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>
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>
I hit another BUG_ON with e240c1839d. In __get_priority_stripe(),
stripe count equals to 0 initially. Between atomic_inc and BUG_ON,
get_active_stripe() finds the stripe. So the stripe count isn't 1 any more.
V2: keeps the BUG_ON suggested by Neil.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
For sequential workload (or request size big workload), get_active_stripe can
find cached stripe. In this case, we always hold device_lock, which exposes a
lot of lock contention for such workload. If stripe count isn't 0, we don't
need hold the lock actually, since we just increase its count. And this is the
hot code path for such workload. Unfortunately we must delete the BUG_ON.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
In NUMA machine, prepare_to_wait/finish_wait in make_request exposes a
lot of contention for sequential workload (or big request size
workload). For such workload, each bio includes several stripes. So we
can just do prepare_to_wait/finish_wait once for the whold bio instead
of every stripe. This reduces the lock contention completely for such
workload. Random workload might have the similar lock contention too,
but I didn't see it yet, maybe because my stroage is still not fast
enough.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
Subsystems that want to register CPU hotplug callbacks, as well as perform
initialization for the CPUs that are already online, often do it as shown
below:
get_online_cpus();
for_each_online_cpu(cpu)
init_cpu(cpu);
register_cpu_notifier(&foobar_cpu_notifier);
put_online_cpus();
This is wrong, since it is prone to ABBA deadlocks involving the
cpu_add_remove_lock and the cpu_hotplug.lock (when running concurrently
with CPU hotplug operations).
Interestingly, the raid5 code can actually prevent double initialization and
hence can use the following simplified form of callback registration:
register_cpu_notifier(&foobar_cpu_notifier);
get_online_cpus();
for_each_online_cpu(cpu)
init_cpu(cpu);
put_online_cpus();
A hotplug operation that occurs between registering the notifier and calling
get_online_cpus(), won't disrupt anything, because the code takes care to
perform the memory allocations only once.
So reorganize the code in raid5 this way to fix the deadlock with callback
registration.
Cc: linux-raid@vger.kernel.org
Cc: stable@vger.kernel.org (v2.6.32+)
Fixes: 36d1c6476b
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
[Srivatsa: Fixed the unregister_cpu_notifier() deadlock, added the
free_scratch_buffer() helper to condense code further and wrote the changelog.]
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Signed-off-by: NeilBrown <neilb@suse.de>
Pull block IO driver changes from Jens Axboe:
- bcache update from Kent Overstreet.
- two bcache fixes from Nicholas Swenson.
- cciss pci init error fix from Andrew.
- underflow fix in the parallel IDE pg_write code from Dan Carpenter.
I'm sure the 1 (or 0) users of that are now happy.
- two PCI related fixes for sx8 from Jingoo Han.
- floppy init fix for first block read from Jiri Kosina.
- pktcdvd error return miss fix from Julia Lawall.
- removal of IRQF_SHARED from the SEGA Dreamcast CD-ROM code from
Michael Opdenacker.
- comment typo fix for the loop driver from Olaf Hering.
- potential oops fix for null_blk from Raghavendra K T.
- two fixes from Sam Bradshaw (Micron) for the mtip32xx driver, fixing
an OOM problem and a problem with handling security locked conditions
* 'for-3.14/drivers' of git://git.kernel.dk/linux-block: (47 commits)
mg_disk: Spelling s/finised/finished/
null_blk: Null pointer deference problem in alloc_page_buffers
mtip32xx: Correctly handle security locked condition
mtip32xx: Make SGL container per-command to eliminate high order dma allocation
drivers/block/loop.c: fix comment typo in loop_config_discard
drivers/block/cciss.c:cciss_init_one(): use proper errnos
drivers/block/paride/pg.c: underflow bug in pg_write()
drivers/block/sx8.c: remove unnecessary pci_set_drvdata()
drivers/block/sx8.c: use module_pci_driver()
floppy: bail out in open() if drive is not responding to block0 read
bcache: Fix auxiliary search trees for key size > cacheline size
bcache: Don't return -EINTR when insert finished
bcache: Improve bucket_prio() calculation
bcache: Add bch_bkey_equal_header()
bcache: update bch_bkey_try_merge
bcache: Move insert_fixup() to btree_keys_ops
bcache: Convert sorting to btree_keys
bcache: Convert debug code to btree_keys
bcache: Convert btree_iter to struct btree_keys
bcache: Refactor bset_tree sysfs stats
...
Pull core block IO changes from Jens Axboe:
"The major piece in here is the immutable bio_ve series from Kent, the
rest is fairly minor. It was supposed to go in last round, but
various issues pushed it to this release instead. The pull request
contains:
- Various smaller blk-mq fixes from different folks. Nothing major
here, just minor fixes and cleanups.
- Fix for a memory leak in the error path in the block ioctl code
from Christian Engelmayer.
- Header export fix from CaiZhiyong.
- Finally the immutable biovec changes from Kent Overstreet. This
enables some nice future work on making arbitrarily sized bios
possible, and splitting more efficient. Related fixes to immutable
bio_vecs:
- dm-cache immutable fixup from Mike Snitzer.
- btrfs immutable fixup from Muthu Kumar.
- bio-integrity fix from Nic Bellinger, which is also going to stable"
* 'for-3.14/core' of git://git.kernel.dk/linux-block: (44 commits)
xtensa: fixup simdisk driver to work with immutable bio_vecs
block/blk-mq-cpu.c: use hotcpu_notifier()
blk-mq: for_each_* macro correctness
block: Fix memory leak in rw_copy_check_uvector() handling
bio-integrity: Fix bio_integrity_verify segment start bug
block: remove unrelated header files and export symbol
blk-mq: uses page->list incorrectly
blk-mq: use __smp_call_function_single directly
btrfs: fix missing increment of bi_remaining
Revert "block: Warn and free bio if bi_end_io is not set"
block: Warn and free bio if bi_end_io is not set
blk-mq: fix initializing request's start time
block: blk-mq: don't export blk_mq_free_queue()
block: blk-mq: make blk_sync_queue support mq
block: blk-mq: support draining mq queue
dm cache: increment bi_remaining when bi_end_io is restored
block: fixup for generic bio chaining
block: Really silence spurious compiler warnings
block: Silence spurious compiler warnings
block: Kill bio_pair_split()
...
As release_stripe and __release_stripe decrement ->count and then
manipulate ->lru both under ->device_lock, it is important that
get_active_stripe() increments ->count and clears ->lru also under
->device_lock.
However we currently list_del_init ->lru under the lock, but increment
the ->count outside the lock. This can lead to races and list
corruption.
So move the atomic_inc(&sh->count) up inside the ->device_lock
protected region.
Note that we still increment ->count without device lock in the case
where get_free_stripe() was called, and in fact don't take
->device_lock at all in that path.
This is safe because if the stripe_head can be found by
get_free_stripe, then the hash lock assures us the no-one else could
possibly be calling release_stripe() at the same time.
Fixes: 566c09c534
Cc: stable@vger.kernel.org (3.13)
Reported-and-tested-by: Ian Kumlien <ian.kumlien@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>
Before a write starts we set a bit in the write-intent bitmap.
When the write completes we clear that bit if the write was successful
to all devices. However if the write wasn't fully successful we
should not clear the bit. If the faulty drive is subsequently
re-added, the fact that the bit is still set ensure that we will
re-write the data that is missing.
This logic is mediated by the STRIPE_DEGRADED flag - we only clear the
bitmap bit when this flag is not set.
Currently we correctly set the flag if a write starts when some
devices are failed or missing. But we do *not* set the flag if some
device failed during the write attempt.
This is wrong and can result in clearing the bit inappropriately.
So: set the flag when a write fails.
This bug has been present since bitmaps were introduces, so the fix is
suitable for any -stable kernel.
Reported-by: Ethan Wilson <ethan.wilson@shiftmail.org>
Cc: stable@vger.kernel.org
Signed-off-by: NeilBrown <neilb@suse.de>
commit 6d183de407
md/raid5: fix newly-broken locking in get_active_stripe.
simplified a BUG_ON, but removed too much so now it sometimes fires
when it shouldn't.
When the STRIPE_EXPANDING flag is set, the stripe_head might be on a
special list while multiple stripe_heads are collected, or it might
not be on any list, even a 'free' list when the refcount is zero. As
long as STRIPE_EXPANDING is set, it will be found and added back to a
list eventually.
So both of the BUG_ONs which test for the ->lru being empty or not
need to avoid the case where STRIPE_EXPANDING is set.
The patch which broke this was marked for -stable, so this patch needs
to be applied to any branch that received 6d183de4
Fixes: 6d183de407
Cc: stable@vger.kernel.org (any release to which above was applied)
Signed-off-by: NeilBrown <neilb@suse.de>
commit 5d8c71f9e5
md: raid5 crash during degradation
Fixed a crash in an overly simplistic way which could leave
R5_WriteError or R5_MadeGood set in the stripe cache for devices
for which it is no longer relevant.
When those devices are removed and spares added the flags are still
set and can cause incorrect behaviour.
commit 14a75d3e07
md/raid5: preferentially read from replacement device if possible.
Fixed the same bug if a more effective way, so we can now revert
the original commit.
Reported-and-tested-by: Alexander Lyakas <alex.bolshoy@gmail.com>
Cc: stable@vger.kernel.org (3.2+ - 3.2 will need a different fix though)
Fixes: 5d8c71f9e5
Signed-off-by: NeilBrown <neilb@suse.de>
Now that we've got code for raid5/6 stripe awareness, bcache just needs
to know about the stripes and when writing partial stripes is expensive
- we probably don't want to enable this optimization for raid1 or 10,
even though they have stripes. So add a flag to queue_limits.
Signed-off-by: Kent Overstreet <kmo@daterainc.com>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1
iQEcBAABAgAGBQJSwLfoAAoJEHm+PkMAQRiGi6QH/1U1B7lmHChDTw3jj1lfm9gA
189Si4QJlnxFWCKHvKEL+pcaVuACU+aMGI8+KyMYK4/JfuWVjjj5fr/SvyHH2/8m
LdSK8aHMhJ46uBS4WJ/l6v46qQa5e2vn8RKSBAyKm/h4vpt+hd6zJdoFrFai4th7
k/TAwOAEHI5uzexUChwLlUBRTvbq4U8QUvDu+DeifC8cT63CGaaJ4qVzjOZrx1an
eP6UXZrKDASZs7RU950i7xnFVDQu4PsjlZi25udsbeiKcZJgPqGgXz5ULf8ZH8RQ
YCi1JOnTJRGGjyIOyLj7pyB01h7XiSM2+eMQ0S7g54F2s7gCJ58c2UwQX45vRWU=
=/4/R
-----END PGP SIGNATURE-----
Merge tag 'v3.13-rc6' into for-3.14/core
Needed to bring blk-mq uptodate, since changes have been going in
since for-3.14/core was established.
Fixup merge issues related to the immutable biovec changes.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Conflicts:
block/blk-flush.c
fs/btrfs/check-integrity.c
fs/btrfs/extent_io.c
fs/btrfs/scrub.c
fs/logfs/dev_bdev.c
commit 566c09c534 raid5: relieve lock contention in get_active_stripe()
modified the locking in get_active_stripe() reducing the range
protected by the (highly contended) device_lock.
Unfortunately it reduced the range too much opening up some races.
One race can occur if get_priority_stripe runs between the
test on sh->count and device_lock being taken.
This will mean that sh->lru is not empty while get_active_stripe
thinks ->count is zero resulting in a 'BUG' firing.
Another race happens if __release_stripe is called immediately
after sh->count is tested and found to be non-zero. If STRIPE_HANDLE
is not set, get_active_stripe should increment ->active_stripes
when it increments ->count from 0, but as it didn't think it was 0,
it doesn't.
Extending device_lock to cover the test on sh->count close these
races.
While we are here, fix the two BUG tests:
-If count is zero, then lru really must not be empty, or we've
lock the stripe_head somehow - no other tests are relevant.
-STRIPE_ON_RELEASE_LIST is completely independent of ->lru so
testing it is pointless.
Reported-and-tested-by: Brassow Jonathan <jbrassow@redhat.com>
Reviewed-by: Shaohua Li <shli@kernel.org>
Fixes: 566c09c534
Signed-off-by: NeilBrown <neilb@suse.de>
In alloc_thread_groups, worker_groups is a pointer to an array,
not an array of pointers.
So
worker_groups[i]
is wrong. It should be
&(*worker_groups)[i]
Found-by: coverity
Fixes: 60aaf93385
Reported-by: Ben Hutchings <bhutchings@solarflare.com>
Cc: majianpeng <majianpeng@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>
More prep work for immutable biovecs - with immutable bvecs drivers
won't be able to use the biovec directly, they'll need to use helpers
that take into account bio->bi_iter.bi_bvec_done.
This updates callers for the new usage without changing the
implementation yet.
Signed-off-by: Kent Overstreet <kmo@daterainc.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: "Ed L. Cashin" <ecashin@coraid.com>
Cc: Nick Piggin <npiggin@kernel.dk>
Cc: Lars Ellenberg <drbd-dev@lists.linbit.com>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Paul Clements <Paul.Clements@steeleye.com>
Cc: Jim Paris <jim@jtan.com>
Cc: Geoff Levand <geoff@infradead.org>
Cc: Yehuda Sadeh <yehuda@inktank.com>
Cc: Sage Weil <sage@inktank.com>
Cc: Alex Elder <elder@inktank.com>
Cc: ceph-devel@vger.kernel.org
Cc: Joshua Morris <josh.h.morris@us.ibm.com>
Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: Neil Brown <neilb@suse.de>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: linux390@de.ibm.com
Cc: Nagalakshmi Nandigama <Nagalakshmi.Nandigama@lsi.com>
Cc: Sreekanth Reddy <Sreekanth.Reddy@lsi.com>
Cc: support@lsi.com
Cc: "James E.J. Bottomley" <JBottomley@parallels.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Steven Whitehouse <swhiteho@redhat.com>
Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Guo Chao <yan@linux.vnet.ibm.com>
Cc: Asai Thambi S P <asamymuthupa@micron.com>
Cc: Selvan Mani <smani@micron.com>
Cc: Sam Bradshaw <sbradshaw@micron.com>
Cc: Matthew Wilcox <matthew.r.wilcox@intel.com>
Cc: Keith Busch <keith.busch@intel.com>
Cc: Stephen Hemminger <shemminger@vyatta.com>
Cc: Quoc-Son Anh <quoc-sonx.anh@intel.com>
Cc: Sebastian Ott <sebott@linux.vnet.ibm.com>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: Seth Jennings <sjenning@linux.vnet.ibm.com>
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: Mike Snitzer <snitzer@redhat.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: "Darrick J. Wong" <darrick.wong@oracle.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Jan Kara <jack@suse.cz>
Cc: linux-m68k@lists.linux-m68k.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: drbd-user@lists.linbit.com
Cc: nbd-general@lists.sourceforge.net
Cc: cbe-oss-dev@lists.ozlabs.org
Cc: xen-devel@lists.xensource.com
Cc: virtualization@lists.linux-foundation.org
Cc: linux-raid@vger.kernel.org
Cc: linux-s390@vger.kernel.org
Cc: DL-MPTFusionLinux@lsi.com
Cc: linux-scsi@vger.kernel.org
Cc: devel@driverdev.osuosl.org
Cc: linux-fsdevel@vger.kernel.org
Cc: cluster-devel@redhat.com
Cc: linux-mm@kvack.org
Acked-by: Geoff Levand <geoff@infradead.org>
Mostly optimisations and obscure bug fixes.
- raid5 gets less lock contention
- raid1 gets less contention between normal-io and resync-io
during resync.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.19 (GNU/Linux)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=8RCg
-----END PGP SIGNATURE-----
Merge tag 'md/3.13' of git://neil.brown.name/md
Pull md update from Neil Brown:
"Mostly optimisations and obscure bug fixes.
- raid5 gets less lock contention
- raid1 gets less contention between normal-io and resync-io during
resync"
* tag 'md/3.13' of git://neil.brown.name/md:
md/raid5: Use conf->device_lock protect changing of multi-thread resources.
md/raid5: Before freeing old multi-thread worker, it should flush them.
md/raid5: For stripe with R5_ReadNoMerge, we replace REQ_FLUSH with REQ_NOMERGE.
UAPI: include <asm/byteorder.h> in linux/raid/md_p.h
raid1: Rewrite the implementation of iobarrier.
raid1: Add some macros to make code clearly.
raid1: Replace raise_barrier/lower_barrier with freeze_array/unfreeze_array when reconfiguring the array.
raid1: Add a field array_frozen to indicate whether raid in freeze state.
md: Convert use of typedef ctl_table to struct ctl_table
md/raid5: avoid deadlock when raid5 array has unack badblocks during md_stop_writes.
md: use MD_RECOVERY_INTR instead of kthread_should_stop in resync thread.
md: fix some places where mddev_lock return value is not checked.
raid5: Retry R5_ReadNoMerge flag when hit a read error.
raid5: relieve lock contention in get_active_stripe()
raid5: relieve lock contention in get_active_stripe()
wait: add wait_event_cmd()
md/raid5.c: add proper locking to error path of raid5_start_reshape.
md: fix calculation of stacking limits on level change.
raid5: Use slow_path to release stripe when mddev->thread is null
For R5_ReadNoMerge,it mean this bio can't merge with other bios or
request.It used REQ_FLUSH to achieve this. But REQ_NOMERGE can do the
same work.
Signed-off-by: Jianpeng Ma <majianpeng@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>
We currently use kthread_should_stop() in various places in the
sync/reshape code to abort early.
However some places set MD_RECOVERY_INTR but don't immediately call
md_reap_sync_thread() (and we will shortly get another one).
When this happens we are relying on md_check_recovery() to reap the
thread and that only happen when it finishes normally.
So MD_RECOVERY_INTR must lead to a normal finish without the
kthread_should_stop() test.
So replace all relevant tests, and be more careful when the thread is
interrupted not to acknowledge that latest step in a reshape as it may
not be fully committed yet.
Also add a test on MD_RECOVERY_INTR in the 'is_mddev_idle' loop
so we don't wait have to wait for the speed to drop before we can abort.
Signed-off-by: NeilBrown <neilb@suse.de>
Because of block layer merge, one bio fails will cause other bios
which belongs to the same request fails, so raid5_end_read_request
will record all these bios as badblocks.
If retry request with R5_ReadNoMerge flag to avoid bios merge,
badblocks can only record sector which is bad exactly.
test:
hdparm --yes-i-know-what-i-am-doing --make-bad-sector 300000 /dev/sdb
mdadm -C /dev/md0 -l5 -n3 /dev/sd[bcd] --assume-clean
mdadm /dev/md0 -f /dev/sdd
mdadm /dev/md0 -r /dev/sdd
mdadm --zero-superblock /dev/sdd
mdadm /dev/md0 -a /dev/sdd
1. Without this patch:
cat /sys/block/md0/md/rd*/bad_blocks
299776 256
299776 256
2. With this patch:
cat /sys/block/md0/md/rd*/bad_blocks
300000 8
300000 8
Signed-off-by: Bian Yu <bianyu@kedacom.com>
Signed-off-by: NeilBrown <neilb@suse.de>
track empty inactive list count, so md_raid5_congested() can use it to make
decision.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
Make this useful helper available for other users.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
get_active_stripe() is the last place we have lock contention. It has two
paths. One is stripe isn't found and new stripe is allocated, the other is
stripe is found.
The first path basically calls __find_stripe and init_stripe. It accesses
conf->generation, conf->previous_raid_disks, conf->raid_disks,
conf->prev_chunk_sectors, conf->chunk_sectors, conf->max_degraded,
conf->prev_algo, conf->algorithm, the stripe_hashtbl and inactive_list. Except
stripe_hashtbl and inactive_list, other fields are changed very rarely.
With this patch, we split inactive_list and add new hash locks. Each free
stripe belongs to a specific inactive list. Which inactive list is determined
by stripe's lock_hash. Note, even a stripe hasn't a sector assigned, it has a
lock_hash assigned. Stripe's inactive list is protected by a hash lock, which
is determined by it's lock_hash too. The lock_hash is derivied from current
stripe_hashtbl hash, which guarantees any stripe_hashtbl list will be assigned
to a specific lock_hash, so we can use new hash lock to protect stripe_hashtbl
list too. The goal of the new hash locks introduced is we can only use the new
locks in the first path of get_active_stripe(). Since we have several hash
locks, lock contention is relieved significantly.
The first path of get_active_stripe() accesses other fields, since they are
changed rarely, changing them now need take conf->device_lock and all hash
locks. For a slow path, this isn't a problem.
If we need lock device_lock and hash lock, we always lock hash lock first. The
tricky part is release_stripe and friends. We need take device_lock first.
Neil's suggestion is we put inactive stripes to a temporary list and readd it
to inactive_list after device_lock is released. In this way, we add stripes to
temporary list with device_lock hold and remove stripes from the list with hash
lock hold. So we don't allow concurrent access to the temporary list, which
means we need allocate temporary list for all participants of release_stripe.
One downside is free stripes are maintained in their inactive list, they can't
across between the lists. By default, we have total 256 stripes and 8 lists, so
each list will have 32 stripes. It's possible one list has free stripe but
other list hasn't. The chance should be rare because stripes allocation are
even distributed. And we can always allocate more stripes for cache, several
mega bytes memory isn't a big deal.
This completely removes the lock contention of the first path of
get_active_stripe(). It slows down the second code path a little bit though
because we now need takes two locks, but since the hash lock isn't contended,
the overhead should be quite small (several atomic instructions). The second
path of get_active_stripe() (basically sequential write or big request size
randwrite) still has lock contentions.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
If raid5_start_reshape errors out, we need to reset all the fields
that were updated (not just some), and need to use the seq_counter
to ensure make_request() doesn't use an inconsitent state.
Signed-off-by: NeilBrown <neilb@suse.de>
When release_stripe() is called in grow_one_stripe(), the
mddev->thread is null. So it will omit one wakeup this thread to
release stripe.
For this condition, use slow_path to release stripe.
Bug was introduced in 3.12
Cc: stable@vger.kernel.org (3.12+)
Fixes: 773ca82fa1
Signed-off-by: Jianpeng Ma <majianpeng@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>
SCSI discard will damage discard stripe bio setting, eg, some fields are
changed. If the stripe is reused very soon, we have wrong bios setting. We
remove discard stripe from hash list, so next time the strip will be fully
initialized.
Suitable for backport to 3.7+.
Cc: <stable@vger.kernel.org> (3.7+)
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
SCSI layer will add new payload for discard request. If two bios are merged
to one, the second bio has bi_vcnt 1 which is set in raid5. This will confuse
SCSI and cause oops.
Suitable for backport to 3.7+
Cc: stable@vger.kernel.org (v3.7+)
Reported-by: Jes Sorensen <Jes.Sorensen@redhat.com>
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
Acked-by: Martin K. Petersen <martin.petersen@oracle.com>
If there are not enough stripes to handle, we'd better not always
queue all available work_structs. If one worker can only handle small
or even none stripes, it will impact request merge and create lock
contention.
With this patch, the number of work_struct running will depend on
pending stripes number. Note: some statistics info used in the patch
are accessed without locking protection. This should doesn't matter,
we just try best to avoid queue unnecessary work_struct.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
Some requests - particularly 'discard' and 'read' are handled
differently depending on whether a reshape is active or not.
It is harmless to assume reshape is active if it isn't but wrong
to act as though reshape is not active when it is.
So when we start reshape - after making clear to all requests that
reshape has started - use mddev_suspend/mddev_resume to flush out all
requests. This will ensure that no requests will be assuming the
absence of reshape once it really starts.
Signed-off-by: NeilBrown <neilb@suse.de>
make_request() access various shape parameters (raid_disks, chunk_size
etc) which might be changed by raid5_start_reshape().
If the later is called at and awkward time during the form, the wrong
stripe_head might be used.
So introduce a 'seqcount' and after finding a stripe_head make sure
there is no reason to expect that we got the wrong one.
Signed-off-by: NeilBrown <neilb@suse.de>
Add a sysfs entry to control running workqueue thread number. If
group_thread_cnt is set to 0, we will disable workqueue offload handling of
stripes.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
This is another attempt to create multiple threads to handle raid5 stripes.
This time I use workqueue.
raid5 handles request (especially write) in stripe unit. A stripe is page size
aligned/long and acrosses all disks. Writing to any disk sector, raid5 runs a
state machine for the corresponding stripe, which includes reading some disks
of the stripe, calculating parity, and writing some disks of the stripe. The
state machine is running in raid5d thread currently. Since there is only one
thread, it doesn't scale well for high speed storage. An obvious solution is
multi-threading.
To get better performance, we have some requirements:
a. locality. stripe corresponding to request submitted from one cpu is better
handled in thread in local cpu or local node. local cpu is preferred but some
times could be a bottleneck, for example, parity calculation is too heavy.
local node running has wide adaptability.
b. configurablity. Different setup of raid5 array might need diffent
configuration. Especially the thread number. More threads don't always mean
better performance because of lock contentions.
My original implementation is creating some kernel threads. There are
interfaces to control which cpu's stripe each thread should handle. And
userspace can set affinity of the threads. This provides biggest flexibility
and configurability. But it's hard to use and apparently a new thread pool
implementation is disfavor.
Recent workqueue improvement is quite promising. unbound workqueue will be
bound to numa node. If WQ_SYSFS is set in workqueue, there are sysfs option to
do affinity setting. For example, we can only include one HT sibling in
affinity. Since work is non-reentrant by default, and we can control running
thread number by limiting dispatched work_struct number.
In this patch, I created several stripe worker group. A group is a numa node.
stripes from cpus of one node will be added to a group list. Workqueue thread
of one node will only handle stripes of worker group of the node. In this way,
stripe handling has numa node locality. And as I said, we can control thread
number by limiting dispatched work_struct number.
The work_struct callback function handles several stripes in one run. A typical
work queue usage is to run one unit in each work_struct. In raid5 case, the
unit is a stripe. But we can't do that:
a. Though handling a stripe doesn't need lock because of reference accounting
and stripe isn't in any list, queuing a work_struct for each stripe will make
workqueue lock contended very heavily.
b. blk_start_plug()/blk_finish_plug() should surround stripe handle, as we
might dispatch request. If each work_struct only handles one stripe, such block
plug is meaningless.
This implementation can't do very fine grained configuration. But the numa
binding is most popular usage model, should be enough for most workloads.
Note: since we have only one stripe queue, switching to multi-thread might
decrease request size dispatching down to low level layer. The impact depends
on thread number, raid configuration and workload. So multi-thread raid5 might
not be proper for all setups.
Changes V1 -> V2:
1. remove WQ_NON_REENTRANT
2. disabling multi-threading by default
3. Add more descriptions in changelog
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
patch "make release_stripe lockless" changes the order stripes are released.
Originally I thought block layer can take care of request merge, but it appears
there are still some requests not merged. It's easy to fix the order.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
release_stripe still has big lock contention. We just add the stripe to a llist
without taking device_lock. We let the raid5d thread to do the real stripe
release, which must hold device_lock anyway. In this way, release_stripe
doesn't hold any locks.
The side effect is the released stripes order is changed. But sounds not a big
deal, stripes are never handled in order. And I thought block layer can already
do nice request merge, which means order isn't that important.
I kept the unplug release batch, which is unnecessary with this patch from lock
contention avoid point of view, and actually if we delete it, the stripe_head
release_list and lru can share storage. But the unplug release batch is also
helpful for request merge. We probably can delay wakeup raid5d till unplug, but
I'm still afraid of the case which raid5d is running.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Signed-off-by: NeilBrown <neilb@suse.de>
If a device in a RAID4/5/6 is being replaced while another is being
recovered, then the writes to the replacement device currently don't
happen, resulting in corruption when the replacement completes and the
new drive takes over.
This is because the replacement writes are only triggered when
's.replacing' is set and not when the similar 's.sync' is set (which
is the case during resync and recovery - it means all devices need to
be read).
So schedule those writes when s.replacing is set as well.
In this case we cannot use "STRIPE_INSYNC" to record that the
replacement has happened as that is needed for recording that any
parity calculation is complete. So introduce STRIPE_REPLACED to
record if the replacement has happened.
For safety we should also check that STRIPE_COMPUTE_RUN is not set.
This has a similar effect to the "s.locked == 0" test. The latter
ensure that now IO has been flagged but not started. The former
checks if any parity calculation has been flagged by not started.
We must wait for both of these to complete before triggering the
'replace'.
Add a similar test to the subsequent check for "are we finished yet".
This possibly isn't needed (is subsumed in the STRIPE_INSYNC test),
but it makes it more obvious that the REPLACE will happen before we
think we are finished.
Finally if a NeedReplace device is not UPTODATE then that is an
error. We really must trigger a warning.
This bug was introduced in commit 9a3e1101b8
(md/raid5: detect and handle replacements during recovery.)
which introduced replacement for raid5.
That was in 3.3-rc3, so any stable kernel since then would benefit
from this fix.
Cc: stable@vger.kernel.org (3.3+)
Reported-by: qindehua <13691222965@163.com>
Tested-by: qindehua <qindehua@163.com>
Signed-off-by: NeilBrown <neilb@suse.de>
There is a bug in 'check_reshape' for raid5.c To checks
that the new minimum number of devices is large enough (which is
good), but it does so also after the reshape has started (bad).
This is bad because
- the calculation is now wrong as mddev->raid_disks has changed
already, and
- it is pointless because it is now too late to stop.
So only perform that test when reshape has not been committed to.
Signed-off-by: NeilBrown <neilb@suse.de>
The usage of strict_strtoul() is not preferred, because
strict_strtoul() is obsolete. Thus, kstrtoul() should be
used.
Signed-off-by: Jingoo Han <jg1.han@samsung.com>
Signed-off-by: NeilBrown <neilb@suse.de>
Some tagged for -stable.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.19 (GNU/Linux)
iQIVAwUAUbl1mznsnt1WYoG5AQKGlQ//eixdawF+DUK5hadqZ9EDni+BAVzb7m69
+zU6ilQ7UOh7bxtAoJqrgFVykK+LG8wvYsEBwMjB9oRDLA96/YDXXiBzXHvd6mGh
g271lwMTQ9h+O8L6psLUX6qsrH3i7SJmF8ySPKi6Fe5ruT8ToOB8Ii8XQebEZdXo
VOzRz2VgSTcBdrTyKPDsBJByDQX36hsK8Gs5YSl5F3nvyV4dvGWMlyoTF1TRRt9K
YCCZ8pSk3kTXaSdl0syrJxI17pEUC8mtcA01S6JD/GV49CGO8LYAckVJ4ijWw7VV
IGGlH0DsYSMgJ7yyuLz4ifaqRnsWsAGW0WyiZYYKvjtNUiyBuBBbo2cQ1lNkR5p4
jnLhpJJVh0hLCPn6wcCWIBIdT/mFaBpXkvZPd3ks5kefGXsfpVPm0fK8r0fzkzgy
tJCZtZFZHeK1qsgaDsiS76S2ZNcFh0HQVIa84Q200/XUDgh8dYlD0+7oIsVu0UBZ
72Aop+Ak9+k4vKTvB9/hpcY+Rt0MI7zKewXBDSDK1sXhIHLQqv8rCEeNYiuPPqr/
ghRukn+C/Wtr7JYBsX+jMjxtmSzYtwBOihwLoZCH9pp3C5jTvyQk9s8n1j13V2RK
sAFtfpCVoQ8tTa7IITKRMfftzHn1WiPlPsj6VbigJ6A4N98csgv7x2rF7FyqcF0X
aoj69nQ3i/4=
=8iy3
-----END PGP SIGNATURE-----
Merge tag 'md-3.10-fixes' of git://neil.brown.name/md
Pull md bugfixes from Neil Brown:
"A few bugfixes for md
Some tagged for -stable"
* tag 'md-3.10-fixes' of git://neil.brown.name/md:
md/raid1,5,10: Disable WRITE SAME until a recovery strategy is in place
md/raid1,raid10: use freeze_array in place of raise_barrier in various places.
md/raid1: consider WRITE as successful only if at least one non-Faulty and non-rebuilding drive completed it.
md: md_stop_writes() should always freeze recovery.
There are cases where the kernel will believe that the WRITE SAME
command is supported by a block device which does not, in fact,
support WRITE SAME. This currently happens for SATA drivers behind a
SAS controller, but there are probably a hundred other ways that can
happen, including drive firmware bugs.
After receiving an error for WRITE SAME the block layer will retry the
request as a plain write of zeroes, but mdraid will consider the
failure as fatal and consider the drive failed. This has the effect
that all the mirrors containing a specific set of data are each
offlined in very rapid succession resulting in data loss.
However, just bouncing the request back up to the block layer isn't
ideal either, because the whole initial request-retry sequence should
be inside the write bitmap fence, which probably means that md needs
to do its own conversion of WRITE SAME to write zero.
Until the failure scenario has been sorted out, disable WRITE SAME for
raid1, raid5, and raid10.
[neilb: added raid5]
This patch is appropriate for any -stable since 3.7 when write_same
support was added.
Cc: stable@vger.kernel.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Signed-off-by: NeilBrown <neilb@suse.de>
The patch that converted raid5 to use bio_reset() forgot to initialize
bi_vcnt.
Signed-off-by: Kent Overstreet <koverstreet@google.com>
Cc: NeilBrown <neilb@suse.de>
Cc: linux-raid@vger.kernel.org
Tested-by: Ilia Mirkin <imirkin@alum.mit.edu>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Pull block core updates from Jens Axboe:
- Major bit is Kents prep work for immutable bio vecs.
- Stable candidate fix for a scheduling-while-atomic in the queue
bypass operation.
- Fix for the hang on exceeded rq->datalen 32-bit unsigned when merging
discard bios.
- Tejuns changes to convert the writeback thread pool to the generic
workqueue mechanism.
- Runtime PM framework, SCSI patches exists on top of these in James'
tree.
- A few random fixes.
* 'for-3.10/core' of git://git.kernel.dk/linux-block: (40 commits)
relay: move remove_buf_file inside relay_close_buf
partitions/efi.c: replace useless kzalloc's by kmalloc's
fs/block_dev.c: fix iov_shorten() criteria in blkdev_aio_read()
block: fix max discard sectors limit
blkcg: fix "scheduling while atomic" in blk_queue_bypass_start
Documentation: cfq-iosched: update documentation help for cfq tunables
writeback: expose the bdi_wq workqueue
writeback: replace custom worker pool implementation with unbound workqueue
writeback: remove unused bdi_pending_list
aoe: Fix unitialized var usage
bio-integrity: Add explicit field for owner of bip_buf
block: Add an explicit bio flag for bios that own their bvec
block: Add bio_alloc_pages()
block: Convert some code to bio_for_each_segment_all()
block: Add bio_for_each_segment_all()
bounce: Refactor __blk_queue_bounce to not use bi_io_vec
raid1: use bio_copy_data()
pktcdvd: Use bio_reset() in disabled code to kill bi_idx usage
pktcdvd: use bio_copy_data()
block: Add bio_copy_data()
...
If we write to a known-bad-block it will be flags as having
a ReadError by analyse_stripe, but the write will proceed anyway
(as it should). Then the read-error handling will kick in an
write again, then re-read.
We don't need that 'write-again', so set R5_ReWrite so it looks like
it has already been done. Then we will just get the re-read, which we
want.
Reported-by: majianpeng <majianpeng@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>
As the function call is the most expensive of these tests it should be
done later in the chain so that it can be avoided in some cases.
Signed-off-by: Jianpeng Ma <majianpeng@gmail.com>
Signed-off-by: NeilBrown <neilb@suse.de>
This reverts commit 3a366e614d.
Wanlong Gao reports that it causes a kernel panic on his machine several
minutes after boot. Reverting it removes the panic.
Jens says:
"It's not quite clear why that is yet, so I think we should just revert
the commit for 3.9 final (which I'm assuming is pretty close).
The wifi is crap at the LSF hotel, so sending this email instead of
queueing up a revert and pull request."
Reported-by: Wanlong Gao <gaowanlong@cn.fujitsu.com>
Requested-by: Jens Axboe <axboe@kernel.dk>
Cc: Tejun Heo <tj@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Tejun writes:
-----
This is the pull request for the earlier patchset[1] with the same
name. It's only three patches (the first one was committed to
workqueue tree) but the merge strategy is a bit involved due to the
dependencies.
* Because the conversion needs features from wq/for-3.10,
block/for-3.10/core is based on rc3, and wq/for-3.10 has conflicts
with rc3, I pulled mainline (rc5) into wq/for-3.10 to prevent those
workqueue conflicts from flaring up in block tree.
* Resolving the issue that Jan and Dave raised about debugging
requires arch-wide changes. The patchset is being worked on[2] but
it'll have to go through -mm after these changes show up in -next,
and not included in this pull request.
The three commits are located in the following git branch.
git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq.git writeback-workqueue
Pulling it into block/for-3.10/core produces a conflict in
drivers/md/raid5.c between the following two commits.
e3620a3ad5 ("MD RAID5: Avoid accessing gendisk or queue structs when not available")
2f6db2a707 ("raid5: use bio_reset()")
The conflict is trivial - one removes an "if ()" conditional while the
other removes "rbi->bi_next = NULL" right above it. We just need to
remove both. The merged branch is available at
git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq.git block-test-merge
so that you can use it for verification. The test merge commit has
proper merge description.
While these changes are a bit of pain to route, they make code simpler
and even have, while minute, measureable performance gain[3] even on a
workload which isn't particularly favorable to showing the benefits of
this conversion.
----
Fixed up the conflict.
Conflicts:
drivers/md/raid5.c
Signed-off-by: Jens Axboe <axboe@kernel.dk>
- recent regressions in raid5
- recent regressions in dmraid
- a few instances of CONFIG_MULTICORE_RAID456 linger
Several tagged for -stable
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2.0.19 (GNU/Linux)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=Rycs
-----END PGP SIGNATURE-----
Merge tag 'md-3.9-fixes' of git://neil.brown.name/md
Pull md fixes from NeilBrown:
"A few bugfixes for md
- recent regressions in raid5
- recent regressions in dmraid
- a few instances of CONFIG_MULTICORE_RAID456 linger
Several tagged for -stable"
* tag 'md-3.9-fixes' of git://neil.brown.name/md:
md: remove CONFIG_MULTICORE_RAID456 entirely
md/raid5: ensure sync and DISCARD don't happen at the same time.
MD: Prevent sysfs operations on uninitialized kobjects
MD RAID5: Avoid accessing gendisk or queue structs when not available
md/raid5: schedule_construction should abort if nothing to do.
