Commit Graph

5760 Commits

Author SHA1 Message Date
179e54d2a9 Fix for slaves chains. Force resync of slaves (simply disconnecting them) when SLAVEOF turns a master into a slave. 2012-03-29 09:24:02 +02:00
52ae8af807 added redis.sha1hex(string) as lua scripting function.
(The original implementation was modified by @antirez to conform Redis
coding standards.)
2012-03-28 20:37:40 +02:00
5471b8babd Fixes for redisLogFromHandler(). 2012-03-28 13:51:23 +02:00
a7d12cbaf1 Log from signal handlers is now safer. 2012-03-28 13:45:39 +02:00
1043c8064b Merge branch 'watchdog' into unstable 2012-03-28 13:16:19 +02:00
e4669c045d Merge pull request #389 from huangz1990/patch-1
fix typo
2012-03-27 14:00:08 -07:00
b57dbdbba3 remove disk-store related comments 2012-03-27 18:46:51 +02:00
8af9fe841c declare hashDictType as external too 2012-03-27 18:18:57 +02:00
d194905449 use server.unixtime instead of time(NULL) where possible (cluster.c not checked though) 2012-03-27 17:39:58 +02:00
024f213b12 fix time() instead of mstime() in expireIfNeeded 2012-03-27 17:31:21 +02:00
d174eed5d7 define zlibc_free() in a way that is not shadowed by jemalloc. 2012-03-27 16:54:53 +02:00
23c0cdd2ad Produce the watchlog warning log in a way that is safer from a signal handler. Fix a memory leak in the backtrace generation function. 2012-03-27 15:24:33 +02:00
aa96122d96 Mask SIGALRM everything but in the main thread.
This is required to ensure that the signal will be delivered to the main
thread when the watchdog timer expires.
2012-03-27 13:48:57 +02:00
a354da9acd Correctly set the SIGARLM timer for the software watchdog. 2012-03-27 12:11:37 +02:00
39bd025c29 Redis software watchdog. 2012-03-27 11:47:51 +02:00
a323870450 SIGSEGV handler refactored so that we can reuse stack trace and current client logging functionalities in other contexts. 2012-03-27 10:40:07 +02:00
ca09ad4d64 CONFIG RESETSTAT resets two more fields. 2012-03-25 11:43:19 +02:00
c1d01b3c57 New INFO field aof_delayed_fsync introduced.
This new field counts all the times Redis is configured with AOF enabled and
fsync policy 'everysec', but the previous fsync performed by the
background thread was not able to complete within two seconds, forcing
Redis to perform a write against the AOF file while the fsync is still
in progress (likely a blocking operation).
2012-03-25 11:27:35 +02:00
1b247d1333 Add used allocator in redis-server -v output. 2012-03-24 11:53:03 +01:00
58e34e6cb1 Fixed memory leak in hash loading. 2012-03-23 20:24:34 +01:00
bd376d13f8 Big endian fix. The bug was introduced because of a typo. 2012-03-23 12:42:20 +01:00
6f0e77ca19 Replicate HINCRBYFLOAT as HSET. 2012-03-23 10:22:58 +01:00
7b558b1d64 Code style hack. 2012-03-22 18:17:09 +01:00
1f6146df0c Result of INCRBYFLOAT and HINCRBYFLOAT should never be in exponential form, and also should never contain trailing zeroes. This is not possible with vanilla printf() format specifiers, so we alter the output. 2012-03-22 18:17:05 +01:00
b22eab8faf Correctly create shared.oomerr as an sds string. 2012-03-21 12:11:07 +01:00
7dcdd281f5 DEBUG should not be flagged as w otherwise we can not call DEBUG DIGEST and other commands against read only slaves. 2012-03-20 17:53:47 +01:00
f3fd419fc9 Support for read-only slaves. Semantical fixes.
This commit introduces support for read only slaves via redis.conf and CONFIG GET/SET commands. Also various semantical fixes are implemented here:

1) MULTI/EXEC with only read commands now work where the server is into a state where writes (or commands increasing memory usage) are not allowed. Before this patch everything inside a transaction would fail in this conditions.

2) Scripts just calling read-only commands will work against read only
slaves, when the server is out of memory, or when persistence is into an
error condition. Before the patch EVAL always failed in this condition.
2012-03-20 17:32:48 +01:00
0d44d50792 Suppress warnings compiling redis-cli with certain gcc versions. 2012-03-19 19:28:49 +01:00
bb0aadbe21 Read-only flag removed from PUBLISH command. 2012-03-19 19:16:41 +01:00
d4a515c56d Memory addressing test implemented. 2012-03-19 14:02:34 +01:00
d033ccb0af More memory tests implemented. Default number of iterations lowered to a more acceptable value of 50. 2012-03-18 18:03:27 +01:00
a5801142a4 Fixed typo. 2012-03-18 17:27:56 +01:00
1a197a3c1a Number of iteration of --test-memory is now 300 (several minutes per gigabyte). Memtest86 and Memtester links are also displayed while running the test. 2012-03-18 17:25:00 +01:00
525be599a8 On crash suggest to give --test-memory a try. 2012-03-18 11:35:35 +01:00
fb068dc91d Memory test function now less boring thanks to screen-wide progress bar. 2012-03-16 21:19:53 +01:00
54e0fa1c27 Hem... actual memtest.c file added. 2012-03-16 17:21:49 +01:00
c5166e3fc5 First implementation of --test-memory. Still a work in progress. 2012-03-16 17:17:39 +01:00
c9d3dda29c Fix for issue #391.
Use a simple protocol between clientsCron() and helper functions to
understand if the client is still valind and clientsCron() should
continue processing or if the client was freed and we should continue
with the next one.
2012-03-15 20:55:14 +01:00
9448ddb0c6 fix typo 2012-03-15 14:27:14 +08:00
ae22bf1ef6 Reclaim space from the client querybuf if needed. 2012-03-14 15:32:30 +01:00
739803c064 sds.c: sdsAllocSize() function added. 2012-03-14 14:58:26 +01:00
9555f8f21b sds.c new function sdsRemoveFreeSpace().
The new function is used in order to resize the string allocation so
that only the minimal allocation possible is used, removing all the free
space at the end of the string normally used to improve efficiency of
concatenation operations.
2012-03-14 10:13:23 +01:00
529bde82ec Call all the helper functions needed by clientsCron() as clientsCronSomething() for clarity. 2012-03-14 09:56:22 +01:00
d19015be12 Process async client checks like client timeouts and BLPOP timeouts incrementally using a circular list. 2012-03-13 18:05:11 +01:00
bbaeda402c Added a qbuf-free field to CLIENT LIST output. 2012-03-13 13:26:33 +01:00
e74dca73d9 Client creation time in redisClient structure. New age field in CLIENT LIST output. 2012-03-13 13:05:08 +01:00
573373802e c->bufpos initialization moved for aesthetics. 2012-03-13 12:59:27 +01:00
c3e7441dad RDB hashes loading, fixed another bug in the loading of HT-encoded hashes: when the hash entry is too big for ziplist, add the field, then convert. The code used to break before the new entry was inserted, resulting into missing fields in the loaded Hash object. 2012-03-13 11:00:18 +01:00
c3c856228d RDB hashes loading fixed removing the assertion that failed every time an HT-encoded hash was loaded. 2012-03-13 09:49:11 +01:00
64b4c33c0b Build dependencies updated. 2012-03-10 12:40:03 +01:00