antirez
63f6351858
RDB: load string objects directly as EMBSTR objects when possible.
2014-07-18 12:20:56 +02:00
michael-grunder
d75fc09354
Fix OBJECT arity
...
Previously, the command definition for the OBJECT command specified
a minimum of two args (and that it was variadic), which meant that
if you sent this:
OBJECT foo
When cluster was enabled, it would result in an assertion/SEGFAULT
when Redis was attempting to extract keys.
It appears that OBJECT is not variadic, and only ever takes 3 args.
https://gist.github.com/michael-grunder/25960ce1508396d0d36a
2014-07-18 12:20:56 +02:00
antirez
a16feb99f2
Fix typo in LATENCY DOCTOR output.
2014-07-18 12:20:56 +02:00
antirez
639674b309
Test: more reliable AOF rewrite test under write load.
2014-07-18 12:20:56 +02:00
antirez
0e22e4ae91
LATENCY command / monitor basic tests.
2014-07-18 12:20:56 +02:00
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
