1===== 2Cache 3===== 4 5Introduction 6============ 7 8dm-cache is a device mapper target written by Joe Thornber, Heinz 9Mauelshagen, and Mike Snitzer. 10 11It aims to improve performance of a block device (eg, a spindle) by 12dynamically migrating some of its data to a faster, smaller device 13(eg, an SSD). 14 15This device-mapper solution allows us to insert this caching at 16different levels of the dm stack, for instance above the data device for 17a thin-provisioning pool. Caching solutions that are integrated more 18closely with the virtual memory system should give better performance. 19 20The target reuses the metadata library used in the thin-provisioning 21library. 22 23The decision as to what data to migrate and when is left to a plug-in 24policy module. Several of these have been written as we experiment, 25and we hope other people will contribute others for specific io 26scenarios (eg. a vm image server). 27 28Glossary 29======== 30 31 Migration 32 Movement of the primary copy of a logical block from one 33 device to the other. 34 Promotion 35 Migration from slow device to fast device. 36 Demotion 37 Migration from fast device to slow device. 38 39The origin device always contains a copy of the logical block, which 40may be out of date or kept in sync with the copy on the cache device 41(depending on policy). 42 43Design 44====== 45 46Sub-devices 47----------- 48 49The target is constructed by passing three devices to it (along with 50other parameters detailed later): 51 521. An origin device - the big, slow one. 53 542. A cache device - the small, fast one. 55 563. A small metadata device - records which blocks are in the cache, 57 which are dirty, and extra hints for use by the policy object. 58 This information could be put on the cache device, but having it 59 separate allows the volume manager to configure it differently, 60 e.g. as a mirror for extra robustness. This metadata device may only 61 be used by a single cache device. 62 63Fixed block size 64---------------- 65 66The origin is divided up into blocks of a fixed size. This block size 67is configurable when you first create the cache. Typically we've been 68using block sizes of 256KB - 1024KB. The block size must be between 64 69sectors (32KB) and 2097152 sectors (1GB) and a multiple of 64 sectors (32KB). 70 71Having a fixed block size simplifies the target a lot. But it is 72something of a compromise. For instance, a small part of a block may be 73getting hit a lot, yet the whole block will be promoted to the cache. 74So large block sizes are bad because they waste cache space. And small 75block sizes are bad because they increase the amount of metadata (both 76in core and on disk). 77 78Cache operating modes 79--------------------- 80 81The cache has three operating modes: writeback, writethrough and 82passthrough. 83 84If writeback, the default, is selected then a write to a block that is 85cached will go only to the cache and the block will be marked dirty in 86the metadata. 87 88If writethrough is selected then a write to a cached block will not 89complete until it has hit both the origin and cache devices. Clean 90blocks should remain clean. 91 92If passthrough is selected, useful when the cache contents are not known 93to be coherent with the origin device, then all reads are served from 94the origin device (all reads miss the cache) and all writes are 95forwarded to the origin device; additionally, write hits cause cache 96block invalidates. To enable passthrough mode the cache must be clean. 97Passthrough mode allows a cache device to be activated without having to 98worry about coherency. Coherency that exists is maintained, although 99the cache will gradually cool as writes take place. If the coherency of 100the cache can later be verified, or established through use of the 101"invalidate_cblocks" message, the cache device can be transitioned to 102writethrough or writeback mode while still warm. Otherwise, the cache 103contents can be discarded prior to transitioning to the desired 104operating mode. 105 106A simple cleaner policy is provided, which will clean (write back) all 107dirty blocks in a cache. Useful for decommissioning a cache or when 108shrinking a cache. Shrinking the cache's fast device requires all cache 109blocks, in the area of the cache being removed, to be clean. If the 110area being removed from the cache still contains dirty blocks the resize 111will fail. Care must be taken to never reduce the volume used for the 112cache's fast device until the cache is clean. This is of particular 113importance if writeback mode is used. Writethrough and passthrough 114modes already maintain a clean cache. Future support to partially clean 115the cache, above a specified threshold, will allow for keeping the cache 116warm and in writeback mode during resize. 117 118Migration throttling 119-------------------- 120 121Migrating data between the origin and cache device uses bandwidth. 122The user can set a throttle to prevent more than a certain amount of 123migration occurring at any one time. Currently we're not taking any 124account of normal io traffic going to the devices. More work needs 125doing here to avoid migrating during those peak io moments. 126 127For the time being, a message "migration_threshold <#sectors>" 128can be used to set the maximum number of sectors being migrated, 129the default being 2048 sectors (1MB). 130 131Updating on-disk metadata 132------------------------- 133 134On-disk metadata is committed every time a FLUSH or FUA bio is written. 135If no such requests are made then commits will occur every second. This 136means the cache behaves like a physical disk that has a volatile write 137cache. If power is lost you may lose some recent writes. The metadata 138should always be consistent in spite of any crash. 139 140The 'dirty' state for a cache block changes far too frequently for us 141to keep updating it on the fly. So we treat it as a hint. In normal 142operation it will be written when the dm device is suspended. If the 143system crashes all cache blocks will be assumed dirty when restarted. 144 145Per-block policy hints 146---------------------- 147 148Policy plug-ins can store a chunk of data per cache block. It's up to 149the policy how big this chunk is, but it should be kept small. Like the 150dirty flags this data is lost if there's a crash so a safe fallback 151value should always be possible. 152 153Policy hints affect performance, not correctness. 154 155Policy messaging 156---------------- 157 158Policies will have different tunables, specific to each one, so we 159need a generic way of getting and setting these. Device-mapper 160messages are used. Refer to cache-policies.txt. 161 162Discard bitset resolution 163------------------------- 164 165We can avoid copying data during migration if we know the block has 166been discarded. A prime example of this is when mkfs discards the 167whole block device. We store a bitset tracking the discard state of 168blocks. However, we allow this bitset to have a different block size 169from the cache blocks. This is because we need to track the discard 170state for all of the origin device (compare with the dirty bitset 171which is just for the smaller cache device). 172 173Target interface 174================ 175 176Constructor 177----------- 178 179 :: 180 181 cache <metadata dev> <cache dev> <origin dev> <block size> 182 <#feature args> [<feature arg>]* 183 <policy> <#policy args> [policy args]* 184 185 ================ ======================================================= 186 metadata dev fast device holding the persistent metadata 187 cache dev fast device holding cached data blocks 188 origin dev slow device holding original data blocks 189 block size cache unit size in sectors 190 191 #feature args number of feature arguments passed 192 feature args writethrough or passthrough (The default is writeback.) 193 194 policy the replacement policy to use 195 #policy args an even number of arguments corresponding to 196 key/value pairs passed to the policy 197 policy args key/value pairs passed to the policy 198 E.g. 'sequential_threshold 1024' 199 See cache-policies.txt for details. 200 ================ ======================================================= 201 202Optional feature arguments are: 203 204 205 ==================== ======================================================== 206 writethrough write through caching that prohibits cache block 207 content from being different from origin block content. 208 Without this argument, the default behaviour is to write 209 back cache block contents later for performance reasons, 210 so they may differ from the corresponding origin blocks. 211 212 passthrough a degraded mode useful for various cache coherency 213 situations (e.g., rolling back snapshots of 214 underlying storage). Reads and writes always go to 215 the origin. If a write goes to a cached origin 216 block, then the cache block is invalidated. 217 To enable passthrough mode the cache must be clean. 218 219 metadata2 use version 2 of the metadata. This stores the dirty 220 bits in a separate btree, which improves speed of 221 shutting down the cache. 222 223 no_discard_passdown disable passing down discards from the cache 224 to the origin's data device. 225 ==================== ======================================================== 226 227A policy called 'default' is always registered. This is an alias for 228the policy we currently think is giving best all round performance. 229 230As the default policy could vary between kernels, if you are relying on 231the characteristics of a specific policy, always request it by name. 232 233Status 234------ 235 236:: 237 238 <metadata block size> <#used metadata blocks>/<#total metadata blocks> 239 <cache block size> <#used cache blocks>/<#total cache blocks> 240 <#read hits> <#read misses> <#write hits> <#write misses> 241 <#demotions> <#promotions> <#dirty> <#features> <features>* 242 <#core args> <core args>* <policy name> <#policy args> <policy args>* 243 <cache metadata mode> 244 245 246========================= ===================================================== 247metadata block size Fixed block size for each metadata block in 248 sectors 249#used metadata blocks Number of metadata blocks used 250#total metadata blocks Total number of metadata blocks 251cache block size Configurable block size for the cache device 252 in sectors 253#used cache blocks Number of blocks resident in the cache 254#total cache blocks Total number of cache blocks 255#read hits Number of times a READ bio has been mapped 256 to the cache 257#read misses Number of times a READ bio has been mapped 258 to the origin 259#write hits Number of times a WRITE bio has been mapped 260 to the cache 261#write misses Number of times a WRITE bio has been 262 mapped to the origin 263#demotions Number of times a block has been removed 264 from the cache 265#promotions Number of times a block has been moved to 266 the cache 267#dirty Number of blocks in the cache that differ 268 from the origin 269#feature args Number of feature args to follow 270feature args 'writethrough' (optional) 271#core args Number of core arguments (must be even) 272core args Key/value pairs for tuning the core 273 e.g. migration_threshold 274policy name Name of the policy 275#policy args Number of policy arguments to follow (must be even) 276policy args Key/value pairs e.g. sequential_threshold 277cache metadata mode ro if read-only, rw if read-write 278 279 In serious cases where even a read-only mode is 280 deemed unsafe no further I/O will be permitted and 281 the status will just contain the string 'Fail'. 282 The userspace recovery tools should then be used. 283needs_check 'needs_check' if set, '-' if not set 284 A metadata operation has failed, resulting in the 285 needs_check flag being set in the metadata's 286 superblock. The metadata device must be 287 deactivated and checked/repaired before the 288 cache can be made fully operational again. 289 '-' indicates needs_check is not set. 290========================= ===================================================== 291 292Messages 293-------- 294 295Policies will have different tunables, specific to each one, so we 296need a generic way of getting and setting these. Device-mapper 297messages are used. (A sysfs interface would also be possible.) 298 299The message format is:: 300 301 <key> <value> 302 303E.g.:: 304 305 dmsetup message my_cache 0 sequential_threshold 1024 306 307 308Invalidation is removing an entry from the cache without writing it 309back. Cache blocks can be invalidated via the invalidate_cblocks 310message, which takes an arbitrary number of cblock ranges. Each cblock 311range's end value is "one past the end", meaning 5-10 expresses a range 312of values from 5 to 9. Each cblock must be expressed as a decimal 313value, in the future a variant message that takes cblock ranges 314expressed in hexadecimal may be needed to better support efficient 315invalidation of larger caches. The cache must be in passthrough mode 316when invalidate_cblocks is used:: 317 318 invalidate_cblocks [<cblock>|<cblock begin>-<cblock end>]* 319 320E.g.:: 321 322 dmsetup message my_cache 0 invalidate_cblocks 2345 3456-4567 5678-6789 323 324Examples 325======== 326 327The test suite can be found here: 328 329https://github.com/jthornber/device-mapper-test-suite 330 331:: 332 333 dmsetup create my_cache --table '0 41943040 cache /dev/mapper/metadata \ 334 /dev/mapper/ssd /dev/mapper/origin 512 1 writeback default 0' 335 dmsetup create my_cache --table '0 41943040 cache /dev/mapper/metadata \ 336 /dev/mapper/ssd /dev/mapper/origin 1024 1 writeback \ 337 mq 4 sequential_threshold 1024 random_threshold 8' 338