Lines Matching refs:in
21 There are two kinds of data sent in the memcache protocol: text lines
25 unstructured data in exactly the same way it received it, as a byte
26 stream. The server doesn't care about byte order issues in
28 characters that may appear in unstructured data; however, the reader
46 that are interested in storing and retrieving it. Currently the
63 retrieve data corresponding to a set of keys (one or more keys in one
84 Meta commands incorporate most features available in the binary protocol, as
91 they are not stored in cache.
95 specialized commands that do not sit in the Storage or Retrieval categories
96 noted in the 'Commands' section above.
116 remaining), it is returned in the same order as they were in the original
122 can return new data or reflect information, in the same order they were
123 supplied in the request. Sending an 't' flag with a get for an item with 20
124 seconds of TTL remaining, would return 't20' in the response.
129 client may prepend a "path" in the key itself: "mg /path/foo v" or in a proxy
148 of seconds in 30 days); if the number sent by a client is larger than
160 from the server. These error strings come in three types:
168 means some sort of client error in the input line, i.e. the input
169 doesn't conform to the protocol in some way. <error> is a
179 case in which the server closes a connection to a client.
235 - <flags> is an arbitrary 16-bit unsigned integer (written out in
239 Note that in memcached 1.2.1 and higher, flags may be 32-bits, instead
245 items). If it's non-zero (either Unix time or offset in seconds from
251 - <bytes> is the number of bytes in the data block to follow, *not*
252 including the delimiting \r\n. <bytes> may be zero (in which case
323 If some of the keys appearing in a retrieval request are not sent back
324 by the server in the item list this means that the server does not
340 reply. See the note in Storage commands regarding malformed
358 in-place, incrementing or decrementing it. The data for the item is
380 reply. See the note in Storage commands regarding malformed
390 Note that underflow in the "decr" command is caught: if a client tries
391 to decrease the value below 0, the new value will be 0. Overflow in
411 item were to expire in 10 seconds, but then was touched with an
412 expiration time of "20", the item would then expire in 20 seconds.
415 reply. See the note in Storage commands regarding malformed
486 la = time in seconds since last access
490 size = total size in bytes
511 If a response line appearing in a retrieval request is not sent back
522 - <size> is the size of <data block> in bytes, minus the \r\n
525 They are added in order specified by the flags sent.
530 If the request did not ask for a value in the response (v) flag, the server
535 If the request resulted in a miss, the response looks like:
548 - l: return time since item was last accessed in seconds
552 - t: return item TTL remaining in seconds (-1 for unlimited)
553 - u: don't bump the item in the LRU
554 - v: return item value in <data block>
573 are sent to memcached in base64 encoding.
575 If 'b' flag is sent in the response, and a key is returned via 'k', this
579 - l: return time since item was last accessed in seconds
595 Opaque tokens may be up to 32 bytes in length, and are a string similar to
607 "EN\r\n" lines in the middle.
611 - u: don't bump the item in the LRU
617 - v: return item value in <data block>
620 passed in. The response code also changes from "HD" to "VA <size>"
633 items. If supplied, and metaget does not find the item in cache, it will
741 - N(token): if in append mode, autovivify on miss with supplied TTL
789 - N(token): if in append mode, autovivify on miss with supplied TTL
794 TTL from N instead of T to be consistent with the usage of N in other
810 The response is in the format:
883 The response is in the format:
1015 will likely be in flux for several versions. See the wiki/mailing list for
1029 worth of free chunks in a slab class. Pages are then re-assigned back into
1033 there is an eviction. It is not recommended to run for very long in this
1095 - The number of microseconds to sleep in between each item checked for
1107 - The maximum number of items to inspect in a slab class per run request. This
1124 The special keyword "all" instructs it to crawl all slabs with items in
1137 - Similar in function to the above "lru_crawler crawl" command, this function
1138 outputs one line for every valid item found in the matching slab classes.
1147 Lines are in "key=value key2=value2" format, with value being URI encoded
1165 - Similar in function to the above "lru_crawler crawl" command, this function
1166 outputs one line for every valid item found in the matching slab classes.
1173 Lines are in a basic metaget format, like: "mg key\r\n". If a key is in
1216 The response format is in "key=value key2=value2" format, for easy parsing.
1220 lines back in order.
1233 - "mutations": Currently emits logs when an item is stored in most cases.
1237 cache. Useful in seeing if items being evicted were actually used, and which
1247 returned to a client while in proxy mode. The conditions which logs are
1273 kinds of arguments and the data sent are not documented in this version
1291 <value> is the data. The following is the list of all names sent in
1321 | rejected_connections | 64u | Conns rejected in maxconns_fast mode |
1325 | response_obj_count | 64u | Total response objects in use |
1337 | proxy_req_active | 64u | Number of in-flight proxy requests |
1338 | proxy_req_await | 64u | Number of in-flight proxy async requests |
1352 | delete_hits | 64u | Number of deletion reqs resulting in |
1391 | | 64u | Number of microseconds in maxconns. |
1423 | slab_reassign_rescues | 64u | Items rescued from eviction in page move |
1426 | | | (due to no free memory in slab) |
1448 | | | resulting in fallback to round robin |
1454 CAVEAT: This section describes statistics which are subject to change in the
1461 Note that these are not guaranteed to return in any specific order and
1468 | maxbytes | size_t | Maximum number of bytes allowed in the cache |
1498 | hash_algorithm | char | Hash table algorithm in use |
1530 | client_flags_size | 32u | Size in bytes of client flags |
1536 CAVEAT: This section describes statistics which are subject to change in the
1540 item storage per slab class. The data is returned in the format:
1556 number Number of items presently stored in this class. Expired
1558 number_hot Number of items presently stored in the HOT LRU.
1559 number_warm Number of items presently stored in the WARM LRU.
1560 number_cold Number of items presently stored in the COLD LRU.
1561 number_temp Number of items presently stored in the TEMPORARY LRU.
1562 age_hot Age of the oldest item in HOT LRU.
1563 age_warm Age of the oldest item in WARM LRU.
1564 age Age of the oldest item in the LRU.
1565 mem_requested Number of bytes requested to be stored in this LRU[*]
1590 lrutail_reflocked Number of items found to be refcount locked in the
1606 * Items are stored in a slab that is the same size or larger than the
1609 wasted in a slab class. If you see a lot of waste, consider tuning
1615 CAVEAT: This section describes statistics which are subject to change in the
1619 general size and count of all items stored in the cache.
1623 The data is returned in the following format:
1637 factor would save memory overhead. For example: generating more classes in the
1639 most of your items are less than 200 bytes in size.
1668 CAVEAT: This section describes statistics which are subject to change in the
1673 information along with some totals. The data is returned in the format:
1688 | | default is less than or equal to one megabyte in size. |
1693 | cmd_set | Total number of set requests storing data in this class. |
1714 for new connections. The data is returned in the format:
1753 | conn_parse_cmd | The server has received a command and is in the middle |
1768 TLS is a compile-time opt-in feature available in versions 1.5.13 and later.
1797 succeeds, and the server sends "OK\r\n" in response (unless "noreply"
1800 specified. After invalidation none of the items will be returned in
1809 The intent of flush_all with a delay, was that in a setting where you
1812 same time (which could e.g. cause a spike in database load with all
1814 have been found in the memcached daemon).
1816 The delay option allows you to have them reset in e.g. 10 second
1827 The argument is in megabytes, not bytes. Input gets multiplied out into
1846 and the server sends "OK\r\n" in response (unless "noreply" is given
1871 The check is available only in Linux builds with seccomp enabled.
1884 Each UDP datagram contains a simple frame header, followed by data in the
1886 implementation, requests must be contained in a single UDP datagram, but
1893 in network byte order, high byte first):
1897 4-5 Total number of datagrams in this message
1910 datagrams in the message. The client should concatenate the payloads of the
1911 datagrams for a given response in sequence number order; the resulting byte
1912 stream will contain a complete response in the same format as the TCP