- 18 Mar, 2012 9 commits
-
-
antirez authored
-
antirez authored
-
antirez authored
More memory tests implemented. Default number of iterations lowered to a more acceptable value of 50.
-
antirez authored
-
antirez authored
Number of iteration of --test-memory is now 300 (several minutes per gigabyte). Memtest86 and Memtester links are also displayed while running the test.
-
antirez authored
-
antirez authored
-
antirez authored
-
antirez authored
-
- 26 Feb, 2012 1 commit
-
-
antirez authored
redis-benchmark: backported the more capable version from the unstable branch (pipelining,run selected tests,fixes)
-
- 22 Feb, 2012 6 commits
-
-
antirez authored
-
Brad Voth authored
centos) as well as debian/ubuntu
-
antirez authored
Fix for issue #306, thanks to tchajed (on github) for the pull request. The original patch was reworked a bit.
-
antirez authored
-
antirez authored
-
antirez authored
zzlIsInRange() now is capable of handling empty sorted sets that may end inside the data set when loading very old RDB files produced by early-stage versions of Redis.
-
- 21 Feb, 2012 9 commits
-
-
Salvatore Sanfilippo authored
Force SIGSEGV without HAVE_BACKTRACE (2.4)
-
Pieter Noordhuis authored
-
Pieter Noordhuis authored
-
antirez authored
-
antirez authored
-
antirez authored
-
antirez authored
Applied a few modifications to hiredis to tune it for speed (redis-benchmark) and ability to read more deeply nested replies (redis-cli).
-
antirez authored
-
antirez authored
-
- 20 Feb, 2012 1 commit
-
-
antirez authored
-
- 16 Feb, 2012 2 commits
- 15 Feb, 2012 10 commits
-
-
antirez authored
-
antirez authored
-
antirez authored
-
antirez authored
-
antirez authored
Fixes to c->reply_bytes computation, and debug messages to closely study the behavior of memory pressure + slaves + maxmemory + blocked slaves.
-
antirez authored
Precision of getClientOutputBufferMemoryUsage() greatily improved, see issue #327 for more information.
-
antirez authored
-
antirez authored
-
antirez authored
1) sendReplyToClient() now no longer stops transferring data to a single client in the case we are out of memory (maxmemory-wise). 2) in processCommand() the idea of we being out of memory is no longer the naive zmalloc_used_memory() > server.maxmemory. To say if we can accept or not write queries is up to the return value of freeMemoryIfNeeded(), that has full control about that. 3) freeMemoryIfNeeded() now does its math without considering output buffers size. But at the same time it can't let the output buffers to put us too much outside the max memory limit, so at the same time it makes sure there is enough effort into delivering the output buffers to the slaves, calling the write handler directly. This three changes are the result of many tests, I found (partially empirically) that is the best way to address the problem, but maybe we'll find better solutions in the future.
-
antirez authored
Initial version of c->reply_bytes implementation backported from unstable to 2.4, in order to apply issue 327 patches.
-
- 14 Feb, 2012 2 commits