dan Williams
2006-09-11 23:18 ` [PATCH 08/19] dmaengine: enable multiple clients and operations Dan Williams
2006-09-11 23:44   ` Jeff Garzik
2006-09-12  0:14     ` Dan Williams
2006-09-12  0:52       ` Roland Dreier
2006-09-12  6:18         ` Dan Williams
2006-09-12  9:15           ` Evgeniy Polyakov
2006-09-13  4:04           ` Jeff Garzik
2006-09-15 16:38     ` Olof Johansson
2006-09-15 19:44       ` [PATCH] dmaengine: clean up and abstract function types (was Re: [PATCH 08/19] dmaengine: enable multiple clients and operations) Olof Johansson
2006-09-15 20:02         ` [PATCH] [v2] " Olof Johansson
2006-09-18 22:56         ` [PATCH] " Dan Williams
2006-09-19  1:05           ` Olof Johansson
2006-09-19 11:20             ` Alan Cox
2006-09-19 16:32               ` Olof Johansson
2006-09-11 23:18 ` [PATCH 09/19] dmaengine: reduce backend address permutations Dan Williams
2006-09-15 14:46   ` Olof Johansson
2006-09-11 23:18 ` [PATCH 10/19] dmaengine: expose per channel dma mapping characteristics to clients Dan Williams
2006-09-11 23:18 ` [PATCH 11/19] dmaengine: add memset as an asynchronous dma operation Dan Williams
2006-09-11 23:50   ` Jeff Garzik
2006-09-11 23:18 ` [PATCH 12/19] dmaengine: dma_async_memcpy_err for DMA engines that do not support memcpy Dan Williams
2006-09-11 23:51   ` Jeff Garzik
2006-09-11 23:18 ` [PATCH 13/19] dmaengine: add support for dma xor zero sum operations Dan Williams
2006-09-11 23:18 ` [PATCH 14/19] dmaengine: add dma_sync_wait Dan Williams
2006-09-11 23:52   ` Jeff Garzik
2006-09-11 23:18 ` [PATCH 15/19] dmaengine: raid5 dma client Dan Williams
2006-09-11 23:54   ` Jeff Garzik
2006-09-11 23:19 ` [PATCH 16/19] dmaengine: Driver for the Intel IOP 32x, 33x, and 13xx RAID engines Dan Williams
2006-09-15 14:57   ` Olof Johansson
2006-09-11 23:19 ` [PATCH 17/19] iop3xx: define IOP3XX_REG_ADDR[32|16|8] and clean up DMA/AAU defs Dan Williams
2006-09-11 23:55   ` Jeff Garzik
2006-09-11 23:19 ` [PATCH 18/19] iop3xx: Give Linux control over PCI (ATU) initialization Dan Williams
2006-09-11 23:56   ` Jeff Garzik
2006-09-11 23:19 ` [PATCH 19/19] iop3xx: IOP 32x and 33x support for the iop-adma driver Dan Williams
2006-09-11 23:38 ` [PATCH 00/19] Hardware Accelerated MD RAID5: Introduction Jeff Garzik
2006-09-11 23:53   ` Dan Williams
2006-09-12  2:41     ` Jeff Garzik
2006-09-12  5:47       ` Dan Williams
2006-09-13  4:05         ` Jeff Garzik
2006-09-13  7:15 ` Jakob Oestergaard
2006-09-13 19:17   ` Dan Williams
2006-09-14  7:42     ` Jakob Oestergaard
2006-10-11  1:46       ` Dan Williams
2006-10-08 22:18 ` Neil Brown
2006-10-10 18:23   ` Dan Williams
2006-10-11  2:44     ` Neil Brown

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=20060911231801.4737.12584.stgit@dwillia2-linux.ch.intel.com \
    --to=dan.j.williams@intel.com \
    --cc=akpm@osdl.org \
    --cc=christopher.leech@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-raid@vger.kernel.org \
    --cc=neilb@suse.de \
    --subject='Re: [PATCH 05/19] raid5: move read completion copies to a workqueue' \
    /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

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).