linux-raid.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: NeilBrown <neilb@suse.de>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-raid@vger.kernel.org, linux-kernel@vger.kernel.org,
	Dan Williams <dan.j.williams@intel.com>
Subject: [PATCH 027 of 29] md: md: replace R5_WantPrexor with R5_WantDrain, add 'prexor' reconstruct_states
Date: Fri, 27 Jun 2008 16:52:18 +1000	[thread overview]
Message-ID: <1080627065218.10761@suse.de> (raw)
In-Reply-To: 20080627164503.9671.patches@notabene


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

Currently ops_run_biodrain and other locations have extra logic to determine
which blocks are processed in the prexor and non-prexor cases.  This can be
eliminated if handle_write_operations5 flags the blocks to be processed in all
cases via R5_Wantdrain.  The presence of the prexor operation is tracked in
sh->reconstruct_state.

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Neil Brown <neilb@suse.de>

### Diffstat output
 ./drivers/md/raid5.c         |   89 ++++++++++++++-----------------------------
 ./include/linux/raid/raid5.h |    6 +-
 2 files changed, 32 insertions(+), 63 deletions(-)

diff .prev/drivers/md/raid5.c ./drivers/md/raid5.c
--- .prev/drivers/md/raid5.c	2008-06-27 16:42:36.000000000 +1000
+++ ./drivers/md/raid5.c	2008-06-27 16:42:56.000000000 +1000
@@ -637,7 +637,7 @@ ops_run_prexor(struct stripe_head *sh, s
 	for (i = disks; i--; ) {
 		struct r5dev *dev = &sh->dev[i];
 		/* Only process blocks that are known to be uptodate */
-		if (dev->towrite && test_bit(R5_Wantprexor, &dev->flags))
+		if (test_bit(R5_Wantdrain, &dev->flags))
 			xor_srcs[count++] = dev->page;
 	}
 
@@ -649,16 +649,10 @@ ops_run_prexor(struct stripe_head *sh, s
 }
 
 static struct dma_async_tx_descriptor *
-ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx,
-		 unsigned long ops_request)
+ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
 {
 	int disks = sh->disks;
-	int pd_idx = sh->pd_idx, i;
-
-	/* check if prexor is active which means only process blocks
-	 * that are part of a read-modify-write (Wantprexor)
-	 */
-	int prexor = test_bit(STRIPE_OP_PREXOR, &ops_request);
+	int i;
 
 	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
@@ -666,20 +660,8 @@ ops_run_biodrain(struct stripe_head *sh,
 	for (i = disks; i--; ) {
 		struct r5dev *dev = &sh->dev[i];
 		struct bio *chosen;
-		int towrite;
 
-		towrite = 0;
-		if (prexor) { /* rmw */
-			if (dev->towrite &&
-			    test_bit(R5_Wantprexor, &dev->flags))
-				towrite = 1;
-		} else { /* rcw */
-			if (i != pd_idx && dev->towrite &&
-				test_bit(R5_LOCKED, &dev->flags))
-				towrite = 1;
-		}
-
-		if (towrite) {
+		if (test_and_clear_bit(R5_Wantdrain, &dev->flags)) {
 			struct bio *wbi;
 
 			spin_lock(&sh->lock);
@@ -704,18 +686,6 @@ ops_run_biodrain(struct stripe_head *sh,
 static void ops_complete_postxor(void *stripe_head_ref)
 {
 	struct stripe_head *sh = stripe_head_ref;
-
-	pr_debug("%s: stripe %llu\n", __func__,
-		(unsigned long long)sh->sector);
-
-	sh->reconstruct_state = reconstruct_state_result;
-	set_bit(STRIPE_HANDLE, &sh->state);
-	release_stripe(sh);
-}
-
-static void ops_complete_write(void *stripe_head_ref)
-{
-	struct stripe_head *sh = stripe_head_ref;
 	int disks = sh->disks, i, pd_idx = sh->pd_idx;
 
 	pr_debug("%s: stripe %llu\n", __func__,
@@ -727,14 +697,21 @@ static void ops_complete_write(void *str
 			set_bit(R5_UPTODATE, &dev->flags);
 	}
 
-	sh->reconstruct_state = reconstruct_state_drain_result;
+	if (sh->reconstruct_state == reconstruct_state_drain_run)
+		sh->reconstruct_state = reconstruct_state_drain_result;
+	else if (sh->reconstruct_state == reconstruct_state_prexor_drain_run)
+		sh->reconstruct_state = reconstruct_state_prexor_drain_result;
+	else {
+		BUG_ON(sh->reconstruct_state != reconstruct_state_run);
+		sh->reconstruct_state = reconstruct_state_result;
+	}
+
 	set_bit(STRIPE_HANDLE, &sh->state);
 	release_stripe(sh);
 }
 
 static void
-ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx,
-		unsigned long ops_request)
+ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
 {
 	/* kernel stack size limits the total number of disks */
 	int disks = sh->disks;
@@ -742,9 +719,8 @@ ops_run_postxor(struct stripe_head *sh, 
 
 	int count = 0, pd_idx = sh->pd_idx, i;
 	struct page *xor_dest;
-	int prexor = test_bit(STRIPE_OP_PREXOR, &ops_request);
+	int prexor = 0;
 	unsigned long flags;
-	dma_async_tx_callback callback;
 
 	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
@@ -752,7 +728,8 @@ ops_run_postxor(struct stripe_head *sh, 
 	/* check if prexor is active which means only process blocks
 	 * that are part of a read-modify-write (written)
 	 */
-	if (prexor) {
+	if (sh->reconstruct_state == reconstruct_state_prexor_drain_run) {
+		prexor = 1;
 		xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page;
 		for (i = disks; i--; ) {
 			struct r5dev *dev = &sh->dev[i];
@@ -768,10 +745,6 @@ ops_run_postxor(struct stripe_head *sh, 
 		}
 	}
 
-	/* check whether this postxor is part of a write */
-	callback = test_bit(STRIPE_OP_BIODRAIN, &ops_request) ?
-		ops_complete_write : ops_complete_postxor;
-
 	/* 1/ if we prexor'd then the dest is reused as a source
 	 * 2/ if we did not prexor then we are redoing the parity
 	 * set ASYNC_TX_XOR_DROP_DST and ASYNC_TX_XOR_ZERO_DST
@@ -785,10 +758,10 @@ ops_run_postxor(struct stripe_head *sh, 
 	if (unlikely(count == 1)) {
 		flags &= ~(ASYNC_TX_XOR_DROP_DST | ASYNC_TX_XOR_ZERO_DST);
 		tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE,
-			flags, tx, callback, sh);
+			flags, tx, ops_complete_postxor, sh);
 	} else
 		tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE,
-			flags, tx, callback, sh);
+			flags, tx, ops_complete_postxor, sh);
 }
 
 static void ops_complete_check(void *stripe_head_ref)
@@ -847,12 +820,12 @@ static void raid5_run_ops(struct stripe_
 		tx = ops_run_prexor(sh, tx);
 
 	if (test_bit(STRIPE_OP_BIODRAIN, &ops_request)) {
-		tx = ops_run_biodrain(sh, tx, ops_request);
+		tx = ops_run_biodrain(sh, tx);
 		overlap_clear++;
 	}
 
 	if (test_bit(STRIPE_OP_POSTXOR, &ops_request))
-		ops_run_postxor(sh, tx, ops_request);
+		ops_run_postxor(sh, tx);
 
 	if (test_bit(STRIPE_OP_CHECK, &ops_request))
 		ops_run_check(sh);
@@ -1669,6 +1642,7 @@ handle_write_operations5(struct stripe_h
 
 			if (dev->towrite) {
 				set_bit(R5_LOCKED, &dev->flags);
+				set_bit(R5_Wantdrain, &dev->flags);
 				if (!expand)
 					clear_bit(R5_UPTODATE, &dev->flags);
 				s->locked++;
@@ -1681,7 +1655,7 @@ handle_write_operations5(struct stripe_h
 		BUG_ON(!(test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags) ||
 			test_bit(R5_Wantcompute, &sh->dev[pd_idx].flags)));
 
-		sh->reconstruct_state = reconstruct_state_drain_run;
+		sh->reconstruct_state = reconstruct_state_prexor_drain_run;
 		set_bit(STRIPE_OP_PREXOR, &s->ops_request);
 		set_bit(STRIPE_OP_BIODRAIN, &s->ops_request);
 		set_bit(STRIPE_OP_POSTXOR, &s->ops_request);
@@ -1691,15 +1665,10 @@ handle_write_operations5(struct stripe_h
 			if (i == pd_idx)
 				continue;
 
-			/* For a read-modify write there may be blocks that are
-			 * locked for reading while others are ready to be
-			 * written so we distinguish these blocks by the
-			 * R5_Wantprexor bit
-			 */
 			if (dev->towrite &&
 			    (test_bit(R5_UPTODATE, &dev->flags) ||
-			    test_bit(R5_Wantcompute, &dev->flags))) {
-				set_bit(R5_Wantprexor, &dev->flags);
+			     test_bit(R5_Wantcompute, &dev->flags))) {
+				set_bit(R5_Wantdrain, &dev->flags);
 				set_bit(R5_LOCKED, &dev->flags);
 				clear_bit(R5_UPTODATE, &dev->flags);
 				s->locked++;
@@ -2660,11 +2629,11 @@ static void handle_stripe5(struct stripe
 	 * completed
 	 */
 	prexor = 0;
-	if (sh->reconstruct_state == reconstruct_state_drain_result) {
+	if (sh->reconstruct_state == reconstruct_state_prexor_drain_result)
+		prexor = 1;
+	if (sh->reconstruct_state == reconstruct_state_drain_result ||
+	    sh->reconstruct_state == reconstruct_state_prexor_drain_result) {
 		sh->reconstruct_state = reconstruct_state_idle;
-		for (i = disks; i--; )
-			prexor += test_and_clear_bit(R5_Wantprexor,
-						     &sh->dev[i].flags);
 
 		/* All the 'written' buffers and the parity block are ready to
 		 * be written back to disk

diff .prev/include/linux/raid/raid5.h ./include/linux/raid/raid5.h
--- .prev/include/linux/raid/raid5.h	2008-06-27 16:42:36.000000000 +1000
+++ ./include/linux/raid/raid5.h	2008-06-27 16:42:56.000000000 +1000
@@ -187,8 +187,10 @@ enum check_states {
  */
 enum reconstruct_states {
 	reconstruct_state_idle = 0,
+	reconstruct_state_prexor_drain_run,	/* prexor-write */
 	reconstruct_state_drain_run,		/* write */
 	reconstruct_state_run,			/* expand */
+	reconstruct_state_prexor_drain_result,
 	reconstruct_state_drain_result,
 	reconstruct_state_result,
 };
@@ -258,9 +260,7 @@ struct r6_state {
 #define	R5_Wantfill	12 /* dev->toread contains a bio that needs
 				    * filling
 				    */
-#define	R5_Wantprexor	13 /* distinguish blocks ready for rmw from
-				    * other "towrites"
-				    */
+#define R5_Wantdrain	13 /* dev->towrite needs to be drained */
 /*
  * Write method
  */

  parent reply	other threads:[~2008-06-27  6:52 UTC|newest]

Thread overview: 47+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-06-27  6:49 [PATCH 000 of 29] md: Introduction : patchbomb for 2.6.27 merge window NeilBrown
2008-06-27  6:49 ` [PATCH 001 of 29] md: Ensure interrupted recovery completed properly (v1 metadata plus bitmap) NeilBrown
2008-07-01  7:20   ` Jan Engelhardt
2008-06-27  6:49 ` [PATCH 002 of 29] md: Don't acknowlege that stripe-expand is complete until it really is NeilBrown
2008-06-27  6:49 ` [PATCH 003 of 29] md: Fix error paths if md_probe fails NeilBrown
2008-06-27  6:49 ` [PATCH 004 of 29] md: linear: correct disk numbering error check NeilBrown
2008-06-27  6:49 ` [PATCH 005 of 29] md: use bio_endio instead of a call to bi_end_io NeilBrown
2008-06-27  6:49 ` [PATCH 006 of 29] md: Improve setting of "events_cleared" for write-intent bitmaps NeilBrown
2008-06-27  6:50 ` [PATCH 007 of 29] md: Allow setting start point for requested check/repair NeilBrown
2008-06-27  6:50 ` [PATCH 008 of 29] md: Close race in md_probe NeilBrown
2008-06-27 12:21   ` Andre Noll
2008-06-27 23:38     ` Neil Brown
2008-06-30  7:52       ` Andre Noll
2008-06-27  6:50 ` [PATCH 009 of 29] md: Don't try to make md arrays dirty if that is not meaningful NeilBrown
2008-06-27  6:50 ` [PATCH 010 of 29] md: Enable setting of 'offset' and 'size' of a hot-added spare NeilBrown
2008-06-27  6:50 ` [PATCH 011 of 29] md: Support adding a spare to a live md array with external metadata NeilBrown
2008-06-27  6:50 ` [PATCH 012 of 29] md: rationalise return value for ->hot_add_disk method NeilBrown
2008-06-27  6:50 ` [PATCH 013 of 29] md: Don't reject HOT_REMOVE_DISK request for an array that is not yet started NeilBrown
2008-06-27  6:50 ` [PATCH 014 of 29] md: Make sure all changes to md/array_state are notified NeilBrown
2008-06-27  6:50 ` [PATCH 015 of 29] md: Make sure all changes to md/sync_action " NeilBrown
2008-06-27  6:51 ` [PATCH 016 of 29] md: Make sure all changes to md/degraded " NeilBrown
2008-06-27  6:51 ` [PATCH 017 of 29] md: Make sure all changes to md/dev-XX/state " NeilBrown
2008-06-27  6:51 ` [PATCH 018 of 29] md: Support changing rdev size on running arrays NeilBrown
2008-06-27 16:09   ` Markus Hochholdinger
2008-06-27 23:41     ` Neil Brown
2010-03-30 14:52       ` Markus Hochholdinger
2010-03-31  5:41         ` Neil Brown
2010-04-01 15:23           ` Markus Hochholdinger
2012-03-24 20:47       ` Markus Hochholdinger
2012-03-25 22:15         ` NeilBrown
2021-11-10 13:09         ` Markus Hochholdinger
2021-11-10 17:51           ` Markus Hochholdinger
2021-11-11 13:10             ` Markus Hochholdinger
2021-11-11 15:09               ` Markus Hochholdinger
2021-11-12  1:22                 ` Guoqing Jiang
2021-11-12 14:31                   ` Markus Hochholdinger
2008-06-27  6:51 ` [PATCH 019 of 29] md: md: kill STRIPE_OP_MOD_DMA in raid5 offload NeilBrown
2008-06-27  6:51 ` [PATCH 020 of 29] md: md: kill STRIPE_OP_IO flag NeilBrown
2008-06-27  6:51 ` [PATCH 021 of 29] md: md: use stripe_head_state in ops_run_io() NeilBrown
2008-06-27  6:51 ` [PATCH 022 of 29] md: md: unify raid5/6 i/o submission NeilBrown
2008-06-27  6:51 ` [PATCH 023 of 29] md: md: replace STRIPE_OP_CHECK with 'check_states' NeilBrown
2008-06-27  6:51 ` [PATCH 024 of 29] md: md: replace STRIPE_OP_BIOFILL with STRIPE_BIOFILL_RUN NeilBrown
2008-06-27  6:52 ` [PATCH 025 of 29] md: md: replace STRIPE_OP_COMPUTE_BLK with STRIPE_COMPUTE_RUN NeilBrown
2008-06-27  6:52 ` [PATCH 026 of 29] md: md: replace STRIPE_OP_{BIODRAIN,PREXOR,POSTXOR} with 'reconstruct_states' NeilBrown
2008-06-27  6:52 ` NeilBrown [this message]
2008-06-27  6:52 ` [PATCH 028 of 29] md: md: handle operation chaining in raid5_run_ops NeilBrown
2008-06-27  6:52 ` [PATCH 029 of 29] md: md: rationalize raid5 function names NeilBrown

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=1080627065218.10761@suse.de \
    --to=neilb@suse.de \
    --cc=akpm@linux-foundation.org \
    --cc=dan.j.williams@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-raid@vger.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).