Commit Graph

1295 Commits

Author SHA1 Message Date
antirez
ca734d17ad Revert "Now maxmemory, VM, and everything else uses the fast RSS memory used estimation instead of raw memory reported by zmalloc(). This means that setting maxmemory to 2GB will really have the effect of using up to 2GB of memory."
This reverts commit a3e60027e7.
2010-11-02 12:09:59 +01:00
antirez
a3e60027e7 Now maxmemory, VM, and everything else uses the fast RSS memory used estimation instead of raw memory reported by zmalloc(). This means that setting maxmemory to 2GB will really have the effect of using up to 2GB of memory. 2010-11-02 11:50:55 +01:00
antirez
7d47ecd543 Function to compute RSS memory usage in a fast way, suitable to be called inside keys eviction loops 2010-11-02 11:40:35 +01:00
antirez
10c12171cc removed a number of stupid compilation warnings on Linux 2010-11-02 11:15:09 +01:00
antirez
92e282288f zmalloc functions to get RSS and fragmentation refactored into two separated functions 2010-11-02 10:51:09 +01:00
antirez
21dbc6499a merge conflict resolved 2010-10-28 22:59:47 +02:00
Pieter Noordhuis
4794d88f15 Rewrite comment that was no longer valid 2010-10-28 16:59:05 +01:00
Pieter Noordhuis
a3a323e0e5 When REDIS_CLOSE_AFTER_REPLY is set, there may never be new replies 2010-10-28 16:52:23 +01:00
Pieter Noordhuis
5e78edb350 Unify two client flags that mean the same 2010-10-28 15:07:45 +01:00
antirez
73abd0a9d2 Merge remote branch 'remotes/pietern/zrevrangebyscore' 2010-10-28 14:12:25 +02:00
antirez
1de98301f6 removed useless spaces from DEBUG OBJECT output 2010-10-27 17:11:17 +02:00
Pieter Noordhuis
e584d82fec Return error to client on wrong type for HMGET 2010-10-26 12:33:17 +02:00
antirez
244201f6ba added a missing prototype from syncio.c in redis.h 2010-10-25 10:54:37 +02:00
antirez
d08fac3eb9 more generally usable i/o functions moved to syncio.c 2010-10-25 10:53:28 +02:00
antirez
19e61097c5 synchronous I/O networking functions originally used just for replication refactored in a file as generally useful, they are used in the cluster branch for MIGRATE. 2010-10-24 16:22:52 +02:00
Pieter Noordhuis
d94ac406ba Exclusively use either tcmalloc or OSX's native malloc_size() 2010-10-23 10:18:48 +02:00
Pieter Noordhuis
7cdc98b630 Don't use prefix when malloc_size() can be called
Also, use tcmalloc functions explicitly via macros to prevent symbol
lookups to resolve to native malloc/free on OSX.
2010-10-23 09:59:28 +02:00
antirez
da47440d44 Make sure to reset the signal handler and deliver again the original crashing signal when dumping the stack trace. This will allow to dump the core if core dumping is enabled. 2010-10-22 23:30:48 +02:00
Robey Pointer
d8a717fb1a if server.saveparamslen is not set, don't save the DB on exit. 2010-10-22 23:17:28 +02:00
antirez
fc41345116 README more specific about tcmalloc space benefits 2010-10-22 00:18:26 +02:00
antirez
1a587ff843 Makefile typo fixed for tcmalloc option 2010-10-22 00:16:32 +02:00
antirez
13b3715925 reports if tcmalloc is in used in INFO output 2010-10-22 00:10:17 +02:00
antirez
0a802bd7a0 support for compiling with tcmalloc 2010-10-22 00:06:44 +02:00
antirez
75fcab8c23 version bumped to 2.1.5 2010-10-21 17:55:44 +02:00
Pieter Noordhuis
a375b077cc Skip object encoding where it doesn't make sense 2010-10-17 18:13:31 +02:00
Pieter Noordhuis
19408d83a4 Object encoding in hash function is done by a more specific function 2010-10-17 17:46:55 +02:00
Pieter Noordhuis
33aba595b0 Removed unused command flags 2010-10-17 17:31:40 +02:00
Pieter Noordhuis
75b41de8ca Convert objects in the command procs instead of the protocol code 2010-10-17 17:21:41 +02:00
Pieter Noordhuis
b19c33d48a Prevent clients from making too large multibulk requests 2010-10-15 19:15:38 +02:00
Pieter Noordhuis
ea5b70924d Add benchmark for MSET 2010-10-15 18:17:06 +02:00
antirez
13a49af44b prevent small integer sharing when maxmemory is active. So every object will use a private LRU field and the LRU algorithm can work well 2010-10-15 18:04:05 +02:00
Pieter Noordhuis
1aa608fc68 Change protocol from bulk to inline in redis-benchmark 2010-10-15 17:34:20 +02:00
Pieter Noordhuis
9da6caac4e Don't reset the client when processCommand returns REDIS_ERR 2010-10-15 17:27:05 +02:00
Pieter Noordhuis
dc11daf3b5 Change tests to use either the inline or the multibulk protocol 2010-10-15 17:25:20 +02:00
Pieter Noordhuis
5b12b47df9 Show output of leaks command on a leak 2010-10-15 15:56:16 +02:00
Pieter Noordhuis
00cf82c0bd Change tcl client to only use the multibulk protocol 2010-10-15 15:50:29 +02:00
Pieter Noordhuis
cd8788f26d Refactor request parsing code for efficiency 2010-10-15 15:44:55 +02:00
Pieter Noordhuis
5a4f9f27e7 Add tests for OK on QUIT 2010-10-15 12:54:53 +02:00
antirez
9f8ded8ced CONFIG RESETSTAT no longer resets the server uptime. Now keyspace hits/misses are reset as well. 2010-10-15 12:29:05 +02:00
antirez
95506e4611 minor aesthetic change 2010-10-15 12:22:48 +02:00
antirez
53eeeaff08 added keyspace_hits and keyspace_misses fields in INFO output 2010-10-15 12:19:21 +02:00
antirez
a36879293d maxmemory-samples implemented in CONFIG command and configuration file 2010-10-15 11:57:38 +02:00
antirez
670bf2fd36 Don't increment dirty on expireIfNeeded() as natural expires are not considered database changes. This will avoid useless read-only commands in the AOF file as a result of, for instance, a GET operation triggering an expirIfNeeded() call resulting in an expired key removed. 2010-10-15 11:29:03 +02:00
antirez
b33ef40105 Merge remote branch 'pietern/ziplist-regression' 2010-10-14 21:23:01 +02:00
antirez
165346ca29 implemented different algorithms for maxmemory 2010-10-14 21:22:21 +02:00
Pieter Noordhuis
306c6a02e3 Replace ziplist stresser and fix regression 2010-10-14 21:11:42 +02:00
antirez
ef59a8bc9e Object approximated LRU algorithm enhanced / fixed / refactored. This is used for the VM currently but will soon be used for maxmemory expiring. 2010-10-14 13:52:58 +02:00
Pieter Noordhuis
7236fdb22f Return error when min and/or max in the sorted set range spec is not a double 2010-10-13 21:59:24 +02:00
Pieter Noordhuis
91504b6cbe Make ZREMRANGEBYSCORE accept the same range spec as ZRANGEBYSCORE
This allows to use inclusive/exclusive bounds for min and max when
deleting a range of scores from a sorted set.
2010-10-13 21:43:58 +02:00
Pieter Noordhuis
26f3388d27 Merge branch 'master' into zrevrangebyscore 2010-10-13 20:29:50 +02:00