Commit 539d39eb27 ("bcache: fix wrong return value in bch_debug_init()")
returns the return value of debugfs_create_dir() to bcache_init(). When
CONFIG_DEBUG_FS=n, bch_debug_init() always returns 1 and makes
bcache_init() failedi.
This patch makes bch_debug_init() always returns 0 if CONFIG_DEBUG_FS=n,
so bcache can continue to work for the kernels which don't have debugfs
enanbled.
Changelog:
v4: Add Acked-by from Kent Overstreet.
v3: Use IS_ENABLED(CONFIG_DEBUG_FS) to replace #ifdef DEBUG_FS.
v2: Remove a warning information
v1: Initial version.
Fixes: Commit 539d39eb27 ("bcache: fix wrong return value in bch_debug_init()")
Cc: stable@vger.kernel.org
Signed-off-by: Coly Li <colyli@suse.de>
Reported-by: Massimo B. <massimo.b@gmx.net>
Reported-by: Kai Krakow <kai@kaishome.de>
Tested-by: Kai Krakow <kai@kaishome.de>
Acked-by: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
It is possible that multiple I/O requests hits on failed cache device or
backing device, therefore it is quite common that CACHE_SET_IO_DISABLE is
set already when a task tries to set the bit from bch_cache_set_error().
Currently the message "CACHE_SET_IO_DISABLE already set" is printed by
pr_warn(), which might mislead users to think a serious fault happens in
source code.
This patch uses pr_info() to print the information in such situation,
avoid extra worries. This information is helpful to understand bcache
behavior in cache device failures, so I still keep them in source code.
Fixes: 771f393e8f ("bcache: add CACHE_SET_IO_DISABLE to struct cache_set flags")
Signed-off-by: Coly Li <colyli@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Commit 7e027ca4b5 ("bcache: add stop_when_cache_set_failed option to
backing device") adds stop_when_cache_set_failed option and stops bcache
device if stop_when_cache_set_failed is auto and there is dirty data on
broken cache device. There might exists a small time gap that the cache
set is released and set to NULL but bcache device is not released yet
(because they are released in parallel). During this time gap, dc->c is
NULL so CACHE_SET_IO_DISABLE won't be checked, and dc->io_disable is still
false, so new coming I/O requests will be accepted and directly go into
backing device as no cache set attached to. If there is dirty data on
cache device, this behavior may introduce potential inconsistent data.
This patch sets dc->io_disable to true before calling bcache_device_stop()
to make sure the backing device will reject new coming I/O request as
well, so even in the small time gap no I/O will directly go into backing
device to corrupt data consistency.
Fixes: 7e027ca4b5 ("bcache: add stop_when_cache_set_failed option to backing device")
Signed-off-by: Coly Li <colyli@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Commit c7b7bd0740 ("bcache: add io_disable to struct cached_dev")
counts backing device I/O requets and set dc->io_disable to true if error
counters exceeds dc->io_error_limit. But it only counts I/O errors for
regular I/O request, neglects errors of write back I/Os when backing device
is offline.
This patch counts the errors of writeback I/Os, in dirty_endio() if
bio->bi_status is not 0, it means error happens when writing dirty keys
to backing device, then bch_count_backing_io_errors() is called.
By this fix, even there is no reqular I/O request coming, if writeback I/O
errors exceed dc->io_error_limit, the bcache device may still be stopped
for the broken backing device.
Fixes: c7b7bd0740 ("bcache: add io_disable to struct cached_dev")
Signed-off-by: Coly Li <colyli@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Commit c7b7bd0740 ("bcache: add io_disable to struct cached_dev") tries
to stop bcache device by calling bcache_device_stop() when too many I/O
errors happened on backing device. But if there is internal I/O happening
on cache device (writeback scan, garbage collection, etc), a regular I/O
request triggers the internal I/Os may still holds a refcount of dc->count,
and the refcount may only be dropped after the internal I/O stopped.
By this patch, bch_cached_dev_error() will check if the backing device is
attached to a cache set, if yes that CACHE_SET_IO_DISABLE will be set to
flags of this cache set. Then internal I/Os on cache device will be
rejected and stopped immediately, and the bcache device can be stopped.
For people who are not familiar with the interesting refcount dependance,
let me explain a bit more how the fix works. Example the writeback thread
will scan cache device for dirty data writeback purpose. Before it stopps,
it holds a refcount of dc->count. When CACHE_SET_IO_DISABLE bit is set,
the internal I/O will stopped and the while-loop in bch_writeback_thread()
quits and calls cached_dev_put() to drop dc->count. If this is the last
refcount to drop, then cached_dev_detach_finish() will be called. In this
call back function, in turn closure_put(dc->disk.cl) is called to drop a
refcount of closure dc->disk.cl. If this is the last refcount of this
closure to drop, then cached_dev_flush() will be called. Then the cached
device is freed. So if CACHE_SET_IO_DISABLE is not set, the bache device
can not be stopped until all inernal cache device I/O stopped. For large
size cache device, and writeback thread competes locks with gc thread,
there might be a quite long time to wait.
Fixes: c7b7bd0740 ("bcache: add io_disable to struct cached_dev")
Signed-off-by: Coly Li <colyli@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Current code uses bdevname() or bio_devname() to reference gendisk
disk name when bcache needs to display the disk names in kernel message.
It was safe before bcache device failure handling patch set merged in,
because when devices are failed, there was deadlock to prevent bcache
printing error messages with gendisk disk name. But after the failure
handling patch set merged, the deadlock is fixed, so it is possible
that the gendisk structure bdev->hd_disk is released when bdevname() is
called to reference bdev->bd_disk->disk_name[]. This is why I receive
bug report of NULL pointers deference panic.
This patch stores gendisk disk name in a buffer inside struct cache and
struct cached_dev, then print out the offline device name won't reference
bdev->hd_disk anymore. And this patch also avoids extra function calls
of bdevname() and bio_devnmae().
Changelog:
v3, add Reviewed-by from Hannes.
v2, call bdevname() earlier in register_bdev()
v1, first version with segguestion from Junhui Tang.
Fixes: c7b7bd0740 ("bcache: add io_disable to struct cached_dev")
Fixes: 5138ac6748 ("bcache: fix misleading error message in bch_count_io_errors()")
Signed-off-by: Coly Li <colyli@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1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=RVhK
-----END PGP SIGNATURE-----
Merge tag 'for-4.17/block-20180402' of git://git.kernel.dk/linux-block
Pull block layer updates from Jens Axboe:
"It's a pretty quiet round this time, which is nice. This contains:
- series from Bart, cleaning up the way we set/test/clear atomic
queue flags.
- series from Bart, fixing races between gendisk and queue
registration and removal.
- set of bcache fixes and improvements from various folks, by way of
Michael Lyle.
- set of lightnvm updates from Matias, most of it being the 1.2 to
2.0 transition.
- removal of unused DIO flags from Nikolay.
- blk-mq/sbitmap memory ordering fixes from Omar.
- divide-by-zero fix for BFQ from Paolo.
- minor documentation patches from Randy.
- timeout fix from Tejun.
- Alpha "can't write a char atomically" fix from Mikulas.
- set of NVMe fixes by way of Keith.
- bsg and bsg-lib improvements from Christoph.
- a few sed-opal fixes from Jonas.
- cdrom check-disk-change deadlock fix from Maurizio.
- various little fixes, comment fixes, etc from various folks"
* tag 'for-4.17/block-20180402' of git://git.kernel.dk/linux-block: (139 commits)
blk-mq: Directly schedule q->timeout_work when aborting a request
blktrace: fix comment in blktrace_api.h
lightnvm: remove function name in strings
lightnvm: pblk: remove some unnecessary NULL checks
lightnvm: pblk: don't recover unwritten lines
lightnvm: pblk: implement 2.0 support
lightnvm: pblk: implement get log report chunk
lightnvm: pblk: rename ppaf* to addrf*
lightnvm: pblk: check for supported version
lightnvm: implement get log report chunk helpers
lightnvm: make address conversions depend on generic device
lightnvm: add support for 2.0 address format
lightnvm: normalize geometry nomenclature
lightnvm: complete geo structure with maxoc*
lightnvm: add shorten OCSSD version in geo
lightnvm: add minor version to generic geometry
lightnvm: simplify geometry structure
lightnvm: pblk: refactor init/exit sequences
lightnvm: Avoid validation of default op value
lightnvm: centralize permission check for lightnvm ioctl
...
Avoid that building with W=1 triggers the following compiler warning:
drivers/md/bcache/super.c:776:20: warning: comparison is always false due to limited range of data type [-Wtype-limits]
d->nr_stripes > SIZE_MAX / sizeof(atomic_t)) {
^
Reviewed-by: Coly Li <colyli@suse.de>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Add more annotations for sparse to inform it about which functions do
not have the same number of spin_lock() and spin_unlock() calls.
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This patch does not change any functionality.
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Reviewed-by: Coly Li <colyli@suse.de>
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Avoid that building with W=1 triggers warnings about the kernel-doc
headers.
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This patch avoids that building with W=1 triggers complaints about
switch fall-throughs.
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Make it possible for the compiler to verify the consistency of the
format string passed to __bch_check_keys() and the arguments that
should be formatted according to that format string.
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This patch avoids that smatch complains about inconsistent indentation.
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Reviewed-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If a bcache device is configured to writeback mode, current code does not
handle write I/O errors on backing devices properly.
In writeback mode, write request is written to cache device, and
latter being flushed to backing device. If I/O failed when writing from
cache device to the backing device, bcache code just ignores the error and
upper layer code is NOT noticed that the backing device is broken.
This patch tries to handle backing device failure like how the cache device
failure is handled,
- Add a error counter 'io_errors' and error limit 'error_limit' in struct
cached_dev. Add another io_disable to struct cached_dev to disable I/Os
on the problematic backing device.
- When I/O error happens on backing device, increase io_errors counter. And
if io_errors reaches error_limit, set cache_dev->io_disable to true, and
stop the bcache device.
The result is, if backing device is broken of disconnected, and I/O errors
reach its error limit, backing device will be disabled and the associated
bcache device will be removed from system.
Changelog:
v2: remove "bcache: " prefix in pr_error(), and use correct name string to
print out bcache device gendisk name.
v1: indeed this is new added in v2 patch set.
Signed-off-by: Coly Li <colyli@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Cc: Michael Lyle <mlyle@lyle.org>
Cc: Junhui Tang <tang.junhui@zte.com.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In order to catch I/O error of backing device, a separate bi_end_io
call back is required. Then a per backing device counter can record I/O
errors number and retire the backing device if the counter reaches a
per backing device I/O error limit.
This patch adds backing_request_endio() to bcache backing device I/O code
path, this is a preparation for further complicated backing device failure
handling. So far there is no real code logic change, I make this change a
separate patch to make sure it is stable and reliable for further work.
Changelog:
v2: Fix code comments typo, remove a redundant bch_writeback_add() line
added in v4 patch set.
v1: indeed this is new added in this patch set.
[mlyle: truncated commit subject]
Signed-off-by: Coly Li <colyli@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Cc: Junhui Tang <tang.junhui@zte.com.cn>
Cc: Michael Lyle <mlyle@lyle.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In current code closure debug file is outside of debug directory
and when unloading module there is lack of removing operation
for closure debug file, so it will cause creating error when trying
to reload module.
This patch move closure debug file into "bcache" debug direcory
so that the file can get deleted properly.
Signed-off-by: Chengguang Xu <cgxu519@gmx.com>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Reviewed-by: Tang Junhui <tang.junhui@zte.com.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In bch_mca_scan(), There are some confusion and logical error in the use of
loop variables. In this patch, we clarify them as:
1) nr: the number of btree nodes needs to scan, which will decrease after
we scan a btree node, and should not be less than 0;
2) i: the number of btree nodes have scanned, includes both
btree_cache_freeable and btree_cache, which should not be bigger than
btree_cache_used;
3) freed: the number of btree nodes have freed.
Signed-off-by: Tang Junhui <tang.junhui@zte.com.cn>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In bch_mca_scan(), the return value should not be the number of freed btree
nodes, but the number of pages of freed btree nodes.
Signed-off-by: Tang Junhui <tang.junhui@zte.com.cn>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Stripe size is shown as zero when no strip in back end device:
[root@ceph132 ~]# cat /sys/block/sdd/bcache/stripe_size
0.0k
Actually it should be 1T Bytes (1 << 31 sectors), but in sysfs
interface, stripe_size was changed from sectors to bytes, and move
9 bits left, so the 32 bits variable overflows.
This patch change the variable to a 64 bits type before moving bits.
Signed-off-by: Tang Junhui <tang.junhui@zte.com.cn>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
When we run IO in a detached device, and run iostat to shows IO status,
normally it will show like bellow (Omitted some fields):
Device: ... avgrq-sz avgqu-sz await r_await w_await svctm %util
sdd ... 15.89 0.53 1.82 0.20 2.23 1.81 52.30
bcache0 ... 15.89 115.42 0.00 0.00 0.00 2.40 69.60
but after IO stopped, there are still very big avgqu-sz and %util
values as bellow:
Device: ... avgrq-sz avgqu-sz await r_await w_await svctm %util
bcache0 ... 0 5326.32 0.00 0.00 0.00 0.00 100.10
The reason for this issue is that, only generic_start_io_acct() called
and no generic_end_io_acct() called for detached device in
cached_dev_make_request(). See the code:
//start generic_start_io_acct()
generic_start_io_acct(q, rw, bio_sectors(bio), &d->disk->part0);
if (cached_dev_get(dc)) {
//will callback generic_end_io_acct()
}
else {
//will not call generic_end_io_acct()
}
This patch calls generic_end_io_acct() in the end of IO for detached
devices, so we can show IO state correctly.
(Modified to use GFP_NOIO in kzalloc() by Coly Li)
Changelog:
v2: fix typo.
v1: the initial version.
Signed-off-by: Tang Junhui <tang.junhui@zte.com.cn>
Reviewed-by: Coly Li <colyli@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
When there are too many I/O errors on cache device, current bcache code
will retire the whole cache set, and detach all bcache devices. But the
detached bcache devices are not stopped, which is problematic when bcache
is in writeback mode.
If the retired cache set has dirty data of backing devices, continue
writing to bcache device will write to backing device directly. If the
LBA of write request has a dirty version cached on cache device, next time
when the cache device is re-registered and backing device re-attached to
it again, the stale dirty data on cache device will be written to backing
device, and overwrite latest directly written data. This situation causes
a quite data corruption.
But we cannot simply stop all attached bcache devices when the cache set is
broken or disconnected. For example, use bcache to accelerate performance
of an email service. In such workload, if cache device is broken but no
dirty data lost, keep the bcache device alive and permit email service
continue to access user data might be a better solution for the cache
device failure.
Nix <nix@esperi.org.uk> points out the issue and provides the above example
to explain why it might be necessary to not stop bcache device for broken
cache device. Pavel Goran <via-bcache@pvgoran.name> provides a brilliant
suggestion to provide "always" and "auto" options to per-cached device
sysfs file stop_when_cache_set_failed. If cache set is retiring and the
backing device has no dirty data on cache, it should be safe to keep the
bcache device alive. In this case, if stop_when_cache_set_failed is set to
"auto", the device failure handling code will not stop this bcache device
and permit application to access the backing device with a unattached
bcache device.
Changelog:
[mlyle: edited to not break string constants across lines]
v3: fix typos pointed out by Nix.
v2: change option values of stop_when_cache_set_failed from 1/0 to
"auto"/"always".
v1: initial version, stop_when_cache_set_failed can be 0 (not stop) or 1
(always stop).
Signed-off-by: Coly Li <colyli@suse.de>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Signed-off-by: Michael Lyle <mlyle@lyle.org>
Cc: Nix <nix@esperi.org.uk>
Cc: Pavel Goran <via-bcache@pvgoran.name>
Cc: Junhui Tang <tang.junhui@zte.com.cn>
Cc: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
When too many I/Os failed on cache device, bch_cache_set_error() is called
in the error handling code path to retire whole problematic cache set. If
new I/O requests continue to come and take refcount dc->count, the cache
set won't be retired immediately, this is a problem.
Further more, there are several kernel thread and self-armed kernel work
may still running after bch_cache_set_error() is called. It needs to wait
quite a while for them to stop, or they won't stop at all. They also
prevent the cache set from being retired.
The solution in this patch is, to add per cache set flag to disable I/O
request on this cache and all attached backing devices. Then new coming I/O
requests can be rejected in *_make_request() before taking refcount, kernel
threads and self-armed kernel worker can stop very fast when flags bit
CACHE_SET_IO_DISABLE is set.
Because bcache also do internal I/Os for writeback, garbage collection,
bucket allocation, journaling, this kind of I/O should be disabled after
bch_cache_set_error() is called. So closure_bio_submit() is modified to
check whether CACHE_SET_IO_DISABLE is set on cache_set->flags. If set,
closure_bio_submit() will set bio->bi_status to BLK_STS_IOERR and
return, generic_make_request() won't be called.
A sysfs interface is also added to set or clear CACHE_SET_IO_DISABLE bit
from cache_set->flags, to disable or enable cache set I/O for debugging. It
is helpful to trigger more corner case issues for failed cache device.
Changelog
v4, add wait_for_kthread_stop(), and call it before exits writeback and gc
kernel threads.
v3, change CACHE_SET_IO_DISABLE from 4 to 3, since it is bit index.
remove "bcache: " prefix when printing out kernel message.
v2, more changes by previous review,
- Use CACHE_SET_IO_DISABLE of cache_set->flags, suggested by Junhui.
- Check CACHE_SET_IO_DISABLE in bch_btree_gc() to stop a while-loop, this
is reported and inspired from origal patch of Pavel Vazharov.
v1, initial version.
Signed-off-by: Coly Li <colyli@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Cc: Junhui Tang <tang.junhui@zte.com.cn>
Cc: Michael Lyle <mlyle@lyle.org>
Cc: Pavel Vazharov <freakpv@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
struct delayed_work writeback_rate_update in struct cache_dev is a delayed
worker to call function update_writeback_rate() in period (the interval is
defined by dc->writeback_rate_update_seconds).
When a metadate I/O error happens on cache device, bcache error handling
routine bch_cache_set_error() will call bch_cache_set_unregister() to
retire whole cache set. On the unregister code path, this delayed work is
stopped by calling cancel_delayed_work_sync(&dc->writeback_rate_update).
dc->writeback_rate_update is a special delayed work from others in bcache.
In its routine update_writeback_rate(), this delayed work is re-armed
itself. That means when cancel_delayed_work_sync() returns, this delayed
work can still be executed after several seconds defined by
dc->writeback_rate_update_seconds.
The problem is, after cancel_delayed_work_sync() returns, the cache set
unregister code path will continue and release memory of struct cache set.
Then the delayed work is scheduled to run, __update_writeback_rate()
will reference the already released cache_set memory, and trigger a NULL
pointer deference fault.
This patch introduces two more bcache device flags,
- BCACHE_DEV_WB_RUNNING
bit set: bcache device is in writeback mode and running, it is OK for
dc->writeback_rate_update to re-arm itself.
bit clear:bcache device is trying to stop dc->writeback_rate_update,
this delayed work should not re-arm itself and quit.
- BCACHE_DEV_RATE_DW_RUNNING
bit set: routine update_writeback_rate() is executing.
bit clear: routine update_writeback_rate() quits.
This patch also adds a function cancel_writeback_rate_update_dwork() to
wait for dc->writeback_rate_update quits before cancel it by calling
cancel_delayed_work_sync(). In order to avoid a deadlock by unexpected
quit dc->writeback_rate_update, after time_out seconds this function will
give up and continue to call cancel_delayed_work_sync().
And here I explain how this patch stops self re-armed delayed work properly
with the above stuffs.
update_writeback_rate() sets BCACHE_DEV_RATE_DW_RUNNING at its beginning
and clears BCACHE_DEV_RATE_DW_RUNNING at its end. Before calling
cancel_writeback_rate_update_dwork() clear flag BCACHE_DEV_WB_RUNNING.
Before calling cancel_delayed_work_sync() wait utill flag
BCACHE_DEV_RATE_DW_RUNNING is clear. So when calling
cancel_delayed_work_sync(), dc->writeback_rate_update must be already re-
armed, or quite by seeing BCACHE_DEV_WB_RUNNING cleared. In both cases
delayed work routine update_writeback_rate() won't be executed after
cancel_delayed_work_sync() returns.
Inside update_writeback_rate() before calling schedule_delayed_work(), flag
BCACHE_DEV_WB_RUNNING is checked before. If this flag is cleared, it means
someone is about to stop the delayed work. Because flag
BCACHE_DEV_RATE_DW_RUNNING is set already and cancel_delayed_work_sync()
has to wait for this flag to be cleared, we don't need to worry about race
condition here.
If update_writeback_rate() is scheduled to run after checking
BCACHE_DEV_RATE_DW_RUNNING and before calling cancel_delayed_work_sync()
in cancel_writeback_rate_update_dwork(), it is also safe. Because at this
moment BCACHE_DEV_WB_RUNNING is cleared with memory barrier. As I mentioned
previously, update_writeback_rate() will see BCACHE_DEV_WB_RUNNING is clear
and quit immediately.
Because there are more dependences inside update_writeback_rate() to struct
cache_set memory, dc->writeback_rate_update is not a simple self re-arm
delayed work. After trying many different methods (e.g. hold dc->count, or
use locks), this is the only way I can find which works to properly stop
dc->writeback_rate_update delayed work.
Changelog:
v3: change values of BCACHE_DEV_WB_RUNNING and BCACHE_DEV_RATE_DW_RUNNING
to bit index, for test_bit().
v2: Try to fix the race issue which is pointed out by Junhui.
v1: The initial version for review
Signed-off-by: Coly Li <colyli@suse.de>
Reviewed-by: Junhui Tang <tang.junhui@zte.com.cn>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Cc: Michael Lyle <mlyle@lyle.org>
Cc: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In patch "bcache: fix cached_dev->count usage for bch_cache_set_error()",
cached_dev_get() is called when creating dc->writeback_thread, and
cached_dev_put() is called when exiting dc->writeback_thread. This
modification works well unless people detach the bcache device manually by
'echo 1 > /sys/block/bcache<N>/bcache/detach'
Because this sysfs interface only calls bch_cached_dev_detach() which wakes
up dc->writeback_thread but does not stop it. The reason is, before patch
"bcache: fix cached_dev->count usage for bch_cache_set_error()", inside
bch_writeback_thread(), if cache is not dirty after writeback,
cached_dev_put() will be called here. And in cached_dev_make_request() when
a new write request makes cache from clean to dirty, cached_dev_get() will
be called there. Since we don't operate dc->count in these locations,
refcount d->count cannot be dropped after cache becomes clean, and
cached_dev_detach_finish() won't be called to detach bcache device.
This patch fixes the issue by checking whether BCACHE_DEV_DETACHING is
set inside bch_writeback_thread(). If this bit is set and cache is clean
(no existing writeback_keys), break the while-loop, call cached_dev_put()
and quit the writeback thread.
Please note if cache is still dirty, even BCACHE_DEV_DETACHING is set the
writeback thread should continue to perform writeback, this is the original
design of manually detach.
It is safe to do the following check without locking, let me explain why,
+ if (!test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags) &&
+ (!atomic_read(&dc->has_dirty) || !dc->writeback_running)) {
If the kenrel thread does not sleep and continue to run due to conditions
are not updated in time on the running CPU core, it just consumes more CPU
cycles and has no hurt. This should-sleep-but-run is safe here. We just
focus on the should-run-but-sleep condition, which means the writeback
thread goes to sleep in mistake while it should continue to run.
1, First of all, no matter the writeback thread is hung or not,
kthread_stop() from cached_dev_detach_finish() will wake up it and
terminate by making kthread_should_stop() return true. And in normal
run time, bit on index BCACHE_DEV_DETACHING is always cleared, the
condition
!test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags)
is always true and can be ignored as constant value.
2, If one of the following conditions is true, the writeback thread should
go to sleep,
"!atomic_read(&dc->has_dirty)" or "!dc->writeback_running)"
each of them independently controls the writeback thread should sleep or
not, let's analyse them one by one.
2.1 condition "!atomic_read(&dc->has_dirty)"
If dc->has_dirty is set from 0 to 1 on another CPU core, bcache will
call bch_writeback_queue() immediately or call bch_writeback_add() which
indirectly calls bch_writeback_queue() too. In bch_writeback_queue(),
wake_up_process(dc->writeback_thread) is called. It sets writeback
thread's task state to TASK_RUNNING and following an implicit memory
barrier, then tries to wake up the writeback thread.
In writeback thread, its task state is set to TASK_INTERRUPTIBLE before
doing the condition check. If other CPU core sets the TASK_RUNNING state
after writeback thread setting TASK_INTERRUPTIBLE, the writeback thread
will be scheduled to run very soon because its state is not
TASK_INTERRUPTIBLE. If other CPU core sets the TASK_RUNNING state before
writeback thread setting TASK_INTERRUPTIBLE, the implict memory barrier
of wake_up_process() will make sure modification of dc->has_dirty on
other CPU core is updated and observed on the CPU core of writeback
thread. Therefore the condition check will correctly be false, and
continue writeback code without sleeping.
2.2 condition "!dc->writeback_running)"
dc->writeback_running can be changed via sysfs file, every time it is
modified, a following bch_writeback_queue() is alwasy called. So the
change is always observed on the CPU core of writeback thread. If
dc->writeback_running is changed from 0 to 1 on other CPU core, this
condition check will observe the modification and allow writeback
thread to continue to run without sleeping.
Now we can see, even without a locking protection, multiple conditions
check is safe here, no deadlock or process hang up will happen.
I compose a separte patch because that patch "bcache: fix cached_dev->count
usage for bch_cache_set_error()" already gets a "Reviewed-by:" from Hannes
Reinecke. Also this fix is not trivial and good for a separate patch.
Signed-off-by: Coly Li <colyli@suse.de>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Huijun Tang <tang.junhui@zte.com.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
When bcache metadata I/O fails, bcache will call bch_cache_set_error()
to retire the whole cache set. The expected behavior to retire a cache
set is to unregister the cache set, and unregister all backing device
attached to this cache set, then remove sysfs entries of the cache set
and all attached backing devices, finally release memory of structs
cache_set, cache, cached_dev and bcache_device.
In my testing when journal I/O failure triggered by disconnected cache
device, sometimes the cache set cannot be retired, and its sysfs
entry /sys/fs/bcache/<uuid> still exits and the backing device also
references it. This is not expected behavior.
When metadata I/O failes, the call senquence to retire whole cache set is,
bch_cache_set_error()
bch_cache_set_unregister()
bch_cache_set_stop()
__cache_set_unregister() <- called as callback by calling
clousre_queue(&c->caching)
cache_set_flush() <- called as a callback when refcount
of cache_set->caching is 0
cache_set_free() <- called as a callback when refcount
of catch_set->cl is 0
bch_cache_set_release() <- called as a callback when refcount
of catch_set->kobj is 0
I find if kernel thread bch_writeback_thread() quits while-loop when
kthread_should_stop() is true and searched_full_index is false, clousre
callback cache_set_flush() set by continue_at() will never be called. The
result is, bcache fails to retire whole cache set.
cache_set_flush() will be called when refcount of closure c->caching is 0,
and in function bcache_device_detach() refcount of closure c->caching is
released to 0 by clousre_put(). In metadata error code path, function
bcache_device_detach() is called by cached_dev_detach_finish(). This is a
callback routine being called when cached_dev->count is 0. This refcount
is decreased by cached_dev_put().
The above dependence indicates, cache_set_flush() will be called when
refcount of cache_set->cl is 0, and refcount of cache_set->cl to be 0
when refcount of cache_dev->count is 0.
The reason why sometimes cache_dev->count is not 0 (when metadata I/O fails
and bch_cache_set_error() called) is, in bch_writeback_thread(), refcount
of cache_dev is not decreased properly.
In bch_writeback_thread(), cached_dev_put() is called only when
searched_full_index is true and cached_dev->writeback_keys is empty, a.k.a
there is no dirty data on cache. In most of run time it is correct, but
when bch_writeback_thread() quits the while-loop while cache is still
dirty, current code forget to call cached_dev_put() before this kernel
thread exits. This is why sometimes cache_set_flush() is not executed and
cache set fails to be retired.
The reason to call cached_dev_put() in bch_writeback_rate() is, when the
cache device changes from clean to dirty, cached_dev_get() is called, to
make sure during writeback operatiions both backing and cache devices
won't be released.
Adding following code in bch_writeback_thread() does not work,
static int bch_writeback_thread(void *arg)
}
+ if (atomic_read(&dc->has_dirty))
+ cached_dev_put()
+
return 0;
}
because writeback kernel thread can be waken up and start via sysfs entry:
echo 1 > /sys/block/bcache<N>/bcache/writeback_running
It is difficult to check whether backing device is dirty without race and
extra lock. So the above modification will introduce potential refcount
underflow in some conditions.
The correct fix is, to take cached dev refcount when creating the kernel
thread, and put it before the kernel thread exits. Then bcache does not
need to take a cached dev refcount when cache turns from clean to dirty,
or to put a cached dev refcount when cache turns from ditry to clean. The
writeback kernel thread is alwasy safe to reference data structure from
cache set, cache and cached device (because a refcount of cache device is
taken for it already), and no matter the kernel thread is stopped by I/O
errors or system reboot, cached_dev->count can always be used correctly.
The patch is simple, but understanding how it works is quite complicated.
Changelog:
v2: set dc->writeback_thread to NULL in this patch, as suggested by Hannes.
v1: initial version for review.
Signed-off-by: Coly Li <colyli@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Cc: Michael Lyle <mlyle@lyle.org>
Cc: Junhui Tang <tang.junhui@zte.com.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Use the blk_queue_flag_{set,clear}() functions instead of open-coding
these.
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This can happen e.g. during disk cloning.
This is an incomplete fix: it does not catch duplicate UUIDs earlier
when things are still unattached. It does not unregister the device.
Further changes to cope better with this are planned but conflict with
Coly's ongoing improvements to handling device errors. In the meantime,
one can manually stop the device after this has happened.
Attempts to attach a duplicate device result in:
[ 136.372404] loop: module loaded
[ 136.424461] bcache: register_bdev() registered backing device loop0
[ 136.424464] bcache: bch_cached_dev_attach() Tried to attach loop0 but duplicate UUID already attached
My test procedure is:
dd if=/dev/sdb1 of=imgfile bs=1024 count=262144
losetup -f imgfile
Signed-off-by: Michael Lyle <mlyle@lyle.org>
Reviewed-by: Tang Junhui <tang.junhui@zte.com.cn>
Cc: <stable@vger.kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Commit 2831231d4c ("bcache: reduce cache_set devices iteration by
devices_max_used") adds c->devices_max_used to reduce iteration of
c->uuids elements, this value is updated in bcache_device_attach().
But for flash only volume, when calling flash_devs_run(), the function
bcache_device_attach() is not called yet and c->devices_max_used is not
updated. The unexpected result is, the flash only volume won't be run
by flash_devs_run().
This patch fixes the issue by iterate all c->uuids elements in
flash_devs_run(). c->devices_max_used will be updated properly when
bcache_device_attach() gets called.
[mlyle: commit subject edited for character limit]
Fixes: 2831231d4c ("bcache: reduce cache_set devices iteration by devices_max_used")
Reported-by: Tang Junhui <tang.junhui@zte.com.cn>
Signed-off-by: Coly Li <colyli@suse.de>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
back-end device sdm has already attached a cache_set with ID
f67ebe1f-f8bc-4d73-bfe5-9dc88607f119, then try to attach with
another cache set, and it returns with an error:
[root]# cd /sys/block/sdm/bcache
[root]# echo 5ccd0a63-148e-48b8-afa2-aca9cbd6279f > attach
-bash: echo: write error: Invalid argument
After that, execute a command to modify the label of bcache
device:
[root]# echo data_disk1 > label
Then we reboot the system, when the system power on, the back-end
device can not attach to cache_set, a messages show in the log:
Feb 5 12:05:52 ceph152 kernel: [922385.508498] bcache:
bch_cached_dev_attach() couldn't find uuid for sdm in set
In sysfs_attach(), dc->sb.set_uuid was assigned to the value
which input through sysfs, no matter whether it is success
or not in bch_cached_dev_attach(). For example, If the back-end
device has already attached to an cache set, bch_cached_dev_attach()
would fail, but dc->sb.set_uuid was changed. Then modify the
label of bcache device, it will call bch_write_bdev_super(),
which would write the dc->sb.set_uuid to the super block, so we
record a wrong cache set ID in the super block, after the system
reboot, the cache set couldn't find the uuid of the back-end
device, so the bcache device couldn't exist and use any more.
In this patch, we don't assigned cache set ID to dc->sb.set_uuid
in sysfs_attach() directly, but input it into bch_cached_dev_attach(),
and assigned dc->sb.set_uuid to the cache set ID after the back-end
device attached to the cache set successful.
Signed-off-by: Tang Junhui <tang.junhui@zte.com.cn>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
I attach a back-end device to a cache set, and the cache set is not
registered yet, this back-end device did not attach successfully, and no
error returned:
[root]# echo 87859280-fec6-4bcc-20df7ca8f86b > /sys/block/sde/bcache/attach
[root]#
In sysfs_attach(), the return value "v" is initialized to "size" in
the beginning, and if no cache set exist in bch_cache_sets, the "v" value
would not change any more, and return to sysfs, sysfs regard it as success
since the "size" is a positive number.
This patch fixes this issue by assigning "v" with "-ENOENT" in the
initialization.
Signed-off-by: Tang Junhui <tang.junhui@zte.com.cn>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
dc->writeback_rate_update_seconds can be set via sysfs and its value can
be set to [1, ULONG_MAX]. It does not make sense to set such a large
value, 60 seconds is long enough value considering the default 5 seconds
works well for long time.
Because dc->writeback_rate_update is a special delayed work, it re-arms
itself inside the delayed work routine update_writeback_rate(). When
stopping it by cancel_delayed_work_sync(), there should be a timeout to
wait and make sure the re-armed delayed work is stopped too. A small max
value of dc->writeback_rate_update_seconds is also helpful to decide a
reasonable small timeout.
This patch limits sysfs interface to set dc->writeback_rate_update_seconds
in range of [1, 60] seconds, and replaces the hand-coded number by macros.
Changelog:
v2: fix a rebase typo in v4, which is pointed out by Michael Lyle.
v1: initial version.
Signed-off-by: Coly Li <colyli@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
After long time running of random small IO writing,
I reboot the machine, and after the machine power on,
I found bcache got stuck, the stack is:
[root@ceph153 ~]# cat /proc/2510/task/*/stack
[<ffffffffa06b2455>] closure_sync+0x25/0x90 [bcache]
[<ffffffffa06b6be8>] bch_journal+0x118/0x2b0 [bcache]
[<ffffffffa06b6dc7>] bch_journal_meta+0x47/0x70 [bcache]
[<ffffffffa06be8f7>] bch_prio_write+0x237/0x340 [bcache]
[<ffffffffa06a8018>] bch_allocator_thread+0x3c8/0x3d0 [bcache]
[<ffffffff810a631f>] kthread+0xcf/0xe0
[<ffffffff8164c318>] ret_from_fork+0x58/0x90
[<ffffffffffffffff>] 0xffffffffffffffff
[root@ceph153 ~]# cat /proc/2038/task/*/stack
[<ffffffffa06b1abd>] __bch_btree_map_nodes+0x12d/0x150 [bcache]
[<ffffffffa06b1bd1>] bch_btree_insert+0xf1/0x170 [bcache]
[<ffffffffa06b637f>] bch_journal_replay+0x13f/0x230 [bcache]
[<ffffffffa06c75fe>] run_cache_set+0x79a/0x7c2 [bcache]
[<ffffffffa06c0cf8>] register_bcache+0xd48/0x1310 [bcache]
[<ffffffff812f702f>] kobj_attr_store+0xf/0x20
[<ffffffff8125b216>] sysfs_write_file+0xc6/0x140
[<ffffffff811dfbfd>] vfs_write+0xbd/0x1e0
[<ffffffff811e069f>] SyS_write+0x7f/0xe0
[<ffffffff8164c3c9>] system_call_fastpath+0x16/0x1
The stack shows the register thread and allocator thread
were getting stuck when registering cache device.
I reboot the machine several times, the issue always
exsit in this machine.
I debug the code, and found the call trace as bellow:
register_bcache()
==>run_cache_set()
==>bch_journal_replay()
==>bch_btree_insert()
==>__bch_btree_map_nodes()
==>btree_insert_fn()
==>btree_split() //node need split
==>btree_check_reserve()
In btree_check_reserve(), It will check if there is enough buckets
of RESERVE_BTREE type, since allocator thread did not work yet, so
no buckets of RESERVE_BTREE type allocated, so the register thread
waits on c->btree_cache_wait, and goes to sleep.
Then the allocator thread initialized, the call trace is bellow:
bch_allocator_thread()
==>bch_prio_write()
==>bch_journal_meta()
==>bch_journal()
==>journal_wait_for_write()
In journal_wait_for_write(), It will check if journal is full by
journal_full(), but the long time random small IO writing
causes the exhaustion of journal buckets(journal.blocks_free=0),
In order to release the journal buckets,
the allocator calls btree_flush_write() to flush keys to
btree nodes, and waits on c->journal.wait until btree nodes writing
over or there has already some journal buckets space, then the
allocator thread goes to sleep. but in btree_flush_write(), since
bch_journal_replay() is not finished, so no btree nodes have journal
(condition "if (btree_current_write(b)->journal)" never satisfied),
so we got no btree node to flush, no journal bucket released,
and allocator sleep all the times.
Through the above analysis, we can see that:
1) Register thread wait for allocator thread to allocate buckets of
RESERVE_BTREE type;
2) Alloctor thread wait for register thread to replay journal, so it
can flush btree nodes and get journal bucket.
then they are all got stuck by waiting for each other.
Hua Rui provided a patch for me, by allocating some buckets of
RESERVE_BTREE type in advance, so the register thread can get bucket
when btree node splitting and no need to waiting for the allocator
thread. I tested it, it has effect, and register thread run a step
forward, but finally are still got stuck, the reason is only 8 bucket
of RESERVE_BTREE type were allocated, and in bch_journal_replay(),
after 2 btree nodes splitting, only 4 bucket of RESERVE_BTREE type left,
then btree_check_reserve() is not satisfied anymore, so it goes to sleep
again, and in the same time, alloctor thread did not flush enough btree
nodes to release a journal bucket, so they all got stuck again.
So we need to allocate more buckets of RESERVE_BTREE type in advance,
but how much is enough? By experience and test, I think it should be
as much as journal buckets. Then I modify the code as this patch,
and test in the machine, and it works.
This patch modified base on Hua Rui’s patch, and allocate more buckets
of RESERVE_BTREE type in advance to avoid register thread and allocate
thread going to wait for each other.
[patch v2] ca->sb.njournal_buckets would be 0 in the first time after
cache creation, and no journal exists, so just 8 btree buckets is OK.
Signed-off-by: Hua Rui <huarui.dev@gmail.com>
Signed-off-by: Tang Junhui <tang.junhui@zte.com.cn>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Struct cache uses io_errors for two purposes,
- Error decay: when cache set error_decay is set, io_errors is used to
generate a small piece of delay when I/O error happens.
- I/O errors counter: in order to generate big enough value for error
decay, I/O errors counter value is stored by left shifting 20 bits (a.k.a
IO_ERROR_SHIFT).
In function bch_count_io_errors(), if I/O errors counter reaches cache set
error limit, bch_cache_set_error() will be called to retire the whold cache
set. But current code is problematic when checking the error limit, see the
following code piece from bch_count_io_errors(),
90 if (error) {
91 char buf[BDEVNAME_SIZE];
92 unsigned errors = atomic_add_return(1 << IO_ERROR_SHIFT,
93 &ca->io_errors);
94 errors >>= IO_ERROR_SHIFT;
95
96 if (errors < ca->set->error_limit)
97 pr_err("%s: IO error on %s, recovering",
98 bdevname(ca->bdev, buf), m);
99 else
100 bch_cache_set_error(ca->set,
101 "%s: too many IO errors %s",
102 bdevname(ca->bdev, buf), m);
103 }
At line 94, errors is right shifting IO_ERROR_SHIFT bits, now it is real
errors counter to compare at line 96. But ca->set->error_limit is initia-
lized with an amplified value in bch_cache_set_alloc(),
1545 c->error_limit = 8 << IO_ERROR_SHIFT;
It means by default, in bch_count_io_errors(), before 8<<20 errors happened
bch_cache_set_error() won't be called to retire the problematic cache
device. If the average request size is 64KB, it means bcache won't handle
failed device until 512GB data is requested. This is too large to be an I/O
threashold. So I believe the correct error limit should be much less.
This patch sets default cache set error limit to 8, then in
bch_count_io_errors() when errors counter reaches 8 (if it is default
value), function bch_cache_set_error() will be called to retire the whole
cache set. This patch also removes bits shifting when store or show
io_error_limit value via sysfs interface.
Nowadays most of SSDs handle internal flash failure automatically by LBA
address re-indirect mapping. If an I/O error can be observed by upper layer
code, it will be a notable error because that SSD can not re-indirect
map the problematic LBA address to an available flash block. This situation
indicates the whole SSD will be failed very soon. Therefore setting 8 as
the default io error limit value makes sense, it is enough for most of
cache devices.
Changelog:
v2: add reviewed-by from Hannes.
v1: initial version for review.
Signed-off-by: Coly Li <colyli@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Tang Junhui <tang.junhui@zte.com.cn>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Cc: Junhui Tang <tang.junhui@zte.com.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Kernel thread routine bch_writeback_thread() has the following code block,
447 down_write(&dc->writeback_lock);
448~450 if (check conditions) {
451 up_write(&dc->writeback_lock);
452 set_current_state(TASK_INTERRUPTIBLE);
453
454 if (kthread_should_stop())
455 return 0;
456
457 schedule();
458 continue;
459 }
If condition check is true, its task state is set to TASK_INTERRUPTIBLE
and call schedule() to wait for others to wake up it.
There are 2 issues in current code,
1, Task state is set to TASK_INTERRUPTIBLE after the condition checks, if
another process changes the condition and call wake_up_process(dc->
writeback_thread), then at line 452 task state is set back to
TASK_INTERRUPTIBLE, the writeback kernel thread will lose a chance to be
waken up.
2, At line 454 if kthread_should_stop() is true, writeback kernel thread
will return to kernel/kthread.c:kthread() with TASK_INTERRUPTIBLE and
call do_exit(). It is not good to enter do_exit() with task state
TASK_INTERRUPTIBLE, in following code path might_sleep() is called and a
warning message is reported by __might_sleep(): "WARNING: do not call
blocking ops when !TASK_RUNNING; state=1 set at [xxxx]".
For the first issue, task state should be set before condition checks.
Ineed because dc->writeback_lock is required when modifying all the
conditions, calling set_current_state() inside code block where dc->
writeback_lock is hold is safe. But this is quite implicit, so I still move
set_current_state() before all the condition checks.
For the second issue, frankley speaking it does not hurt when kernel thread
exits with TASK_INTERRUPTIBLE state, but this warning message scares users,
makes them feel there might be something risky with bcache and hurt their
data. Setting task state to TASK_RUNNING before returning fixes this
problem.
In alloc.c:allocator_wait(), there is also a similar issue, and is also
fixed in this patch.
Changelog:
v3: merge two similar fixes into one patch
v2: fix the race issue in v1 patch.
v1: initial buggy fix.
Signed-off-by: Coly Li <colyli@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Cc: Michael Lyle <mlyle@lyle.org>
Cc: Junhui Tang <tang.junhui@zte.com.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
After long time small writing I/O running, we found the occupancy of CPU
is very high and I/O performance has been reduced by about half:
[root@ceph151 internal]# top
top - 15:51:05 up 1 day,2:43, 4 users, load average: 16.89, 15.15, 16.53
Tasks: 2063 total, 4 running, 2059 sleeping, 0 stopped, 0 zombie
%Cpu(s):4.3 us, 17.1 sy 0.0 ni, 66.1 id, 12.0 wa, 0.0 hi, 0.5 si, 0.0 st
KiB Mem : 65450044 total, 24586420 free, 38909008 used, 1954616 buff/cache
KiB Swap: 65667068 total, 65667068 free, 0 used. 25136812 avail Mem
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
2023 root 20 0 0 0 0 S 55.1 0.0 0:04.42 kworker/11:191
14126 root 20 0 0 0 0 S 42.9 0.0 0:08.72 kworker/10:3
9292 root 20 0 0 0 0 S 30.4 0.0 1:10.99 kworker/6:1
8553 ceph 20 0 4242492 1.805g 18804 S 30.0 2.9 410:07.04 ceph-osd
12287 root 20 0 0 0 0 S 26.7 0.0 0:28.13 kworker/7:85
31019 root 20 0 0 0 0 S 26.1 0.0 1:30.79 kworker/22:1
1787 root 20 0 0 0 0 R 25.7 0.0 5:18.45 kworker/8:7
32169 root 20 0 0 0 0 S 14.5 0.0 1:01.92 kworker/23:1
21476 root 20 0 0 0 0 S 13.9 0.0 0:05.09 kworker/1:54
2204 root 20 0 0 0 0 S 12.5 0.0 1:25.17 kworker/9:10
16994 root 20 0 0 0 0 S 12.2 0.0 0:06.27 kworker/5:106
15714 root 20 0 0 0 0 R 10.9 0.0 0:01.85 kworker/19:2
9661 ceph 20 0 4246876 1.731g 18800 S 10.6 2.8 403:00.80 ceph-osd
11460 ceph 20 0 4164692 2.206g 18876 S 10.6 3.5 360:27.19 ceph-osd
9960 root 20 0 0 0 0 S 10.2 0.0 0:02.75 kworker/2:139
11699 ceph 20 0 4169244 1.920g 18920 S 10.2 3.1 355:23.67 ceph-osd
6843 ceph 20 0 4197632 1.810g 18900 S 9.6 2.9 380:08.30 ceph-osd
The kernel work consumed a lot of CPU, and I found they are running journal
work, The journal is reclaiming source and flush btree node with surprising
frequency.
Through further analysis, we found that in btree_flush_write(), we try to
get a btree node with the smallest fifo idex to flush by traverse all the
btree nodein c->bucket_hash, after we getting it, since no locker protects
it, this btree node may have been written to cache device by other works,
and if this occurred, we retry to traverse in c->bucket_hash and get
another btree node. When the problem occurrd, the retry times is very high,
and we consume a lot of CPU in looking for a appropriate btree node.
In this patch, we try to record 128 btree nodes with the smallest fifo idex
in heap, and pop one by one when we need to flush btree node. It greatly
reduces the time for the loop to find the appropriate BTREE node, and also
reduce the occupancy of CPU.
[note by mpl: this triggers a checkpatch error because of adjacent,
pre-existing style violations]
Signed-off-by: Tang Junhui <tang.junhui@zte.com.cn>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Sometimes, Journal takes up a lot of CPU, we need statistics
to know what's the journal is doing. So this patch provide
some journal statistics:
1) reclaim: how many times the journal try to reclaim resource,
usually the journal bucket or/and the pin are exhausted.
2) flush_write: how many times the journal try to flush btree node
to cache device, usually the journal bucket are exhausted.
3) retry_flush_write: how many times the journal retry to flush
the next btree node, usually the previous tree node have been
flushed by other thread.
we show these statistic by sysfs interface. Through these statistics
We can totally see the status of journal module when the CPU is too
high.
Signed-off-by: Tang Junhui <tang.junhui@zte.com.cn>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Otherwise, architectures that do negated adds of atomics (e.g. s390)
to do atomic_sub fail in closure_set_stopped.
Signed-off-by: Michael Lyle <mlyle@lyle.org>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Bcache needs to scale the dirty data in the cache over the multiple
backing disks in order to calculate writeback rates for each.
The previous code did this by multiplying the target number of dirty
sectors by the backing device size, and expected it to fit into a
uint64_t; this blows up on relatively small backing devices.
The new approach figures out the bdev's share in 16384ths of the overall
cached data. This is chosen to cope well when bdevs drastically vary in
size and to ensure that bcache can cross the petabyte boundary for each
backing device.
This has been improved based on Tang Junhui's feedback to ensure that
every device gets a share of dirty data, no matter how small it is
compared to the total backing pool.
The existing mechanism is very limited; this is purely a bug fix to
remove limits on volume size. However, there still needs to be change
to make this "fair" over many volumes where some are idle.
Reported-by: Jack Douglas <jack@douglastechnology.co.uk>
Signed-off-by: Michael Lyle <mlyle@lyle.org>
Reviewed-by: Tang Junhui <tang.junhui@zte.com.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Bcache only does recoverable I/O for read operations by calling
cached_dev_read_error(). For write opertions there is no I/O recovery for
failed requests.
But in bch_count_io_errors() no matter read or write I/Os, before errors
counter reaches io error limit, pr_err() always prints "IO error on %,
recoverying". For write requests this information is misleading, because
there is no I/O recovery at all.
This patch adds a parameter 'is_read' to bch_count_io_errors(), and only
prints "recovering" by pr_err() when the bio direction is READ.
Signed-off-by: Coly Li <colyli@suse.de>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Reviewed-by: Tang Junhui <tang.junhui@zte.com.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Member devices of struct cache_set is used to reference all attached
bcache devices to this cache set. If it is treated as array of pointers,
size of devices[] is indicated by member nr_uuids of struct cache_set.
nr_uuids is calculated in drivers/md/super.c:bch_cache_set_alloc(),
bucket_bytes(c) / sizeof(struct uuid_entry)
Bucket size is determined by user space tool "make-bcache", by default it
is 1024 sectors (defined in bcache-tools/make-bcache.c:main()). So default
nr_uuids value is 4096 from the above calculation.
Every time when bcache code iterates bcache devices of a cache set, all
the 4096 pointers are checked even only 1 bcache device is attached to the
cache set, that's a wast of time and unncessary.
This patch adds a member devices_max_used to struct cache_set. Its value
is 1 + the maximum used index of devices[] in a cache set. When iterating
all valid bcache devices of a cache set, use c->devices_max_used in
for-loop may reduce a lot of useless checking.
Personally, my motivation of this patch is not for performance, I use it
in bcache debugging, which helps me to narrow down the scape to check
valid bcached devices of a cache set.
Signed-off-by: Coly Li <colyli@suse.de>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Reviewed-by: Tang Junhui <tang.junhui@zte.com.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The function cached_dev_make_request() and flash_dev_make_request() call
generic_start_io_acct() with (struct bcache_device)->disk when they start a
closure. Then the function bio_complete() calls generic_end_io_acct() with
(struct search)->orig_bio->bi_disk when the closure has done.
Since the `bi_disk` is not the bcache device, the generic_end_io_acct() is
called with a wrong device queue.
It causes the "inflight" (in struct hd_struct) counter keep increasing
without decreasing.
This patch fix the problem by calling generic_end_io_acct() with
(struct bcache_device)->disk.
Signed-off-by: Zhai Zhaoxuan <kxuanobj@gmail.com>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Reviewed-by: Coly Li <colyli@suse.de>
Reviewed-by: Tang Junhui <tang.junhui@zte.com.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
[edit by mlyle: include sched/debug.h to get __sched]
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Michael Lyle <mlyle@lyle.org>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Eliminates cases where sync can race and fail to complete / get stuck.
Removes many status flags and simplifies entering-and-exiting closure
sleeping behaviors.
[mlyle: fixed conflicts due to changed return behavior in mainline.
extended commit comment, and squashed down two commits that were mostly
contradictory to get to this state. Changed __set_current_state to
set_current_state per Jens review comment]
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Michael Lyle <mlyle@lyle.org>
Reviewed-by: Michael Lyle <mlyle@lyle.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If the control system would wait for at least half a second, and there's
been no reqs hitting the backing disk for awhile: use an alternate mode
where we have at most one contiguous set of writebacks in flight at a
time. (But don't otherwise delay). If front-end IO appears, it will
still be quick, as it will only have to contend with one real operation
in flight. But otherwise, we'll be sending data to the backing disk as
quickly as it can accept it (with one op at a time).
Signed-off-by: Michael Lyle <mlyle@lyle.org>
Reviewed-by: Tang Junhui <tang.junhui@zte.com.cn>
Acked-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Writeback keys are presently iterated and dispatched for writeback in
order of the logical block address on the backing device. Multiple may
be, in parallel, read from the cache device and then written back
(especially when there are contiguous I/O).
However-- there was no guarantee with the existing code that the writes
would be issued in LBA order, as the reads from the cache device are
often re-ordered. In turn, when writing back quickly, the backing disk
often has to seek backwards-- this slows writeback and increases
utilization.
This patch introduces an ordering mechanism that guarantees that the
original order of issue is maintained for the write portion of the I/O.
Performance for writeback is significantly improved when there are
multiple contiguous keys or high writeback rates.
Signed-off-by: Michael Lyle <mlyle@lyle.org>
Reviewed-by: Tang Junhui <tang.junhui@zte.com.cn>
Tested-by: Tang Junhui <tang.junhui@zte.com.cn>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
