2834 Commits

Author SHA1 Message Date
Pieter Noordhuis
0ef889274f Compare integers in ziplist regardless of encoding
Because of the introduction of new integer encoding types for ziplists
in the 2.6 tree, the same integer value may have a different encoding in
different versions of the ziplist implementation. This means that the
encoding can NOT be used as a fast path in comparing integers.
2012-05-04 17:26:24 -07:00
Pieter Noordhuis
1b1cf8e7bf Fix install target on OSX (see #495) 2012-05-04 11:54:25 -07:00
quiver
7f10703b33 fix several bugs of init.d scripts
- PIDFILE environ variable was not properly retrieved
- chkconfig command failed
2012-05-04 13:42:03 +02:00
antirez
0cf10e8e86 syncio.c read / write functions reworked for correctness and performance.
The new implementation start reading / writing before blocking with
aeWait(), likely the descriptor can accept writes or has buffered data
inside and we can go faster, otherwise we get an error and wait.

This change has effects on speed but also on correctness: on socket
errors when we perform non blocking connect(2) write is performed ASAP
and the error is returned ASAP before waiting.

So the practical effect is that now a Redis slave is more available if it
can not connect to the master, previously the slave continued to block on
syncWrite() trying to send SYNC, and serving commands very slowly.
2012-05-02 22:45:12 +02:00
antirez
9b43b1ef4d Remove useless trailing space in SYNC command sent to master. 2012-05-02 21:48:08 +02:00
antirez
0b08d64882 Use specific error if master is down and slave-serve-stale-data is set to no.
We used to reply -ERR ... message ..., now the reply is
instead -MASTERDOWN ... message ... so that it can be distinguished
easily by the other error conditions.
2012-05-02 17:14:45 +02:00
antirez
96d9c6cb8b Add a note abotu read-only slaves in 2.6 release notes. 2012-05-02 16:35:53 +02:00
antirez
0f07781538 Redis 2.5.8 (2.6.0 RC2). 2.6.0-rc2 2012-05-02 12:17:21 +02:00
antirez
1858da2faa Test "Turning off AOF kills the background writing child if any" is now more reliable. 2012-05-02 11:40:55 +02:00
Salvatore Sanfilippo
83b1092cf2 Merge pull request #488 from pietern/2.6-safekeys
Use safe dictionary iterator from KEYS (fixes #487)
2012-05-01 01:50:25 -07:00
Pieter Noordhuis
9311d2b527 Use safe dictionary iterator from KEYS
Every matched key in a KEYS call is checked for expiration. When the key
is set to expire, the call to `getExpire` will assert that the key also
exists in the main dictionary. This in turn causes a rehashing step to
be executed. Rehashing a dictionary when there is an iterator active may
result in the iterator emitting duplicate entries, or not emitting some
entries at all. By using a safe iterator, the rehash step is omitted.
2012-04-30 10:16:20 -07:00
Harmen
8520066d7b Show problem with 'keys' command with specific command sequence. 2012-04-30 09:51:23 -07:00
antirez
8f984bef29 Properly wait the slave to sync with master in BRPOPLPUSH test. 2012-04-30 11:32:02 +02:00
antirez
dd418873db A more lightweight implementation of issue 141 regression test. 2012-04-29 17:16:47 +02:00
antirez
b330de57ff Added "read-only slaves" in new features section of 2.6 release notes. 2012-04-27 23:06:02 +02:00
antirez
18759c927a yet another typo fixed in release notes. 2012-04-27 17:04:03 +02:00
antirez
8b97442c20 Fixed release notes typo 2012-04-27 17:01:44 +02:00
antirez
7c5d96d98e Redis 2.5.7 (2.6 RC1) 2.6.0-rc1 2012-04-27 16:40:07 +02:00
antirez
603adb2b29 memtest.c fixed to actually use v1 and v2 in memtest_fill_value(). 2012-04-27 16:28:31 +02:00
antirez
748f206e3d Release notes updated with the new 2.6 features. 2012-04-27 16:07:42 +02:00
antirez
2c0aae760f redis-cli commands description in help.h updated. 2012-04-27 15:57:17 +02:00
antirez
b1aa7183d7 Update makefile dependencies. 2012-04-27 15:56:16 +02:00
antirez
77a75fdef5 Set LUA_MASKCOUNT hook more selectively. Fixes issue #480.
An user reported a crash with Redis scripting (see issue #480 on
github), inspection of the kindly provided strack trace showed that
server.lua_caller was probably set to NULL. The stack trace also slowed
that the call to the hook was originating from a point where we just
used to set/get a few global variables in the Lua state.

What was happening is that we did not set the timeout hook selectively
only when the user script was called. Now we set it more selectively,
specifically only in the context of the lua_pcall() call, and make sure
to remove the hook when the call returns. Otherwise the hook can get
called in random contexts every time we do something with the Lua
state.
2012-04-27 11:47:30 +02:00
antirez
e69e76d442 Re-introduce -g -rdynamic -ggdb when linking, fixing strack traces.
A previous commit removed -g -rdynamic -ggdb as LDFLAGS, not allowing
Redis to produce a stack trace wth symbol names on crash.
This commit fixes the issue.
2012-04-27 11:47:27 +02:00
antirez
9db4cea235 Produce the stack trace in an async safe way. 2012-04-27 11:47:22 +02:00
antirez
a28ab2a92b Don't use an alternative stack for SIGSEGV & co.
This commit reverts most of c575766202773c858be0870c20cd495b722927c3, in
order to use back main stack for signal handling.

The main reason is that otherwise it is completely pointless that we do
a lot of efforts to print the stack trace on crash, and the content of
the stack and registers as well. Using an alternate stack broken this
feature completely.
2012-04-27 11:47:18 +02:00
antirez
b1ee7da75a Redis test: More reliable BRPOPLPUSH replication test.
Now it uses the new wait_for_condition testing primitive.
Also wait_for_condition implementation was fixed in this commit to properly
escape the expr command and its argument.
2012-04-27 11:47:15 +02:00
antirez
d7bad544dc Redis test: scripting EVALSHA replication test more reliable.
A new primitive wait_for_condition was introduced in the scripting
engine that makes waiting for events simpler, so that it is simpler to
write tests that are more resistant to timing issues.
2012-04-27 11:47:12 +02:00
David Tran
8111a803cb Spelling: s/synchrnonization/synchronization 2012-04-27 11:47:08 +02:00
antirez
c16bf717de Explicitly use bash for install_server.sh. Fixes issue #397 2012-04-24 19:35:40 +02:00
antirez
12a042f863 redis-check-dump now is RDB version 6 ready. 2012-04-24 19:35:36 +02:00
antirez
717145c1a3 Spurious debugging printf removed. 2012-04-24 19:35:33 +02:00
antirez
dcd4efe9ef Added two new encodings to ziplist.c
1) One integer "immediate" encoding that can encode from 0 to 12 in the
encoding byte itself.
2) One 8 bit signed integer encoding that can encode 8 bit signed small
integers in a single byte.

The idea is to exploit all the not used bits we have around in a
backward compatible way.
2012-04-24 19:35:29 +02:00
antirez
62bfa66284 rdbLoad() should check REDIS_RDB_VERSION instead of hardcoded number. 2012-04-24 19:35:25 +02:00
antirez
dd51571cc3 ziplist.c: added comments about the new 24 bit encoding. 2012-04-24 19:35:22 +02:00
Grisha Trubetskoy
ad91404a32 Add a 24bit integer to ziplists to save one byte for ints that can
fit in 24 bits (thanks to antirez for catching and solving the two's compliment
bug).

Increment REDIS_RDB_VERSION to 6
2012-04-24 19:35:18 +02:00
antirez
9de5d4600a A few compiler warnings suppressed. 2012-04-24 19:35:03 +02:00
antirez
38b60dea54 Fix and refactoring of code used to get registers on crash.
This fixes compilation on FreeBSD (and possibly other systems) by
not using ucontext_t at all if HAVE_BACKTRACE is not defined.
Also the ifdefs to get the registers are modified to explicitly test for the
operating system in the first level, and the arch in the second level
of nesting.
2012-04-24 19:34:15 +02:00
antirez
69b30cfcb6 Ziplist encoding now tested with negative integers as well. 2012-04-24 19:34:08 +02:00
antirez
0a8a1e78dc New time limit for protocol desync test set to 30 seconds to reduce false positives. 2012-04-24 19:34:03 +02:00
antirez
537dafab84 Remove loadfile() access from the scripting engine. 2012-04-24 19:33:58 +02:00
Michael Schlenker
7d6bf7956e Replace unnecessary calls to echo and cat
Tcl's exec can send data to stdout itself, no need to call cat/echo for
that usually.
2012-04-24 19:33:54 +02:00
antirez
e337b26050 Even inside #if 0 comments are comments. 2012-04-21 21:49:34 +02:00
antirez
590d55a206 Limit memory used by big SLOWLOG entries.
Two limits are added:

1) Up to SLOWLOG_ENTRY_MAX_ARGV arguments are logged.
2) Up to SLOWLOG_ENTRY_MAX_STRING bytes per argument are logged.
3) slowlog-max-len is set to 128 by default (was 1024).

The number of remaining arguments / bytes is logged in the entry
so that the user can understand better the nature of the logged command.
2012-04-21 21:00:33 +02:00
antirez
c11a01a030 redis.conf AOF section comments improved. 2012-04-21 12:17:33 +02:00
antirez
30e89410d4 README now makes clear that our support for solaris derived systems is "best effort". 2012-04-21 12:17:29 +02:00
antirez
abfd08f5ad New tests related to scripts max execution time. 2012-04-19 23:49:46 +02:00
antirez
ca577d162a SHUTDOWN NOSAVE now can stop a non returning script. Issue #466. 2012-04-19 23:36:04 +02:00
antirez
d54943b76d Currenly not used code in dict.c commented out. 2012-04-18 23:56:15 +02:00
antirez
c3312760fe Tests for scripting PRNG. 2012-04-18 23:50:27 +02:00