1 Say you've got a big slow raid 6, and an X-25E or three. Wouldn't it be
2 nice if you could use them as cache... Hence bcache.
4 Wiki and git repositories are at:
5 http://bcache.evilpiepirate.org
6 http://evilpiepirate.org/git/linux-bcache.git
7 http://evilpiepirate.org/git/bcache-tools.git
9 It's designed around the performance characteristics of SSDs - it only allocates
10 in erase block sized buckets, and it uses a hybrid btree/log to track cached
11 extants (which can be anywhere from a single sector to the bucket size). It's
12 designed to avoid random writes at all costs; it fills up an erase block
13 sequentially, then issues a discard before reusing it.
15 Both writethrough and writeback caching are supported. Writeback defaults to
16 off, but can be switched on and off arbitrarily at runtime. Bcache goes to
17 great lengths to protect your data - it reliably handles unclean shutdown. (It
18 doesn't even have a notion of a clean shutdown; bcache simply doesn't return
19 writes as completed until they're on stable storage).
21 Writeback caching can use most of the cache for buffering writes - writing
22 dirty data to the backing device is always done sequentially, scanning from the
23 start to the end of the index.
25 Since random IO is what SSDs excel at, there generally won't be much benefit
26 to caching large sequential IO. Bcache detects sequential IO and skips it;
27 it also keeps a rolling average of the IO sizes per task, and as long as the
28 average is above the cutoff it will skip all IO from that task - instead of
29 caching the first 512k after every seek. Backups and large file copies should
30 thus entirely bypass the cache.
32 In the event of a data IO error on the flash it will try to recover by reading
33 from disk or invalidating cache entries. For unrecoverable errors (meta data
34 or dirty data), caching is automatically disabled; if dirty data was present
35 in the cache it first disables writeback caching and waits for all dirty data
39 You'll need make-bcache from the bcache-tools repository. Both the cache device
40 and backing device must be formatted before use.
41 make-bcache -B /dev/sdb
42 make-bcache -C /dev/sdc
44 make-bcache has the ability to format multiple devices at the same time - if
45 you format your backing devices and cache device at the same time, you won't
46 have to manually attach:
47 make-bcache -B /dev/sda /dev/sdb -C /dev/sdc
49 To make bcache devices known to the kernel, echo them to /sys/fs/bcache/register:
51 echo /dev/sdb > /sys/fs/bcache/register
52 echo /dev/sdc > /sys/fs/bcache/register
54 To register your bcache devices automatically, you could add something like
55 this to an init script:
57 echo /dev/sd* > /sys/fs/bcache/register_quiet
59 It'll look for bcache superblocks and ignore everything that doesn't have one.
61 Registering the backing device makes the bcache show up in /dev; you can now
62 format it and use it as normal. But the first time using a new bcache device,
63 it'll be running in passthrough mode until you attach it to a cache. See the
66 The devices show up at /dev/bcacheN, and can be controlled via sysfs from
67 /sys/block/bcacheN/bcache:
69 mkfs.ext4 /dev/bcache0
70 mount /dev/bcache0 /mnt
72 Cache devices are managed as sets; multiple caches per set isn't supported yet
73 but will allow for mirroring of metadata and dirty data in the future. Your new
74 cache set shows up as /sys/fs/bcache/<UUID>
78 After your cache device and backing device are registered, the backing device
79 must be attached to your cache set to enable caching. Attaching a backing
80 device to a cache set is done thusly, with the UUID of the cache set in
83 echo <UUID> > /sys/block/bcache0/bcache/attach
85 This only has to be done once. The next time you reboot, just reregister all
86 your bcache devices. If a backing device has data in a cache somewhere, the
87 /dev/bcache# device won't be created until the cache shows up - particularly
88 important if you have writeback caching turned on.
90 If you're booting up and your cache device is gone and never coming back, you
91 can force run the backing device:
93 echo 1 > /sys/block/sdb/bcache/running
95 (You need to use /sys/block/sdb (or whatever your backing device is called), not
96 /sys/block/bcache0, because bcache0 doesn't exist yet. If you're using a
97 partition, the bcache directory would be at /sys/block/sdb/sdb2/bcache)
99 The backing device will still use that cache set if it shows up in the future,
100 but all the cached data will be invalidated. If there was dirty data in the
101 cache, don't expect the filesystem to be recoverable - you will have massive
102 filesystem corruption, though ext4's fsck does work miracles.
104 SYSFS - BACKING DEVICE:
107 Echo the UUID of a cache set to this file to enable caching.
110 Can be one of either writethrough, writeback, writearound or none.
113 Writing to this file resets the running total stats (not the day/hour/5 minute
117 Write to this file to detach from a cache set. If there is dirty data in the
118 cache, it will be flushed first.
121 Amount of dirty data for this backing device in the cache. Continuously
122 updated unlike the cache set's version, but may be slightly off.
125 Name of underlying device.
128 Size of readahead that should be performed. Defaults to 0. If set to e.g.
129 1M, it will round cache miss reads up to that size, but without overlapping
130 existing cache entries.
133 1 if bcache is running (i.e. whether the /dev/bcache device exists, whether
134 it's in passthrough mode or caching).
137 A sequential IO will bypass the cache once it passes this threshhold; the
138 most recent 128 IOs are tracked so sequential IO can be detected even when
139 it isn't all done at once.
142 If non zero, bcache keeps a list of the last 128 requests submitted to compare
143 against all new requests to determine which new requests are sequential
144 continuations of previous requests for the purpose of determining sequential
145 cutoff. This is necessary if the sequential cutoff value is greater than the
146 maximum acceptable sequential size for any single request.
149 The backing device can be in one of four different states:
151 no cache: Has never been attached to a cache set.
153 clean: Part of a cache set, and there is no cached dirty data.
155 dirty: Part of a cache set, and there is cached dirty data.
157 inconsistent: The backing device was forcibly run by the user when there was
158 dirty data cached but the cache set was unavailable; whatever data was on the
159 backing device has likely been corrupted.
162 Write to this file to shut down the bcache device and close the backing
166 When dirty data is written to the cache and it previously did not contain
167 any, waits some number of seconds before initiating writeback. Defaults to
171 If nonzero, bcache tries to keep around this percentage of the cache dirty by
172 throttling background writeback and using a PD controller to smoothly adjust
176 Rate in sectors per second - if writeback_percent is nonzero, background
177 writeback is throttled to this rate. Continuously adjusted by bcache but may
178 also be set by the user.
181 If off, writeback of dirty data will not take place at all. Dirty data will
182 still be added to the cache until it is mostly full; only meant for
183 benchmarking. Defaults to on.
185 SYSFS - BACKING DEVICE STATS:
187 There are directories with these numbers for a running total, as well as
188 versions that decay over the past day, hour and 5 minutes; they're also
189 aggregated in the cache set directory as well.
192 Amount of IO (both reads and writes) that has bypassed the cache
197 Hits and misses are counted per individual IO as bcache sees them; a
198 partial hit is counted as a miss.
202 Hits and misses for IO that is intended to skip the cache are still counted,
205 cache_miss_collisions
206 Counts instances where data was going to be inserted into the cache from a
207 cache miss, but raced with a write and data was already present (usually 0
208 since the synchronization for cache misses was rewritten)
211 Count of times readahead occured.
216 Average data per key in the btree.
219 Symlink to each of the attached backing devices.
222 Block size of the cache devices.
225 Amount of memory currently used by the btree cache
231 Symlink to each of the cache devices comprising this cache set.
233 cache_available_percent
234 Percentage of cache device free.
237 Clears the statistics associated with this cache
240 Amount of dirty data is in the cache (updated when garbage collection runs).
243 Echoing a size to this file (in human readable units, k/M/G) creates a thinly
244 provisioned volume backed by the cache set.
248 These determines how many errors we accept before disabling the cache.
249 Each error is decayed by the half life (in # ios). If the decaying count
250 reaches io_error_limit dirty data is written out and the cache is disabled.
253 Journal writes will delay for up to this many milliseconds, unless a cache
254 flush happens sooner. Defaults to 100.
257 Percentage of the root btree node in use. If this gets too high the node
258 will split, increasing the tree depth.
261 Write to this file to shut down the cache set - waits until all attached
262 backing devices have been shut down.
265 Depth of the btree (A single node btree has depth 0).
268 Detaches all backing devices and closes the cache devices; if dirty data is
269 present it will disable writeback caching and wait for it to be flushed.
271 SYSFS - CACHE SET INTERNAL:
273 This directory also exposes timings for a number of internal operations, with
274 separate files for average duration, average frequency, last occurence and max
275 duration: garbage collection, btree read, btree node sorts and btree splits.
277 active_journal_entries
278 Number of journal entries that are newer than the index.
281 Total nodes in the btree.
284 Average fraction of btree in use.
287 Statistics about the auxiliary search trees
289 btree_cache_max_chain
290 Longest chain in the btree node cache's hash table
293 Counts instances where while data was being read from the cache, the bucket
294 was reused and invalidated - i.e. where the pointer was stale after the read
295 completed. When this occurs the data is reread from the backing device.
298 Writing to this file forces garbage collection to run.
300 SYSFS - CACHE DEVICE:
303 Minimum granularity of writes - should match hardware sector size.
306 Sum of all btree writes, in (kilo/mega/giga) bytes
311 cache_replacement_policy
312 One of either lru, fifo or random.
315 Boolean; if on a discard/TRIM will be issued to each bucket before it is
316 reused. Defaults to off, since SATA TRIM is an unqueued command (and thus
320 Size of the freelist as a percentage of nbuckets. Can be written to to
321 increase the number of buckets kept on the freelist, which lets you
322 artificially reduce the size of the cache at runtime. Mostly for testing
323 purposes (i.e. testing how different size caches affect your hit rate), but
324 since buckets are discarded when they move on to the freelist will also make
325 the SSD's garbage collection easier by effectively giving it more reserved
329 Number of errors that have occured, decayed by io_error_halflife.
332 Sum of all non data writes (btree writes and all other metadata).
335 Total buckets in this cache
338 Statistics about how recently data in the cache has been accessed. This can
339 reveal your working set size.
342 Sum of all data that has been written to the cache; comparison with
343 btree_written gives the amount of write inflation in bcache.