1 Guidance for writing policies
2 =============================
4 Try to keep transactionality out of it. The core is careful to
5 avoid asking about anything that is migrating. This is a pain, but
6 makes it easier to write the policies.
8 Mappings are loaded into the policy at construction time.
10 Every bio that is mapped by the target is referred to the policy.
11 The policy can return a simple HIT or MISS or issue a migration.
13 Currently there's no way for the policy to issue background work,
14 e.g. to start writing back dirty blocks that are going to be evicted
17 Because we map bios, rather than requests it's easy for the policy
18 to get fooled by many small bios. For this reason the core target
19 issues periodic ticks to the policy. It's suggested that the policy
20 doesn't update states (eg, hit counts) for a block more than once
21 for each tick. The core ticks by watching bios complete, and so
22 trying to see when the io scheduler has let the ios run.
25 Overview of supplied cache replacement policies
26 ===============================================
31 This policy is now an alias for smq (see below).
33 The following tunables are accepted, but have no effect:
35 'sequential_threshold <#nr_sequential_ios>'
36 'random_threshold <#nr_random_ios>'
37 'read_promote_adjustment <value>'
38 'write_promote_adjustment <value>'
39 'discard_promote_adjustment <value>'
41 Stochastic multiqueue (smq)
42 ---------------------------
44 This policy is the default.
46 The stochastic multi-queue (smq) policy addresses some of the problems
47 with the multiqueue (mq) policy.
49 The smq policy (vs mq) offers the promise of less memory utilization,
50 improved performance and increased adaptability in the face of changing
51 workloads. smq also does not have any cumbersome tuning knobs.
53 Users may switch from "mq" to "smq" simply by appropriately reloading a
54 DM table that is using the cache target. Doing so will cause all of the
55 mq policy's hints to be dropped. Also, performance of the cache may
56 degrade slightly until smq recalculates the origin device's hotspots
57 that should be cached.
60 The mq policy used a lot of memory; 88 bytes per cache block on a 64
63 smq uses 28bit indexes to implement its data structures rather than
64 pointers. It avoids storing an explicit hit count for each block. It
65 has a 'hotspot' queue, rather than a pre-cache, which uses a quarter of
66 the entries (each hotspot block covers a larger area than a single
69 All this means smq uses ~25bytes per cache block. Still a lot of
70 memory, but a substantial improvement nontheless.
73 mq placed entries in different levels of the multiqueue structures
74 based on their hit count (~ln(hit count)). This meant the bottom
75 levels generally had the most entries, and the top ones had very
76 few. Having unbalanced levels like this reduced the efficacy of the
79 smq does not maintain a hit count, instead it swaps hit entries with
80 the least recently used entry from the level above. The overall
81 ordering being a side effect of this stochastic process. With this
82 scheme we can decide how many entries occupy each multiqueue level,
83 resulting in better promotion/demotion decisions.
86 The mq policy maintained a hit count for each cache block. For a
87 different block to get promoted to the cache its hit count has to
88 exceed the lowest currently in the cache. This meant it could take a
89 long time for the cache to adapt between varying IO patterns.
91 smq doesn't maintain hit counts, so a lot of this problem just goes
92 away. In addition it tracks performance of the hotspot queue, which
93 is used to decide which blocks to promote. If the hotspot queue is
94 performing badly then it starts moving entries more quickly between
95 levels. This lets it adapt to new IO patterns very quickly.
98 Testing smq shows substantially better performance than mq.
103 The cleaner writes back all dirty blocks in a cache to decommission it.
108 The syntax for a table is:
109 cache <metadata dev> <cache dev> <origin dev> <block size>
110 <#feature_args> [<feature arg>]*
111 <policy> <#policy_args> [<policy arg>]*
113 The syntax to send a message using the dmsetup command is:
114 dmsetup message <mapped device> 0 sequential_threshold 1024
115 dmsetup message <mapped device> 0 random_threshold 8
118 dmsetup create blah --table "0 268435456 cache /dev/sdb /dev/sdc \
119 /dev/sdd 512 0 mq 4 sequential_threshold 1024 random_threshold 8"
120 creates a 128GB large mapped device named 'blah' with the
121 sequential threshold set to 1024 and the random_threshold set to 8.