|
Revision tags: 8.0-m02, 6.2.16, 7.2.6, 7.4.1, 8.0-m01, 7.4.0, 7.4-rc2, 7.4-rc1, 7.2.5, 7.2.4, 7.0.15, 7.2.3, 7.2.2, 7.0.14, 6.2.14, 6.2.15, 7.2.1, 7.0.13, 7.2.0, 7.2-rc3, 7.0.12, 6.2.13, 6.0.20, 7.2-rc2, 6.0.19, 6.2.12, 7.0.11, 7.2-rc1, 7.0.10, 7.0.9, 6.2.11, 6.0.18, 6.2.10, 6.0.17, 6.2.9, 7.0.8, 7.0.7, 7.0.6, 6.2.8, 7.0.5, 7.0.4, 7.0.3, 7.0.2, 7.0.1, 7.0.0, 6.2.7, 7.0-rc3, 7.0-rc2, 7.0-rc1, 6.2.6, 6.0.16, 5.0.14, 5.0.13, 6.0.15, 6.2.5, 6.0.14, 6.2.4, 6.2.3, 6.0.13, 6.2.2, 6.2.1, 6.0.12, 5.0.12, 6.0.11, 6.2.0, 5.0.11, 6.2-rc3, 6.0.10, 6.2-rc2, 6.2-rc1, 6.0.9, 5.0.10, 6.0.8, 6.0.7, 6.0.6, 6.0.5, 6.0.4, 6.0.3, 6.0.2, 6.0.1, 6.0.0, 5.0.9, 6.0-rc4, 6.0-rc3, 5.0.8, 6.0-rc2, 6.0-rc1, 5.0.7, 5.0.6, 5.0.5, 3.2.13, 4.0.14, 5.0.4, 4.0.13, 5.0.3, 4.0.12, 5.0.2, 5.0.1, 5.0.0, 5.0-rc6, 5.0-rc5, 4.0.11, 5.0-rc4, 5.0-rc3, 5.0-rc2, 4.0.10, 3.2.12, 5.0-rc1, 4.0.9, 4.0.8, 4.0.7, 4.0.6, 4.0.5, 4.0.4, 4.0.3, 3.2.11, 4.0.2, 3.2.10, 4.0.1, 4.0.0, 3.2.9, 4.0-rc3, 3.2.8, 3.2.7, 3.2.6, 4.0-rc2, 4.0-rc1, 3.2.5, 3.2.4, 3.2.3, 3.2.2, 3.2.1, 3.2.0, 3.2.0-rc3, 3.0.7, 3.2.0-rc2, 3.2-rc1, 3.0.6, 2.8.24, 3.0.5, 2.8.23, 2.8.22, 3.0.4, 3.0.3, 3.0.2, 2.8.21, 2.8.20, 3.0.1, 3.0.0, 3.0.0-rc6, 3.0.0-rc5, 3.0.0-rc4, 3.0.0-rc3, 3.0.0-rc2 |
|
| #
615f6923 |
| 17-Dec-2014 |
antirez <[email protected]> |
getMemorySize() moved into zmalloc.c with other low level mem utils.
See issue #2218.
|
|
Revision tags: 2.8.19, 2.8.18 |
|
| #
3ef0876b |
| 12-Nov-2014 |
antirez <[email protected]> |
THP detection / reporting functions added.
|
|
Revision tags: 3.0.0-rc1, 2.8.17, 2.8.16, 2.8.15, 2.8.14, 3.0.0-beta8, 2.8.13, 3.0.0-beta7, 2.8.12, 2.8.11, 3.0.0-beta6, 2.8.10, 3.0.0-beta5, 3.0.0-beta4, 3.0.0-beta3, 2.8.9, 2.8.8 |
|
| #
93253c27 |
| 24-Mar-2014 |
antirez <[email protected]> |
Sample and cache RSS in serverCron().
Obtaining the RSS (Resident Set Size) info is slow in Linux and OSX.
This slowed down the generation of the INFO 'memory' section.
Since the RSS does not requi
Sample and cache RSS in serverCron().
Obtaining the RSS (Resident Set Size) info is slow in Linux and OSX.
This slowed down the generation of the INFO 'memory' section.
Since the RSS does not require to be a real-time measurement, we
now sample it with server.hz frequency (10 times per second by default)
and use this value both to show the INFO rss field and to compute the
fragmentation ratio.
Practically this does not make any difference for memory profiling of
Redis but speeds up the INFO call significantly.
show more ...
|
|
Revision tags: 3.0.0-beta2, 2.8.7, 2.8.6, 3.0.0-beta1, 2.8.5, 2.8.4, 2.6.17, 2.8.3, 2.8.2, 2.8.1, 2.8.0, 2.8.0-rc6, 2.8.0-rc5, 2.8.0-rc4, 2.6.16, 2.6.15, 2.8.0-rc3, 2.8.0-rc2, 2.8.0-rc1, 2.6.14-2, 2.6.14-1, 2.6.14, 2.6.13, 2.6.12, 2.6.10-3, 2.6.10-2, 2.6.11, 2.6.10-1, 2.6.10, 2.6.9-1, 2.6.9, 2.6.8-1, 2.6.8, 2.6.7-1, 2.6.7, 2.6.6, 2.4.18, 2.6.5 |
|
| #
3bfeb9c1 |
| 19-Nov-2012 |
antirez <[email protected]> |
zmalloc_get_private_dirty() function added (Linux only).
For non Linux systmes it just returns 0.
This function is useful to estimate copy-on-write because of childs
saving stuff on disk.
|
|
Revision tags: 2.6.4, 2.6.3, 2.6.2, 2.6.1, 2.6.0, 2.6.0-rc8, 2.6.0-rc7, 2.4.17 |
|
| #
6fdc6354 |
| 24-Aug-2012 |
antirez <[email protected]> |
Better Out of Memory handling.
The previous implementation of zmalloc.c was not able to handle out of
memory in an application-specific way. It just logged an error on
standard error, and aborted.
Better Out of Memory handling.
The previous implementation of zmalloc.c was not able to handle out of
memory in an application-specific way. It just logged an error on
standard error, and aborted.
The result was that in the case of an actual out of memory in Redis
where malloc returned NULL (In Linux this actually happens under
specific overcommit policy settings and/or with no or little swap
configured) the error was not properly logged in the Redis log.
This commit fixes this problem, fixing issue #509.
Now the out of memory is properly reported in the Redis log and a stack
trace is generated.
The approach used is to provide a configurable out of memory handler
to zmalloc (otherwise the default one logging the event on the
standard output is used).
show more ...
|
|
Revision tags: 2.6.0-rc6, 2.4.16, 2.4.15, 2.6.0-rc5, 2.6.0-rc4, 2.4.14 |
|
| #
ad4c0b41 |
| 15-May-2012 |
antirez <[email protected]> |
Jemalloc updated to 3.0.0.
Full changelog here:
http://www.canonware.com/cgi-bin/gitweb.cgi?p=jemalloc.git;a=blob_plain;f=ChangeLog;hb=master
Notable improvements from the point of view of Redis:
Jemalloc updated to 3.0.0.
Full changelog here:
http://www.canonware.com/cgi-bin/gitweb.cgi?p=jemalloc.git;a=blob_plain;f=ChangeLog;hb=master
Notable improvements from the point of view of Redis:
1) Bugfixing.
2) Support for Valgrind.
3) Support for OSX Lion, FreeBSD.
show more ...
|
|
Revision tags: 2.6.0-rc3, 2.6.0-rc2, 2.4.13, 2.4.12, 2.6.0-rc1, 2.4.11 |
|
| #
ebba7b3c |
| 05-Apr-2012 |
Premysl Hruby <[email protected]> |
future-proof version comparison
|
|
Revision tags: 2.4.10 |
|
| #
23c0cdd2 |
| 27-Mar-2012 |
antirez <[email protected]> |
Produce the watchlog warning log in a way that is safer from a signal handler. Fix a memory leak in the backtrace generation function.
|
|
Revision tags: 2.4.9, 2.4.8 |
|
| #
442246dd |
| 07-Feb-2012 |
antirez <[email protected]> |
Precision of getClientOutputBufferMemoryUsage() greatily improved, see issue #327 for more information.
|
|
Revision tags: 2.4.7, 2.4.6, 2.4.5, 2.4.4, 2.4.3, 2.4.2, 2.2.15, 2.4.1, 2.4.0, 2.2.14, 2.4.0-rc8, 2.2.13, 2.4.0-rc7, 2.4.0-rc6, 2.4.0-rc5, 2.4.0-rc4, 2.2.12, 2.4.0-rc3 |
|
| #
65046340 |
| 02-Jul-2011 |
antirez <[email protected]> |
no more allocation stats info in INFO, useless now that we have jemalloc.
|
|
Revision tags: with-deprecated-diskstore, 2.2.111-scripting, 2.2.11 |
|
| #
29d04257 |
| 20-Jun-2011 |
antirez <[email protected]> |
forward-ported changes in zmalloc.c/h to support jemalloc build
|
|
Revision tags: 2.2.110-scripting, 2.2.10, 2.2.9, 2.4.0-rc2, 2.4.0-rc1, 2.2.8, 2.2.107-scripting, 2.2.7, 2.2.106-scripting, 2.2.6, 2.2.105-scripting, 2.2.5, 2.2.4, 2.2.3, 3.0-alpha0, 2.0.5, 2.2.2, 2.2.1, 2.2.0, 2.2.0-rc4, 2.2.0-rc3, 2.3-alpha0 |
|
| #
67a1810b |
| 09-Jan-2011 |
antirez <[email protected]> |
allocation stats in INFO
|
|
Revision tags: 2.2.0-rc2, 2.2.0-rc1, 2.2-alpha6, 2.2-alpha5, 2.0.4, v2.0.4-stable, 2.2-alpha4 |
|
| #
92e28228 |
| 02-Nov-2010 |
antirez <[email protected]> |
zmalloc functions to get RSS and fragmentation refactored into two separated functions
|
|
Revision tags: 2.2-alpha3, 2.0.3, v2.0.3-stable, 2.0.2, v2.0.2-stable, 2.0.1, v2.0.1-stable, 2.2-alpha2, 2.0.0, v2.0.0-stable |
|
| #
eddb388e |
| 02-Sep-2010 |
antirez <antirez@metal.(none)> |
memory fragmentation ratio in INFO output
|
|
Revision tags: 2.2-alpha1, twitter-20100825, twitter-20100804, 2.2-alpha0, v2.0.0-rc4 |
|
| #
399f2f40 |
| 24-Jul-2010 |
Benjamin Kramer <[email protected]> |
Add zcalloc and use it where appropriate
calloc is more effecient than malloc+memset when the system uses mmap to
allocate memory. mmap always returns zeroed memory so the memset can be
avoided. Th
Add zcalloc and use it where appropriate
calloc is more effecient than malloc+memset when the system uses mmap to
allocate memory. mmap always returns zeroed memory so the memset can be
avoided. The threshold to use mmap is 16k in osx libc and 128k in bsd
libc and glibc. The kernel can lazily allocate the pages, this reduces
memory usage when we have a page table or hash table that is mostly
empty.
This change is most visible when you start a new redis instance with vm
enabled. You'll see no increased memory usage no matter how big your
page table is.
show more ...
|
|
Revision tags: v2.0.0-rc3, v2.0.0-rc2 |
|
| #
e2641e09 |
| 21-Jun-2010 |
antirez <[email protected]> |
redis.c split into many different C files.
networking related stuff moved into networking.c
moved more code
more work on layout of source code
SDS instantaneuos memory saving. By Pieter and Salva
redis.c split into many different C files.
networking related stuff moved into networking.c
moved more code
more work on layout of source code
SDS instantaneuos memory saving. By Pieter and Salvatore at VMware ;)
cleanly compiling again after the first split, now splitting it in more C files
moving more things around... work in progress
split replication code
splitting more
Sets split
Hash split
replication split
even more splitting
more splitting
minor change
show more ...
|