2244 Commits

Author SHA1 Message Date
antirez
24b3799238 redis-cli --pipe: send final ECHO in a safer way.
If the protocol read from stdin happened to contain grabage (invalid
random chars), in the previous implementation it was possible to end
with something like:

dksfjdksjflskfjl*2\r\n$4\r\nECHO....

That is invalid as the *2 should start into a new line. Now we prefix
the ECHO with a CRLF that has no effects on the server but prevents this
issues most of the times.

Of course if the offending wrong sequence is something like:

$3248772349\r\n

No one is going to save us as Redis will wait for data in the context of
a big argument, so this fix does not cover all the cases.

This partially fixes issue #681.
2013-07-03 12:02:09 +02:00
antirez
2f6560f351 pqsort.c: remove the "switch to insertion sort" optimization.
It causes catastrophic performance for certain inputs.

Relevant NetBSD commit:

http://cvsweb.netbsd.org/bsdweb.cgi/src/lib/libc/stdlib/qsort.c?rev=1.20&content-type=text/x-cvsweb-markup&only_with_tag=MAIN

This fixes issue #968.
2013-07-02 17:48:49 +02:00
charsyam
847a40805f fix randstring bug 2013-07-02 12:25:30 +02:00
antirez
aaf5623535 Only allow basenames for dbfilename and appendfilename.
This fixes issue #1094.
2013-07-02 12:24:12 +02:00
antirez
25a3ad7f74 pathIsBaseName() added to utils.c
The function is used to test that the specified string looks like just
as the basename of a path, without any absolute or relative path.
2013-07-02 12:24:08 +02:00
antirez
028fdbb70b getAbsolutePath() moved into utils.c 2013-07-02 12:24:05 +02:00
antirez
8090c37f71 CONFIG SET maxclients. 2013-07-01 10:44:08 +02:00
antirez
75dc48f04a ae.c event loop: API to resize the fd set size on the run. 2013-07-01 10:44:04 +02:00
antirez
0a0fd37e5b Allow SHUTDOWN in loading state. 2013-06-27 12:14:23 +02:00
antirez
7bfbc38068 Redis 2.7.3 2013-06-26 15:26:11 +02:00
antirez
bb0d0fd479 function renamed: popcount_binary -> redisPopcount. 2013-06-26 15:24:58 +02:00
antirez
cdf79c063f Don't disconnect pre PSYNC replication clients for timeout.
Clients using SYNC to replicate are older implementations, such as
redis-cli --slave, and are not designed to acknowledge the master with
REPLCONF ACK commands, so we don't have any feedback and should not
disconnect them on timeout.
2013-06-26 15:24:30 +02:00
antirez
29308077a8 Flush the replication script cache after SCRIPT FLUSH. 2013-06-26 15:24:22 +02:00
antirez
d34c1ac208 Force propagation of SCRIPT LOAD to AOF. 2013-06-26 15:24:09 +02:00
antirez
b7233f40fb SCRIPT FLUSH comment minor pedantic improvement. 2013-06-26 15:24:04 +02:00
antirez
8450d6e24d Move Replication Script Cache initialization in safer place.
It should be called just one time at startup and not every time the Lua
scripting engine is re-initialized, otherwise memory is leaked.
2013-06-26 15:23:52 +02:00
antirez
545fe0c318 Use the RSC to replicate EVALSHA unmodified.
This commit uses the Replication Script Cache in order to avoid
translating EVALSHA into EVAL whenever possible for both the AOF and
slaves.
2013-06-26 15:23:29 +02:00
antirez
9d894b1b8c Replication of scripts as EVALSHA: sha1 caching implemented.
This code is only responsible to take an LRU-evicted fixed length cache
of SHA1 that we are sure all the slaves received.

In this commit only the implementation is provided, but the Redis core
does not use it to actually send EVALSHA to slaves when possible.
2013-06-26 15:23:15 +02:00
antirez
8328d993e1 New API to force propagation.
The old REDIS_CMD_FORCE_REPLICATION flag was removed from the
implementation of Redis, now there is a new API to force specific
executions of a command to be propagated to AOF / Replication link:

    void forceCommandPropagation(int flags);

The new API is also compatible with Lua scripting, so a script that will
execute commands that are forced to be propagated, will also be
propagated itself accordingly even if no change to data is operated.

As a side effect, this new design fixes the issue with scripts not able
to propagate PUBLISH to slaves (issue #873).
2013-06-26 15:21:55 +02:00
antirez
aeab473dfb Allow PUBSUB NUMSUB without channels.
The result is an empty list but it is handy to call it programmatically.
2013-06-26 15:21:12 +02:00
antirez
a8f1474dfd PUBSUB command implemented.
Currently it implements three subcommands:

PUBSUB CHANNELS [<pattern>]    List channels with non-zero subscribers.
PUBSUB NUMSUB [channel_1 ...]  List number of subscribers for channels.
PUBSUB NUMPAT                  Return number of subscribed patterns.
2013-06-26 15:21:08 +02:00
YAMAMOTO Takashi
3642557ae6 don't assume time_t == long
time_t is always 64bit on recent versions of NetBSD.
2013-06-26 15:20:59 +02:00
YAMAMOTO Takashi
30f3ae03a5 use nanosleep instead of usleep
SUSv3 says that:
	The useconds argument shall be less than one million. If the value of
	useconds is 0, then the call has no effect.
and actually NetBSD's implementation rejects such a value with EINVAL.
use nanosleep which has no such a limitation instead.
2013-06-26 15:20:56 +02:00
YAMAMOTO Takashi
f27896a17d rename popcount to popcount_binary to avoid a conflict with NetBSD libc
NetBSD-current's libc has a function named popcount.
hiding these extensions using feature macros is not possible because
redis uses other extensions covered by the same feature macro.
eg. inet_aton
2013-06-26 15:20:32 +02:00
YAMAMOTO Takashi
9a7b09ed35 don't define _XOPEN_SOURCE for NetBSD
on NetBSD, defining _XOPEN_SOURCE hides extensions
like inet_aton, strcasecmp, etc.
2013-06-26 15:20:03 +02:00
Jan-Erik Rediger
90c3a14ac0 Initialize char* to NULL to remove compiler warning 2013-06-20 16:59:04 +02:00
antirez
9af8125c7d Sentinel: parse new INFO replication output correctly.
Sentinel was not able to detect slaves when connected to a very recent
version of Redis master since a previos non-backward compatible change
to INFO broken the parsing of the slaves ip:port INFO output.

This fixes issue #1164
2013-06-20 10:24:31 +02:00
antirez
86147afd08 Allow writes from scripts called by AOF loading in read-only slaves.
This fixes issue #1163
2013-06-19 18:29:05 +02:00
antirez
449ec38fe4 Fix logStackTrace() when logging to stdout.
When the semantics changed from logfile = NULL to logfile = "" to log
into standard output, no proper change was made to logStackTrace() to
make it able to work with the new setup.

This commit fixes the issue.
2013-06-19 14:45:38 +02:00
antirez
bf8e078aa2 Lua script errors format more unified.
lua_pcall error handler now formats errors in a way more similar to
luaPushError() so that errors generated in different contexts look alike.
2013-06-18 19:38:23 +02:00
antirez
b3fbc84cc1 Lua scripting: improve error reporting.
When calling Lua scripts we try to report not just the error but
information about the code line causing the error.
2013-06-18 19:38:19 +02:00
ioddly
e34f00842f Try to report source of bad Lua API calls 2013-06-18 19:38:10 +02:00
antirez
b435817b17 Binary safe dump of object content in redisLogObjectDebugInfo(). 2013-06-04 15:55:35 +02:00
antirez
054632f551 CONFIG SET: accept slave-priority zero, it is valid. 2013-05-31 19:31:51 +02:00
antirez
fe4b62fcaf Refresh good slaves count after CONFIG SET min-slaves-...
This way just after the CONFIG SET enabling the min-slaves feature it is
possible to write to the database without delays.
2013-05-31 07:20:19 +02:00
antirez
971217c7b4 New INFO field "min_slaves_good_slaves".
When min-slaves-to-write feature is active, this field reports the
number of slaves considered good (online state, lag within the specified
range).
2013-05-31 07:19:45 +02:00
antirez
f5275da6e9 Refresh good slaves count when setting slave state as online. 2013-05-31 07:19:42 +02:00
antirez
9d1bc3efcf min-replicas-to-write: only deny write commands.
I guess I needed another coffee...
2013-05-30 11:32:00 +02:00
antirez
d0d67f8d42 min-slaves-to-write: don't accept writes with less than N replicas.
This feature allows the user to specify the minimum number of
connected replicas having a lag less or equal than the specified
amount of seconds for writes to be accepted.
2013-05-30 11:31:46 +02:00
antirez
75fcf5c936 repl_offset field in INFO replication is now just offset. 2013-05-29 19:56:40 +02:00
antirez
c64338aa8f Slaves list in INFO output: lag added, format changed.
There is a new 'lag' information in the list of slaves, in the
"replication" section of the INFO output.

Also the format was changed in a backward incompatible way in order to
make it more easy to parse if new fields are added in the future, as the
new format is comma separated but has named fields (no longer positional
fields).
2013-05-29 19:55:11 +02:00
antirez
889d39b5ba Accept REPLCONF in any state. 2013-05-28 15:26:55 +02:00
antirez
1b87b3ef38 A comment about BLPOP timeout did not reflected actual behavior. 2013-05-27 19:34:12 +02:00
antirez
2d497014ea Version bumped to 2.7.2. 2013-05-27 11:43:47 +02:00
antirez
308940aa2c Close connection with timedout slaves.
Now masters, using the time at which the last REPLCONF ACK was received,
are able to explicitly disconnect slaves that are no longer responding.

Previously the only chance was to see a very long output buffer, that
was highly suboptimal.
2013-05-27 11:43:17 +02:00
antirez
45e6a4023a Send ACK to master once every second.
ACKs can be also used as a base for synchronous replication. However in
that case they'll be explicitly requested by the master when the client
sends a request that needs to be replicated synchronously.
2013-05-27 11:43:14 +02:00
antirez
a74f8fe1ad Don't ACK the master after every command.
Sending an ACK is now moved into the replicationSendAck() function.
2013-05-27 11:43:10 +02:00
antirez
0000d5334d Make sure that REPLCONF ACK really has no return value. 2013-05-27 11:43:06 +02:00
antirez
146f1d7d86 Replication: send REPLCONF ACK to master. 2013-05-27 11:43:03 +02:00
antirez
1e77b77de4 REPLCONF ACK command.
This special command is used by the slave to inform the master the
amount of replication stream it currently consumed.

it does not return anything so that we not need to consume additional
bandwidth needed by the master to reply something.

The master can do a number of things knowing the amount of stream
processed, such as understanding the "lag" in bytes of the slave, verify
if a given command was already processed by the slave, and so forth.
2013-05-27 11:43:00 +02:00