The new per-cpu counter for writes_pending is initialised in
md_alloc(), which is not called by dm-raid.
So dm-raid fails when md_write_start() is called.
Move the initialization to the personality modules
that need it. This way it is always initialised when needed,
but isn't unnecessarily initialized (requiring memory allocation)
when the personality doesn't use writes_pending.
Reported-by: Heinz Mauelshagen <heinzm@redhat.com>
Fixes: 4ad23a9764 ("MD: use per-cpu counter for writes_pending")
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
If an array consists of two drives and the first drive has the bad
block, the read request to the region overlapping the bad block chooses
the same disk (with bad block) as device to read from over and over and
the request gets stuck. If the first disk only partially overlaps with
bad block, it becomes a candidate ("best disk") for shorter range of
sectors. The second disk is capable of reading the entire requested
range and it is updated accordingly, however it is not recorded as a
best device for the request. In the end the request is sent to the first
disk to read entire range of sectors. It fails and is re-tried in a
moment but with the same outcome.
Actually it is quite likely scenario but it had little exposure in my
test until commit 715d40b93b10 ("md/raid1: add failfast handling for
reads.") removed preference for idle disk. Such scenario had been
passing as second disk was always chosen when idle.
Reset a candidate ("best disk") to read from if disk can read entire
range. Do it only if other disk has already been chosen as a candidate
for a smaller range. The head position / disk type logic will select
the best disk to read from - it is fine as disk with bad block won't be
considered for it.
Signed-off-by: Tomasz Majchrzak <tomasz.majchrzak@intel.com>
Signed-off-by: Shaohua Li <shli@fb.com>
If we add bios to block plugging list, locking is unnecessry, since the block
unplug is guaranteed not to run at that time.
Reviewed-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
This essentially reverts commit b5470dc5fc ("md: resolve external
metadata handling deadlock in md_allow_write") with some adjustments.
Since commit 6791875e2e ("md: make reconfig_mutex optional for writes
to md sysfs files.") changing array_state to 'active' does not use
mddev_lock() and will not cause a deadlock with md_allow_write(). This
revert simplifies userspace tools that write to sysfs attributes like
"stripe_cache_size" or "consistency_policy" because it removes the need
for special handling for external metadata arrays, checking for EAGAIN
and retrying the write.
Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Signed-off-by: Shaohua Li <shli@fb.com>
In new barrier codes, raise_barrier waits if conf->nr_pending[idx] is not zero.
After all the conditions are true, the resync request can go on be handled. But
it adds conf->nr_pending[idx] again. The next resync request hit the same bucket
idx need to wait the resync request which is submitted before. The performance
of resync/recovery is degraded.
So we should use a new variable to count sync requests which are in flight.
I did a simple test:
1. Without the patch, create a raid1 with two disks. The resync speed:
Device: rrqm/s wrqm/s r/s w/s rMB/s wMB/s avgrq-sz avgqu-sz await r_await w_await svctm %util
sdb 0.00 0.00 166.00 0.00 10.38 0.00 128.00 0.03 0.20 0.20 0.00 0.19 3.20
sdc 0.00 0.00 0.00 166.00 0.00 10.38 128.00 0.96 5.77 0.00 5.77 5.75 95.50
2. With the patch, the result is:
sdb 2214.00 0.00 766.00 0.00 185.69 0.00 496.46 2.80 3.66 3.66 0.00 1.03 79.10
sdc 0.00 2205.00 0.00 769.00 0.00 186.44 496.52 5.25 6.84 0.00 6.84 1.30 100.10
Suggested-by: Shaohua Li <shli@kernel.org>
Signed-off-by: Xiao Ni <xni@redhat.com>
Acked-by: Coly Li <colyli@suse.de>
Signed-off-by: Shaohua Li <shli@fb.com>
We can clear 'WantReplacement' flag directly no
matter it's replacement existed or not since the
semantic is same as before.
Also since the disk is removed from array, then
it is straightforward to remove 'WantReplacement'
flag and the comments in raid10/5 can be removed
as well.
Signed-off-by: Guoqing Jiang <gqjiang@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
A queue is declared and get from the disk of the array, but it's not
used anywhere. So removing it from the source.
Signed-off-by: Lidong Zhong <lzhong@suse.com>
Acted-by: Guoqing Jiang <gqjiang@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
flush_pending_writes() and raid1_unplug() each contain identical
copies of a fairly large slab of code. So factor that out into
new flush_bio_list() to simplify maintenance.
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
handle_read_error() duplicates a lot of the work that raid1_read_request()
does, so it makes sense to just use that function.
This doesn't quite work as handle_read_error() relies on the same r1bio
being re-used so that, in the case of a read-only array, setting
IO_BLOCKED in r1bio->bios[] ensures read_balance() won't re-use
that device.
So we need to allow a r1bio to be passed to raid1_read_request(), and to
have that function mostly initialise the r1bio, but leave the bios[]
array untouched.
Two parts of handle_read_error() that need to be preserved are the warning
message it prints, so they are conditionally added to raid1_read_request().
Note that this highlights a minor bug on alloc_r1bio(). It doesn't
initalise the bios[] array, so it is possible that old content is there,
which might cause read_balance() to ignore some devices with no good reason.
With this change, we no longer need inc_pending(), or the sectors_handled
arg to alloc_r1bio().
As handle_read_error() is called from raid1d() and allocates memory,
there is tiny chance of a deadlock. All element of various pools
could be queued waiting for raid1 to handle them, and there may be no
extra memory free.
Achieving guaranteed forward progress would probably require a second
thread and another mempool. Instead of that complexity, add
__GFP_HIGH to any allocations when read1_read_request() is called
from raid1d.
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
Now that we always always pass an offset of 0 and a size
that matches the bio to alloc_behind_master_bio(),
we can remove the offset/size args and simplify the code.
We could probably remove bio_copy_data_partial() too.
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
raid1 currently splits requests in two different ways for
two different reasons.
First, bio_split() is used to ensure the bio fits within a
resync accounting region.
Second, multiple r1bios are allocated for each bio to handle
the possiblity of known bad blocks on some devices.
This can be simplified to just use bio_split() once, and not
use multiple r1bios.
We delay the split until we know a maximum bio size that can
be handled with a single r1bio, and then split the bio and
queue the remainder for later handling.
This avoids all loops inside raid1.c request handling. Just
a single read, or a single set of writes, is submitted to
lower-level devices for each bio that comes from
generic_make_request().
When the bio needs to be split, generic_make_request() will
do the necessary looping and call md_make_request() multiple
times.
raid1_make_request() no longer queues request for raid1 to handle,
so we can remove that branch from the 'if'.
This patch also creates a new private bio_set
(conf->bio_split) for splitting bios. Using fs_bio_set
is wrong, as it is meant to be used by filesystems, not
block devices. Using it inside md can lead to deadlocks
under high memory pressure.
Delete unused variable in raid1_write_request() (Shaohua)
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
fix_sync_read_error() modifies a bio on a newly faulty
device by setting bi_end_io to end_sync_write.
This ensure that put_buf() will still call rdev_dec_pending()
as required, but makes sure that subsequent code in
fix_sync_read_error() doesn't try to read from the device.
Unfortunately this interacts badly with sync_request_write()
which assumes that any bio with bi_end_io set to non-NULL
other than end_sync_read is safe to write to.
As the device is now faulty it doesn't make sense to write.
As the bio was recently used for a read, it is "dirty"
and not suitable for immediate submission.
In particular, ->bi_next might be non-NULL, which will cause
generic_make_request() to complain.
Break this interaction by refusing to write to devices
which are marked as Faulty.
Reported-and-tested-by: Michael Wang <yun.wang@profitbricks.com>
Fixes: 2e52d449bc ("md/raid1: add failfast handling for reads.")
Cc: stable@vger.kernel.org (v4.10+)
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
Copy & paste from the REQ_OP_WRITE_SAME code.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
This patch kills the warning reported on powerpc_pseries,
and actually we don't need the initialization.
After merging the md tree, today's linux-next build (powerpc
pseries_le_defconfig) produced this warning:
drivers/md/raid1.c: In function 'raid1d':
drivers/md/raid1.c:2172:9: warning: 'page_len$' may be used uninitialized in this function [-Wmaybe-uninitialized]
if (memcmp(page_address(ppages[j]),
^
drivers/md/raid1.c:2160:7: note: 'page_len$' was declared here
int page_len[RESYNC_PAGES];
^
Signed-off-by: Ming Lei <tom.leiming@gmail.com>
Signed-off-by: Shaohua Li <shli@fb.com>
discard request doesn't have data attached, so it's meaningless to
allocate memory and copy from original bio for behind IO. And the copy
is bogus because bio_copy_data_partial can't handle discard request.
We don't support writesame/writezeros request so far.
Reviewed-by: Ming Lei <tom.leiming@gmail.com>
Signed-off-by: Shaohua Li <shli@fb.com>
This patch improve handling of write behind in the following ways:
- introduce behind master bio to hold all write behind pages
- fast clone bios from behind master bio
- avoid to change bvec table directly
- use bio_copy_data() and make code more clean
Suggested-by: Shaohua Li <shli@fb.com>
Signed-off-by: Ming Lei <tom.leiming@gmail.com>
Signed-off-by: Shaohua Li <shli@fb.com>
The 'offset' local variable can't be changed inside the loop, so
move it out.
Signed-off-by: Ming Lei <tom.leiming@gmail.com>
Signed-off-by: Shaohua Li <shli@fb.com>
Now one page array is allocated for each resync bio, and we can
retrieve page from this table directly.
Signed-off-by: Ming Lei <tom.leiming@gmail.com>
Signed-off-by: Shaohua Li <shli@fb.com>
Now we allocate one page array for managing resync pages, instead
of using bio's vec table to do that, and the old way is very hacky
and won't work any more if multipage bvec is enabled.
The introduced cost is that we need to allocate (128 + 16) * raid_disks
bytes per r1_bio, and it is fine because the inflight r1_bio for
resync shouldn't be much, as pointed by Shaohua.
Also the bio_reset() in raid1_sync_request() is removed because
all bios are freshly new now and not necessary to reset any more.
This patch can be thought as a cleanup too
Suggested-by: Shaohua Li <shli@kernel.org>
Signed-off-by: Ming Lei <tom.leiming@gmail.com>
Signed-off-by: Shaohua Li <shli@fb.com>
This patch gets each page's reference of each bio for resync,
then r1buf_pool_free() gets simplified a lot.
The same policy has been taken in raid10's buf pool allocation/free
too.
Signed-off-by: Ming Lei <tom.leiming@gmail.com>
Signed-off-by: Shaohua Li <shli@fb.com>
Both raid1 and raid10 share common resync
block size and page count, so move them into md.h.
Signed-off-by: Ming Lei <tom.leiming@gmail.com>
Signed-off-by: Shaohua Li <shli@fb.com>
All bio_add_page() is for adding one page into resync bio,
which is big enough to hold RESYNC_PAGES pages, and
the current bio_add_page() doesn't check queue limit any more,
so it won't fail at all.
remove unused label (shaohua)
Signed-off-by: Ming Lei <tom.leiming@gmail.com>
Signed-off-by: Shaohua Li <shli@fb.com>
Change to use bio->__bi_remaining to count number of r1bio attached
to a bio.
See precious raid10 patch for more details.
Like the raid10.c patch, this fixes a bug as nr_queued and nr_pending
used to measure different things, but were being compared.
This patch fixes another bug in that nr_pending previously did not
could write-behind requests, so behind writes could continue while
resync was happening. How that nr_pending counts all r1_bio,
the resync cannot commence until the behind writes have completed.
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
When raid1 or raid10 find they will need to allocate a new
r1bio/r10bio, in order to work around a known bad block, they
account for the allocation well before the allocation is
made. This separation makes the correctness less obvious
and requires comments.
The accounting needs to be a little before: before the first
rXbio is submitted, but that is all.
So move the accounting down to where it makes more sense.
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
Include information about PPL location and size into mdp_superblock_1
and copy it to/from rdev. Because PPL is mutually exclusive with bitmap,
put it in place of 'bitmap_offset'. Add a new flag MD_FEATURE_PPL for
'feature_map', analogically to MD_FEATURE_BITMAP_OFFSET. Add MD_HAS_PPL
to mddev->flags to indicate that PPL is enabled on an array.
Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Signed-off-by: Shaohua Li <shli@fb.com>
raid1.c: fix a trivial typo in comments of freeze_array().
Cc: Jack Wang <jack.wang.usish@gmail.com>
Cc: Guoqing Jiang <gqjiang@suse.com>
Cc: John Stoffel <john@stoffel.org>
Acked-by: Coly Li <colyli@suse.de>
Signed-off-by: Zhilong Liu <zlliu@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
Neil Brown pointed out a potential deadlock in raid 10 code with
bio_split/chain. The raid1 code could have the same issue, but recent
barrier rework makes it less likely to happen. The deadlock happens in
below sequence:
1. generic_make_request(bio), this will set current->bio_list
2. raid10_make_request will split bio to bio1 and bio2
3. __make_request(bio1), wait_barrer, add underlayer disk bio to
current->bio_list
4. __make_request(bio2), wait_barrer
If raise_barrier happens between 3 & 4, since wait_barrier runs at 3,
raise_barrier waits for IO completion from 3. And since raise_barrier
sets barrier, 4 waits for raise_barrier. But IO from 3 can't be
dispatched because raid10_make_request() doesn't finished yet.
The solution is to adjust the IO ordering. Quotes from Neil:
"
It is much safer to:
if (need to split) {
split = bio_split(bio, ...)
bio_chain(...)
make_request_fn(split);
generic_make_request(bio);
} else
make_request_fn(mddev, bio);
This way we first process the initial section of the bio (in 'split')
which will queue some requests to the underlying devices. These
requests will be queued in generic_make_request.
Then we queue the remainder of the bio, which will be added to the end
of the generic_make_request queue.
Then we return.
generic_make_request() will pop the lower-level device requests off the
queue and handle them first. Then it will process the remainder
of the original bio once the first section has been fully processed.
"
Note, this only happens in read path. In write path, the bio is flushed to
underlaying disks either by blk flush (from schedule) or offladed to raid1/10d.
It's queued in current->bio_list.
Cc: Coly Li <colyli@suse.de>
Cc: stable@vger.kernel.org (v3.14+, only the raid10 part)
Suggested-by: NeilBrown <neilb@suse.com>
Reviewed-by: Jack Wang <jinpu.wang@profitbricks.com>
Signed-off-by: Shaohua Li <shli@fb.com>
raid1_resize and raid5_resize should also check the
mddev->queue if run underneath dm-raid.
And both set_capacity and revalidate_disk are used in
pers->resize such as raid1, raid10 and raid5. So
move them from personality file to common code.
Reviewed-by: NeilBrown <neilb@suse.com>
Signed-off-by: Guoqing Jiang <gqjiang@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
We are going to split <linux/sched/signal.h> out of <linux/sched.h>, which
will have to be picked up from other headers and a couple of .c files.
Create a trivial placeholder <linux/sched/signal.h> file that just
maps to <linux/sched.h> to make this patch obviously correct and
bisectable.
Include the new header in the files that are going to need it.
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Pull md updates from Shaohua Li:
"Mainly fixes bugs and improves performance:
- Improve scalability for raid1 from Coly
- Improve raid5-cache read performance, disk efficiency and IO
pattern from Song and me
- Fix a race condition of disk hotplug for linear from Coly
- A few cleanup patches from Ming and Byungchul
- Fix a memory leak from Neil
- Fix WRITE SAME IO failure from me
- Add doc for raid5-cache from me"
* 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/shli/md: (23 commits)
md/raid1: fix write behind issues introduced by bio_clone_bioset_partial
md/raid1: handle flush request correctly
md/linear: shutup lockdep warnning
md/raid1: fix a use-after-free bug
RAID1: avoid unnecessary spin locks in I/O barrier code
RAID1: a new I/O barrier implementation to remove resync window
md/raid5: Don't reinvent the wheel but use existing llist API
md: fast clone bio in bio_clone_mddev()
md: remove unnecessary check on mddev
md/raid1: use bio_clone_bioset_partial() in case of write behind
md: fail if mddev->bio_set can't be created
block: introduce bio_clone_bioset_partial()
md: disable WRITE SAME if it fails in underlayer disks
md/raid5-cache: exclude reclaiming stripes in reclaim check
md/raid5-cache: stripe reclaim only counts valid stripes
MD: add doc for raid5-cache
Documentation: move MD related doc into a separate dir
md: ensure md devices are freed before module is unloaded.
md/r5cache: improve journal device efficiency
md/r5cache: enable chunk_aligned_read with write back cache
...
There are two issues, introduced by commit 8e58e32(md/raid1: use
bio_clone_bioset_partial() in case of write behind):
- bio_clone_bioset_partial() uses bytes instead of sectors as parameters
- in writebehind mode, we return bio if all !writemostly disk bios finish,
which could happen before writemostly disk bios run. So all
writemostly disk bios should have their bvec. Here we just make sure
all bios are cloned instead of fast cloned.
Reviewed-by: Ming Lei <tom.leiming@gmail.com>
Signed-off-by: Shaohua Li <shli@fb.com>
I got a warning triggered in align_to_barrier_unit_end. It's a flush
request so sectors == 0. The flush request happens to work well without
the new barrier patch, but we'd better handle it explictly.
Cc: NeilBrown <neilb@suse.com>
Acked-by: Coly Li <colyli@suse.de>
Signed-off-by: Shaohua Li <shli@fb.com>
Commit fd76863 (RAID1: a new I/O barrier implementation to remove resync
window) introduces a user-after-free bug.
Signed-off-by: Shaohua Li <shli@fb.com>
When I run a parallel reading performan testing on a md raid1 device with
two NVMe SSDs, I observe very bad throughput in supprise: by fio with 64KB
block size, 40 seq read I/O jobs, 128 iodepth, overall throughput is
only 2.7GB/s, this is around 50% of the idea performance number.
The perf reports locking contention happens at allow_barrier() and
wait_barrier() code,
- 41.41% fio [kernel.kallsyms] [k] _raw_spin_lock_irqsave
- _raw_spin_lock_irqsave
+ 89.92% allow_barrier
+ 9.34% __wake_up
- 37.30% fio [kernel.kallsyms] [k] _raw_spin_lock_irq
- _raw_spin_lock_irq
- 100.00% wait_barrier
The reason is, in these I/O barrier related functions,
- raise_barrier()
- lower_barrier()
- wait_barrier()
- allow_barrier()
They always hold conf->resync_lock firstly, even there are only regular
reading I/Os and no resync I/O at all. This is a huge performance penalty.
The solution is a lockless-like algorithm in I/O barrier code, and only
holding conf->resync_lock when it has to.
The original idea is from Hannes Reinecke, and Neil Brown provides
comments to improve it. I continue to work on it, and make the patch into
current form.
In the new simpler raid1 I/O barrier implementation, there are two
wait barrier functions,
- wait_barrier()
Which calls _wait_barrier(), is used for regular write I/O. If there is
resync I/O happening on the same I/O barrier bucket, or the whole
array is frozen, task will wait until no barrier on same barrier bucket,
or the whold array is unfreezed.
- wait_read_barrier()
Since regular read I/O won't interfere with resync I/O (read_balance()
will make sure only uptodate data will be read out), it is unnecessary
to wait for barrier in regular read I/Os, waiting in only necessary
when the whole array is frozen.
The operations on conf->nr_pending[idx], conf->nr_waiting[idx], conf->
barrier[idx] are very carefully designed in raise_barrier(),
lower_barrier(), _wait_barrier() and wait_read_barrier(), in order to
avoid unnecessary spin locks in these functions. Once conf->
nr_pengding[idx] is increased, a resync I/O with same barrier bucket index
has to wait in raise_barrier(). Then in _wait_barrier() if no barrier
raised in same barrier bucket index and array is not frozen, the regular
I/O doesn't need to hold conf->resync_lock, it can just increase
conf->nr_pending[idx], and return to its caller. wait_read_barrier() is
very similar to _wait_barrier(), the only difference is it only waits when
array is frozen. For heavy parallel reading I/Os, the lockless I/O barrier
code almostly gets rid of all spin lock cost.
This patch significantly improves raid1 reading peroformance. From my
testing, a raid1 device built by two NVMe SSD, runs fio with 64KB
blocksize, 40 seq read I/O jobs, 128 iodepth, overall throughput
increases from 2.7GB/s to 4.6GB/s (+70%).
Changelog
V4:
- Change conf->nr_queued[] to atomic_t.
- Define BARRIER_BUCKETS_NR_BITS by (PAGE_SHIFT - ilog2(sizeof(atomic_t)))
V3:
- Add smp_mb__after_atomic() as Shaohua and Neil suggested.
- Change conf->nr_queued[] from atomic_t to int.
- Change conf->array_frozen from atomic_t back to int, and use
READ_ONCE(conf->array_frozen) to check value of conf->array_frozen
in _wait_barrier() and wait_read_barrier().
- In _wait_barrier() and wait_read_barrier(), add a call to
wake_up(&conf->wait_barrier) after atomic_dec(&conf->nr_pending[idx]),
to fix a deadlock between _wait_barrier()/wait_read_barrier and
freeze_array().
V2:
- Remove a spin_lock/unlock pair in raid1d().
- Add more code comments to explain why there is no racy when checking two
atomic_t variables at same time.
V1:
- Original RFC patch for comments.
Signed-off-by: Coly Li <colyli@suse.de>
Cc: Shaohua Li <shli@fb.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Cc: Guoqing Jiang <gqjiang@suse.com>
Reviewed-by: Neil Brown <neilb@suse.de>
Signed-off-by: Shaohua Li <shli@fb.com>
'Commit 79ef3a8aa1 ("raid1: Rewrite the implementation of iobarrier.")'
introduces a sliding resync window for raid1 I/O barrier, this idea limits
I/O barriers to happen only inside a slidingresync window, for regular
I/Os out of this resync window they don't need to wait for barrier any
more. On large raid1 device, it helps a lot to improve parallel writing
I/O throughput when there are background resync I/Os performing at
same time.
The idea of sliding resync widow is awesome, but code complexity is a
challenge. Sliding resync window requires several variables to work
collectively, this is complexed and very hard to make it work correctly.
Just grep "Fixes: 79ef3a8aa1" in kernel git log, there are 8 more patches
to fix the original resync window patch. This is not the end, any further
related modification may easily introduce more regreassion.
Therefore I decide to implement a much simpler raid1 I/O barrier, by
removing resync window code, I believe life will be much easier.
The brief idea of the simpler barrier is,
- Do not maintain a global unique resync window
- Use multiple hash buckets to reduce I/O barrier conflicts, regular
I/O only has to wait for a resync I/O when both them have same barrier
bucket index, vice versa.
- I/O barrier can be reduced to an acceptable number if there are enough
barrier buckets
Here I explain how the barrier buckets are designed,
- BARRIER_UNIT_SECTOR_SIZE
The whole LBA address space of a raid1 device is divided into multiple
barrier units, by the size of BARRIER_UNIT_SECTOR_SIZE.
Bio requests won't go across border of barrier unit size, that means
maximum bio size is BARRIER_UNIT_SECTOR_SIZE<<9 (64MB) in bytes.
For random I/O 64MB is large enough for both read and write requests,
for sequential I/O considering underlying block layer may merge them
into larger requests, 64MB is still good enough.
Neil also points out that for resync operation, "we want the resync to
move from region to region fairly quickly so that the slowness caused
by having to synchronize with the resync is averaged out over a fairly
small time frame". For full speed resync, 64MB should take less then 1
second. When resync is competing with other I/O, it could take up a few
minutes. Therefore 64MB size is fairly good range for resync.
- BARRIER_BUCKETS_NR
There are BARRIER_BUCKETS_NR buckets in total, which is defined by,
#define BARRIER_BUCKETS_NR_BITS (PAGE_SHIFT - 2)
#define BARRIER_BUCKETS_NR (1<<BARRIER_BUCKETS_NR_BITS)
this patch makes the bellowed members of struct r1conf from integer
to array of integers,
- int nr_pending;
- int nr_waiting;
- int nr_queued;
- int barrier;
+ int *nr_pending;
+ int *nr_waiting;
+ int *nr_queued;
+ int *barrier;
number of the array elements is defined as BARRIER_BUCKETS_NR. For 4KB
kernel space page size, (PAGE_SHIFT - 2) indecates there are 1024 I/O
barrier buckets, and each array of integers occupies single memory page.
1024 means for a request which is smaller than the I/O barrier unit size
has ~0.1% chance to wait for resync to pause, which is quite a small
enough fraction. Also requesting single memory page is more friendly to
kernel page allocator than larger memory size.
- I/O barrier bucket is indexed by bio start sector
If multiple I/O requests hit different I/O barrier units, they only need
to compete I/O barrier with other I/Os which hit the same I/O barrier
bucket index with each other. The index of a barrier bucket which a
bio should look for is calculated by sector_to_idx() which is defined
in raid1.h as an inline function,
static inline int sector_to_idx(sector_t sector)
{
return hash_long(sector >> BARRIER_UNIT_SECTOR_BITS,
BARRIER_BUCKETS_NR_BITS);
}
Here sector_nr is the start sector number of a bio.
- Single bio won't go across boundary of a I/O barrier unit
If a request goes across boundary of barrier unit, it will be split. A
bio may be split in raid1_make_request() or raid1_sync_request(), if
sectors returned by align_to_barrier_unit_end() is smaller than
original bio size.
Comparing to single sliding resync window,
- Currently resync I/O grows linearly, therefore regular and resync I/O
will conflict within a single barrier units. So the I/O behavior is
similar to single sliding resync window.
- But a barrier unit bucket is shared by all barrier units with identical
barrier uinit index, the probability of conflict might be higher
than single sliding resync window, in condition that writing I/Os
always hit barrier units which have identical barrier bucket indexs with
the resync I/Os. This is a very rare condition in real I/O work loads,
I cannot imagine how it could happen in practice.
- Therefore we can achieve a good enough low conflict rate with much
simpler barrier algorithm and implementation.
There are two changes should be noticed,
- In raid1d(), I change the code to decrease conf->nr_pending[idx] into
single loop, it looks like this,
spin_lock_irqsave(&conf->device_lock, flags);
conf->nr_queued[idx]--;
spin_unlock_irqrestore(&conf->device_lock, flags);
This change generates more spin lock operations, but in next patch of
this patch set, it will be replaced by a single line code,
atomic_dec(&conf->nr_queueud[idx]);
So we don't need to worry about spin lock cost here.
- Mainline raid1 code split original raid1_make_request() into
raid1_read_request() and raid1_write_request(). If the original bio
goes across an I/O barrier unit size, this bio will be split before
calling raid1_read_request() or raid1_write_request(), this change
the code logic more simple and clear.
- In this patch wait_barrier() is moved from raid1_make_request() to
raid1_write_request(). In raid_read_request(), original wait_barrier()
is replaced by raid1_read_request().
The differnece is wait_read_barrier() only waits if array is frozen,
using different barrier function in different code path makes the code
more clean and easy to read.
Changelog
V4:
- Add alloc_r1bio() to remove redundant r1bio memory allocation code.
- Fix many typos in patch comments.
- Use (PAGE_SHIFT - ilog2(sizeof(int))) to define BARRIER_BUCKETS_NR_BITS.
V3:
- Rebase the patch against latest upstream kernel code.
- Many fixes by review comments from Neil,
- Back to use pointers to replace arraries in struct r1conf
- Remove total_barriers from struct r1conf
- Add more patch comments to explain how/why the values of
BARRIER_UNIT_SECTOR_SIZE and BARRIER_BUCKETS_NR are decided.
- Use get_unqueued_pending() to replace get_all_pendings() and
get_all_queued()
- Increase bucket number from 512 to 1024
- Change code comments format by review from Shaohua.
V2:
- Use bio_split() to split the orignal bio if it goes across barrier unit
bounday, to make the code more simple, by suggestion from Shaohua and
Neil.
- Use hash_long() to replace original linear hash, to avoid a possible
confilict between resync I/O and sequential write I/O, by suggestion from
Shaohua.
- Add conf->total_barriers to record barrier depth, which is used to
control number of parallel sync I/O barriers, by suggestion from Shaohua.
- In V1 patch the bellowed barrier buckets related members in r1conf are
allocated in memory page. To make the code more simple, V2 patch moves
the memory space into struct r1conf, like this,
- int nr_pending;
- int nr_waiting;
- int nr_queued;
- int barrier;
+ int nr_pending[BARRIER_BUCKETS_NR];
+ int nr_waiting[BARRIER_BUCKETS_NR];
+ int nr_queued[BARRIER_BUCKETS_NR];
+ int barrier[BARRIER_BUCKETS_NR];
This change is by the suggestion from Shaohua.
- Remove some inrelavent code comments, by suggestion from Guoqing.
- Add a missing wait_barrier() before jumping to retry_write, in
raid1_make_write_request().
V1:
- Original RFC patch for comments
Signed-off-by: Coly Li <colyli@suse.de>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Cc: Guoqing Jiang <gqjiang@suse.com>
Reviewed-by: Neil Brown <neilb@suse.de>
Signed-off-by: Shaohua Li <shli@fb.com>
Firstly bio_clone_mddev() is used in raid normal I/O and isn't
in resync I/O path.
Secondly all the direct access to bvec table in raid happens on
resync I/O except for write behind of raid1, in which we still
use bio_clone() for allocating new bvec table.
So this patch replaces bio_clone() with bio_clone_fast()
in bio_clone_mddev().
Also kill bio_clone_mddev() and call bio_clone_fast() directly, as
suggested by Christoph Hellwig.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ming Lei <tom.leiming@gmail.com>
Signed-off-by: Shaohua Li <shli@fb.com>
Write behind need to replace pages in bio's bvecs, and we have
to clone a fresh bio with new bvec table, so use the introduced
bio_clone_bioset_partial() for it.
For other bio_clone_mddev() cases, we will use fast clone since
they don't need to touch bvec table.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ming Lei <tom.leiming@gmail.com>
Signed-off-by: Shaohua Li <shli@fb.com>
We will want to have struct backing_dev_info allocated separately from
struct request_queue. As the first step add pointer to backing_dev_info
to request_queue and convert all users touching it. No functional
changes in this patch.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jens Axboe <axboe@fb.com>
No need for the local variables, the bio is still live and we can just
assign the bits we want directly. Make me wonder why we can't assign
all the bio flags to start with.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
Commit 6995f0b (md: takeover should clear unrelated bits) clear
unrelated bits, but it's quite fragile. To avoid error in the future,
define a macro for unsupported mddev flags for each raid type and use it
to clear unsupported mddev flags. This should be less error-prone.
Suggested-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
Refactor raid1_make_request to make read and write code in their own
functions to clean up the code.
Signed-off-by: Robert LeBlanc <robert@leblancnet.us>
Signed-off-by: Shaohua Li <shli@fb.com>
The mddev->flags are used for different purposes. There are a lot of
places we check/change the flags without masking unrelated flags, we
could check/change unrelated flags. These usage are most for superblock
write, so spearate superblock related flags. This should make the code
clearer and also fix real bugs.
Reviewed-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
When we change level from raid1 to raid5, the MD_FAILFAST_SUPPORTED bit
will be accidentally set, but raid5 doesn't support it. The same is true
for the MD_HAS_JOURNAL bit.
Fix: 46533ff (md: Use REQ_FAILFAST_* on metadata writes where appropriate)
Reviewed-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
When writing to a fastfail device we use MD_FASTFAIL unless
it is the only device being written to.
For resync/recovery, assume there was a working device to
read from so always use REQ_FASTFAIL_DEV.
If a write for resync/recovery fails, we just fail the
device - there is not much else to do.
If a normal failfast write fails, but the device cannot be
failed (must be only one left), we queue for write error
handling. This will call narrow_write_error() to retry the
write synchronously and without any FAILFAST flags.
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
If a device is marked FailFast and it is not the only device
we can read from, we mark the bio with REQ_FAILFAST_* flags.
If this does fail, we don't try read repair but just allow
failure. If it was the last device it doesn't fail of
course, so the retry happens on the same device - this time
without FAILFAST. A subsequent failure will not retry but
will just pass up the error.
During resync we may use FAILFAST requests and on a failure
we will simply use the other device(s).
During recovery we will only use FAILFAST in the unusual
case were there are multiple places to read from - i.e. if
there are > 2 devices. If we get a failure we will fail the
device and complete the resync/recovery with remaining
devices.
The new R1BIO_FailFast flag is set on read reqest to suggest
the a FAILFAST request might be acceptable. The rdev needs
to have FailFast set as well for the read to actually use
REQ_FAILFAST_*.
We need to know there are at least two working devices
before we can set R1BIO_FailFast, so we mustn't stop looking
at the first device we find. So the "min_pending == 0"
handling to not exit early, but too always choose the
best_pending_disk if min_pending == 0.
The spinlocked region in raid1_error() in enlarged to ensure
that if two bios, reading from two different devices, fail
at the same time, then there is no risk that both devices
will be marked faulty, leaving zero "In_sync" devices.
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
This can only be supported on personalities which ensure
that md_error() never causes an array to enter the 'failed'
state. i.e. if marking a device Faulty would cause some
data to be inaccessible, the device is status is left as
non-Faulty. This is true for RAID1 and RAID10.
If we get a failure writing metadata but the device doesn't
fail, it must be the last device so we re-write without
FAILFAST to improve chance of success. We also flag the
device as LastDev so that future metadata updates don't
waste time on failfast writes.
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
Both raid1 and raid10 will sometimes delay handling an IO request,
such as when resync is happening or there are too many requests queued.
Add some blktrace messsages so we can see when that is happening when
looking for performance artefacts.
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
The block tracing infrastructure (accessed with blktrace/blkparse)
supports the tracing of mapping bios from one device to another.
This is currently used when a bio in a partition is mapped to the
whole device, when bios are mapped by dm, and for mapping in md/raid5.
Other md personalities do not include this tracing yet, so add it.
When a read-error is detected we redirect the request to a different device.
This could justifiably be seen as a new mapping for the originial bio,
or a secondary mapping for the bio that errors. This patch uses
the second option.
When md is used under dm-raid, the mappings are not traced as we do
not have access to the block device number of the parent.
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
NeilBrown