Lines Matching refs:a
15 with a very large number (many hundreds, more than a thousand if
17 overhead associated with establishing a TCP connection (the overhead
18 of preparing for a new connection on the server side is insignificant
23 and responses from servers. Unstructured data is sent when a client
25 unstructured data in exactly the same way it received it, as a byte
29 of such data (either a client or a server) will always know, from a
35 may also appear inside the data. Therefore, when a client retrieves
36 data from a server, it must use the length of the data block (which it
44 Data stored by memcached is identified with the help of a key. A key
45 is a text string which should uniquely identify the data for clients
47 length limit of a key is set at 250 characters (of course, normally
57 "prepend" and "cas") ask the server to store some data identified by a
58 key. The client sends a command line, and then a data block; after
63 retrieve data corresponding to a set of keys (one or more keys in one
64 request). The client sends a command line, which includes all the
82 Some commands involve a client sending some kind of expiration time
85 Unix time (number of seconds since January 1, 1970, as a 32-bit
86 value), or a number of seconds starting from current time. In the
88 of seconds in 30 days); if the number sent by a client is larger than
96 Each command sent by a client may be answered with an error string
101 means the client sent a nonexistent command name.
106 doesn't conform to the protocol in some way. <error> is a
112 out the command. <error> is a human-readable error string. In cases
116 case in which the server closes a connection to a client.
127 First, the client sends a command line which looks like this:
150 "cas" is a check and set operation which means "store this data but
157 when the item is retrieved. Clients may use this as a bit field to
168 server time). If a negative value is given the item is immediately
175 - <cas unique> is a unique 64-bit value of an existing entry.
189 - <data block> is a chunk of arbitrary 8-bit data of length <bytes>
199 condition for an "add" or a "replace" command wasn't met.
202 a "cas" command has been modified since you last fetched it.
205 with a "cas" command did not exist.
219 which is received as a text line followed by a data block. After all
238 - <cas unique> is a unique 64-bit integer that uniquely identifies
243 If some of the keys appearing in a retrieval request are not sent back
247 deleted by a client).
279 treated as decimal representation of a 64-bit unsigned integer. If
280 the current data value does not conform to such a representation, the
284 that a non-existent key exists with value 0; instead, they will fail.
297 the item. It is a decimal representation of a 64-bit unsigned integer.
310 Note that underflow in the "decr" command is caught: if a client tries
314 Note also that decrementing a number such that it loses length isn't
350 The slabs reassign command is used to redistribute memory once a running
356 - <source class> is an id number for the slab class to steal a page from
360 - <dest class> is an id number for the slab class to move a page to
366 - "BUSY [message]" to indicate a page is already being processed, try again
369 - "BADCLASS [message]" a bad class id was specified
375 - "UNSAFE [message]" source class cannot move a page right now
384 The slabs automove command enables a background thread which decides on its
399 - <1> means to return pages to a global pool when there are more than 2 pages
400 worth of free chunks in a slab class. Pages are then re-assigned back into
403 - <2> is a highly aggressive mode which causes pages to be moved every time
415 items. This is useful if you have a mix of items with both long and short
439 - "CLIENT_ERROR [message]" indicating a format or bounds issue.
443 - The maximum number of items to inspect in a slab class per run request. This
451 - "CLIENT_ERROR [message]" indicating a format or bound issue.
455 - Takes a single, or a list of, numeric classids (ie: 1,3,10). This instructs
467 - "BUSY [message]" to indicate the crawler is already processing a request.
474 Watchers are a way to connect to memcached and inspect what's going on
480 - Turn connection into a watcher. Options can be stacked and are
490 Lines are prepending with "ts=" for a timestamp and "gid=" for a global ID
503 This means a "set" command would also emit an item_get log, as it checks for
537 a number of lines which look like this:
550 In the type column below, "32u" means a 32-bit unsigned integer, "64u"
551 means a 64-bit unsigned integer. '32u.32u' means two 32-bit unsigned
552 integers separated by a colon (treat this as a floating point number).
600 | cas_badval | 64u | Number of CAS reqs for which a key was |
603 | | | a new expiration time |
633 | | | grown to a new size |
639 | slab_reassign_running | bool | If a slab page is being moved |
657 | | 64u | Valid items evicted during a page move |
661 | | | during a page move. |
667 | | 64u | Items busy during page move, requiring a |
669 | log_worker_dropped | 64u | Logs a worker never wrote due to full buf |
670 | log_worker_written | 64u | Logs written by a worker, to be picked up |
733 | track_sizes | bool | If yes, a "stats sizes" histogram is being |
776 store a new item. This means you are running with -M or
778 tailrepairs Number of times we self-healed a slab with a refcount
779 leak. If this counter is increasing a lot, please
795 tails to find memory for a new item.
822 This is essentially a display of all of your items if there was a slab class
831 histogram at runtime. This has a small overhead to every store or delete
891 | cas_badval | Total number of CAS commands that failed to modify a |
892 | | value due to a bad CAS id. |
903 * Items are stored in a slab that is the same size or larger than the
904 item. mem_requested shows the size of all items within a
906 wasted in a slab class. If you see a lot of waste, consider tuning
935 | | "state" indicates a command is currently executing, |
946 | conn_listening | Listening for new connections or a new UDP request. |
947 | conn_mwrite | Writing a complex response, e.g., to a "get" command. |
948 | conn_new_cmd | Connection is being prepared to accept a new command. |
949 | conn_nread | Reading extended data, typically for a command such as |
951 | conn_parse_cmd | The server has received a command and is in the middle |
959 | conn_write | Writing a simple response (anything that doesn't involve |
968 "flush_all" is a command with an optional numeric argument. It always
973 response to a retrieval command (unless it's stored again under the
981 The intent of flush_all with a delay, was that in a setting where you
982 have a pool of memcached servers, and you need to flush all content,
984 same time (which could e.g. cause a spike in database load with all
992 "cache_memlimit" is a command with a numeric argument. This allows runtime
999 "version" is a command with no arguments:
1008 "verbosity" is a command with a numeric argument. It always succeeds,
1013 "quit" is a command with no arguments:
1027 also a UDP-based interface. The UDP interface does not provide guaranteed
1029 succeed; typically it is used for "get" requests where a missing or
1030 incomplete response can simply be treated as a cache miss.
1032 Each UDP datagram contains a simple frame header, followed by data in the
1034 implementation, requests must be contained in a single UDP datagram, but
1048 The request ID is supplied by the client. Typically it will be a
1049 monotonically increasing value starting from a random seed, but the client
1059 datagrams for a given response in sequence number order; the resulting byte
1060 stream will contain a complete response in the same format as the TCP