About Kernel Documentation Linux Kernel Contact Linux Resources Linux Blog

Documentation / bcache.txt

Custom Search

Based on kernel version 4.13.3. Page generated on 2017-09-23 13:54 EST.

1	============================
2	A block layer cache (bcache)
3	============================
5	Say you've got a big slow raid 6, and an ssd or three. Wouldn't it be
6	nice if you could use them as cache... Hence bcache.
8	Wiki and git repositories are at:
10	  - http://bcache.evilpiepirate.org
11	  - http://evilpiepirate.org/git/linux-bcache.git
12	  - http://evilpiepirate.org/git/bcache-tools.git
14	It's designed around the performance characteristics of SSDs - it only allocates
15	in erase block sized buckets, and it uses a hybrid btree/log to track cached
16	extents (which can be anywhere from a single sector to the bucket size). It's
17	designed to avoid random writes at all costs; it fills up an erase block
18	sequentially, then issues a discard before reusing it.
20	Both writethrough and writeback caching are supported. Writeback defaults to
21	off, but can be switched on and off arbitrarily at runtime. Bcache goes to
22	great lengths to protect your data - it reliably handles unclean shutdown. (It
23	doesn't even have a notion of a clean shutdown; bcache simply doesn't return
24	writes as completed until they're on stable storage).
26	Writeback caching can use most of the cache for buffering writes - writing
27	dirty data to the backing device is always done sequentially, scanning from the
28	start to the end of the index.
30	Since random IO is what SSDs excel at, there generally won't be much benefit
31	to caching large sequential IO. Bcache detects sequential IO and skips it;
32	it also keeps a rolling average of the IO sizes per task, and as long as the
33	average is above the cutoff it will skip all IO from that task - instead of
34	caching the first 512k after every seek. Backups and large file copies should
35	thus entirely bypass the cache.
37	In the event of a data IO error on the flash it will try to recover by reading
38	from disk or invalidating cache entries.  For unrecoverable errors (meta data
39	or dirty data), caching is automatically disabled; if dirty data was present
40	in the cache it first disables writeback caching and waits for all dirty data
41	to be flushed.
43	Getting started:
44	You'll need make-bcache from the bcache-tools repository. Both the cache device
45	and backing device must be formatted before use::
47	  make-bcache -B /dev/sdb
48	  make-bcache -C /dev/sdc
50	make-bcache has the ability to format multiple devices at the same time - if
51	you format your backing devices and cache device at the same time, you won't
52	have to manually attach::
54	  make-bcache -B /dev/sda /dev/sdb -C /dev/sdc
56	bcache-tools now ships udev rules, and bcache devices are known to the kernel
57	immediately.  Without udev, you can manually register devices like this::
59	  echo /dev/sdb > /sys/fs/bcache/register
60	  echo /dev/sdc > /sys/fs/bcache/register
62	Registering the backing device makes the bcache device show up in /dev; you can
63	now format it and use it as normal. But the first time using a new bcache
64	device, it'll be running in passthrough mode until you attach it to a cache.
65	If you are thinking about using bcache later, it is recommended to setup all your
66	slow devices as bcache backing devices without a cache, and you can choose to add
67	a caching device later.
68	See 'ATTACHING' section below.
70	The devices show up as::
72	  /dev/bcache<N>
74	As well as (with udev)::
76	  /dev/bcache/by-uuid/<uuid>
77	  /dev/bcache/by-label/<label>
79	To get started::
81	  mkfs.ext4 /dev/bcache0
82	  mount /dev/bcache0 /mnt
84	You can control bcache devices through sysfs at /sys/block/bcache<N>/bcache .
85	You can also control them through /sys/fs//bcache/<cset-uuid>/ .
87	Cache devices are managed as sets; multiple caches per set isn't supported yet
88	but will allow for mirroring of metadata and dirty data in the future. Your new
89	cache set shows up as /sys/fs/bcache/<UUID>
91	Attaching
92	---------
94	After your cache device and backing device are registered, the backing device
95	must be attached to your cache set to enable caching. Attaching a backing
96	device to a cache set is done thusly, with the UUID of the cache set in
97	/sys/fs/bcache::
99	  echo <CSET-UUID> > /sys/block/bcache0/bcache/attach
101	This only has to be done once. The next time you reboot, just reregister all
102	your bcache devices. If a backing device has data in a cache somewhere, the
103	/dev/bcache<N> device won't be created until the cache shows up - particularly
104	important if you have writeback caching turned on.
106	If you're booting up and your cache device is gone and never coming back, you
107	can force run the backing device::
109	  echo 1 > /sys/block/sdb/bcache/running
111	(You need to use /sys/block/sdb (or whatever your backing device is called), not
112	/sys/block/bcache0, because bcache0 doesn't exist yet. If you're using a
113	partition, the bcache directory would be at /sys/block/sdb/sdb2/bcache)
115	The backing device will still use that cache set if it shows up in the future,
116	but all the cached data will be invalidated. If there was dirty data in the
117	cache, don't expect the filesystem to be recoverable - you will have massive
118	filesystem corruption, though ext4's fsck does work miracles.
120	Error Handling
121	--------------
123	Bcache tries to transparently handle IO errors to/from the cache device without
124	affecting normal operation; if it sees too many errors (the threshold is
125	configurable, and defaults to 0) it shuts down the cache device and switches all
126	the backing devices to passthrough mode.
128	 - For reads from the cache, if they error we just retry the read from the
129	   backing device.
131	 - For writethrough writes, if the write to the cache errors we just switch to
132	   invalidating the data at that lba in the cache (i.e. the same thing we do for
133	   a write that bypasses the cache)
135	 - For writeback writes, we currently pass that error back up to the
136	   filesystem/userspace. This could be improved - we could retry it as a write
137	   that skips the cache so we don't have to error the write.
139	 - When we detach, we first try to flush any dirty data (if we were running in
140	   writeback mode). It currently doesn't do anything intelligent if it fails to
141	   read some of the dirty data, though.
144	Howto/cookbook
145	--------------
147	A) Starting a bcache with a missing caching device
149	If registering the backing device doesn't help, it's already there, you just need
150	to force it to run without the cache::
152		host:~# echo /dev/sdb1 > /sys/fs/bcache/register
153		[  119.844831] bcache: register_bcache() error opening /dev/sdb1: device already registered
155	Next, you try to register your caching device if it's present. However
156	if it's absent, or registration fails for some reason, you can still
157	start your bcache without its cache, like so::
159		host:/sys/block/sdb/sdb1/bcache# echo 1 > running
161	Note that this may cause data loss if you were running in writeback mode.
164	B) Bcache does not find its cache::
166		host:/sys/block/md5/bcache# echo 0226553a-37cf-41d5-b3ce-8b1e944543a8 > attach
167		[ 1933.455082] bcache: bch_cached_dev_attach() Couldn't find uuid for md5 in set
168		[ 1933.478179] bcache: __cached_dev_store() Can't attach 0226553a-37cf-41d5-b3ce-8b1e944543a8
169		[ 1933.478179] : cache set not found
171	In this case, the caching device was simply not registered at boot
172	or disappeared and came back, and needs to be (re-)registered::
174		host:/sys/block/md5/bcache# echo /dev/sdh2 > /sys/fs/bcache/register
177	C) Corrupt bcache crashes the kernel at device registration time:
179	This should never happen.  If it does happen, then you have found a bug!
180	Please report it to the bcache development list: linux-bcache@vger.kernel.org
182	Be sure to provide as much information that you can including kernel dmesg
183	output if available so that we may assist.
186	D) Recovering data without bcache:
188	If bcache is not available in the kernel, a filesystem on the backing
189	device is still available at an 8KiB offset. So either via a loopdev
190	of the backing device created with --offset 8K, or any value defined by
191	--data-offset when you originally formatted bcache with `make-bcache`.
193	For example::
195		losetup -o 8192 /dev/loop0 /dev/your_bcache_backing_dev
197	This should present your unmodified backing device data in /dev/loop0
199	If your cache is in writethrough mode, then you can safely discard the
200	cache device without loosing data.
203	E) Wiping a cache device
205	::
207		host:~# wipefs -a /dev/sdh2
208		16 bytes were erased at offset 0x1018 (bcache)
209		they were: c6 85 73 f6 4e 1a 45 ca 82 65 f5 7f 48 ba 6d 81
211	After you boot back with bcache enabled, you recreate the cache and attach it::
213		host:~# make-bcache -C /dev/sdh2
214		UUID:                   7be7e175-8f4c-4f99-94b2-9c904d227045
215		Set UUID:               5bc072a8-ab17-446d-9744-e247949913c1
216		version:                0
217		nbuckets:               106874
218		block_size:             1
219		bucket_size:            1024
220		nr_in_set:              1
221		nr_this_dev:            0
222		first_bucket:           1
223		[  650.511912] bcache: run_cache_set() invalidating existing data
224		[  650.549228] bcache: register_cache() registered cache device sdh2
226	start backing device with missing cache::
228		host:/sys/block/md5/bcache# echo 1 > running
230	attach new cache::
232		host:/sys/block/md5/bcache# echo 5bc072a8-ab17-446d-9744-e247949913c1 > attach
233		[  865.276616] bcache: bch_cached_dev_attach() Caching md5 as bcache0 on set 5bc072a8-ab17-446d-9744-e247949913c1
236	F) Remove or replace a caching device::
238		host:/sys/block/sda/sda7/bcache# echo 1 > detach
239		[  695.872542] bcache: cached_dev_detach_finish() Caching disabled for sda7
241		host:~# wipefs -a /dev/nvme0n1p4
242		wipefs: error: /dev/nvme0n1p4: probing initialization failed: Device or resource busy
243		Ooops, it's disabled, but not unregistered, so it's still protected
245	We need to go and unregister it::
247		host:/sys/fs/bcache/b7ba27a1-2398-4649-8ae3-0959f57ba128# ls -l cache0
248		lrwxrwxrwx 1 root root 0 Feb 25 18:33 cache0 -> ../../../devices/pci0000:00/0000:00:1d.0/0000:70:00.0/nvme/nvme0/nvme0n1/nvme0n1p4/bcache/
249		host:/sys/fs/bcache/b7ba27a1-2398-4649-8ae3-0959f57ba128# echo 1 > stop
250		kernel: [  917.041908] bcache: cache_set_free() Cache set b7ba27a1-2398-4649-8ae3-0959f57ba128 unregistered
252	Now we can wipe it::
254		host:~# wipefs -a /dev/nvme0n1p4
255		/dev/nvme0n1p4: 16 bytes were erased at offset 0x00001018 (bcache): c6 85 73 f6 4e 1a 45 ca 82 65 f5 7f 48 ba 6d 81
258	G) dm-crypt and bcache
260	First setup bcache unencrypted and then install dmcrypt on top of
261	/dev/bcache<N> This will work faster than if you dmcrypt both the backing
262	and caching devices and then install bcache on top. [benchmarks?]
265	H) Stop/free a registered bcache to wipe and/or recreate it
267	Suppose that you need to free up all bcache references so that you can
268	fdisk run and re-register a changed partition table, which won't work
269	if there are any active backing or caching devices left on it:
271	1) Is it present in /dev/bcache* ? (there are times where it won't be)
273	   If so, it's easy::
275		host:/sys/block/bcache0/bcache# echo 1 > stop
277	2) But if your backing device is gone, this won't work::
279		host:/sys/block/bcache0# cd bcache
280		bash: cd: bcache: No such file or directory
282	   In this case, you may have to unregister the dmcrypt block device that
283	   references this bcache to free it up::
285		host:~# dmsetup remove oldds1
286		bcache: bcache_device_free() bcache0 stopped
287		bcache: cache_set_free() Cache set 5bc072a8-ab17-446d-9744-e247949913c1 unregistered
289	   This causes the backing bcache to be removed from /sys/fs/bcache and
290	   then it can be reused.  This would be true of any block device stacking
291	   where bcache is a lower device.
293	3) In other cases, you can also look in /sys/fs/bcache/::
295		host:/sys/fs/bcache# ls -l */{cache?,bdev?}
296		lrwxrwxrwx 1 root root 0 Mar  5 09:39 0226553a-37cf-41d5-b3ce-8b1e944543a8/bdev1 -> ../../../devices/virtual/block/dm-1/bcache/
297		lrwxrwxrwx 1 root root 0 Mar  5 09:39 0226553a-37cf-41d5-b3ce-8b1e944543a8/cache0 -> ../../../devices/virtual/block/dm-4/bcache/
298		lrwxrwxrwx 1 root root 0 Mar  5 09:39 5bc072a8-ab17-446d-9744-e247949913c1/cache0 -> ../../../devices/pci0000:00/0000:00:01.0/0000:01:00.0/ata10/host9/target9:0:0/9:0:0:0/block/sdl/sdl2/bcache/
300	   The device names will show which UUID is relevant, cd in that directory
301	   and stop the cache::
303		host:/sys/fs/bcache/5bc072a8-ab17-446d-9744-e247949913c1# echo 1 > stop
305	   This will free up bcache references and let you reuse the partition for
306	   other purposes.
310	Troubleshooting performance
311	---------------------------
313	Bcache has a bunch of config options and tunables. The defaults are intended to
314	be reasonable for typical desktop and server workloads, but they're not what you
315	want for getting the best possible numbers when benchmarking.
317	 - Backing device alignment
319	   The default metadata size in bcache is 8k.  If your backing device is
320	   RAID based, then be sure to align this by a multiple of your stride
321	   width using `make-bcache --data-offset`. If you intend to expand your
322	   disk array in the future, then multiply a series of primes by your
323	   raid stripe size to get the disk multiples that you would like.
325	   For example:  If you have a 64k stripe size, then the following offset
326	   would provide alignment for many common RAID5 data spindle counts::
328		64k * 2*2*2*3*3*5*7 bytes = 161280k
330	   That space is wasted, but for only 157.5MB you can grow your RAID 5
331	   volume to the following data-spindle counts without re-aligning::
333		3,4,5,6,7,8,9,10,12,14,15,18,20,21 ...
335	 - Bad write performance
337	   If write performance is not what you expected, you probably wanted to be
338	   running in writeback mode, which isn't the default (not due to a lack of
339	   maturity, but simply because in writeback mode you'll lose data if something
340	   happens to your SSD)::
342		# echo writeback > /sys/block/bcache0/bcache/cache_mode
344	 - Bad performance, or traffic not going to the SSD that you'd expect
346	   By default, bcache doesn't cache everything. It tries to skip sequential IO -
347	   because you really want to be caching the random IO, and if you copy a 10
348	   gigabyte file you probably don't want that pushing 10 gigabytes of randomly
349	   accessed data out of your cache.
351	   But if you want to benchmark reads from cache, and you start out with fio
352	   writing an 8 gigabyte test file - so you want to disable that::
354		# echo 0 > /sys/block/bcache0/bcache/sequential_cutoff
356	   To set it back to the default (4 mb), do::
358		# echo 4M > /sys/block/bcache0/bcache/sequential_cutoff
360	 - Traffic's still going to the spindle/still getting cache misses
362	   In the real world, SSDs don't always keep up with disks - particularly with
363	   slower SSDs, many disks being cached by one SSD, or mostly sequential IO. So
364	   you want to avoid being bottlenecked by the SSD and having it slow everything
365	   down.
367	   To avoid that bcache tracks latency to the cache device, and gradually
368	   throttles traffic if the latency exceeds a threshold (it does this by
369	   cranking down the sequential bypass).
371	   You can disable this if you need to by setting the thresholds to 0::
373		# echo 0 > /sys/fs/bcache/<cache set>/congested_read_threshold_us
374		# echo 0 > /sys/fs/bcache/<cache set>/congested_write_threshold_us
376	   The default is 2000 us (2 milliseconds) for reads, and 20000 for writes.
378	 - Still getting cache misses, of the same data
380	   One last issue that sometimes trips people up is actually an old bug, due to
381	   the way cache coherency is handled for cache misses. If a btree node is full,
382	   a cache miss won't be able to insert a key for the new data and the data
383	   won't be written to the cache.
385	   In practice this isn't an issue because as soon as a write comes along it'll
386	   cause the btree node to be split, and you need almost no write traffic for
387	   this to not show up enough to be noticeable (especially since bcache's btree
388	   nodes are huge and index large regions of the device). But when you're
389	   benchmarking, if you're trying to warm the cache by reading a bunch of data
390	   and there's no other traffic - that can be a problem.
392	   Solution: warm the cache by doing writes, or use the testing branch (there's
393	   a fix for the issue there).
396	Sysfs - backing device
397	----------------------
399	Available at /sys/block/<bdev>/bcache, /sys/block/bcache*/bcache and
400	(if attached) /sys/fs/bcache/<cset-uuid>/bdev*
402	attach
403	  Echo the UUID of a cache set to this file to enable caching.
405	cache_mode
406	  Can be one of either writethrough, writeback, writearound or none.
408	clear_stats
409	  Writing to this file resets the running total stats (not the day/hour/5 minute
410	  decaying versions).
412	detach
413	  Write to this file to detach from a cache set. If there is dirty data in the
414	  cache, it will be flushed first.
416	dirty_data
417	  Amount of dirty data for this backing device in the cache. Continuously
418	  updated unlike the cache set's version, but may be slightly off.
420	label
421	  Name of underlying device.
423	readahead
424	  Size of readahead that should be performed.  Defaults to 0.  If set to e.g.
425	  1M, it will round cache miss reads up to that size, but without overlapping
426	  existing cache entries.
428	running
429	  1 if bcache is running (i.e. whether the /dev/bcache device exists, whether
430	  it's in passthrough mode or caching).
432	sequential_cutoff
433	  A sequential IO will bypass the cache once it passes this threshold; the
434	  most recent 128 IOs are tracked so sequential IO can be detected even when
435	  it isn't all done at once.
437	sequential_merge
438	  If non zero, bcache keeps a list of the last 128 requests submitted to compare
439	  against all new requests to determine which new requests are sequential
440	  continuations of previous requests for the purpose of determining sequential
441	  cutoff. This is necessary if the sequential cutoff value is greater than the
442	  maximum acceptable sequential size for any single request.
444	state
445	  The backing device can be in one of four different states:
447	  no cache: Has never been attached to a cache set.
449	  clean: Part of a cache set, and there is no cached dirty data.
451	  dirty: Part of a cache set, and there is cached dirty data.
453	  inconsistent: The backing device was forcibly run by the user when there was
454	  dirty data cached but the cache set was unavailable; whatever data was on the
455	  backing device has likely been corrupted.
457	stop
458	  Write to this file to shut down the bcache device and close the backing
459	  device.
461	writeback_delay
462	  When dirty data is written to the cache and it previously did not contain
463	  any, waits some number of seconds before initiating writeback. Defaults to
464	  30.
466	writeback_percent
467	  If nonzero, bcache tries to keep around this percentage of the cache dirty by
468	  throttling background writeback and using a PD controller to smoothly adjust
469	  the rate.
471	writeback_rate
472	  Rate in sectors per second - if writeback_percent is nonzero, background
473	  writeback is throttled to this rate. Continuously adjusted by bcache but may
474	  also be set by the user.
476	writeback_running
477	  If off, writeback of dirty data will not take place at all. Dirty data will
478	  still be added to the cache until it is mostly full; only meant for
479	  benchmarking. Defaults to on.
481	Sysfs - backing device stats
482	~~~~~~~~~~~~~~~~~~~~~~~~~~~~
484	There are directories with these numbers for a running total, as well as
485	versions that decay over the past day, hour and 5 minutes; they're also
486	aggregated in the cache set directory as well.
488	bypassed
489	  Amount of IO (both reads and writes) that has bypassed the cache
491	cache_hits, cache_misses, cache_hit_ratio
492	  Hits and misses are counted per individual IO as bcache sees them; a
493	  partial hit is counted as a miss.
495	cache_bypass_hits, cache_bypass_misses
496	  Hits and misses for IO that is intended to skip the cache are still counted,
497	  but broken out here.
499	cache_miss_collisions
500	  Counts instances where data was going to be inserted into the cache from a
501	  cache miss, but raced with a write and data was already present (usually 0
502	  since the synchronization for cache misses was rewritten)
504	cache_readaheads
505	  Count of times readahead occurred.
507	Sysfs - cache set
508	~~~~~~~~~~~~~~~~~
510	Available at /sys/fs/bcache/<cset-uuid>
512	average_key_size
513	  Average data per key in the btree.
515	bdev<0..n>
516	  Symlink to each of the attached backing devices.
518	block_size
519	  Block size of the cache devices.
521	btree_cache_size
522	  Amount of memory currently used by the btree cache
524	bucket_size
525	  Size of buckets
527	cache<0..n>
528	  Symlink to each of the cache devices comprising this cache set.
530	cache_available_percent
531	  Percentage of cache device which doesn't contain dirty data, and could
532	  potentially be used for writeback.  This doesn't mean this space isn't used
533	  for clean cached data; the unused statistic (in priority_stats) is typically
534	  much lower.
536	clear_stats
537	  Clears the statistics associated with this cache
539	dirty_data
540	  Amount of dirty data is in the cache (updated when garbage collection runs).
542	flash_vol_create
543	  Echoing a size to this file (in human readable units, k/M/G) creates a thinly
544	  provisioned volume backed by the cache set.
546	io_error_halflife, io_error_limit
547	  These determines how many errors we accept before disabling the cache.
548	  Each error is decayed by the half life (in # ios).  If the decaying count
549	  reaches io_error_limit dirty data is written out and the cache is disabled.
551	journal_delay_ms
552	  Journal writes will delay for up to this many milliseconds, unless a cache
553	  flush happens sooner. Defaults to 100.
555	root_usage_percent
556	  Percentage of the root btree node in use.  If this gets too high the node
557	  will split, increasing the tree depth.
559	stop
560	  Write to this file to shut down the cache set - waits until all attached
561	  backing devices have been shut down.
563	tree_depth
564	  Depth of the btree (A single node btree has depth 0).
566	unregister
567	  Detaches all backing devices and closes the cache devices; if dirty data is
568	  present it will disable writeback caching and wait for it to be flushed.
570	Sysfs - cache set internal
571	~~~~~~~~~~~~~~~~~~~~~~~~~~
573	This directory also exposes timings for a number of internal operations, with
574	separate files for average duration, average frequency, last occurrence and max
575	duration: garbage collection, btree read, btree node sorts and btree splits.
577	active_journal_entries
578	  Number of journal entries that are newer than the index.
580	btree_nodes
581	  Total nodes in the btree.
583	btree_used_percent
584	  Average fraction of btree in use.
586	bset_tree_stats
587	  Statistics about the auxiliary search trees
589	btree_cache_max_chain
590	  Longest chain in the btree node cache's hash table
592	cache_read_races
593	  Counts instances where while data was being read from the cache, the bucket
594	  was reused and invalidated - i.e. where the pointer was stale after the read
595	  completed. When this occurs the data is reread from the backing device.
597	trigger_gc
598	  Writing to this file forces garbage collection to run.
600	Sysfs - Cache device
601	~~~~~~~~~~~~~~~~~~~~
603	Available at /sys/block/<cdev>/bcache
605	block_size
606	  Minimum granularity of writes - should match hardware sector size.
608	btree_written
609	  Sum of all btree writes, in (kilo/mega/giga) bytes
611	bucket_size
612	  Size of buckets
614	cache_replacement_policy
615	  One of either lru, fifo or random.
617	discard
618	  Boolean; if on a discard/TRIM will be issued to each bucket before it is
619	  reused. Defaults to off, since SATA TRIM is an unqueued command (and thus
620	  slow).
622	freelist_percent
623	  Size of the freelist as a percentage of nbuckets. Can be written to to
624	  increase the number of buckets kept on the freelist, which lets you
625	  artificially reduce the size of the cache at runtime. Mostly for testing
626	  purposes (i.e. testing how different size caches affect your hit rate), but
627	  since buckets are discarded when they move on to the freelist will also make
628	  the SSD's garbage collection easier by effectively giving it more reserved
629	  space.
631	io_errors
632	  Number of errors that have occurred, decayed by io_error_halflife.
634	metadata_written
635	  Sum of all non data writes (btree writes and all other metadata).
637	nbuckets
638	  Total buckets in this cache
640	priority_stats
641	  Statistics about how recently data in the cache has been accessed.
642	  This can reveal your working set size.  Unused is the percentage of
643	  the cache that doesn't contain any data.  Metadata is bcache's
644	  metadata overhead.  Average is the average priority of cache buckets.
645	  Next is a list of quantiles with the priority threshold of each.
647	written
648	  Sum of all data that has been written to the cache; comparison with
649	  btree_written gives the amount of write inflation in bcache.
Hide Line Numbers
About Kernel Documentation Linux Kernel Contact Linux Resources Linux Blog

Information is copyright its respective author. All material is available from the Linux Kernel Source distributed under a GPL License. This page is provided as a free service by mjmwired.net.