]>
git.saurik.com Git - redis.git/log
antirez [Thu, 28 Jan 2010 15:12:04 +0000 (10:12 -0500)]
loading side of the threaded VM
antirez [Tue, 26 Jan 2010 10:02:27 +0000 (05:02 -0500)]
TODO cahnges
antirez [Sat, 23 Jan 2010 16:55:04 +0000 (11:55 -0500)]
Fixed memory human style memory reporting, removed server.usedmemory, now zmalloc_used_memory() is used always.
antirez [Fri, 22 Jan 2010 17:58:11 +0000 (12:58 -0500)]
VM tuning thanks to redis-stat vmstat. Now it performs much better under high load
antirez [Thu, 21 Jan 2010 15:36:32 +0000 (10:36 -0500)]
Changelog updated
antirez [Thu, 21 Jan 2010 12:27:32 +0000 (07:27 -0500)]
REDIS_MAX_COMPLETED_JOBS_PROCESSED is now in percentage, not number of jobs. Moved a debugging message a few lines forward as it was called where a few logged parameters where invalid, leading to a crash
antirez [Wed, 20 Jan 2010 21:57:00 +0000 (16:57 -0500)]
fixed a deadlock caused by too much finished processes in queue so that I/O clients writing to the wirte side of the pipe used to awake the main thread where blocking. Then a BGSAVE started waiting for the last active thread to finish, condition impossible because all the I/O threads where blocking on threads. Takes this as a note to myself...
antirez [Wed, 20 Jan 2010 18:38:59 +0000 (13:38 -0500)]
ae.c event loop does no longer support exception notifications, as they are fully pointless. Also a theoretical bug that never happens in practice fixed.
antirez [Tue, 19 Jan 2010 18:32:36 +0000 (13:32 -0500)]
commercial tools stuff removed from the Redis makefile. cotools are now migrated into a different repos
antirez [Tue, 19 Jan 2010 18:02:02 +0000 (13:02 -0500)]
removed a bug in the function to cancel an I/O job
antirez [Sun, 17 Jan 2010 16:24:37 +0000 (11:24 -0500)]
static symbols update
antirez [Sat, 16 Jan 2010 12:57:32 +0000 (07:57 -0500)]
removed support for REDIS_HELGRIND_FRIENDLY since Helgrind 3.5.0 is friendly enough even with many threads created and destroyed
antirez [Fri, 15 Jan 2010 21:42:29 +0000 (16:42 -0500)]
now redis-cli understands -h
antirez [Fri, 15 Jan 2010 19:02:18 +0000 (14:02 -0500)]
Create swap file only if not exists
antirez [Fri, 15 Jan 2010 18:55:52 +0000 (13:55 -0500)]
I hate warnings
antirez [Fri, 15 Jan 2010 18:35:13 +0000 (13:35 -0500)]
fixed a minor memory leak in configuration file parsing
antirez [Fri, 15 Jan 2010 18:17:43 +0000 (13:17 -0500)]
minor fix
antirez [Fri, 15 Jan 2010 18:14:23 +0000 (13:14 -0500)]
support for named VM swap file. Fixed a few important interaction issues between the background saving processes and IO threads
antirez [Fri, 15 Jan 2010 15:37:37 +0000 (10:37 -0500)]
fix for the just added new test
antirez [Fri, 15 Jan 2010 14:39:44 +0000 (09:39 -0500)]
useless debugging messages removed
antirez [Fri, 15 Jan 2010 14:37:26 +0000 (09:37 -0500)]
new test added
antirez [Fri, 15 Jan 2010 13:52:20 +0000 (08:52 -0500)]
thread safe zmalloc used memory counter
antirez [Fri, 15 Jan 2010 10:16:12 +0000 (05:16 -0500)]
A define to make Redis more helgrind friendly
antirez [Fri, 15 Jan 2010 10:09:18 +0000 (05:09 -0500)]
removed a few races from threaded VM
antirez [Thu, 14 Jan 2010 22:18:27 +0000 (17:18 -0500)]
Fixed a never experienced, theoretical bug that can actually happen in practice. Basically when a thread is working on a I/O Job we need to wait it to finish before to cancel the Job in vmCancelThreadedIOJob(), otherwise the thread may mess with an object that is being manipulated by the main thread as well.
antirez [Thu, 14 Jan 2010 13:58:41 +0000 (08:58 -0500)]
Set the new threads stack size to a LZF friendly amount
antirez [Wed, 13 Jan 2010 21:26:41 +0000 (16:26 -0500)]
access to already freed job structure fixed by statements reoredering
antirez [Wed, 13 Jan 2010 18:41:38 +0000 (13:41 -0500)]
removed a useless debugging message
antirez [Wed, 13 Jan 2010 18:38:30 +0000 (13:38 -0500)]
Wait zero active threads condition before to fork() for BGSAVE or BGREWRITEAOF
antirez [Wed, 13 Jan 2010 18:18:07 +0000 (13:18 -0500)]
list API is now thread safe
antirez [Wed, 13 Jan 2010 14:40:50 +0000 (09:40 -0500)]
minor TODO and debugging info changes
antirez [Tue, 12 Jan 2010 20:23:52 +0000 (15:23 -0500)]
support for blocking VM in config file
antirez [Tue, 12 Jan 2010 20:09:11 +0000 (15:09 -0500)]
more non blocking VM changes
antirez [Tue, 12 Jan 2010 15:01:59 +0000 (10:01 -0500)]
fix for test #11
antirez [Tue, 12 Jan 2010 14:57:00 +0000 (09:57 -0500)]
a few more stuff in INFO about VM. Test #11 changed a bit in order to be less lame
antirez [Tue, 12 Jan 2010 12:27:54 +0000 (07:27 -0500)]
Added a define to configure how many completed IO jobs the handler should process at every call.
antirez [Tue, 12 Jan 2010 00:47:18 +0000 (19:47 -0500)]
Fixed a bug in the IO Job canceling funtion
antirez [Mon, 11 Jan 2010 22:26:58 +0000 (17:26 -0500)]
more steps towards a working non blocking VM
antirez [Mon, 11 Jan 2010 18:10:43 +0000 (13:10 -0500)]
converted random printfs in debug logs
antirez [Mon, 11 Jan 2010 17:54:29 +0000 (12:54 -0500)]
removed a bug introduced with non blocking VM
antirez [Mon, 11 Jan 2010 17:45:15 +0000 (12:45 -0500)]
a few non blocking VM bugs fixed
antirez [Mon, 11 Jan 2010 16:42:15 +0000 (11:42 -0500)]
More work on non-blocking VM. Should work in a few days
antirez [Mon, 11 Jan 2010 10:15:54 +0000 (05:15 -0500)]
More threaded I/O VM work + Redis init script
antirez [Sun, 10 Jan 2010 16:23:01 +0000 (11:23 -0500)]
more work on VM threaded I/O. Still nothing of usable
antirez [Sat, 9 Jan 2010 17:46:52 +0000 (12:46 -0500)]
non-blocking VM data structures, just a start
antirez [Fri, 8 Jan 2010 15:38:48 +0000 (10:38 -0500)]
used_memory_human added to INFO output. Human readable amount of memory used.
antirez [Thu, 7 Jan 2010 21:51:58 +0000 (16:51 -0500)]
Now DEBUG OBJECT plays well with swapped out objects
antirez [Thu, 7 Jan 2010 20:53:12 +0000 (15:53 -0500)]
fflush VM swap file after object swapping
antirez [Thu, 7 Jan 2010 20:49:00 +0000 (15:49 -0500)]
added the fmacros to enable support for fseeko() lseeko() with 64bit off_t
antirez [Thu, 7 Jan 2010 15:41:08 +0000 (10:41 -0500)]
VM now swaps objects out while loading datasets not fitting into vm-max-memory bytes of RAM
antirez [Thu, 7 Jan 2010 13:56:57 +0000 (08:56 -0500)]
added process id information in INFO
antirez [Thu, 7 Jan 2010 02:05:03 +0000 (21:05 -0500)]
vm-enabled set to no by default in redis.conf
antirez [Thu, 7 Jan 2010 02:03:16 +0000 (21:03 -0500)]
a new default redis.conf
antirez [Thu, 7 Jan 2010 01:14:27 +0000 (20:14 -0500)]
VM stats in INFO command
antirez [Wed, 6 Jan 2010 14:15:17 +0000 (09:15 -0500)]
Introduced a new log verbosity level, so now DEBUG is really for debugging. Refactored a bit maxmemory. When virtual memory is short in RAM free the objects freelist as well as swapping things out.
antirez [Wed, 6 Jan 2010 00:51:30 +0000 (19:51 -0500)]
fixed a bug in bgsave when VM is off but still it was testing for obj->storage field
antirez [Wed, 6 Jan 2010 00:44:22 +0000 (19:44 -0500)]
converted a few calls to assert() => redisAssert() to print stack trace
antirez [Wed, 6 Jan 2010 00:15:15 +0000 (19:15 -0500)]
BGREWRITEAOF now works with swapping on
antirez [Tue, 5 Jan 2010 19:25:56 +0000 (14:25 -0500)]
A first fix for SET key overwrite
antirez [Tue, 5 Jan 2010 18:51:46 +0000 (13:51 -0500)]
SAVE now works with VM
antirez [Tue, 5 Jan 2010 18:16:41 +0000 (13:16 -0500)]
swapping algorithm a bit more aggressive under low memory
antirez [Tue, 5 Jan 2010 17:46:59 +0000 (12:46 -0500)]
basic VM mostly working!
antirez [Tue, 5 Jan 2010 15:38:58 +0000 (10:38 -0500)]
New object field (one of the unused bytes) to hold the type of the swapped out value object in key objects
antirez [Tue, 5 Jan 2010 15:34:05 +0000 (10:34 -0500)]
VM internals bugfixes, set 1
antirez [Tue, 5 Jan 2010 12:28:06 +0000 (07:28 -0500)]
load key from swap on key lookup
antirez [Tue, 5 Jan 2010 12:19:09 +0000 (07:19 -0500)]
more object-level VM primitives
antirez [Tue, 5 Jan 2010 10:37:19 +0000 (05:37 -0500)]
Redis objects swapping / loading
antirez [Tue, 5 Jan 2010 09:49:02 +0000 (04:49 -0500)]
rdbLoadObject() as a separated function to load objects from disk. Dropped support for RDB version 0, I guess no longer has this legacy DBs around
antirez [Tue, 5 Jan 2010 00:52:08 +0000 (19:52 -0500)]
VM low level pages handling
antirez [Mon, 4 Jan 2010 21:01:40 +0000 (16:01 -0500)]
vm swap file creation, and some basic configuration
antirez [Mon, 4 Jan 2010 20:01:55 +0000 (15:01 -0500)]
version marked 1.3.2
antirez [Mon, 4 Jan 2010 20:00:43 +0000 (15:00 -0500)]
saving code refactored a bit, added a function returning the number of bytes an object will use on disk
antirez [Sat, 2 Jan 2010 15:02:24 +0000 (10:02 -0500)]
Now the PUSH side of RPOPLPUSH is able to unblock clients blocked on BLPOP
antirez [Sat, 2 Jan 2010 14:37:01 +0000 (09:37 -0500)]
Version is now 1.3.1
antirez [Sat, 2 Jan 2010 14:06:44 +0000 (09:06 -0500)]
New vararg BLPOP able to block against multiple keys
antirez [Wed, 30 Dec 2009 00:11:05 +0000 (19:11 -0500)]
fixed a problem with BLPOP timeout of zero, now it blocks forever
antirez [Tue, 29 Dec 2009 21:26:05 +0000 (16:26 -0500)]
BLPOP timeouts implemented
antirez [Tue, 29 Dec 2009 21:05:56 +0000 (16:05 -0500)]
first working implementation of BLPOP and BRPOP, still everything is to test well
antirez [Tue, 29 Dec 2009 20:50:08 +0000 (15:50 -0500)]
a few more fixes, still broken
antirez [Tue, 29 Dec 2009 20:32:37 +0000 (15:32 -0500)]
First fix, still broken
antirez [Tue, 29 Dec 2009 20:03:44 +0000 (15:03 -0500)]
minor fix for Linux 64 bit
antirez [Tue, 29 Dec 2009 19:59:40 +0000 (14:59 -0500)]
not yet working BLPOP implementation
antirez [Mon, 28 Dec 2009 01:40:11 +0000 (20:40 -0500)]
AOFSYNC removed, got a better idea...
antirez [Mon, 28 Dec 2009 01:31:16 +0000 (20:31 -0500)]
AOFSYNC command implemented
antirez [Sun, 27 Dec 2009 21:26:51 +0000 (16:26 -0500)]
Version changed to 1.3.0, welcome to the new unstable
antirez [Sun, 27 Dec 2009 20:58:03 +0000 (15:58 -0500)]
Now MULTI returns +OK as well
antirez [Sun, 27 Dec 2009 20:47:28 +0000 (15:47 -0500)]
MULTI/EXEC first implementation
antirez [Thu, 24 Dec 2009 14:40:11 +0000 (09:40 -0500)]
Fixed a minor bug in GETSET, now the SET part is not performed if the GET fails because the key does not contain a string value
antirez [Wed, 23 Dec 2009 16:15:07 +0000 (11:15 -0500)]
html doc readded
antirez [Wed, 23 Dec 2009 16:12:01 +0000 (11:12 -0500)]
ZRANGE WITHSCORES test added
antirez [Wed, 23 Dec 2009 16:01:31 +0000 (11:01 -0500)]
version is now 1.1.94
antirez [Wed, 23 Dec 2009 11:23:32 +0000 (06:23 -0500)]
Add the command name in the unknown command error message.
antirez [Tue, 22 Dec 2009 21:09:27 +0000 (16:09 -0500)]
ZRANGE, ZREVRANGE now support WITHSCORES options
antirez [Tue, 22 Dec 2009 20:08:50 +0000 (15:08 -0500)]
html docs update (ZINCRBY added)
antirez [Fri, 18 Dec 2009 20:49:22 +0000 (15:49 -0500)]
TODO list update
antirez [Fri, 18 Dec 2009 20:39:19 +0000 (15:39 -0500)]
the pipelining test was ran against DB 1 for error, now it runs on DB 9 like all the other tests
antirez [Fri, 18 Dec 2009 14:19:36 +0000 (09:19 -0500)]
still more tests
antirez [Fri, 18 Dec 2009 14:09:18 +0000 (09:09 -0500)]
SORT STORE test added
antirez [Fri, 18 Dec 2009 14:06:53 +0000 (09:06 -0500)]
Now SORT returns an empty bulk reply if the key does not exist
antirez [Fri, 18 Dec 2009 12:51:23 +0000 (07:51 -0500)]
modified a bit the ZREVRANGE test to cover a few lines of code more