^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1) ============================
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2) A block layer cache (bcache)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 3) ============================
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 4)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 5) Say you've got a big slow raid 6, and an ssd or three. Wouldn't it be
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 6) nice if you could use them as cache... Hence bcache.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 7)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 8) The bcache wiki can be found at:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 9) https://bcache.evilpiepirate.org
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 10)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 11) This is the git repository of bcache-tools:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 12) https://git.kernel.org/pub/scm/linux/kernel/git/colyli/bcache-tools.git/
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 13)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 14) The latest bcache kernel code can be found from mainline Linux kernel:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 15) https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 16)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 17) It's designed around the performance characteristics of SSDs - it only allocates
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 18) in erase block sized buckets, and it uses a hybrid btree/log to track cached
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 19) extents (which can be anywhere from a single sector to the bucket size). It's
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 20) designed to avoid random writes at all costs; it fills up an erase block
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 21) sequentially, then issues a discard before reusing it.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 22)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 23) Both writethrough and writeback caching are supported. Writeback defaults to
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 24) off, but can be switched on and off arbitrarily at runtime. Bcache goes to
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 25) great lengths to protect your data - it reliably handles unclean shutdown. (It
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 26) doesn't even have a notion of a clean shutdown; bcache simply doesn't return
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 27) writes as completed until they're on stable storage).
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 28)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 29) Writeback caching can use most of the cache for buffering writes - writing
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 30) dirty data to the backing device is always done sequentially, scanning from the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 31) start to the end of the index.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 32)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 33) Since random IO is what SSDs excel at, there generally won't be much benefit
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 34) to caching large sequential IO. Bcache detects sequential IO and skips it;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 35) it also keeps a rolling average of the IO sizes per task, and as long as the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 36) average is above the cutoff it will skip all IO from that task - instead of
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 37) caching the first 512k after every seek. Backups and large file copies should
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 38) thus entirely bypass the cache.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 39)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 40) In the event of a data IO error on the flash it will try to recover by reading
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 41) from disk or invalidating cache entries. For unrecoverable errors (meta data
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 42) or dirty data), caching is automatically disabled; if dirty data was present
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 43) in the cache it first disables writeback caching and waits for all dirty data
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 44) to be flushed.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 45)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 46) Getting started:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 47) You'll need bcache util from the bcache-tools repository. Both the cache device
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 48) and backing device must be formatted before use::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 49)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 50) bcache make -B /dev/sdb
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 51) bcache make -C /dev/sdc
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 52)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 53) `bcache make` has the ability to format multiple devices at the same time - if
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 54) you format your backing devices and cache device at the same time, you won't
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 55) have to manually attach::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 56)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 57) bcache make -B /dev/sda /dev/sdb -C /dev/sdc
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 58)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 59) If your bcache-tools is not updated to latest version and does not have the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 60) unified `bcache` utility, you may use the legacy `make-bcache` utility to format
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 61) bcache device with same -B and -C parameters.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 62)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 63) bcache-tools now ships udev rules, and bcache devices are known to the kernel
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 64) immediately. Without udev, you can manually register devices like this::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 65)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 66) echo /dev/sdb > /sys/fs/bcache/register
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 67) echo /dev/sdc > /sys/fs/bcache/register
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 68)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 69) Registering the backing device makes the bcache device show up in /dev; you can
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 70) now format it and use it as normal. But the first time using a new bcache
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 71) device, it'll be running in passthrough mode until you attach it to a cache.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 72) If you are thinking about using bcache later, it is recommended to setup all your
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 73) slow devices as bcache backing devices without a cache, and you can choose to add
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 74) a caching device later.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 75) See 'ATTACHING' section below.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 76)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 77) The devices show up as::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 78)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 79) /dev/bcache<N>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 80)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 81) As well as (with udev)::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 82)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 83) /dev/bcache/by-uuid/<uuid>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 84) /dev/bcache/by-label/<label>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 85)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 86) To get started::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 87)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 88) mkfs.ext4 /dev/bcache0
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 89) mount /dev/bcache0 /mnt
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 90)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 91) You can control bcache devices through sysfs at /sys/block/bcache<N>/bcache .
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 92) You can also control them through /sys/fs//bcache/<cset-uuid>/ .
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 93)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 94) Cache devices are managed as sets; multiple caches per set isn't supported yet
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 95) but will allow for mirroring of metadata and dirty data in the future. Your new
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 96) cache set shows up as /sys/fs/bcache/<UUID>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 97)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 98) Attaching
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 99) ---------
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 100)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 101) After your cache device and backing device are registered, the backing device
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 102) must be attached to your cache set to enable caching. Attaching a backing
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 103) device to a cache set is done thusly, with the UUID of the cache set in
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 104) /sys/fs/bcache::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 105)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 106) echo <CSET-UUID> > /sys/block/bcache0/bcache/attach
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 107)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 108) This only has to be done once. The next time you reboot, just reregister all
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 109) your bcache devices. If a backing device has data in a cache somewhere, the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 110) /dev/bcache<N> device won't be created until the cache shows up - particularly
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 111) important if you have writeback caching turned on.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 112)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 113) If you're booting up and your cache device is gone and never coming back, you
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 114) can force run the backing device::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 115)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 116) echo 1 > /sys/block/sdb/bcache/running
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 117)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 118) (You need to use /sys/block/sdb (or whatever your backing device is called), not
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 119) /sys/block/bcache0, because bcache0 doesn't exist yet. If you're using a
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 120) partition, the bcache directory would be at /sys/block/sdb/sdb2/bcache)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 121)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 122) The backing device will still use that cache set if it shows up in the future,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 123) but all the cached data will be invalidated. If there was dirty data in the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 124) cache, don't expect the filesystem to be recoverable - you will have massive
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 125) filesystem corruption, though ext4's fsck does work miracles.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 126)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 127) Error Handling
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 128) --------------
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 129)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 130) Bcache tries to transparently handle IO errors to/from the cache device without
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 131) affecting normal operation; if it sees too many errors (the threshold is
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 132) configurable, and defaults to 0) it shuts down the cache device and switches all
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 133) the backing devices to passthrough mode.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 134)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 135) - For reads from the cache, if they error we just retry the read from the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 136) backing device.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 137)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 138) - For writethrough writes, if the write to the cache errors we just switch to
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 139) invalidating the data at that lba in the cache (i.e. the same thing we do for
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 140) a write that bypasses the cache)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 141)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 142) - For writeback writes, we currently pass that error back up to the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 143) filesystem/userspace. This could be improved - we could retry it as a write
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 144) that skips the cache so we don't have to error the write.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 145)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 146) - When we detach, we first try to flush any dirty data (if we were running in
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 147) writeback mode). It currently doesn't do anything intelligent if it fails to
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 148) read some of the dirty data, though.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 149)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 150)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 151) Howto/cookbook
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 152) --------------
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 153)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 154) A) Starting a bcache with a missing caching device
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 155)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 156) If registering the backing device doesn't help, it's already there, you just need
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 157) to force it to run without the cache::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 158)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 159) host:~# echo /dev/sdb1 > /sys/fs/bcache/register
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 160) [ 119.844831] bcache: register_bcache() error opening /dev/sdb1: device already registered
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 161)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 162) Next, you try to register your caching device if it's present. However
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 163) if it's absent, or registration fails for some reason, you can still
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 164) start your bcache without its cache, like so::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 165)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 166) host:/sys/block/sdb/sdb1/bcache# echo 1 > running
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 167)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 168) Note that this may cause data loss if you were running in writeback mode.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 169)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 170)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 171) B) Bcache does not find its cache::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 172)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 173) host:/sys/block/md5/bcache# echo 0226553a-37cf-41d5-b3ce-8b1e944543a8 > attach
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 174) [ 1933.455082] bcache: bch_cached_dev_attach() Couldn't find uuid for md5 in set
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 175) [ 1933.478179] bcache: __cached_dev_store() Can't attach 0226553a-37cf-41d5-b3ce-8b1e944543a8
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 176) [ 1933.478179] : cache set not found
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 177)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 178) In this case, the caching device was simply not registered at boot
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 179) or disappeared and came back, and needs to be (re-)registered::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 180)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 181) host:/sys/block/md5/bcache# echo /dev/sdh2 > /sys/fs/bcache/register
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 182)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 183)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 184) C) Corrupt bcache crashes the kernel at device registration time:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 185)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 186) This should never happen. If it does happen, then you have found a bug!
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 187) Please report it to the bcache development list: linux-bcache@vger.kernel.org
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 188)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 189) Be sure to provide as much information that you can including kernel dmesg
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 190) output if available so that we may assist.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 191)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 192)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 193) D) Recovering data without bcache:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 194)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 195) If bcache is not available in the kernel, a filesystem on the backing
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 196) device is still available at an 8KiB offset. So either via a loopdev
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 197) of the backing device created with --offset 8K, or any value defined by
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 198) --data-offset when you originally formatted bcache with `bcache make`.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 199)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 200) For example::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 201)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 202) losetup -o 8192 /dev/loop0 /dev/your_bcache_backing_dev
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 203)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 204) This should present your unmodified backing device data in /dev/loop0
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 205)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 206) If your cache is in writethrough mode, then you can safely discard the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 207) cache device without loosing data.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 208)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 209)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 210) E) Wiping a cache device
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 211)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 212) ::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 213)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 214) host:~# wipefs -a /dev/sdh2
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 215) 16 bytes were erased at offset 0x1018 (bcache)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 216) they were: c6 85 73 f6 4e 1a 45 ca 82 65 f5 7f 48 ba 6d 81
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 217)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 218) After you boot back with bcache enabled, you recreate the cache and attach it::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 219)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 220) host:~# bcache make -C /dev/sdh2
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 221) UUID: 7be7e175-8f4c-4f99-94b2-9c904d227045
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 222) Set UUID: 5bc072a8-ab17-446d-9744-e247949913c1
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 223) version: 0
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 224) nbuckets: 106874
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 225) block_size: 1
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 226) bucket_size: 1024
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 227) nr_in_set: 1
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 228) nr_this_dev: 0
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 229) first_bucket: 1
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 230) [ 650.511912] bcache: run_cache_set() invalidating existing data
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 231) [ 650.549228] bcache: register_cache() registered cache device sdh2
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 232)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 233) start backing device with missing cache::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 234)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 235) host:/sys/block/md5/bcache# echo 1 > running
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 236)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 237) attach new cache::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 238)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 239) host:/sys/block/md5/bcache# echo 5bc072a8-ab17-446d-9744-e247949913c1 > attach
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 240) [ 865.276616] bcache: bch_cached_dev_attach() Caching md5 as bcache0 on set 5bc072a8-ab17-446d-9744-e247949913c1
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 241)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 242)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 243) F) Remove or replace a caching device::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 244)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 245) host:/sys/block/sda/sda7/bcache# echo 1 > detach
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 246) [ 695.872542] bcache: cached_dev_detach_finish() Caching disabled for sda7
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 247)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 248) host:~# wipefs -a /dev/nvme0n1p4
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 249) wipefs: error: /dev/nvme0n1p4: probing initialization failed: Device or resource busy
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 250) Ooops, it's disabled, but not unregistered, so it's still protected
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 251)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 252) We need to go and unregister it::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 253)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 254) host:/sys/fs/bcache/b7ba27a1-2398-4649-8ae3-0959f57ba128# ls -l cache0
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 255) 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/
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 256) host:/sys/fs/bcache/b7ba27a1-2398-4649-8ae3-0959f57ba128# echo 1 > stop
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 257) kernel: [ 917.041908] bcache: cache_set_free() Cache set b7ba27a1-2398-4649-8ae3-0959f57ba128 unregistered
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 258)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 259) Now we can wipe it::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 260)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 261) host:~# wipefs -a /dev/nvme0n1p4
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 262) /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
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 263)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 264)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 265) G) dm-crypt and bcache
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 266)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 267) First setup bcache unencrypted and then install dmcrypt on top of
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 268) /dev/bcache<N> This will work faster than if you dmcrypt both the backing
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 269) and caching devices and then install bcache on top. [benchmarks?]
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 270)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 271)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 272) H) Stop/free a registered bcache to wipe and/or recreate it
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 273)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 274) Suppose that you need to free up all bcache references so that you can
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 275) fdisk run and re-register a changed partition table, which won't work
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 276) if there are any active backing or caching devices left on it:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 277)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 278) 1) Is it present in /dev/bcache* ? (there are times where it won't be)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 279)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 280) If so, it's easy::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 281)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 282) host:/sys/block/bcache0/bcache# echo 1 > stop
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 283)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 284) 2) But if your backing device is gone, this won't work::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 285)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 286) host:/sys/block/bcache0# cd bcache
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 287) bash: cd: bcache: No such file or directory
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 288)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 289) In this case, you may have to unregister the dmcrypt block device that
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 290) references this bcache to free it up::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 291)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 292) host:~# dmsetup remove oldds1
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 293) bcache: bcache_device_free() bcache0 stopped
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 294) bcache: cache_set_free() Cache set 5bc072a8-ab17-446d-9744-e247949913c1 unregistered
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 295)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 296) This causes the backing bcache to be removed from /sys/fs/bcache and
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 297) then it can be reused. This would be true of any block device stacking
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 298) where bcache is a lower device.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 299)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 300) 3) In other cases, you can also look in /sys/fs/bcache/::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 301)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 302) host:/sys/fs/bcache# ls -l */{cache?,bdev?}
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 303) lrwxrwxrwx 1 root root 0 Mar 5 09:39 0226553a-37cf-41d5-b3ce-8b1e944543a8/bdev1 -> ../../../devices/virtual/block/dm-1/bcache/
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 304) lrwxrwxrwx 1 root root 0 Mar 5 09:39 0226553a-37cf-41d5-b3ce-8b1e944543a8/cache0 -> ../../../devices/virtual/block/dm-4/bcache/
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 305) 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/
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 306)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 307) The device names will show which UUID is relevant, cd in that directory
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 308) and stop the cache::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 309)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 310) host:/sys/fs/bcache/5bc072a8-ab17-446d-9744-e247949913c1# echo 1 > stop
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 311)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 312) This will free up bcache references and let you reuse the partition for
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 313) other purposes.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 314)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 315)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 316)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 317) Troubleshooting performance
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 318) ---------------------------
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 319)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 320) Bcache has a bunch of config options and tunables. The defaults are intended to
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 321) be reasonable for typical desktop and server workloads, but they're not what you
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 322) want for getting the best possible numbers when benchmarking.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 323)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 324) - Backing device alignment
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 325)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 326) The default metadata size in bcache is 8k. If your backing device is
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 327) RAID based, then be sure to align this by a multiple of your stride
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 328) width using `bcache make --data-offset`. If you intend to expand your
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 329) disk array in the future, then multiply a series of primes by your
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 330) raid stripe size to get the disk multiples that you would like.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 331)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 332) For example: If you have a 64k stripe size, then the following offset
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 333) would provide alignment for many common RAID5 data spindle counts::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 334)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 335) 64k * 2*2*2*3*3*5*7 bytes = 161280k
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 336)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 337) That space is wasted, but for only 157.5MB you can grow your RAID 5
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 338) volume to the following data-spindle counts without re-aligning::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 339)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 340) 3,4,5,6,7,8,9,10,12,14,15,18,20,21 ...
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 341)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 342) - Bad write performance
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 343)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 344) If write performance is not what you expected, you probably wanted to be
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 345) running in writeback mode, which isn't the default (not due to a lack of
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 346) maturity, but simply because in writeback mode you'll lose data if something
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 347) happens to your SSD)::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 348)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 349) # echo writeback > /sys/block/bcache0/bcache/cache_mode
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 350)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 351) - Bad performance, or traffic not going to the SSD that you'd expect
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 352)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 353) By default, bcache doesn't cache everything. It tries to skip sequential IO -
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 354) because you really want to be caching the random IO, and if you copy a 10
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 355) gigabyte file you probably don't want that pushing 10 gigabytes of randomly
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 356) accessed data out of your cache.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 357)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 358) But if you want to benchmark reads from cache, and you start out with fio
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 359) writing an 8 gigabyte test file - so you want to disable that::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 360)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 361) # echo 0 > /sys/block/bcache0/bcache/sequential_cutoff
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 362)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 363) To set it back to the default (4 mb), do::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 364)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 365) # echo 4M > /sys/block/bcache0/bcache/sequential_cutoff
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 366)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 367) - Traffic's still going to the spindle/still getting cache misses
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 368)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 369) In the real world, SSDs don't always keep up with disks - particularly with
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 370) slower SSDs, many disks being cached by one SSD, or mostly sequential IO. So
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 371) you want to avoid being bottlenecked by the SSD and having it slow everything
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 372) down.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 373)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 374) To avoid that bcache tracks latency to the cache device, and gradually
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 375) throttles traffic if the latency exceeds a threshold (it does this by
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 376) cranking down the sequential bypass).
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 377)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 378) You can disable this if you need to by setting the thresholds to 0::
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 379)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 380) # echo 0 > /sys/fs/bcache/<cache set>/congested_read_threshold_us
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 381) # echo 0 > /sys/fs/bcache/<cache set>/congested_write_threshold_us
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 382)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 383) The default is 2000 us (2 milliseconds) for reads, and 20000 for writes.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 384)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 385) - Still getting cache misses, of the same data
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 386)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 387) One last issue that sometimes trips people up is actually an old bug, due to
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 388) the way cache coherency is handled for cache misses. If a btree node is full,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 389) a cache miss won't be able to insert a key for the new data and the data
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 390) won't be written to the cache.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 391)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 392) In practice this isn't an issue because as soon as a write comes along it'll
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 393) cause the btree node to be split, and you need almost no write traffic for
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 394) this to not show up enough to be noticeable (especially since bcache's btree
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 395) nodes are huge and index large regions of the device). But when you're
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 396) benchmarking, if you're trying to warm the cache by reading a bunch of data
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 397) and there's no other traffic - that can be a problem.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 398)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 399) Solution: warm the cache by doing writes, or use the testing branch (there's
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 400) a fix for the issue there).
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 401)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 402)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 403) Sysfs - backing device
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 404) ----------------------
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 405)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 406) Available at /sys/block/<bdev>/bcache, /sys/block/bcache*/bcache and
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 407) (if attached) /sys/fs/bcache/<cset-uuid>/bdev*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 408)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 409) attach
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 410) Echo the UUID of a cache set to this file to enable caching.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 411)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 412) cache_mode
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 413) Can be one of either writethrough, writeback, writearound or none.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 414)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 415) clear_stats
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 416) Writing to this file resets the running total stats (not the day/hour/5 minute
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 417) decaying versions).
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 418)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 419) detach
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 420) Write to this file to detach from a cache set. If there is dirty data in the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 421) cache, it will be flushed first.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 422)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 423) dirty_data
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 424) Amount of dirty data for this backing device in the cache. Continuously
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 425) updated unlike the cache set's version, but may be slightly off.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 426)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 427) label
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 428) Name of underlying device.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 429)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 430) readahead
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 431) Size of readahead that should be performed. Defaults to 0. If set to e.g.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 432) 1M, it will round cache miss reads up to that size, but without overlapping
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 433) existing cache entries.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 434)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 435) running
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 436) 1 if bcache is running (i.e. whether the /dev/bcache device exists, whether
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 437) it's in passthrough mode or caching).
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 438)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 439) sequential_cutoff
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 440) A sequential IO will bypass the cache once it passes this threshold; the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 441) most recent 128 IOs are tracked so sequential IO can be detected even when
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 442) it isn't all done at once.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 443)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 444) sequential_merge
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 445) If non zero, bcache keeps a list of the last 128 requests submitted to compare
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 446) against all new requests to determine which new requests are sequential
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 447) continuations of previous requests for the purpose of determining sequential
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 448) cutoff. This is necessary if the sequential cutoff value is greater than the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 449) maximum acceptable sequential size for any single request.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 450)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 451) state
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 452) The backing device can be in one of four different states:
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 453)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 454) no cache: Has never been attached to a cache set.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 455)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 456) clean: Part of a cache set, and there is no cached dirty data.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 457)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 458) dirty: Part of a cache set, and there is cached dirty data.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 459)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 460) inconsistent: The backing device was forcibly run by the user when there was
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 461) dirty data cached but the cache set was unavailable; whatever data was on the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 462) backing device has likely been corrupted.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 463)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 464) stop
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 465) Write to this file to shut down the bcache device and close the backing
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 466) device.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 467)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 468) writeback_delay
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 469) When dirty data is written to the cache and it previously did not contain
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 470) any, waits some number of seconds before initiating writeback. Defaults to
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 471) 30.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 472)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 473) writeback_percent
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 474) If nonzero, bcache tries to keep around this percentage of the cache dirty by
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 475) throttling background writeback and using a PD controller to smoothly adjust
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 476) the rate.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 477)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 478) writeback_rate
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 479) Rate in sectors per second - if writeback_percent is nonzero, background
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 480) writeback is throttled to this rate. Continuously adjusted by bcache but may
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 481) also be set by the user.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 482)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 483) writeback_running
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 484) If off, writeback of dirty data will not take place at all. Dirty data will
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 485) still be added to the cache until it is mostly full; only meant for
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 486) benchmarking. Defaults to on.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 487)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 488) Sysfs - backing device stats
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 489) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 490)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 491) There are directories with these numbers for a running total, as well as
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 492) versions that decay over the past day, hour and 5 minutes; they're also
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 493) aggregated in the cache set directory as well.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 494)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 495) bypassed
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 496) Amount of IO (both reads and writes) that has bypassed the cache
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 497)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 498) cache_hits, cache_misses, cache_hit_ratio
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 499) Hits and misses are counted per individual IO as bcache sees them; a
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 500) partial hit is counted as a miss.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 501)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 502) cache_bypass_hits, cache_bypass_misses
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 503) Hits and misses for IO that is intended to skip the cache are still counted,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 504) but broken out here.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 505)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 506) cache_miss_collisions
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 507) Counts instances where data was going to be inserted into the cache from a
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 508) cache miss, but raced with a write and data was already present (usually 0
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 509) since the synchronization for cache misses was rewritten)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 510)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 511) cache_readaheads
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 512) Count of times readahead occurred.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 513)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 514) Sysfs - cache set
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 515) ~~~~~~~~~~~~~~~~~
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 516)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 517) Available at /sys/fs/bcache/<cset-uuid>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 518)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 519) average_key_size
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 520) Average data per key in the btree.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 521)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 522) bdev<0..n>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 523) Symlink to each of the attached backing devices.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 524)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 525) block_size
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 526) Block size of the cache devices.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 527)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 528) btree_cache_size
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 529) Amount of memory currently used by the btree cache
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 530)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 531) bucket_size
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 532) Size of buckets
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 533)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 534) cache<0..n>
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 535) Symlink to each of the cache devices comprising this cache set.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 536)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 537) cache_available_percent
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 538) Percentage of cache device which doesn't contain dirty data, and could
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 539) potentially be used for writeback. This doesn't mean this space isn't used
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 540) for clean cached data; the unused statistic (in priority_stats) is typically
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 541) much lower.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 542)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 543) clear_stats
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 544) Clears the statistics associated with this cache
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 545)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 546) dirty_data
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 547) Amount of dirty data is in the cache (updated when garbage collection runs).
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 548)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 549) flash_vol_create
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 550) Echoing a size to this file (in human readable units, k/M/G) creates a thinly
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 551) provisioned volume backed by the cache set.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 552)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 553) io_error_halflife, io_error_limit
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 554) These determines how many errors we accept before disabling the cache.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 555) Each error is decayed by the half life (in # ios). If the decaying count
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 556) reaches io_error_limit dirty data is written out and the cache is disabled.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 557)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 558) journal_delay_ms
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 559) Journal writes will delay for up to this many milliseconds, unless a cache
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 560) flush happens sooner. Defaults to 100.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 561)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 562) root_usage_percent
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 563) Percentage of the root btree node in use. If this gets too high the node
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 564) will split, increasing the tree depth.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 565)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 566) stop
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 567) Write to this file to shut down the cache set - waits until all attached
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 568) backing devices have been shut down.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 569)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 570) tree_depth
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 571) Depth of the btree (A single node btree has depth 0).
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 572)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 573) unregister
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 574) Detaches all backing devices and closes the cache devices; if dirty data is
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 575) present it will disable writeback caching and wait for it to be flushed.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 576)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 577) Sysfs - cache set internal
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 578) ~~~~~~~~~~~~~~~~~~~~~~~~~~
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 579)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 580) This directory also exposes timings for a number of internal operations, with
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 581) separate files for average duration, average frequency, last occurrence and max
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 582) duration: garbage collection, btree read, btree node sorts and btree splits.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 583)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 584) active_journal_entries
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 585) Number of journal entries that are newer than the index.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 586)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 587) btree_nodes
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 588) Total nodes in the btree.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 589)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 590) btree_used_percent
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 591) Average fraction of btree in use.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 592)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 593) bset_tree_stats
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 594) Statistics about the auxiliary search trees
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 595)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 596) btree_cache_max_chain
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 597) Longest chain in the btree node cache's hash table
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 598)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 599) cache_read_races
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 600) Counts instances where while data was being read from the cache, the bucket
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 601) was reused and invalidated - i.e. where the pointer was stale after the read
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 602) completed. When this occurs the data is reread from the backing device.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 603)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 604) trigger_gc
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 605) Writing to this file forces garbage collection to run.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 606)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 607) Sysfs - Cache device
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 608) ~~~~~~~~~~~~~~~~~~~~
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 609)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 610) Available at /sys/block/<cdev>/bcache
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 611)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 612) block_size
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 613) Minimum granularity of writes - should match hardware sector size.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 614)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 615) btree_written
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 616) Sum of all btree writes, in (kilo/mega/giga) bytes
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 617)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 618) bucket_size
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 619) Size of buckets
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 620)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 621) cache_replacement_policy
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 622) One of either lru, fifo or random.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 623)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 624) discard
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 625) Boolean; if on a discard/TRIM will be issued to each bucket before it is
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 626) reused. Defaults to off, since SATA TRIM is an unqueued command (and thus
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 627) slow).
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 628)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 629) freelist_percent
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 630) Size of the freelist as a percentage of nbuckets. Can be written to to
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 631) increase the number of buckets kept on the freelist, which lets you
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 632) artificially reduce the size of the cache at runtime. Mostly for testing
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 633) purposes (i.e. testing how different size caches affect your hit rate), but
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 634) since buckets are discarded when they move on to the freelist will also make
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 635) the SSD's garbage collection easier by effectively giving it more reserved
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 636) space.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 637)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 638) io_errors
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 639) Number of errors that have occurred, decayed by io_error_halflife.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 640)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 641) metadata_written
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 642) Sum of all non data writes (btree writes and all other metadata).
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 643)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 644) nbuckets
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 645) Total buckets in this cache
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 646)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 647) priority_stats
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 648) Statistics about how recently data in the cache has been accessed.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 649) This can reveal your working set size. Unused is the percentage of
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 650) the cache that doesn't contain any data. Metadata is bcache's
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 651) metadata overhead. Average is the average priority of cache buckets.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 652) Next is a list of quantiles with the priority threshold of each.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 653)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 654) written
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 655) Sum of all data that has been written to the cache; comparison with
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 656) btree_written gives the amount of write inflation in bcache.
Orange Pi5 kernel
Deprecated Linux kernel 5.10.110 for OrangePi 5/5B/5+ boards
3 Commits
0 Branches
0 Tags