2aa26d2a63
CONFIG SET/GET support for loglevel
2011-10-05 16:08:35 +02:00
ad7a86fbe0
just minor aesthetic changes to cluster.c
2011-10-05 16:02:45 +02:00
eab0e26e03
replaced redisAssert() with redisAssertWithInfo() in a shitload of places.
2011-10-04 18:43:03 +02:00
bab205f787
redisAssertWithClientInfo() is now redisAssertWithInfo() that is also able to report an optional object. The client is also optional. Specifying NULL will prevent dumping the not available information (either client or object).
2011-10-04 18:05:26 +02:00
e3e6993510
Introduced a redisAssert() variant that is able to show information about the client in the context where the failed assertion was detected.
2011-10-04 17:22:29 +02:00
909aee2c6c
redis-trib: create subcommand fixed calling node info loading method. Was needed after recent refactoring.
2011-10-04 15:53:07 +02:00
0bb5160cb0
Revert "Use the new install script as make install target. Message about install script requiring root changed a bit to make it more evident."
...
After talking with Pieter he changed my mind about this, it is better to
have a simpler install script that works everywhere, and the complex one
can be always executed if needed by hand. We'll make possibly a new
target for the full featured installation script, and even suggest it
after a Make install.
This reverts commit f1e60d7530
2011-10-03 16:04:44 +02:00
37d650032a
Rewrite MIGRATE as DEL for AOF/replication. Also increment the dirty counter to both force replication and persistence.
2011-10-03 15:51:10 +02:00
2a95c944ff
increment server.dirty in restore command to make sure it is replicated and increments the dirty count for persistence concerns.
2011-10-03 15:45:14 +02:00
cd73df62af
Merge pull request #114 from pietern/unstable-zcount
...
Use rank information to compute ZCOUNT
2011-10-03 06:20:23 -07:00
0cfc894066
Remove ZCOUNT branches from generic RANGEBYSCORE code
2011-10-03 14:23:31 +02:00
62d774e5ba
Use element rank instead of iterating in ZCOUNT
2011-10-03 14:14:43 +02:00
f1e60d7530
Use the new install script as make install target. Message about install script requiring root changed a bit to make it more evident.
2011-10-03 13:28:54 +02:00
13c7e5ef29
Exact variant of CRC16 specified into crc16.c
2011-10-02 14:05:29 +02:00
66c146592a
when processing gossip packets make sure to also update the node bitmap when associating slots to nodes. Fixed simply using the appropriate helper function to add a slot.
2011-10-01 15:11:07 +02:00
7112580cb3
fixed a few problems with redis-trib resharding.
2011-10-01 01:31:46 +02:00
a0189bbe75
redis-trib: initial working implementation of cluster rehashing, more work needed to make it more correct, more reliable.
2011-09-30 22:18:07 +02:00
d38d2fdfdc
Fixed two bugs in the CLUSTER SETSLOT ... NODE subcommand
2011-09-30 22:17:24 +02:00
9a38df8799
redis-trib: actual slot migration work in progress, more work needed.
2011-09-30 19:21:36 +02:00
c5954c1966
Clear the importing status from the slot if a CLUSTER SETSLOT command permanently assigns the slot to the importing node.
2011-09-30 19:20:56 +02:00
6c0047c430
redis-trib: better slots allocation strategy for resharding
2011-09-30 18:41:25 +02:00
841cd7684c
redis-trib: initial slots allocation strategy, still to improve for better balancing when there are just a few slots to move.
2011-09-30 18:28:51 +02:00
85b514d165
redis-trib: reshard command work in progress
2011-09-29 16:06:49 +02:00
9514aa3251
redis-trib: minor refactoring creating a method to load the cluster information starting from a single node
2011-09-29 15:45:10 +02:00
5d8f25da36
redis-trib: don't crash loading node info for nodes without assigned slots
2011-09-29 15:31:02 +02:00
3b5289a04c
added comment about SETSLOT NODE form.
2011-09-29 15:26:01 +02:00
7afc3a9611
Fixed command table for RESTORE to make it accepting keys only for the right slots when cluster is enabled.
2011-09-29 15:14:06 +02:00
d7021b081b
redis-trib: added cluster state to node info string
2011-09-29 15:04:23 +02:00
92dd76c8ee
redis-trib: all node information into a single hash
2011-09-29 14:44:27 +02:00
b08c9dd280
redis-trib: when loading node info also fetch the output of CLUSTER INFO.
2011-09-29 13:18:09 +02:00
f639f99180
redis-trib cluster check command: check that all the 4096 slots are covered
2011-09-29 12:50:46 +02:00
0cae060a26
Compilation fixed on OpenBSD making sure that _XOPEN_SOURCE is set to 700 in fmacros.h
2011-09-29 10:20:03 +02:00
d3f7fbfc09
initial node loading info code for redis-trib
2011-09-28 19:08:35 +02:00
1ef8b0a96d
show node with myself flag always as connected in CLUSTER NODES output.
2011-09-28 18:28:36 +02:00
002d5626e0
Scripting engine now only loads selected libraries, using code originally contributed by @loopole.
2011-09-27 18:46:23 +02:00
9f772cc237
Return errors if a write command is called inside a Lua script after a random command was called. See https://github.com/antirez/redis/issues/95 for more information.
2011-09-27 15:30:31 +02:00
15ef605340
Deny commands flagged as REDIS_CMD_NOSCRIPT from Lua scripts
2011-09-27 13:57:10 +02:00
b60ed6e812
added the NOSCRIPT and RANDOM command flags
2011-09-27 13:45:46 +02:00
5d02b00f56
command table refactoring to make it simpler adding new flags
2011-09-26 15:40:39 +02:00
e108bab043
Lua math.random and math.randomseed replaced with our own version based on redisSrand48(). Seed initialized to the same value at every EVAL/EVALSHA call.
2011-09-23 15:40:58 +02:00
69786b262d
Defined macro with bigger number that redisLrand48() can output.
2011-09-23 15:06:07 +02:00
cbdac04a5e
libc neutral random function derived from a drand48() implementation added. Will be used to replace Lua's math.random implementation.
2011-09-23 14:51:48 +02:00
f96a8a8054
rioInitWithFile nad rioInitWithBuffer functions now take a rio structure pointer to avoid copying a structure to return value to the caller.
2011-09-22 16:00:40 +02:00
69cecb511f
make sure to return just 1 for rio.c write when the target is a buffer, as we do when the target is a file.
2011-09-22 15:54:08 +02:00
4c0462972e
comment on top of the _rio structure modified for correctness as actually fwrite/fread semantics is different in general, but was 0/1 in our old usage before rio.c as we always used 1 as number items, and the actual number of bytes to read as item length.
2011-09-22 15:47:48 +02:00
f9c6f39b2b
merge conflicts resolved
2011-09-22 15:15:26 +02:00
7c748c061e
Merge pull request #97 from jvain/redis-cli
...
redis-cli segfaults with single numeric argument greater than zero
2011-09-21 13:32:24 -07:00
aee7f99760
fixed a small bug that caused redis-cli to segfault when given single numeric parameter greater that zero.
2011-09-21 23:22:14 +03:00
ac1f6fd07a
Merge pull request #78 from vambo/patch-1
...
Corrected typo in documentation for R_Zero, R_PosInf, R_NegInf, R_Nan;
2011-09-20 02:00:58 -07:00
5bae401107
Merge pull request #79 from annulen/mac_ppc
...
Fixed compilation on Mac/PPC
2011-09-20 01:58:55 -07:00
