Commit Graph

4593 Commits

Author SHA1 Message Date
cceb58d233 Unix domain sockets incorrectly listed as IPv6. 2014-09-18 17:07:29 +03:00
2374496799 Cluster: claim ping_sent time even if we can't connect.
This fixes a potential bug that was never observed in practice since
what happens is that the asynchronous connect returns ok (to fail later,
calling the handler) every time, so a ping is queued, and sent_ping
happens to always be populated.

Howver technically connect(2) with a non blocking socket may return an
error synchronously, so before this fix the code was not correct.
2014-09-17 16:39:41 +02:00
c89afc8e5d Cluster: new option to work with partial slots coverage. 2014-09-17 11:10:09 +02:00
a2c740ea93 Better truncated AOF loading tests.
Now there are tests to write more data after loading a truncated AOF,
testing that the loaded data is correct, appending more, and testing
again.
2014-09-16 11:05:12 +02:00
878c089ec9 Seek at the end of AOF after truncate call.
It is not clear if files open in append only mode will automatically fix
their offset after a truncate(2) operation. This commit makes sure that
we reposition the AOF file descriptor offset at the end of the file
after a truncated AOF is loaded and trimmed to the last valid command.
2014-09-16 10:57:40 +02:00
0ba8fe1a43 On AOF end of file, truncate the AOF to last valid command.
Recently we introduced the ability to load truncated AOFs, but
unfortuantely the support was broken since the server, after loading the
truncated AOF, continues appending to the file that is corrupted at the
end. The problem is fixed only in the next AOF rewrite.

This commit fixes the issue by truncating the AOF to the last valid
opcode, and aborting if it is not possible to truncate the file
correctly.
2014-09-16 10:32:58 +02:00
046a00a03d Don't propagate SAVE.
This is a general fix (check that dirty delta is positive) but actually
should have as the only effect fixing the SAVE propagation to
AOF and slaves.
2014-09-16 10:12:50 +02:00
b82d650afa Cluster test: unit 09, Pub/Sub across the cluster. 2014-09-15 18:11:45 +02:00
3064e9bd4b Cluster test: unit 08, update messages. 2014-09-15 16:48:26 +02:00
f5efa9bbad Sentinel sentinelGetLeader() top comment improved. 2014-09-11 19:27:45 +02:00
f4be6f16f2 Sentinel: fix computation of total number of votes.
The code to check the number of voters was never updated to follow the new
Sentinel specification, so the number of voters was computed using only
the set of Sentinels that provided a vote.

This means that there is a changing majority on partitions, even if
usually the issue is not triggered because of the configured quorum
check (what was broken was the other implicit check that requires anyway
half of the known sentinels to agree in order to start a failover).
2014-09-11 18:53:31 +02:00
12b56a969f luaRedisGenericCommand() cached argv handling simplified.
As discussed in issue #1945.
2014-09-10 15:45:59 +02:00
99871803c8 Merge pull request #1993 from xiaost/limit-scan-iter-count
Limit the *SCAN command `dictScan` iterations
2014-09-10 09:57:54 +02:00
acfc19633d Limit the *SCAN command dictScan iterations
*SCAN will cause redis server to hang for seconds
after millions of keys was deleted by SCAN/DEL pairs
2014-09-09 17:53:30 +08:00
b892ea70ae Tests for aof-load-truncated = yes. 2014-09-08 10:56:52 +02:00
9f40c25a08 AOF tests fixed turning aof-load-truncated to no.
When aof-load-truncated option was introduced, with a default of "yes",
the past behavior of the server to abort with trunncated AOF changed, so
we need to explicitly configure the tests to abort with truncated AOF
by setting the option to no.
2014-09-08 10:56:52 +02:00
31f79a46ff Make aof-load-truncated option actually configurable. 2014-09-08 10:56:52 +02:00
de663966c6 Correct cleanup when aborting AOF loading.
Because of the new ability to start with a truncated AOF, we need
to correctly release all the memory on EOF error. Otherwise there is a
small leak, that is not really a problem, but causes a false positive in
the tests that detect memory leaks.
2014-09-08 10:56:52 +02:00
132550efc3 AOF ability to load truncated files. 2014-09-08 10:56:52 +02:00
7b2e5ff9f9 Test AOF format error detection. 2014-09-08 10:56:52 +02:00
0ab04287aa AOF loading: split handling of format errors from unexpected EOF. 2014-09-08 10:56:52 +02:00
d9f0094154 Merge branch 'unstable' of github.com:/antirez/redis into unstable 2014-09-04 11:46:18 +02:00
0a6cbabb26 Sentinel: don't set announce-ip if is empty. 2014-09-04 11:45:58 +02:00
c9437fe5a3 Sentinel: clarify announce-ip/port options in sentinel.conf. 2014-09-04 11:30:11 +02:00
cd576a1aab Sentinel: announce ip/port changes + rewrite.
The original implementation was modified in order to allow to
selectively announce a different IP or port, and to rewrite the two
options in the config file after a rewrite.
2014-09-04 11:23:31 +02:00
3d939266be sentinel: Decouple bind address from address sent to other sentinels
There are instances such as EC2 where the bind address is private
(behind a NAT) and cannot be accessible from WAN.

https://groups.google.com/d/msg/redis-db/PVVvjO4nMd0/P3oWC036v3cJ
2014-09-04 10:54:21 +02:00
0019479f86 Merge pull request #1982 from mattsta/fix-getrange-32bit
Increase size of range request in getrange
2014-09-03 15:10:35 +02:00
b20df972ed Return empty string if GETRANGE of empty string
Previously, GETRANGE of a key containing nothing ("")
would allocate a large (size_t)-1 return value causing
crashes on 32bit builds when it tried to allocate the
4 GB return string.
2014-09-02 18:56:28 -04:00
f0e306f4a0 Increase size of range request in getrange
32 bit builds don't have a big enough long to capture
the same range as a 64 bit build.  If we use "long long"
we get proper size limits everywhere.

Also updates size of unsigned comparison to fit new size of `end`.

Fixes #1981
2014-09-02 18:56:01 -04:00
67e414c7b8 Sentinel: Abort Hello quicker if not connected
We can save a little work by aborting when we enter the function
if we're disconnected.
2014-09-01 16:34:06 +02:00
a23502e5e8 Add regression test for issue #1939 2014-09-01 10:42:27 +02:00
86cde329d1 Store the length of the static argv when first allocated. 2014-09-01 10:42:27 +02:00
91e6b4d74e Fix dictRehash assert casting type.
Also related to #1929.
2014-08-26 10:32:44 +02:00
72aa797c89 Cast to right type in dictNext().
This closes issue #1929, the other part was fixed in the context of issue
2014-08-26 10:26:36 +02:00
064d5c96ac Use long for rehash and iterator index in dict.h.
This allows to support datasets with more than 2 billion of keys
(possible in very large memory instances, this bug was actually
reported).

Closes issue #1814.
2014-08-26 10:18:56 +02:00
293348d0de Missing va_end also added in hiredis copy of sds.c. 2014-08-26 10:05:32 +02:00
26744da0d1 Merge pull request #1964 from mariano-perez-rodriguez/patch-2
Missing assert removal from sdsIncrLen()
2014-08-26 10:03:54 +02:00
8bbc1897c4 Missing assert removal from sdsIncrLen()
Companion for 8eeb1802ec, but dealing with hiredis.
2014-08-25 15:24:15 -03:00
119a7000b5 Use modern typedef form in cluster.h. 2014-08-25 10:42:18 +02:00
8eeb1802ec No longer useful assert removed from sdsIncrLen(). 2014-08-25 10:36:26 +02:00
209f266cc5 Merge branch '1906-merge' into unstable 2014-08-25 10:27:53 +02:00
1f8a6d806c Fix redis-benchmark abort output 2014-08-25 10:26:30 +02:00
6b099c7de6 Deny CLIENT command in scripts
We don't want scripts doing CLIENT SETNAME
or CLIENT KILL or CLIENT LIST or CLIENT PAUSE.

Originally reported by Chris Wj then proper
action inspired by Itamar Haber.

Reference: https://groups.google.com/forum/#!topic/redis-db/09B2EYwyVgk
2014-08-25 10:25:30 +02:00
aa404fc11b redis-benchmark: Remove unused buffer
This just deletes old code that didn't get removed when
logic changed.  We were setting offsets that never
got read anywhere.

Since clients are now just cloned, we don't need to track
per-client buffer offsets anywhere because they are all
the same from the original client.
2014-08-25 10:19:43 +02:00
b34a8c3b75 redis-benchmark: add auth option
Closes #1097
2014-08-25 10:17:33 +02:00
7e63dd23f3 Rename two 'buf' vars to 'ip' for better clarity
Clearly ip[32] is wrong, but it's less clear that buf[32] was wrong
without further reading.
2014-08-25 10:16:20 +02:00
c38884ceac Sentinel: fix bufsize to support IPv6 address
Closes #1914
2014-08-25 10:15:43 +02:00
ef57f94df0 Use correct github url to find commands.json
Once this is merged:
  - merge the latest changes to commands.json in antirez/redis-doc
  - re-run: utils/generate-command-help.rb > src/help.h

Then we'll have nice and easy tab-completed help in redis-cli again.

Closes #1909
2014-08-25 10:15:28 +02:00
5afe1e37c7 Stop tests from leaving a black background
Uses ANSI "default background" color code after closing tests
so any non-black terminals don't remain polluted.

Fixes #1649
Closes #1912
2014-08-25 10:14:03 +02:00
681de88df4 Sentinel: Reject config from STDIN
Sentinel needs to die with a more accurate error message
when attempted to open a config from STDIN.

See: https://groups.google.com/forum/#!topic/redis-db/sYx7VNMWaNM
2014-08-25 10:13:34 +02:00