1Protocol 2-------- 3 4Clients of memcached communicate with server through TCP connections. 5(A UDP interface is also available; details are below under "UDP 6protocol.") A given running memcached server listens on some 7(configurable) port; clients connect to that port, send commands to 8the server, read responses, and eventually close the connection. 9 10There is no need to send any command to end the session. A client may 11just close the connection at any moment it no longer needs it. Note, 12however, that clients are encouraged to cache their connections rather 13than reopen them every time they need to store or retrieve data. This 14is because memcached is especially designed to work very efficiently 15with a very large number (many hundreds, more than a thousand if 16necessary) of open connections. Caching connections will eliminate the 17overhead associated with establishing a TCP connection (the overhead 18of preparing for a new connection on the server side is insignificant 19compared to this). 20 21There are two kinds of data sent in the memcache protocol: text lines 22and unstructured data. Text lines are used for commands from clients 23and responses from servers. Unstructured data is sent when a client 24wants to store or retrieve data. The server will transmit back 25unstructured data in exactly the same way it received it, as a byte 26stream. The server doesn't care about byte order issues in 27unstructured data and isn't aware of them. There are no limitations on 28characters that may appear in unstructured data; however, the reader 29of such data (either a client or a server) will always know, from a 30preceding text line, the exact length of the data block being 31transmitted. 32 33Text lines are always terminated by \r\n. Unstructured data is _also_ 34terminated by \r\n, even though \r, \n or any other 8-bit characters 35may also appear inside the data. Therefore, when a client retrieves 36data from a server, it must use the length of the data block (which it 37will be provided with) to determine where the data block ends, and not 38the fact that \r\n follows the end of the data block, even though it 39does. 40 41Keys 42---- 43 44Data stored by memcached is identified with the help of a key. A key 45is a text string which should uniquely identify the data for clients 46that are interested in storing and retrieving it. Currently the 47length limit of a key is set at 250 characters (of course, normally 48clients wouldn't need to use such long keys); the key must not include 49control characters or whitespace. 50 51Commands 52-------- 53 54There are three types of commands. 55 56Storage commands (there are six: "set", "add", "replace", "append" 57"prepend" and "cas") ask the server to store some data identified by a 58key. The client sends a command line, and then a data block; after 59that the client expects one line of response, which will indicate 60success or failure. 61 62Retrieval commands (there are two: "get" and "gets") ask the server to 63retrieve data corresponding to a set of keys (one or more keys in one 64request). The client sends a command line, which includes all the 65requested keys; after that for each item the server finds it sends to 66the client one response line with information about the item, and one 67data block with the item's data; this continues until the server 68finished with the "END" response line. 69 70All other commands don't involve unstructured data. In all of them, 71the client sends one command line, and expects (depending on the 72command) either one line of response, or several lines of response 73ending with "END" on the last line. 74 75A command line always starts with the name of the command, followed by 76parameters (if any) delimited by whitespace. Command names are 77lower-case and are case-sensitive. 78 79Expiration times 80---------------- 81 82Some commands involve a client sending some kind of expiration time 83(relative to an item or to an operation requested by the client) to 84the server. In all such cases, the actual value sent may either be 85Unix time (number of seconds since January 1, 1970, as a 32-bit 86value), or a number of seconds starting from current time. In the 87latter case, this number of seconds may not exceed 60*60*24*30 (number 88of seconds in 30 days); if the number sent by a client is larger than 89that, the server will consider it to be real Unix time value rather 90than an offset from current time. 91 92 93Error strings 94------------- 95 96Each command sent by a client may be answered with an error string 97from the server. These error strings come in three types: 98 99- "ERROR\r\n" 100 101 means the client sent a nonexistent command name. 102 103- "CLIENT_ERROR <error>\r\n" 104 105 means some sort of client error in the input line, i.e. the input 106 doesn't conform to the protocol in some way. <error> is a 107 human-readable error string. 108 109- "SERVER_ERROR <error>\r\n" 110 111 means some sort of server error prevents the server from carrying 112 out the command. <error> is a human-readable error string. In cases 113 of severe server errors, which make it impossible to continue 114 serving the client (this shouldn't normally happen), the server will 115 close the connection after sending the error line. This is the only 116 case in which the server closes a connection to a client. 117 118 119In the descriptions of individual commands below, these error lines 120are not again specifically mentioned, but clients must allow for their 121possibility. 122 123 124Storage commands 125---------------- 126 127First, the client sends a command line which looks like this: 128 129<command name> <key> <flags> <exptime> <bytes> [noreply]\r\n 130cas <key> <flags> <exptime> <bytes> <cas unique> [noreply]\r\n 131 132- <command name> is "set", "add", "replace", "append" or "prepend" 133 134 "set" means "store this data". 135 136 "add" means "store this data, but only if the server *doesn't* already 137 hold data for this key". 138 139 "replace" means "store this data, but only if the server *does* 140 already hold data for this key". 141 142 "append" means "add this data to an existing key after existing data". 143 144 "prepend" means "add this data to an existing key before existing data". 145 146 The append and prepend commands do not accept flags or exptime. 147 They update existing data portions, and ignore new flag and exptime 148 settings. 149 150 "cas" is a check and set operation which means "store this data but 151 only if no one else has updated since I last fetched it." 152 153- <key> is the key under which the client asks to store the data 154 155- <flags> is an arbitrary 16-bit unsigned integer (written out in 156 decimal) that the server stores along with the data and sends back 157 when the item is retrieved. Clients may use this as a bit field to 158 store data-specific information; this field is opaque to the server. 159 Note that in memcached 1.2.1 and higher, flags may be 32-bits, instead 160 of 16, but you might want to restrict yourself to 16 bits for 161 compatibility with older versions. 162 163- <exptime> is expiration time. If it's 0, the item never expires 164 (although it may be deleted from the cache to make place for other 165 items). If it's non-zero (either Unix time or offset in seconds from 166 current time), it is guaranteed that clients will not be able to 167 retrieve this item after the expiration time arrives (measured by 168 server time). 169 170- <bytes> is the number of bytes in the data block to follow, *not* 171 including the delimiting \r\n. <bytes> may be zero (in which case 172 it's followed by an empty data block). 173 174- <cas unique> is a unique 64-bit value of an existing entry. 175 Clients should use the value returned from the "gets" command 176 when issuing "cas" updates. 177 178- "noreply" optional parameter instructs the server to not send the 179 reply. NOTE: if the request line is malformed, the server can't 180 parse "noreply" option reliably. In this case it may send the error 181 to the client, and not reading it on the client side will break 182 things. Client should construct only valid requests. 183 184After this line, the client sends the data block: 185 186<data block>\r\n 187 188- <data block> is a chunk of arbitrary 8-bit data of length <bytes> 189 from the previous line. 190 191After sending the command line and the data blockm the client awaits 192the reply, which may be: 193 194- "STORED\r\n", to indicate success. 195 196- "NOT_STORED\r\n" to indicate the data was not stored, but not 197because of an error. This normally means that the 198condition for an "add" or a "replace" command wasn't met. 199 200- "EXISTS\r\n" to indicate that the item you are trying to store with 201a "cas" command has been modified since you last fetched it. 202 203- "NOT_FOUND\r\n" to indicate that the item you are trying to store 204with a "cas" command did not exist. 205 206 207Retrieval command: 208------------------ 209 210The retrieval commands "get" and "gets" operates like this: 211 212get <key>*\r\n 213gets <key>*\r\n 214 215- <key>* means one or more key strings separated by whitespace. 216 217After this command, the client expects zero or more items, each of 218which is received as a text line followed by a data block. After all 219the items have been transmitted, the server sends the string 220 221"END\r\n" 222 223to indicate the end of response. 224 225Each item sent by the server looks like this: 226 227VALUE <key> <flags> <bytes> [<cas unique>]\r\n 228<data block>\r\n 229 230- <key> is the key for the item being sent 231 232- <flags> is the flags value set by the storage command 233 234- <bytes> is the length of the data block to follow, *not* including 235 its delimiting \r\n 236 237- <cas unique> is a unique 64-bit integer that uniquely identifies 238 this specific item. 239 240- <data block> is the data for this item. 241 242If some of the keys appearing in a retrieval request are not sent back 243by the server in the item list this means that the server does not 244hold items with such keys (because they were never stored, or stored 245but deleted to make space for more items, or expired, or explicitly 246deleted by a client). 247 248 249Deletion 250-------- 251 252The command "delete" allows for explicit deletion of items: 253 254delete <key> [noreply]\r\n 255 256- <key> is the key of the item the client wishes the server to delete 257 258- "noreply" optional parameter instructs the server to not send the 259 reply. See the note in Storage commands regarding malformed 260 requests. 261 262The response line to this command can be one of: 263 264- "DELETED\r\n" to indicate success 265 266- "NOT_FOUND\r\n" to indicate that the item with this key was not 267 found. 268 269See the "flush_all" command below for immediate invalidation 270of all existing items. 271 272 273Increment/Decrement 274------------------- 275 276Commands "incr" and "decr" are used to change data for some item 277in-place, incrementing or decrementing it. The data for the item is 278treated as decimal representation of a 64-bit unsigned integer. If 279the current data value does not conform to such a representation, the 280incr/decr commands return an error (memcached <= 1.2.6 treated the 281bogus value as if it were 0, leading to confusion). Also, the item 282must already exist for incr/decr to work; these commands won't pretend 283that a non-existent key exists with value 0; instead, they will fail. 284 285The client sends the command line: 286 287incr <key> <value> [noreply]\r\n 288 289or 290 291decr <key> <value> [noreply]\r\n 292 293- <key> is the key of the item the client wishes to change 294 295- <value> is the amount by which the client wants to increase/decrease 296the item. It is a decimal representation of a 64-bit unsigned integer. 297 298- "noreply" optional parameter instructs the server to not send the 299 reply. See the note in Storage commands regarding malformed 300 requests. 301 302The response will be one of: 303 304- "NOT_FOUND\r\n" to indicate the item with this value was not found 305 306- <value>\r\n , where <value> is the new value of the item's data, 307 after the increment/decrement operation was carried out. 308 309Note that underflow in the "decr" command is caught: if a client tries 310to decrease the value below 0, the new value will be 0. Overflow in 311the "incr" command will wrap around the 64 bit mark. 312 313Note also that decrementing a number such that it loses length isn't 314guaranteed to decrement its returned length. The number MAY be 315space-padded at the end, but this is purely an implementation 316optimization, so you also shouldn't rely on that. 317 318Touch 319----- 320 321The "touch" command is used to update the expiration time of an existing item 322without fetching it. 323 324touch <key> <exptime> [noreply]\r\n 325 326- <key> is the key of the item the client wishes the server to delete 327 328- <exptime> is expiration time. Works the same as with the update commands 329 (set/add/etc). This replaces the existing expiration time. If an existing 330 item were to expire in 10 seconds, but then was touched with an 331 expiration time of "20", the item would then expire in 20 seconds. 332 333- "noreply" optional parameter instructs the server to not send the 334 reply. See the note in Storage commands regarding malformed 335 requests. 336 337The response line to this command can be one of: 338 339- "TOUCHED\r\n" to indicate success 340 341- "NOT_FOUND\r\n" to indicate that the item with this key was not 342 found. 343 344Slabs Reassign 345-------------- 346 347NOTE: This command is subject to change as of this writing. 348 349The slabs reassign command is used to redistribute memory once a running 350instance has hit its limit. It might be desireable to have memory laid out 351differently than was automatically assigned after the server started. 352 353slabs reassign <source class> <dest class>\r\n 354 355- <source class> is an id number for the slab class to steal a page from 356 357A source class id of -1 means "pick from any valid class" 358 359- <dest class> is an id number for the slab class to move a page to 360 361The response line could be one of: 362 363- "OK" to indicate the page has been scheduled to move 364 365- "BUSY [message]" to indicate a page is already being processed, try again 366 later. 367 368- "BADCLASS [message]" a bad class id was specified 369 370- "NOSPARE [message]" source class has no spare pages 371 372- "NOTFULL [message]" dest class must be full to move new pages to it 373 374- "UNSAFE [message]" source class cannot move a page right now 375 376- "SAME [message]" must specify different source/dest ids. 377 378Slabs Automove 379-------------- 380 381NOTE: This command is subject to change as of this writing. 382 383The slabs automove command enables a background thread which decides on its 384own when to move memory between slab classes. Its implementation and options 385will likely be in flux for several versions. See the wiki/mailing list for 386more details. 387 388The automover can be enabled or disabled at runtime with this command. 389 390slabs automove <0|1> 391 392- 0|1|2 is the indicator on whether to enable the slabs automover or not. 393 394The response should always be "OK\r\n" 395 396- <0> means to set the thread on standby 397 398- <1> means to run the builtin slow algorithm to choose pages to move 399 400- <2> is a highly aggressive mode which causes pages to be moved every time 401 there is an eviction. It is not recommended to run for very long in this 402 mode unless your access patterns are very well understood. 403 404LRU_Crawler 405----------- 406 407NOTE: This command (and related commands) are subject to change as of this 408writing. 409 410The LRU Crawler is an optional background thread which will walk from the tail 411toward the head of requested slab classes, actively freeing memory for expired 412items. This is useful if you have a mix of items with both long and short 413TTL's, but aren't accessed very often. This system is not required for normal 414usage, and can add small amounts of latency and increase CPU usage. 415 416lru_crawler <enable|disable> 417 418- Enable or disable the LRU Crawler background thread. 419 420The response line could be one of: 421 422- "OK" to indicate the crawler has been started or stopped. 423 424- "ERROR [message]" something went wrong while enabling or disabling. 425 426lru_crawler sleep <microseconds> 427 428- The number of microseconds to sleep inbetween each item checked for 429 expiration. Smaller numbers will obviously impact the system more. 430 A value of "0" disables the sleep, "1000000" (one second) is the max. 431 432The response line could be one of: 433 434- "OK" 435 436- "CLIENT_ERROR [message]" indicating a format or bounds issue. 437 438lru_crawler tocrawl <32u> 439 440- The maximum number of items to inspect in a slab class per run request. This 441 allows you to avoid scanning all of very large slabs when it is unlikely to 442 find items to expire. 443 444The response line could be one of: 445 446- "OK" 447 448- "CLIENT_ERROR [message]" indicating a format or bound issue. 449 450lru_crawler crawl <classid,classid,classid|all> 451 452- Takes a single, or a list of, numeric classids (ie: 1,3,10). This instructs 453 the crawler to start at the tail of each of these classids and run to the 454 head. The crawler cannot be stopped or restarted until it completes the 455 previous request. 456 457 The special keyword "all" instructs it to crawl all slabs with items in 458 them. 459 460The response line could be one of: 461 462- "OK" to indicate successful launch. 463 464- "BUSY [message]" to indicate the crawler is already processing a request. 465 466- "BADCLASS [message]" to indicate an invalid class was specified. 467 468Statistics 469---------- 470 471The command "stats" is used to query the server about statistics it 472maintains and other internal data. It has two forms. Without 473arguments: 474 475stats\r\n 476 477it causes the server to output general-purpose statistics and 478settings, documented below. In the other form it has some arguments: 479 480stats <args>\r\n 481 482Depending on <args>, various internal data is sent by the server. The 483kinds of arguments and the data sent are not documented in this version 484of the protocol, and are subject to change for the convenience of 485memcache developers. 486 487 488General-purpose statistics 489-------------------------- 490 491Upon receiving the "stats" command without arguments, the server sents 492a number of lines which look like this: 493 494STAT <name> <value>\r\n 495 496The server terminates this list with the line 497 498END\r\n 499 500In each line of statistics, <name> is the name of this statistic, and 501<value> is the data. The following is the list of all names sent in 502response to the "stats" command, together with the type of the value 503sent for this name, and the meaning of the value. 504 505In the type column below, "32u" means a 32-bit unsigned integer, "64u" 506means a 64-bit unsigned integer. '32u.32u' means two 32-bit unsigned 507integers separated by a colon (treat this as a floating point number). 508 509|-----------------------+---------+-------------------------------------------| 510| Name | Type | Meaning | 511|-----------------------+---------+-------------------------------------------| 512| pid | 32u | Process id of this server process | 513| uptime | 32u | Number of secs since the server started | 514| time | 32u | current UNIX time according to the server | 515| version | string | Version string of this server | 516| pointer_size | 32 | Default size of pointers on the host OS | 517| | | (generally 32 or 64) | 518| rusage_user | 32u.32u | Accumulated user time for this process | 519| | | (seconds:microseconds) | 520| rusage_system | 32u.32u | Accumulated system time for this process | 521| | | (seconds:microseconds) | 522| curr_items | 32u | Current number of items stored | 523| total_items | 32u | Total number of items stored since | 524| | | the server started | 525| bytes | 64u | Current number of bytes used | 526| | | to store items | 527| curr_connections | 32u | Number of open connections | 528| total_connections | 32u | Total number of connections opened since | 529| | | the server started running | 530| connection_structures | 32u | Number of connection structures allocated | 531| | | by the server | 532| reserved_fds | 32u | Number of misc fds used internally | 533| cmd_get | 64u | Cumulative number of retrieval reqs | 534| cmd_set | 64u | Cumulative number of storage reqs | 535| cmd_flush | 64u | Cumulative number of flush reqs | 536| cmd_touch | 64u | Cumulative number of touch reqs | 537| get_hits | 64u | Number of keys that have been requested | 538| | | and found present | 539| get_misses | 64u | Number of items that have been requested | 540| | | and not found | 541| delete_misses | 64u | Number of deletions reqs for missing keys | 542| delete_hits | 64u | Number of deletion reqs resulting in | 543| | | an item being removed. | 544| incr_misses | 64u | Number of incr reqs against missing keys. | 545| incr_hits | 64u | Number of successful incr reqs. | 546| decr_misses | 64u | Number of decr reqs against missing keys. | 547| decr_hits | 64u | Number of successful decr reqs. | 548| cas_misses | 64u | Number of CAS reqs against missing keys. | 549| cas_hits | 64u | Number of successful CAS reqs. | 550| cas_badval | 64u | Number of CAS reqs for which a key was | 551| | | found, but the CAS value did not match. | 552| touch_hits | 64u | Numer of keys that have been touched with | 553| | | a new expiration time | 554| touch_misses | 64u | Numer of items that have been touched and | 555| | | not found | 556| auth_cmds | 64u | Number of authentication commands | 557| | | handled, success or failure. | 558| auth_errors | 64u | Number of failed authentications. | 559| evictions | 64u | Number of valid items removed from cache | 560| | | to free memory for new items | 561| reclaimed | 64u | Number of times an entry was stored using | 562| | | memory from an expired entry | 563| bytes_read | 64u | Total number of bytes read by this server | 564| | | from network | 565| bytes_written | 64u | Total number of bytes sent by this server | 566| | | to network | 567| limit_maxbytes | 32u | Number of bytes this server is allowed to | 568| | | use for storage. | 569| threads | 32u | Number of worker threads requested. | 570| | | (see doc/threads.txt) | 571| conn_yields | 64u | Number of times any connection yielded to | 572| | | another due to hitting the -R limit. | 573| hash_power_level | 32u | Current size multiplier for hash table | 574| hash_bytes | 64u | Bytes currently used by hash tables | 575| hash_is_expanding | bool | Indicates if the hash table is being | 576| | | grown to a new size | 577| expired_unfetched | 64u | Items pulled from LRU that were never | 578| | | touched by get/incr/append/etc before | 579| | | expiring | 580| evicted_unfetched | 64u | Items evicted from LRU that were never | 581| | | touched by get/incr/append/etc. | 582| slab_reassign_running | bool | If a slab page is being moved | 583| slabs_moved | 64u | Total slab pages moved | 584| crawler_reclaimed | 64u | Total items freed by LRU Crawler | 585| lrutail_reflocked | 64u | Times LRU tail was found with active ref. | 586| | | Items moved to head to avoid OOM errors. | 587|-----------------------+---------+-------------------------------------------| 588 589Settings statistics 590------------------- 591CAVEAT: This section describes statistics which are subject to change in the 592future. 593 594The "stats" command with the argument of "settings" returns details of 595the settings of the running memcached. This is primarily made up of 596the results of processing commandline options. 597 598Note that these are not guaranteed to return in any specific order and 599this list may not be exhaustive. Otherwise, this returns like any 600other stats command. 601 602|-------------------+----------+----------------------------------------------| 603| Name | Type | Meaning | 604|-------------------+----------+----------------------------------------------| 605| maxbytes | size_t | Maximum number of bytes allows in this cache | 606| maxconns | 32 | Maximum number of clients allowed. | 607| tcpport | 32 | TCP listen port. | 608| udpport | 32 | UDP listen port. | 609| inter | string | Listen interface. | 610| verbosity | 32 | 0 = none, 1 = some, 2 = lots | 611| oldest | 32u | Age of the oldest honored object. | 612| evictions | on/off | When off, LRU evictions are disabled. | 613| domain_socket | string | Path to the domain socket (if any). | 614| umask | 32 (oct) | umask for the creation of the domain socket. | 615| growth_factor | float | Chunk size growth factor. | 616| chunk_size | 32 | Minimum space allocated for key+value+flags. | 617| num_threads | 32 | Number of threads (including dispatch). | 618| stat_key_prefix | char | Stats prefix separator character. | 619| detail_enabled | bool | If yes, stats detail is enabled. | 620| reqs_per_event | 32 | Max num IO ops processed within an event. | 621| cas_enabled | bool | When no, CAS is not enabled for this server. | 622| tcp_backlog | 32 | TCP listen backlog. | 623| auth_enabled_sasl | yes/no | SASL auth requested and enabled. | 624| item_size_max | size_t | maximum item size | 625| maxconns_fast | bool | If fast disconnects are enabled | 626| hashpower_init | 32 | Starting size multiplier for hash table | 627| slab_reassign | bool | Whether slab page reassignment is allowed | 628| slab_automove | bool | Whether slab page automover is enabled | 629| hash_algorithm | char | Hash table algorithm in use | 630| lru_crawler | bool | Whether the LRU crawler is enabled | 631| lru_crawler_sleep | 32 | Microseconds to sleep between LRU crawls | 632| lru_crawler_tocrawl| 32u | Max items to crawl per slab per run | 633|-------------------+----------+----------------------------------------------| 634 635 636Item statistics 637--------------- 638CAVEAT: This section describes statistics which are subject to change in the 639future. 640 641The "stats" command with the argument of "items" returns information about 642item storage per slab class. The data is returned in the format: 643 644STAT items:<slabclass>:<stat> <value>\r\n 645 646The server terminates this list with the line 647 648END\r\n 649 650The slabclass aligns with class ids used by the "stats slabs" command. Where 651"stats slabs" describes size and memory usage, "stats items" shows higher 652level information. 653 654The following item values are defined as of writing. 655 656Name Meaning 657------------------------------ 658number Number of items presently stored in this class. Expired 659 items are not automatically excluded. 660age Age of the oldest item in the LRU. 661evicted Number of times an item had to be evicted from the LRU 662 before it expired. 663evicted_nonzero Number of times an item which had an explicit expire 664 time set had to be evicted from the LRU before it 665 expired. 666evicted_time Seconds since the last access for the most recent item 667 evicted from this class. Use this to judge how 668 recently active your evicted data is. 669outofmemory Number of times the underlying slab class was unable to 670 store a new item. This means you are running with -M or 671 an eviction failed. 672tailrepairs Number of times we self-healed a slab with a refcount 673 leak. If this counter is increasing a lot, please 674 report your situation to the developers. 675reclaimed Number of times an entry was stored using memory from 676 an expired entry. 677expired_unfetched Number of expired items reclaimed from the LRU which 678 were never touched after being set. 679evicted_unfetched Number of valid items evicted from the LRU which were 680 never touched after being set. 681crawler_reclaimed Number of items freed by the LRU Crawler. 682 683Note this will only display information about slabs which exist, so an empty 684cache will return an empty set. 685 686 687Item size statistics 688-------------------- 689CAVEAT: This section describes statistics which are subject to change in the 690future. 691 692The "stats" command with the argument of "sizes" returns information about the 693general size and count of all items stored in the cache. 694WARNING: This command WILL lock up your cache! It iterates over *every item* 695and examines the size. While the operation is fast, if you have many items 696you could prevent memcached from serving requests for several seconds. 697 698The data is returned in the following format: 699 700<size> <count>\r\n 701 702The server terminates this list with the line 703 704END\r\n 705 706'size' is an approximate size of the item, within 32 bytes. 707'count' is the amount of items that exist within that 32-byte range. 708 709This is essentially a display of all of your items if there was a slab class 710for every 32 bytes. You can use this to determine if adjusting the slab growth 711factor would save memory overhead. For example: generating more classes in the 712lower range could allow items to fit more snugly into their slab classes, if 713most of your items are less than 200 bytes in size. 714 715 716Slab statistics 717--------------- 718CAVEAT: This section describes statistics which are subject to change in the 719future. 720 721The "stats" command with the argument of "slabs" returns information about 722each of the slabs created by memcached during runtime. This includes per-slab 723information along with some totals. The data is returned in the format: 724 725STAT <slabclass>:<stat> <value>\r\n 726STAT <stat> <value>\r\n 727 728The server terminates this list with the line 729 730END\r\n 731 732|-----------------+----------------------------------------------------------| 733| Name | Meaning | 734|-----------------+----------------------------------------------------------| 735| chunk_size | The amount of space each chunk uses. One item will use | 736| | one chunk of the appropriate size. | 737| chunks_per_page | How many chunks exist within one page. A page by | 738| | default is less than or equal to one megabyte in size. | 739| | Slabs are allocated by page, then broken into chunks. | 740| total_pages | Total number of pages allocated to the slab class. | 741| total_chunks | Total number of chunks allocated to the slab class. | 742| get_hits | Total number of get requests serviced by this class. | 743| cmd_set | Total number of set requests storing data in this class. | 744| delete_hits | Total number of successful deletes from this class. | 745| incr_hits | Total number of incrs modifying this class. | 746| decr_hits | Total number of decrs modifying this class. | 747| cas_hits | Total number of CAS commands modifying this class. | 748| cas_badval | Total number of CAS commands that failed to modify a | 749| | value due to a bad CAS id. | 750| touch_hits | Total number of touches serviced by this class. | 751| used_chunks | How many chunks have been allocated to items. | 752| free_chunks | Chunks not yet allocated to items, or freed via delete. | 753| free_chunks_end | Number of free chunks at the end of the last allocated | 754| | page. | 755| mem_requested | Number of bytes requested to be stored in this slab[*]. | 756| active_slabs | Total number of slab classes allocated. | 757| total_malloced | Total amount of memory allocated to slab pages. | 758|-----------------+----------------------------------------------------------| 759 760* Items are stored in a slab that is the same size or larger than the 761 item. mem_requested shows the size of all items within a 762 slab. (total_chunks * chunk_size) - mem_requested shows memory 763 wasted in a slab class. If you see a lot of waste, consider tuning 764 the slab factor. 765 766 767Connection statistics 768--------------------- 769The "stats" command with the argument of "conns" returns information 770about currently active connections and about sockets that are listening 771for new connections. The data is returned in the format: 772 773STAT <file descriptor>:<stat> <value>\r\n 774 775The server terminates this list with the line 776 777END\r\n 778 779The following "stat" keywords may be present: 780 781|---------------------+------------------------------------------------------| 782| Name | Meaning | 783|---------------------+------------------------------------------------------| 784| addr | The address of the remote side. For listening | 785| | sockets this is the listen address. Note that some | 786| | socket types (such as UNIX-domain) don't have | 787| | meaningful remote addresses. | 788| state | The current state of the connection. See below. | 789| secs_since_last_cmd | The number of seconds since the most recently | 790| | issued command on the connection. This measures | 791| | the time since the start of the command, so if | 792| | "state" indicates a command is currently executing, | 793| | this will be the number of seconds the current | 794| | command has been running. | 795|---------------------+------------------------------------------------------| 796 797The value of the "state" stat may be one of the following: 798 799|----------------+-----------------------------------------------------------| 800| Name | Meaning | 801|----------------+-----------------------------------------------------------| 802| conn_closing | Shutting down the connection. | 803| conn_listening | Listening for new connections or a new UDP request. | 804| conn_mwrite | Writing a complex response, e.g., to a "get" command. | 805| conn_new_cmd | Connection is being prepared to accept a new command. | 806| conn_nread | Reading extended data, typically for a command such as | 807| | "set" or "put". | 808| conn_parse_cmd | The server has received a command and is in the middle | 809| | of parsing it or executing it. | 810| conn_read | Reading newly-arrived command data. | 811| conn_swallow | Discarding excess input, e.g., after an error has | 812| | occurred. | 813| conn_waiting | A partial command has been received and the server is | 814| | waiting for the rest of it to arrive (note the difference | 815| | between this and conn_nread). | 816| conn_write | Writing a simple response (anything that doesn't involve | 817| | sending back multiple lines of response data). | 818|----------------+-----------------------------------------------------------| 819 820 821 822Other commands 823-------------- 824 825"flush_all" is a command with an optional numeric argument. It always 826succeeds, and the server sends "OK\r\n" in response (unless "noreply" 827is given as the last parameter). Its effect is to invalidate all 828existing items immediately (by default) or after the expiration 829specified. After invalidation none of the items will be returned in 830response to a retrieval command (unless it's stored again under the 831same key *after* flush_all has invalidated the items). flush_all 832doesn't actually free all the memory taken up by existing items; that 833will happen gradually as new items are stored. The most precise 834definition of what flush_all does is the following: it causes all 835items whose update time is earlier than the time at which flush_all 836was set to be executed to be ignored for retrieval purposes. 837 838The intent of flush_all with a delay, was that in a setting where you 839have a pool of memcached servers, and you need to flush all content, 840you have the option of not resetting all memcached servers at the 841same time (which could e.g. cause a spike in database load with all 842clients suddenly needing to recreate content that would otherwise 843have been found in the memcached daemon). 844 845The delay option allows you to have them reset in e.g. 10 second 846intervals (by passing 0 to the first, 10 to the second, 20 to the 847third, etc. etc.). 848 849 850"version" is a command with no arguments: 851 852version\r\n 853 854In response, the server sends 855 856"VERSION <version>\r\n", where <version> is the version string for the 857server. 858 859"verbosity" is a command with a numeric argument. It always succeeds, 860and the server sends "OK\r\n" in response (unless "noreply" is given 861as the last parameter). Its effect is to set the verbosity level of 862the logging output. 863 864"quit" is a command with no arguments: 865 866quit\r\n 867 868Upon receiving this command, the server closes the 869connection. However, the client may also simply close the connection 870when it no longer needs it, without issuing this command. 871 872 873UDP protocol 874------------ 875 876For very large installations where the number of clients is high enough 877that the number of TCP connections causes scaling difficulties, there is 878also a UDP-based interface. The UDP interface does not provide guaranteed 879delivery, so should only be used for operations that aren't required to 880succeed; typically it is used for "get" requests where a missing or 881incomplete response can simply be treated as a cache miss. 882 883Each UDP datagram contains a simple frame header, followed by data in the 884same format as the TCP protocol described above. In the current 885implementation, requests must be contained in a single UDP datagram, but 886responses may span several datagrams. (The only common requests that would 887span multiple datagrams are huge multi-key "get" requests and "set" 888requests, both of which are more suitable to TCP transport for reliability 889reasons anyway.) 890 891The frame header is 8 bytes long, as follows (all values are 16-bit integers 892in network byte order, high byte first): 893 8940-1 Request ID 8952-3 Sequence number 8964-5 Total number of datagrams in this message 8976-7 Reserved for future use; must be 0 898 899The request ID is supplied by the client. Typically it will be a 900monotonically increasing value starting from a random seed, but the client 901is free to use whatever request IDs it likes. The server's response will 902contain the same ID as the incoming request. The client uses the request ID 903to differentiate between responses to outstanding requests if there are 904several pending from the same server; any datagrams with an unknown request 905ID are probably delayed responses to an earlier request and should be 906discarded. 907 908The sequence number ranges from 0 to n-1, where n is the total number of 909datagrams in the message. The client should concatenate the payloads of the 910datagrams for a given response in sequence number order; the resulting byte 911stream will contain a complete response in the same format as the TCP 912protocol (including terminating \r\n sequences). 913