fluencelabs/redis
1
0
Fork 0
mirror of https://github.com/fluencelabs/redis synced 2025-06-12 00:31:21 +00:00
Code Issues Projects Releases Wiki Activity
4,915 Commits 53 Branches 231 Tags
3cfca5afdcb0df598303fa54962d6412826aae3c
Commit Graph

4915 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
antirez
034f39f14d LATENCY HISTORY returns empty array if no data is available. 
Previously we returned an error.
 2014-07-18 12:20:56 +02:00
antirez
ef7c1fbcef Test: enable latency monitor in the default config. 
This way as a side effect of running the test we also stress the latency
monitor data collection.
 2014-07-18 12:20:56 +02:00
antirez
93c6ea6c6f Test: AOF rewrite during write load. 2014-07-18 12:20:56 +02:00
antirez
959667ffe1 Fixed a few missing newline in createLatencyReport(). 2014-07-18 12:20:56 +02:00
antirez
c9ddd141dd createLatencyReport(): compile before commit avoids commits. 2014-07-18 12:20:56 +02:00
antirez
1b6d614f2c createLatencyReport(), fix mount option name. 2014-07-18 12:20:56 +02:00
antirez
44de3a9cfb createLatencyReport(): initialize all advices to zero. 2014-07-18 12:20:56 +02:00
antirez
a117fd2a44 LATENCY DOCTOR first implementation complete. 2014-07-18 12:20:56 +02:00
antirez
31e1e30aa6 Fix analyzeLatencyForEvent() MAD computation. 2014-07-18 12:20:56 +02:00
antirez
9ed02e137c LATENCY DOCTOR: initial draft and events summary output. 2014-07-18 12:20:56 +02:00
antirez
c7f1aa74d7 Latency: low level time series analysis implemented. 2014-07-18 12:20:56 +02:00
antirez
9a037792b6 LATENCY SAMPLES renamed LATENCY HISTORY. 2014-07-18 12:20:56 +02:00
antirez
7c6a028a3a LATENCY RESET implemented. 2014-07-18 12:20:56 +02:00
antirez
cc7b10cb52 Better "final read from parent" algorithm in rewriteAppendOnlyFile*(. 
We now wait up to 1 second for diff data to come from the parent,
however we use poll(2) to wait for more data, and use a counter of
contiguous failures to get data for N times (set to 20 experimentally
after different tests) as an early stop condition to avoid wasting 1
second when the write traffic is too low.
 2014-07-18 12:20:56 +02:00
antirez
d721e6e5c3 Log AOF diff sizes in MBs instead of bytes. 2014-07-18 12:20:56 +02:00
antirez
e615539cc7 aofChildWriteDiffData() better handling of free blocks. 2014-07-18 12:20:55 +02:00
antirez
f0a58bfaba redis-benchmark: abort when all clients are disconnected. 2014-07-18 12:20:55 +02:00
antirez
d3514edd3e Fine tuning of aofReadDiffFromParent() calls trigger. 2014-07-18 12:20:55 +02:00
antirez
180c9143b9 Use amount of I/O not ops to trigger aofReadDiffFromParent(). 2014-07-18 12:20:55 +02:00
antirez
e05cd36326 aofChildWriteDiffData(): write as much as possible. 2014-07-18 12:20:55 +02:00
antirez
9494c84523 Handle write failure in AOF parent -> child ACK. 2014-07-18 12:20:55 +02:00
antirez
896256210f Use a timeout when reading parent ack from AOF child. 2014-07-18 12:20:55 +02:00
antirez
576056d973 Send AOF diffs from parent to child to improve latency. 2014-07-18 12:20:55 +02:00
antirez
ca2db2bcb9 Use fsync instead of aof_fsync in final AOF sync. 
This happens in the child process so we don't care about latency:
better to sync metadata as well.
 2014-07-18 12:20:55 +02:00
antirez
74423be7a5 Fixed conditional for aof-write-pending-fsync latency event selection. 2014-07-18 12:20:55 +02:00
antirez
7989b612af Dependencies updated. 2014-07-18 12:20:55 +02:00
antirez
289e83f1c9 Cast void* to char* to avoid waring in latencyCommand(). 2014-07-18 12:20:55 +02:00
antirez
a7dc975a81 Properly initialize min/max in latency.c. 2014-07-18 12:20:55 +02:00
antirez
b2d6266521 latencyStartMonitor() modified to avoid warnings. 2014-07-18 12:20:55 +02:00
antirez
cd5c13e12f Latency monitor: specialize delayed aof writes events. 2014-07-18 12:20:55 +02:00
antirez
231e016235 LATENCY GRAPH: filling under the curve is more readable. 2014-07-18 12:20:55 +02:00
antirez
3bd6917b0d LATENCY GRAPH implemented. 2014-07-18 12:20:55 +02:00
antirez
6fb6609600 latencyTimeSeries structure max field type fixed. 2014-07-18 12:20:55 +02:00
antirez
9bc408493e Free labels in freeSparklineSequence(). 2014-07-18 12:20:55 +02:00
antirez
b58c960eb2 LATENCY LATEST: add the max field. 2014-07-18 12:20:55 +02:00
antirez
a9d9898680 Latency monitor trheshold value is now configurable. 
This commit adds both support for redis.conf and CONFIG SET/GET.
 2014-07-18 12:20:55 +02:00
antirez
b71a980687 ASCII sparklines generation API. 2014-07-18 12:20:55 +02:00
antirez
e817f6c013 License added to latency.h. 2014-07-18 12:20:55 +02:00
antirez
0f674f3368 Latency monitor turned off by default. 
It is not a good idea to bloat the code with gettimeofday() calls if the
instance is working well, and turning monitoring on at runtime is a
joke.
 2014-07-18 12:20:55 +02:00
antirez
2b5a0e8066 Latency monitor: more hooks around the code. 2014-07-18 12:20:55 +02:00
antirez
372484ab8e Latency monitor: don't add new samples in the same second. 
Instead we update the old sample with the new latency if it is greater.
 2014-07-18 12:20:55 +02:00
antirez
5e56590198 LATENCY LATEST implemented. 2014-07-18 12:20:55 +02:00
antirez
485a5908c0 Latency monitor: command duration is in useconds. Convert. 2014-07-18 12:20:55 +02:00
antirez
41c9d1c08f LATENCY SAMPLES implemented. 2014-07-18 12:20:55 +02:00
antirez
44cf7395a2 Latency monitor: collect slow commands. 
We introduce the distinction between slow and fast commands since those
are two different sources of latency. An O(1) or O(log N) command without
side effects (can't trigger deletion of large objects as a side effect of
its execution) if delayed is a symptom of inherent latency of the system.

A non-fast command (commands that may run large O(N) computations) if
delayed may just mean that the user is executing slow operations.

The advices LATENCY should provide in this two different cases are
different, so we log the two classes of commands in a separated way.
 2014-07-18 12:20:55 +02:00
antirez
62ca4bd438 Latency monitor: basic samples collection. 2014-07-18 12:20:55 +02:00
antirez
4a7fca7c07 Fix Solaris compilation due to ctime_r() call. 
Introduced in Redis 2.8.10 because of a change in Sentinel.
This closes issue #1837.
 2014-06-30 16:28:22 +02:00
antirez
f884be6854 Redis 2.9.56 (Redis 3.0.0 beta-7). 3.0.0-beta7 2014-06-30 12:11:22 +02:00
antirez
05b6b147ec Test: find_available_port: check that cluster port is free as well. 
The function will only return ports that have also port+10000 free, so
that Redis Cluster instances can be executed at the returned port.
 2014-06-30 12:11:22 +02:00
antirez
a5aa3b6491 Test: fix instances.tcl restart_instance abort error. 2014-06-30 12:11:22 +02:00