| blob | 770267af5b3e2c992eb081d2827a77acccd1ae7e |
1 ==========================
2 General Filesystem Caching
3 ==========================
5 ========
6 OVERVIEW
7 ========
9 This facility is a general purpose cache for network filesystems, though it
10 could be used for caching other things such as ISO9660 filesystems too.
12 FS-Cache mediates between cache backends (such as CacheFS) and network
13 filesystems:
15 +---------+
16 | | +--------------+
17 | NFS |--+ | |
18 | | | +-->| CacheFS |
19 +---------+ | +----------+ | | /dev/hda5 |
20 | | | | +--------------+
21 +---------+ +-->| | |
22 | | | |--+
23 | AFS |----->| FS-Cache |
24 | | | |--+
25 +---------+ +-->| | |
26 | | | | +--------------+
27 +---------+ | +----------+ | | |
28 | | | +-->| CacheFiles |
29 | ISOFS |--+ | /var/cache |
30 | | +--------------+
31 +---------+
33 Or to look at it another way, FS-Cache is a module that provides a caching
34 facility to a network filesystem such that the cache is transparent to the
35 user:
37 +---------+
38 | |
39 | Server |
40 | |
41 +---------+
42 | NETWORK
43 ~~~~~|~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
44 |
45 | +----------+
46 V | |
47 +---------+ | |
48 | | | |
49 | NFS |----->| FS-Cache |
50 | | | |--+
51 +---------+ | | | +--------------+ +--------------+
52 | | | | | | | |
53 V +----------+ +-->| CacheFiles |-->| Ext3 |
54 +---------+ | /var/cache | | /dev/sda6 |
55 | | +--------------+ +--------------+
56 | VFS | ^ ^
57 | | | |
58 +---------+ +--------------+ |
59 | KERNEL SPACE | |
60 ~~~~~|~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~|~~~~~~|~~~~
61 | USER SPACE | |
62 V | |
63 +---------+ +--------------+
64 | | | |
65 | Process | | cachefilesd |
66 | | | |
67 +---------+ +--------------+
70 FS-Cache does not follow the idea of completely loading every netfs file
71 opened in its entirety into a cache before permitting it to be accessed and
72 then serving the pages out of that cache rather than the netfs inode because:
74 (1) It must be practical to operate without a cache.
76 (2) The size of any accessible file must not be limited to the size of the
77 cache.
79 (3) The combined size of all opened files (this includes mapped libraries)
80 must not be limited to the size of the cache.
82 (4) The user should not be forced to download an entire file just to do a
83 one-off access of a small portion of it (such as might be done with the
84 "file" program).
86 It instead serves the cache out in PAGE_SIZE chunks as and when requested by
87 the netfs('s) using it.
90 FS-Cache provides the following facilities:
92 (1) More than one cache can be used at once. Caches can be selected
93 explicitly by use of tags.
95 (2) Caches can be added / removed at any time.
97 (3) The netfs is provided with an interface that allows either party to
98 withdraw caching facilities from a file (required for (2)).
100 (4) The interface to the netfs returns as few errors as possible, preferring
101 rather to let the netfs remain oblivious.
103 (5) Cookies are used to represent indices, files and other objects to the
104 netfs. The simplest cookie is just a NULL pointer - indicating nothing
105 cached there.
107 (6) The netfs is allowed to propose - dynamically - any index hierarchy it
108 desires, though it must be aware that the index search function is
109 recursive, stack space is limited, and indices can only be children of
110 indices.
112 (7) Data I/O is done direct to and from the netfs's pages. The netfs
113 indicates that page A is at index B of the data-file represented by cookie
114 C, and that it should be read or written. The cache backend may or may
115 not start I/O on that page, but if it does, a netfs callback will be
116 invoked to indicate completion. The I/O may be either synchronous or
117 asynchronous.
119 (8) Cookies can be "retired" upon release. At this point FS-Cache will mark
120 them as obsolete and the index hierarchy rooted at that point will get
121 recycled.
123 (9) The netfs provides a "match" function for index searches. In addition to
124 saying whether a match was made or not, this can also specify that an
125 entry should be updated or deleted.
127 (10) As much as possible is done asynchronously.
130 FS-Cache maintains a virtual indexing tree in which all indices, files, objects
131 and pages are kept. Bits of this tree may actually reside in one or more
132 caches.
134 FSDEF
135 |
136 +------------------------------------+
137 | |
138 NFS AFS
139 | |
140 +--------------------------+ +-----------+
141 | | | |
142 homedir mirror afs.org redhat.com
143 | | |
144 +------------+ +---------------+ +----------+
145 | | | | | |
146 00001 00002 00007 00125 vol00001 vol00002
147 | | | | |
148 +---+---+ +-----+ +---+ +------+------+ +-----+----+
149 | | | | | | | | | | | | |
150 PG0 PG1 PG2 PG0 XATTR PG0 PG1 DIRENT DIRENT DIRENT R/W R/O Bak
151 | |
152 PG0 +-------+
153 | |
154 00001 00003
155 |
156 +---+---+
157 | | |
158 PG0 PG1 PG2
160 In the example above, you can see two netfs's being backed: NFS and AFS. These
161 have different index hierarchies:
163 (*) The NFS primary index contains per-server indices. Each server index is
164 indexed by NFS file handles to get data file objects. Each data file
165 objects can have an array of pages, but may also have further child
166 objects, such as extended attributes and directory entries. Extended
167 attribute objects themselves have page-array contents.
169 (*) The AFS primary index contains per-cell indices. Each cell index contains
170 per-logical-volume indices. Each of volume index contains up to three
171 indices for the read-write, read-only and backup mirrors of those volumes.
172 Each of these contains vnode data file objects, each of which contains an
173 array of pages.
175 The very top index is the FS-Cache master index in which individual netfs's
176 have entries.
178 Any index object may reside in more than one cache, provided it only has index
179 children. Any index with non-index object children will be assumed to only
180 reside in one cache.
183 The netfs API to FS-Cache can be found in:
185 Documentation/filesystems/caching/netfs-api.txt
187 The cache backend API to FS-Cache can be found in:
189 Documentation/filesystems/caching/backend-api.txt
191 A description of the internal representations and object state machine can be
192 found in:
194 Documentation/filesystems/caching/object.txt
197 =======================
198 STATISTICAL INFORMATION
199 =======================
201 If FS-Cache is compiled with the following options enabled:
203 CONFIG_FSCACHE_STATS=y
204 CONFIG_FSCACHE_HISTOGRAM=y
206 then it will gather certain statistics and display them through a number of
207 proc files.
209 (*) /proc/fs/fscache/stats
211 This shows counts of a number of events that can happen in FS-Cache:
213 CLASS EVENT MEANING
214 ======= ======= =======================================================
215 Cookies idx=N Number of index cookies allocated
216 dat=N Number of data storage cookies allocated
217 spc=N Number of special cookies allocated
218 Objects alc=N Number of objects allocated
219 nal=N Number of object allocation failures
220 avl=N Number of objects that reached the available state
221 ded=N Number of objects that reached the dead state
222 ChkAux non=N Number of objects that didn't have a coherency check
223 ok=N Number of objects that passed a coherency check
224 upd=N Number of objects that needed a coherency data update
225 obs=N Number of objects that were declared obsolete
226 Pages mrk=N Number of pages marked as being cached
227 unc=N Number of uncache page requests seen
228 Acquire n=N Number of acquire cookie requests seen
229 nul=N Number of acq reqs given a NULL parent
230 noc=N Number of acq reqs rejected due to no cache available
231 ok=N Number of acq reqs succeeded
232 nbf=N Number of acq reqs rejected due to error
233 oom=N Number of acq reqs failed on ENOMEM
234 Lookups n=N Number of lookup calls made on cache backends
235 neg=N Number of negative lookups made
236 pos=N Number of positive lookups made
237 crt=N Number of objects created by lookup
238 tmo=N Number of lookups timed out and requeued
239 Updates n=N Number of update cookie requests seen
240 nul=N Number of upd reqs given a NULL parent
241 run=N Number of upd reqs granted CPU time
242 Relinqs n=N Number of relinquish cookie requests seen
243 nul=N Number of rlq reqs given a NULL parent
244 wcr=N Number of rlq reqs waited on completion of creation
245 AttrChg n=N Number of attribute changed requests seen
246 ok=N Number of attr changed requests queued
247 nbf=N Number of attr changed rejected -ENOBUFS
248 oom=N Number of attr changed failed -ENOMEM
249 run=N Number of attr changed ops given CPU time
250 Allocs n=N Number of allocation requests seen
251 ok=N Number of successful alloc reqs
252 wt=N Number of alloc reqs that waited on lookup completion
253 nbf=N Number of alloc reqs rejected -ENOBUFS
254 int=N Number of alloc reqs aborted -ERESTARTSYS
255 ops=N Number of alloc reqs submitted
256 owt=N Number of alloc reqs waited for CPU time
257 abt=N Number of alloc reqs aborted due to object death
258 Retrvls n=N Number of retrieval (read) requests seen
259 ok=N Number of successful retr reqs
260 wt=N Number of retr reqs that waited on lookup completion
261 nod=N Number of retr reqs returned -ENODATA
262 nbf=N Number of retr reqs rejected -ENOBUFS
263 int=N Number of retr reqs aborted -ERESTARTSYS
264 oom=N Number of retr reqs failed -ENOMEM
265 ops=N Number of retr reqs submitted
266 owt=N Number of retr reqs waited for CPU time
267 abt=N Number of retr reqs aborted due to object death
268 Stores n=N Number of storage (write) requests seen
269 ok=N Number of successful store reqs
270 agn=N Number of store reqs on a page already pending storage
271 nbf=N Number of store reqs rejected -ENOBUFS
272 oom=N Number of store reqs failed -ENOMEM
273 ops=N Number of store reqs submitted
274 run=N Number of store reqs granted CPU time
275 pgs=N Number of pages given store req processing time
276 rxd=N Number of store reqs deleted from tracking tree
277 olm=N Number of store reqs over store limit
278 VmScan nos=N Number of release reqs against pages with no pending store
279 gon=N Number of release reqs against pages stored by time lock granted
280 bsy=N Number of release reqs ignored due to in-progress store
281 can=N Number of page stores cancelled due to release req
282 Ops pend=N Number of times async ops added to pending queues
283 run=N Number of times async ops given CPU time
284 enq=N Number of times async ops queued for processing
285 can=N Number of async ops cancelled
286 rej=N Number of async ops rejected due to object lookup/create failure
287 dfr=N Number of async ops queued for deferred release
288 rel=N Number of async ops released
289 gc=N Number of deferred-release async ops garbage collected
290 CacheOp alo=N Number of in-progress alloc_object() cache ops
291 luo=N Number of in-progress lookup_object() cache ops
292 luc=N Number of in-progress lookup_complete() cache ops
293 gro=N Number of in-progress grab_object() cache ops
294 upo=N Number of in-progress update_object() cache ops
295 dro=N Number of in-progress drop_object() cache ops
296 pto=N Number of in-progress put_object() cache ops
297 syn=N Number of in-progress sync_cache() cache ops
298 atc=N Number of in-progress attr_changed() cache ops
299 rap=N Number of in-progress read_or_alloc_page() cache ops
300 ras=N Number of in-progress read_or_alloc_pages() cache ops
301 alp=N Number of in-progress allocate_page() cache ops
302 als=N Number of in-progress allocate_pages() cache ops
303 wrp=N Number of in-progress write_page() cache ops
304 ucp=N Number of in-progress uncache_page() cache ops
305 dsp=N Number of in-progress dissociate_pages() cache ops
308 (*) /proc/fs/fscache/histogram
310 cat /proc/fs/fscache/histogram
311 JIFS SECS OBJ INST OP RUNS OBJ RUNS RETRV DLY RETRIEVLS
312 ===== ===== ========= ========= ========= ========= =========
314 This shows the breakdown of the number of times each amount of time
315 between 0 jiffies and HZ-1 jiffies a variety of tasks took to run. The
316 columns are as follows:
318 COLUMN TIME MEASUREMENT
319 ======= =======================================================
320 OBJ INST Length of time to instantiate an object
321 OP RUNS Length of time a call to process an operation took
322 OBJ RUNS Length of time a call to process an object event took
323 RETRV DLY Time between an requesting a read and lookup completing
324 RETRIEVLS Time between beginning and end of a retrieval
326 Each row shows the number of events that took a particular range of times.
327 Each step is 1 jiffy in size. The JIFS column indicates the particular
328 jiffy range covered, and the SECS field the equivalent number of seconds.
331 ===========
332 OBJECT LIST
333 ===========
335 If CONFIG_FSCACHE_OBJECT_LIST is enabled, the FS-Cache facility will maintain a
336 list of all the objects currently allocated and allow them to be viewed
337 through:
339 /proc/fs/fscache/objects
341 This will look something like:
343 [root@andromeda ~]# head /proc/fs/fscache/objects
344 OBJECT PARENT STAT CHLDN OPS OOP IPR EX READS EM EV F S | NETFS_COOKIE_DEF TY FL NETFS_DATA OBJECT_KEY, AUX_DATA
345 ======== ======== ==== ===== === === === == ===== == == = = | ================ == == ================ ================
346 17e4b 2 ACTV 0 0 0 0 0 0 7b 4 0 0 | NFS.fh DT 0 ffff88001dd82820 010006017edcf8bbc93b43298fdfbe71e50b57b13a172c0117f38472, e567634700000000000000000000000063f2404a000000000000000000000000c9030000000000000000000063f2404a
347 1693a 2 ACTV 0 0 0 0 0 0 7b 4 0 0 | NFS.fh DT 0 ffff88002db23380 010006017edcf8bbc93b43298fdfbe71e50b57b1e0162c01a2df0ea6, 420ebc4a000000000000000000000000420ebc4a0000000000000000000000000e1801000000000000000000420ebc4a
349 where the first set of columns before the '|' describe the object:
351 COLUMN DESCRIPTION
352 ======= ===============================================================
353 OBJECT Object debugging ID (appears as OBJ%x in some debug messages)
354 PARENT Debugging ID of parent object
355 STAT Object state
356 CHLDN Number of child objects of this object
357 OPS Number of outstanding operations on this object
358 OOP Number of outstanding child object management operations
359 IPR
360 EX Number of outstanding exclusive operations
361 READS Number of outstanding read operations
362 EM Object's event mask
363 EV Events raised on this object
364 F Object flags
365 S Object work item busy state mask (1:pending 2:running)
367 and the second set of columns describe the object's cookie, if present:
369 COLUMN DESCRIPTION
370 =============== =======================================================
371 NETFS_COOKIE_DEF Name of netfs cookie definition
372 TY Cookie type (IX - index, DT - data, hex - special)
373 FL Cookie flags
374 NETFS_DATA Netfs private data stored in the cookie
375 OBJECT_KEY Object key } 1 column, with separating comma
376 AUX_DATA Object aux data } presence may be configured
378 The data shown may be filtered by attaching the a key to an appropriate keyring
379 before viewing the file. Something like:
381 keyctl add user fscache:objlist <restrictions> @s
383 where <restrictions> are a selection of the following letters:
385 K Show hexdump of object key (don't show if not given)
386 A Show hexdump of object aux data (don't show if not given)
388 and the following paired letters:
390 C Show objects that have a cookie
391 c Show objects that don't have a cookie
392 B Show objects that are busy
393 b Show objects that aren't busy
394 W Show objects that have pending writes
395 w Show objects that don't have pending writes
396 R Show objects that have outstanding reads
397 r Show objects that don't have outstanding reads
398 S Show objects that have work queued
399 s Show objects that don't have work queued
401 If neither side of a letter pair is given, then both are implied. For example:
403 keyctl add user fscache:objlist KB @s
405 shows objects that are busy, and lists their object keys, but does not dump
406 their auxiliary data. It also implies "CcWwRrSs", but as 'B' is given, 'b' is
407 not implied.
409 By default all objects and all fields will be shown.
412 =========
413 DEBUGGING
414 =========
416 If CONFIG_FSCACHE_DEBUG is enabled, the FS-Cache facility can have runtime
417 debugging enabled by adjusting the value in:
419 /sys/module/fscache/parameters/debug
421 This is a bitmask of debugging streams to enable:
423 BIT VALUE STREAM POINT
424 ======= ======= =============================== =======================
425 0 1 Cache management Function entry trace
426 1 2 Function exit trace
427 2 4 General
428 3 8 Cookie management Function entry trace
429 4 16 Function exit trace
430 5 32 General
431 6 64 Page handling Function entry trace
432 7 128 Function exit trace
433 8 256 General
434 9 512 Operation management Function entry trace
435 10 1024 Function exit trace
436 11 2048 General
438 The appropriate set of values should be OR'd together and the result written to
439 the control file. For example:
441 echo $((1|8|64)) >/sys/module/fscache/parameters/debug
443 will turn on all function entry debugging.