From 4e857c58efeb99393cba5a5d0d8ec7117183137c Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 17 Mar 2014 18:06:10 +0100
Subject: arch: Mass conversion of smp_mb__*()
Mostly scripted conversion of the smp_mb__* barriers.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/n/tip-55dhyhocezdw1dg7u19hmh1u@git.kernel.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-arch@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
drivers/md/raid5.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'drivers/md/raid5.c')
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index ad1b9bea446..2afef4ec931 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -4400,7 +4400,7 @@ static void raid5_unplug(struct blk_plug_cb *blk_cb, bool from_schedule)
* STRIPE_ON_UNPLUG_LIST clear but the stripe
* is still in our list
*/
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(STRIPE_ON_UNPLUG_LIST, &sh->state);
/*
* STRIPE_ON_RELEASE_LIST could be set here. In that
--
cgit v1.2.3-70-g09d2
From 67f455486d2ea20b2d94d6adf5b9b783d079e321 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.de>
Date: Wed, 28 May 2014 13:39:22 +1000
Subject: md/raid56: Don't perform reads to support writes until stripe is
ready.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
If it is found that we need to pre-read some blocks before a write
can succeed, we normally set STRIPE_DELAYED and don't actually perform
the read until STRIPE_PREREAD_ACTIVE subsequently gets set.
However for a degraded RAID6 we currently perform the reads as soon
as we see that a write is pending. This significantly hurts
throughput.
So:
- when handle_stripe_dirtying find a block that it wants on a device
that is failed, set STRIPE_DELAY, instead of doing nothing, and
- when fetch_block detects that a read might be required to satisfy a
write, only perform the read if STRIPE_PREREAD_ACTIVE is set,
and if we would actually need to read something to complete the write.
This also helps RAID5, though less often as RAID5 supports a
read-modify-write cycle. For RAID5 the read is performed too early
only if the write is not a full 4K aligned write (i.e. no an
R5_OVERWRITE).
Also clean up a couple of horrible bits of formatting.
Reported-by: Patrik Horník <patrik@dsl.sk>
Signed-off-by: NeilBrown <neilb@suse.de>
---
drivers/md/raid5.c | 30 ++++++++++++++++++------------
1 file changed, 18 insertions(+), 12 deletions(-)
(limited to 'drivers/md/raid5.c')
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index ad1b9bea446..c1e8607d834 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -292,9 +292,12 @@ static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh,
BUG_ON(atomic_read(&conf->active_stripes)==0);
if (test_bit(STRIPE_HANDLE, &sh->state)) {
if (test_bit(STRIPE_DELAYED, &sh->state) &&
- !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
+ !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
list_add_tail(&sh->lru, &conf->delayed_list);
- else if (test_bit(STRIPE_BIT_DELAY, &sh->state) &&
+ if (atomic_read(&conf->preread_active_stripes)
+ < IO_THRESHOLD)
+ md_wakeup_thread(conf->mddev->thread);
+ } else if (test_bit(STRIPE_BIT_DELAY, &sh->state) &&
sh->bm_seq - conf->seq_write > 0)
list_add_tail(&sh->lru, &conf->bitmap_list);
else {
@@ -2886,8 +2889,11 @@ static int fetch_block(struct stripe_head *sh, struct stripe_head_state *s,
(s->failed >= 1 && fdev[0]->toread) ||
(s->failed >= 2 && fdev[1]->toread) ||
(sh->raid_conf->level <= 5 && s->failed && fdev[0]->towrite &&
+ (!test_bit(R5_Insync, &dev->flags) || test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) &&
!test_bit(R5_OVERWRITE, &fdev[0]->flags)) ||
- (sh->raid_conf->level == 6 && s->failed && s->to_write))) {
+ (sh->raid_conf->level == 6 && s->failed && s->to_write &&
+ s->to_write < sh->raid_conf->raid_disks - 2 &&
+ (!test_bit(R5_Insync, &dev->flags) || test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))))) {
/* we would like to get this block, possibly by computing it,
* otherwise read it if the backing disk is insync
*/
@@ -3086,7 +3092,8 @@ static void handle_stripe_dirtying(struct r5conf *conf,
!test_bit(R5_LOCKED, &dev->flags) &&
!(test_bit(R5_UPTODATE, &dev->flags) ||
test_bit(R5_Wantcompute, &dev->flags))) {
- if (test_bit(R5_Insync, &dev->flags)) rcw++;
+ if (test_bit(R5_Insync, &dev->flags))
+ rcw++;
else
rcw += 2*disks;
}
@@ -3107,10 +3114,10 @@ static void handle_stripe_dirtying(struct r5conf *conf,
!(test_bit(R5_UPTODATE, &dev->flags) ||
test_bit(R5_Wantcompute, &dev->flags)) &&
test_bit(R5_Insync, &dev->flags)) {
- if (
- test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
- pr_debug("Read_old block "
- "%d for r-m-w\n", i);
+ if (test_bit(STRIPE_PREREAD_ACTIVE,
+ &sh->state)) {
+ pr_debug("Read_old block %d for r-m-w\n",
+ i);
set_bit(R5_LOCKED, &dev->flags);
set_bit(R5_Wantread, &dev->flags);
s->locked++;
@@ -3133,10 +3140,9 @@ static void handle_stripe_dirtying(struct r5conf *conf,
!(test_bit(R5_UPTODATE, &dev->flags) ||
test_bit(R5_Wantcompute, &dev->flags))) {
rcw++;
- if (!test_bit(R5_Insync, &dev->flags))
- continue; /* it's a failed drive */
- if (
- test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
+ if (test_bit(R5_Insync, &dev->flags) &&
+ test_bit(STRIPE_PREREAD_ACTIVE,
+ &sh->state)) {
pr_debug("Read_old block "
"%d for Reconstruct\n", i);
set_bit(R5_LOCKED, &dev->flags);
--
cgit v1.2.3-70-g09d2
From cf170f3fa451350e431314e1a0a52014fda4b2d6 Mon Sep 17 00:00:00 2001
From: Eivind Sarto <eivindsarto@gmail.com>
Date: Wed, 28 May 2014 13:39:23 +1000
Subject: raid5: avoid release list until last reference of the stripe
The (lockless) release_list reduces lock contention, but there is excessive
queueing and dequeuing of stripes on this list. A stripe will currently be
queued on the release_list with a stripe reference count > 1. This can cause
the raid5 kernel thread(s) to dequeue the stripe and decrement the refcount
without doing any other useful processing of the stripe. The are two cases
when the stripe can be put on the release_list multiple times before it is
actually handled by the kernel thread(s).
1) make_request() activates the stripe processing in 4k increments. When a
write request is large enough to span multiple chunks of a stripe_head, the
first 4k chunk adds the stripe to the plug list. The next 4k chunk that is
processed for the same stripe puts the stripe on the release_list with a
refcount=2. This can cause the kernel thread to process and decrement the
stripe before the stripe us unplugged, which again will put it back on the
release_list.
2) Whenever IO is scheduled on a stripe (pre-read and/or write), the stripe
refcount is set to the number of active IO (for each chunk). The stripe is
released as each IO complete, and can be queued and dequeued multiple times
on the release_list, until its refcount finally reached zero.
This simple patch will ensure a stripe is only queued on the release_list when
its refcount=1 and is ready to be handled by the kernel thread(s). I added some
instrumentation to raid5 and counted the number of times striped were queued on
the release_list for a variety of write IO sizes. Without this patch the number
of times stripes got queued on the release_list was 100-500% higher than with
the patch. The excess queuing will increase with the IO size. The patch also
improved throughput by 5-10%.
Signed-off-by: Eivind Sarto <esarto@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
---
drivers/md/raid5.c | 5 +++++
1 file changed, 5 insertions(+)
(limited to 'drivers/md/raid5.c')
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index c1e8607d834..348a857ab0f 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -416,6 +416,11 @@ static void release_stripe(struct stripe_head *sh)
int hash;
bool wakeup;
+ /* Avoid release_list until the last reference.
+ */
+ if (atomic_add_unless(&sh->count, -1, 1))
+ return;
+
if (unlikely(!conf->mddev->thread) ||
test_and_set_bit(STRIPE_ON_RELEASE_LIST, &sh->state))
goto slow_path;
--
cgit v1.2.3-70-g09d2
From d592a9969141e67a3874c808999a4db4bf82ed83 Mon Sep 17 00:00:00 2001
From: Shaohua Li <shli@kernel.org>
Date: Wed, 21 May 2014 17:57:44 +0800
Subject: raid5: add an option to avoid copy data from bio to stripe cache
The stripe cache has two goals:
1. cache data, so next time if data can be found in stripe cache, disk access
can be avoided.
2. stable data. data is copied from bio to stripe cache and calculated parity.
data written to disk is from stripe cache, so if upper layer changes bio data,
data written to disk isn't impacted.
In my environment, I can guarantee 2 will not happen. And BDI_CAP_STABLE_WRITES
can guarantee 2 too. For 1, it's not common too. block plug mechanism will
dispatch a bunch of sequentail small requests together. And since I'm using
SSD, I'm using small chunk size. It's rare case stripe cache is really useful.
So I'd like to avoid the copy from bio to stripe cache and it's very helpful
for performance. In my 1M randwrite tests, avoid the copy can increase the
performance more than 30%.
Of course, this shouldn't be enabled by default. It's reported enabling
BDI_CAP_STABLE_WRITES can harm some workloads before, so I added an option to
control it.
Neilb:
changed BUG_ON to WARN_ON
Removed some assignments from raid5_build_block which are now not needed.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
---
drivers/md/raid5.c | 119 +++++++++++++++++++++++++++++++++++++++++++----------
drivers/md/raid5.h | 4 +-
2 files changed, 101 insertions(+), 22 deletions(-)
(limited to 'drivers/md/raid5.c')
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 348a857ab0f..d69fd9888c2 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -487,6 +487,7 @@ static void shrink_buffers(struct stripe_head *sh)
int num = sh->raid_conf->pool_size;
for (i = 0; i < num ; i++) {
+ WARN_ON(sh->dev[i].page != sh->dev[i].orig_page);
p = sh->dev[i].page;
if (!p)
continue;
@@ -507,6 +508,7 @@ static int grow_buffers(struct stripe_head *sh)
return 1;
}
sh->dev[i].page = page;
+ sh->dev[i].orig_page = page;
}
return 0;
}
@@ -863,6 +865,9 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags))
bi->bi_rw |= REQ_NOMERGE;
+ if (test_bit(R5_SkipCopy, &sh->dev[i].flags))
+ WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags));
+ sh->dev[i].vec.bv_page = sh->dev[i].page;
bi->bi_vcnt = 1;
bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
bi->bi_io_vec[0].bv_offset = 0;
@@ -907,6 +912,9 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
else
rbi->bi_iter.bi_sector = (sh->sector
+ rrdev->data_offset);
+ if (test_bit(R5_SkipCopy, &sh->dev[i].flags))
+ WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags));
+ sh->dev[i].rvec.bv_page = sh->dev[i].page;
rbi->bi_vcnt = 1;
rbi->bi_io_vec[0].bv_len = STRIPE_SIZE;
rbi->bi_io_vec[0].bv_offset = 0;
@@ -935,8 +943,9 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
}
static struct dma_async_tx_descriptor *
-async_copy_data(int frombio, struct bio *bio, struct page *page,
- sector_t sector, struct dma_async_tx_descriptor *tx)
+async_copy_data(int frombio, struct bio *bio, struct page **page,
+ sector_t sector, struct dma_async_tx_descriptor *tx,
+ struct stripe_head *sh)
{
struct bio_vec bvl;
struct bvec_iter iter;
@@ -973,11 +982,16 @@ async_copy_data(int frombio, struct bio *bio, struct page *page,
if (clen > 0) {
b_offset += bvl.bv_offset;
bio_page = bvl.bv_page;
- if (frombio)
- tx = async_memcpy(page, bio_page, page_offset,
+ if (frombio) {
+ if (sh->raid_conf->skip_copy &&
+ b_offset == 0 && page_offset == 0 &&
+ clen == STRIPE_SIZE)
+ *page = bio_page;
+ else
+ tx = async_memcpy(*page, bio_page, page_offset,
b_offset, clen, &submit);
- else
- tx = async_memcpy(bio_page, page, b_offset,
+ } else
+ tx = async_memcpy(bio_page, *page, b_offset,
page_offset, clen, &submit);
}
/* chain the operations */
@@ -1053,8 +1067,8 @@ static void ops_run_biofill(struct stripe_head *sh)
spin_unlock_irq(&sh->stripe_lock);
while (rbi && rbi->bi_iter.bi_sector <
dev->sector + STRIPE_SECTORS) {
- tx = async_copy_data(0, rbi, dev->page,
- dev->sector, tx);
+ tx = async_copy_data(0, rbi, &dev->page,
+ dev->sector, tx, sh);
rbi = r5_next_bio(rbi, dev->sector);
}
}
@@ -1392,6 +1406,7 @@ ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
BUG_ON(dev->written);
wbi = dev->written = chosen;
spin_unlock_irq(&sh->stripe_lock);
+ WARN_ON(dev->page != dev->orig_page);
while (wbi && wbi->bi_iter.bi_sector <
dev->sector + STRIPE_SECTORS) {
@@ -1401,9 +1416,15 @@ ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
set_bit(R5_SyncIO, &dev->flags);
if (wbi->bi_rw & REQ_DISCARD)
set_bit(R5_Discard, &dev->flags);
- else
- tx = async_copy_data(1, wbi, dev->page,
- dev->sector, tx);
+ else {
+ tx = async_copy_data(1, wbi, &dev->page,
+ dev->sector, tx, sh);
+ if (dev->page != dev->orig_page) {
+ set_bit(R5_SkipCopy, &dev->flags);
+ clear_bit(R5_UPTODATE, &dev->flags);
+ clear_bit(R5_OVERWRITE, &dev->flags);
+ }
+ }
wbi = r5_next_bio(wbi, dev->sector);
}
}
@@ -1434,7 +1455,7 @@ static void ops_complete_reconstruct(void *stripe_head_ref)
struct r5dev *dev = &sh->dev[i];
if (dev->written || i == pd_idx || i == qd_idx) {
- if (!discard)
+ if (!discard && !test_bit(R5_SkipCopy, &dev->flags))
set_bit(R5_UPTODATE, &dev->flags);
if (fua)
set_bit(R5_WantFUA, &dev->flags);
@@ -1847,8 +1868,10 @@ static int resize_stripes(struct r5conf *conf, int newsize)
osh = get_free_stripe(conf, hash);
unlock_device_hash_lock(conf, hash);
atomic_set(&nsh->count, 1);
- for(i=0; i<conf->pool_size; i++)
+ for(i=0; i<conf->pool_size; i++) {
nsh->dev[i].page = osh->dev[i].page;
+ nsh->dev[i].orig_page = osh->dev[i].page;
+ }
for( ; i<newsize; i++)
nsh->dev[i].page = NULL;
nsh->hash_lock_index = hash;
@@ -1904,6 +1927,7 @@ static int resize_stripes(struct r5conf *conf, int newsize)
if (nsh->dev[i].page == NULL) {
struct page *p = alloc_page(GFP_NOIO);
nsh->dev[i].page = p;
+ nsh->dev[i].orig_page = p;
if (!p)
err = -ENOMEM;
}
@@ -2141,24 +2165,20 @@ static void raid5_end_write_request(struct bio *bi, int error)
}
static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous);
-
+
static void raid5_build_block(struct stripe_head *sh, int i, int previous)
{
struct r5dev *dev = &sh->dev[i];
bio_init(&dev->req);
dev->req.bi_io_vec = &dev->vec;
- dev->req.bi_vcnt++;
- dev->req.bi_max_vecs++;
+ dev->req.bi_max_vecs = 1;
dev->req.bi_private = sh;
- dev->vec.bv_page = dev->page;
bio_init(&dev->rreq);
dev->rreq.bi_io_vec = &dev->rvec;
- dev->rreq.bi_vcnt++;
- dev->rreq.bi_max_vecs++;
+ dev->rreq.bi_max_vecs = 1;
dev->rreq.bi_private = sh;
- dev->rvec.bv_page = dev->page;
dev->flags = 0;
dev->sector = compute_blocknr(sh, i, previous);
@@ -2758,6 +2778,11 @@ handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
/* and fail all 'written' */
bi = sh->dev[i].written;
sh->dev[i].written = NULL;
+ if (test_and_clear_bit(R5_SkipCopy, &sh->dev[i].flags)) {
+ WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags));
+ sh->dev[i].page = sh->dev[i].orig_page;
+ }
+
if (bi) bitmap_end = 1;
while (bi && bi->bi_iter.bi_sector <
sh->dev[i].sector + STRIPE_SECTORS) {
@@ -3002,12 +3027,17 @@ static void handle_stripe_clean_event(struct r5conf *conf,
dev = &sh->dev[i];
if (!test_bit(R5_LOCKED, &dev->flags) &&
(test_bit(R5_UPTODATE, &dev->flags) ||
- test_bit(R5_Discard, &dev->flags))) {
+ test_bit(R5_Discard, &dev->flags) ||
+ test_bit(R5_SkipCopy, &dev->flags))) {
/* We can return any write requests */
struct bio *wbi, *wbi2;
pr_debug("Return write for disc %d\n", i);
if (test_and_clear_bit(R5_Discard, &dev->flags))
clear_bit(R5_UPTODATE, &dev->flags);
+ if (test_and_clear_bit(R5_SkipCopy, &dev->flags)) {
+ WARN_ON(test_bit(R5_UPTODATE, &dev->flags));
+ dev->page = dev->orig_page;
+ }
wbi = dev->written;
dev->written = NULL;
while (wbi && wbi->bi_iter.bi_sector <
@@ -3026,6 +3056,8 @@ static void handle_stripe_clean_event(struct r5conf *conf,
0);
} else if (test_bit(R5_Discard, &dev->flags))
discard_pending = 1;
+ WARN_ON(test_bit(R5_SkipCopy, &dev->flags));
+ WARN_ON(dev->page != dev->orig_page);
}
if (!discard_pending &&
test_bit(R5_Discard, &sh->dev[sh->pd_idx].flags)) {
@@ -5365,6 +5397,50 @@ raid5_preread_bypass_threshold = __ATTR(preread_bypass_threshold,
raid5_show_preread_threshold,
raid5_store_preread_threshold);
+static ssize_t
+raid5_show_skip_copy(struct mddev *mddev, char *page)
+{
+ struct r5conf *conf = mddev->private;
+ if (conf)
+ return sprintf(page, "%d\n", conf->skip_copy);
+ else
+ return 0;
+}
+
+static ssize_t
+raid5_store_skip_copy(struct mddev *mddev, const char *page, size_t len)
+{
+ struct r5conf *conf = mddev->private;
+ unsigned long new;
+ if (len >= PAGE_SIZE)
+ return -EINVAL;
+ if (!conf)
+ return -ENODEV;
+
+ if (kstrtoul(page, 10, &new))
+ return -EINVAL;
+ new = !!new;
+ if (new == conf->skip_copy)
+ return len;
+
+ mddev_suspend(mddev);
+ conf->skip_copy = new;
+ if (new)
+ mddev->queue->backing_dev_info.capabilities |=
+ BDI_CAP_STABLE_WRITES;
+ else
+ mddev->queue->backing_dev_info.capabilities &=
+ ~BDI_CAP_STABLE_WRITES;
+ mddev_resume(mddev);
+ return len;
+}
+
+static struct md_sysfs_entry
+raid5_skip_copy = __ATTR(skip_copy, S_IRUGO | S_IWUSR,
+ raid5_show_skip_copy,
+ raid5_store_skip_copy);
+
+
static ssize_t
stripe_cache_active_show(struct mddev *mddev, char *page)
{
@@ -5450,6 +5526,7 @@ static struct attribute *raid5_attrs[] = {
&raid5_stripecache_active.attr,
&raid5_preread_bypass_threshold.attr,
&raid5_group_thread_cnt.attr,
+ &raid5_skip_copy.attr,
NULL,
};
static struct attribute_group raid5_attrs_group = {
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 01ad8ae8f57..bc72cd4be5f 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -232,7 +232,7 @@ struct stripe_head {
*/
struct bio req, rreq;
struct bio_vec vec, rvec;
- struct page *page;
+ struct page *page, *orig_page;
struct bio *toread, *read, *towrite, *written;
sector_t sector; /* sector of this page */
unsigned long flags;
@@ -299,6 +299,7 @@ enum r5dev_flags {
* data in, and now is a good time to write it out.
*/
R5_Discard, /* Discard the stripe */
+ R5_SkipCopy, /* Don't copy data from bio to stripe cache */
};
/*
@@ -436,6 +437,7 @@ struct r5conf {
atomic_t pending_full_writes; /* full write backlog */
int bypass_count; /* bypassed prereads */
int bypass_threshold; /* preread nice */
+ int skip_copy; /* Don't copy data from bio to stripe cache */
struct list_head *last_hold; /* detect hold_list promotions */
atomic_t reshape_stripes; /* stripes with pending writes for reshape */
--
cgit v1.2.3-70-g09d2
From 2844dc32ea67044b345221067207ce67ffe8da76 Mon Sep 17 00:00:00 2001
From: hui jiao <simonjiaoh@gmail.com>
Date: Thu, 5 Jun 2014 11:34:24 +0800
Subject: md/raid5: deadlock between retry_aligned_read with barrier io
A chunk aligned read increases counter active_aligned_reads and
decreases it after sub-device handle it successfully. But when a read
error occurs, the read redispatched by raid5d, and the
active_aligned_reads will not be decreased until we can grab a stripe
head in retry_aligned_read. Now suppose, a barrier io comes, set
conf->quiesce to 2, and wait until both active_stripes and
active_aligned_reads are zero. The retried chunk aligned read gets
stuck at get_active_stripe waiting until conf->quiesce becomes 0.
Retry_aligned_read and barrier io are waiting each other now.
One possible solution is that we ignore conf->quiesce, let the retried
aligned read finish. I reproduced this deadlock and test this patch on
centos6.0
Signed-off-by: NeilBrown <neilb@suse.de>
---
drivers/md/raid5.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'drivers/md/raid5.c')
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index d69fd9888c2..ce421e3a398 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5115,7 +5115,7 @@ static int retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
/* already done this stripe */
continue;
- sh = get_active_stripe(conf, sector, 0, 1, 0);
+ sh = get_active_stripe(conf, sector, 0, 1, 1);
if (!sh) {
/* failed to get a stripe - must wait */
--
cgit v1.2.3-70-g09d2
From 053f5b6525ae32da397e6c47721961f800d2c924 Mon Sep 17 00:00:00 2001
From: Eivind Sarto <eivindsarto@gmail.com>
Date: Mon, 9 Jun 2014 17:06:19 -0700
Subject: raid5: speedup sync_request processing
The raid5 sync_request() processing calls handle_stripe() within the context of
the resync-thread. The resync-thread issues the first set of read requests
and this adds execution latency and slows down the scheduling of the next
sync_request().
The current rebuild/resync speed of raid5 is not much faster than what
rotational HDDs can sustain.
Testing the following patch on a 6-drive array, I can increase the rebuild
speed from 100 MB/s to 175 MB/s.
The sync_request() now just sets STRIPE_HANDLE and releases the stripe. This
creates some more parallelism between the resync-thread and raid5 kernel daemon.
Signed-off-by: Eivind Sarto <esarto@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
---
drivers/md/raid5.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'drivers/md/raid5.c')
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index ce421e3a398..28219fa66e7 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5074,8 +5074,8 @@ static inline sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int
bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, still_degraded);
set_bit(STRIPE_SYNC_REQUESTED, &sh->state);
+ set_bit(STRIPE_HANDLE, &sh->state);
- handle_stripe(sh);
release_stripe(sh);
return STRIPE_SECTORS;
--
cgit v1.2.3-70-g09d2