20927 Commits

Author SHA1 Message Date
Wen Hui
38da8d07d0
Clean up no-conf server warning for sentinel mode (#8769) 2021-04-13 16:28:54 +03:00
Oran Agra
8133b72268 fix access to uninitialized var in checkClientPauseTimeoutAndReturnIfPaused (#8765)
server.client_pause_end_time is uninitialized, or actually 0, at startup,
which means this method would think the timeout was reached
and go look for paused clients.

This causes no harm since unpauseClients will not find any paused clients.
2021-04-13 08:41:12 +03:00
Oran Agra
733daef127
fix access to uninitialized var in checkClientPauseTimeoutAndReturnIfPaused (#8765)
server.client_pause_end_time is uninitialized, or actually 0, at startup,
which means this method would think the timeout was reached
and go look for paused clients.

This causes no harm since unpauseClients will not find any paused clients.
2021-04-13 08:41:12 +03:00
Oran Agra
e57e8779d8 Fix busy loop in ae.c when timer event is about to fire (#8764)
The code used to decide on the next time to wake on a timer with
microsecond accuracy, but when deciding to go to sleep it used
milliseconds accuracy (with truncation), this means that it would wake
up too early, see that there's no timer to process, and go to sleep
again for 0ms again and again until the right microsecond arrived.

i.e. a timer for 100ms, would sleep for 99ms, but then do a busy loop
through the kernel in the last millisecond, triggering many calls to
beforeSleep.

The fix is to change all the logic in ae.c to work with microseconds,
which is good since most of the ae backends support micro (or even nano)
seconds. however the epoll backend, doesn't support micro, so to avoid
this problem it needs to round upwards, rather than truncate.

Issue created by the monotonic timer PR #7644 (redis 6.2)
Before that, all the timers in ae.c were in milliseconds (using
mstime), so when it requested the backend to sleep till the next timer
event, it would have worked ok.
2021-04-13 07:35:03 +03:00
Oran Agra
175a9e3199
Fix busy loop in ae.c when timer event is about to fire (#8764)
The code used to decide on the next time to wake on a timer with
microsecond accuracy, but when deciding to go to sleep it used
milliseconds accuracy (with truncation), this means that it would wake
up too early, see that there's no timer to process, and go to sleep
again for 0ms again and again until the right microsecond arrived.

i.e. a timer for 100ms, would sleep for 99ms, but then do a busy loop
through the kernel in the last millisecond, triggering many calls to
beforeSleep.

The fix is to change all the logic in ae.c to work with microseconds,
which is good since most of the ae backends support micro (or even nano)
seconds. however the epoll backend, doesn't support micro, so to avoid
this problem it needs to round upwards, rather than truncate.

Issue created by the monotonic timer PR #7644 (redis 6.2)
Before that, all the timers in ae.c were in milliseconds (using
mstime), so when it requested the backend to sleep till the next timer
event, it would have worked ok.
2021-04-13 07:35:03 +03:00
John Sully
7f68765981 Allow prefetch even with a single thread
Former-commit-id: 2e68821b330a6bae8a352e37c3da643d504b2ce3
2021-04-12 04:44:52 +00:00
John Sully
b2ffe82640 Allow prefetch even with a single thread
Former-commit-id: 2e68821b330a6bae8a352e37c3da643d504b2ce3
2021-04-12 04:44:52 +00:00
John Sully
92028ddb5c Avoid posting unnecessary async tasks
Former-commit-id: 1661d2a05943f96992be195f5dc32dd9a67c0e68
2021-04-12 03:44:29 +00:00
John Sully
211b0e5f80 Avoid posting unnecessary async tasks
Former-commit-id: 1661d2a05943f96992be195f5dc32dd9a67c0e68
2021-04-12 03:44:29 +00:00
John Sully
2eb3710039 Fix issue where GC is not free'd until a BGSAVE
Former-commit-id: 38523e6b508cf5f4b40c178dfe98554abea8f6bd
2021-04-12 03:44:15 +00:00
John Sully
ea2bbfb5c1 Fix issue where GC is not free'd until a BGSAVE
Former-commit-id: 38523e6b508cf5f4b40c178dfe98554abea8f6bd
2021-04-12 03:44:15 +00:00
John Sully
2c8540c4fd Make prefetch more aggressive
Former-commit-id: 25a5cfefcf7fa3451e92500f5d310290c4b6bbde
2021-04-12 03:42:05 +00:00
John Sully
14250faddd Make prefetch more aggressive
Former-commit-id: 25a5cfefcf7fa3451e92500f5d310290c4b6bbde
2021-04-12 03:42:05 +00:00
John Sully
5793bb0c34 Don't prefetch when lock contention is low, it increases latency
Former-commit-id: 0d21614e0e5aba28acd364231823d51a3073081f
2021-04-12 03:41:53 +00:00
John Sully
1b121723e2 Don't prefetch when lock contention is low, it increases latency
Former-commit-id: 0d21614e0e5aba28acd364231823d51a3073081f
2021-04-12 03:41:53 +00:00
John Sully
3ed9963363 Reduce P99 latency with async rehash
Former-commit-id: 7ea4c26fd82c0cdfa377183083f38a43336e480b
2021-04-12 03:39:13 +00:00
John Sully
e6782d8f1b Reduce P99 latency with async rehash
Former-commit-id: 7ea4c26fd82c0cdfa377183083f38a43336e480b
2021-04-12 03:39:13 +00:00
John Sully
aa64a260fc Make prefetch configurable
Former-commit-id: 3b660347d70cc25d57119080bd43fb4671e36488
2021-04-12 03:38:57 +00:00
John Sully
df66c598e9 Make prefetch configurable
Former-commit-id: 3b660347d70cc25d57119080bd43fb4671e36488
2021-04-12 03:38:57 +00:00
John Sully
da545be5b5 Make prefetch more aggressive
Former-commit-id: 9cb0be197fb96d7fb3cb697c19b5be313b01337a
2021-04-12 03:24:05 +00:00
John Sully
e541d82e1f Make prefetch more aggressive
Former-commit-id: 9cb0be197fb96d7fb3cb697c19b5be313b01337a
2021-04-12 03:24:05 +00:00
John Sully
5ccaa9265c Don't prefetch when lock contention is low, it increases latency
Former-commit-id: 9b2629f6a20368cec8e55f0d006f3a67c8b770b7
2021-04-12 03:23:49 +00:00
John Sully
c070f6ece2 Don't prefetch when lock contention is low, it increases latency
Former-commit-id: 9b2629f6a20368cec8e55f0d006f3a67c8b770b7
2021-04-12 03:23:49 +00:00
John Sully
2d2ae90f30 Reduce P99 latency with async rehash
Former-commit-id: 6c045837c7cf92dc92be35465229b482e09e46d2
2021-04-12 03:22:22 +00:00
John Sully
5b53c8e88e Reduce P99 latency with async rehash
Former-commit-id: 6c045837c7cf92dc92be35465229b482e09e46d2
2021-04-12 03:22:22 +00:00
Wang Yuan
8c5634f4eb Fix wrong check for aof fsync and handle aof fsync errno (#8751)
The bio aof fsync fd may be closed by main thread (AOFRW done handler)
and even possibly reused for another socket, pipe, or file.
This can can an EBADF or EINVAL fsync error, which will lead to -MISCONF errors failing all writes.
We just ignore these errno because aof fsync did not really fail.

We handle errno when fsyncing aof in bio, so we could know the real reason
when users get -MISCONF Errors writing to the AOF file error

Issue created with #8419
2021-04-11 08:14:31 +03:00
Wang Yuan
a0e19e3cf1
Fix wrong check for aof fsync and handle aof fsync errno (#8751)
The bio aof fsync fd may be closed by main thread (AOFRW done handler)
and even possibly reused for another socket, pipe, or file.
This can can an EBADF or EINVAL fsync error, which will lead to -MISCONF errors failing all writes.
We just ignore these errno because aof fsync did not really fail.

We handle errno when fsyncing aof in bio, so we could know the real reason
when users get -MISCONF Errors writing to the AOF file error

Issue created with #8419
2021-04-11 08:14:31 +03:00
yjph
2fa3e1d999 Fix the display of make install (#8667) 2021-04-10 21:25:53 +03:00
yjph
cd03e293c3
Fix the display of make install (#8667) 2021-04-10 21:25:53 +03:00
John Sully
c92b90eb91 DO not set the timethread as high priority, it can starve the server threads
Former-commit-id: faeac65371af9d6b6effe0886bcbdefaec24ad6d
2021-04-09 01:06:24 +00:00
John Sully
d58a415e29 DO not set the timethread as high priority, it can starve the server threads
Former-commit-id: faeac65371af9d6b6effe0886bcbdefaec24ad6d
2021-04-09 01:06:24 +00:00
John Sully
e1adedb1fa DO not set the timethread as high priority, it can starve the server threads
Former-commit-id: 5355207a0ad3f1a191fa06450490c792caa76e87
2021-04-09 01:05:55 +00:00
John Sully
788119a964 DO not set the timethread as high priority, it can starve the server threads
Former-commit-id: 5355207a0ad3f1a191fa06450490c792caa76e87
2021-04-09 01:05:55 +00:00
John Sully
69f7a194bc Make prefetch configurable
Former-commit-id: 16996c048042bd3799c8051645bbe7c54137d54c
2021-04-08 19:52:38 +00:00
John Sully
9d0001ae7c Make prefetch configurable
Former-commit-id: 16996c048042bd3799c8051645bbe7c54137d54c
2021-04-08 19:52:38 +00:00
John Sully
571718f774 Avoid posting unnecessary async tasks
Former-commit-id: 08f63fdfd6c78388bba093ec2edda7d77fc9173e
2021-04-07 17:41:20 +00:00
John Sully
5d924bf16a Avoid posting unnecessary async tasks
Former-commit-id: 08f63fdfd6c78388bba093ec2edda7d77fc9173e
2021-04-07 17:41:20 +00:00
John Sully
635ddad7fc Fix issue where GC is not free'd until a BGSAVE
Former-commit-id: e19350005b571591876e49219bfca75e905604a5
2021-04-07 17:30:59 +00:00
John Sully
c0e80ffcda Fix issue where GC is not free'd until a BGSAVE
Former-commit-id: e19350005b571591876e49219bfca75e905604a5
2021-04-07 17:30:59 +00:00
John Sully
55a118ecd0 Reduce connection latency for cluster clients
Former-commit-id: f1acee99bdaee4faf9e18cdf4734d51a73e78a41
2021-04-07 15:49:58 +00:00
John Sully
86a5b2fbc7 Reduce connection latency for cluster clients
Former-commit-id: f1acee99bdaee4faf9e18cdf4734d51a73e78a41
2021-04-07 15:49:58 +00:00
John Sully
eb818d4c00 Fix build break from merge conflicts
Former-commit-id: 5052388bd43b0e42430fd741fb2b403544684246
2021-04-07 15:25:22 +00:00
John Sully
1bf5477602 Fix build break from merge conflicts
Former-commit-id: 5052388bd43b0e42430fd741fb2b403544684246
2021-04-07 15:25:22 +00:00
John Sully
ca13d87204 Merge branch 'keydbpro' of https://gitlab.eqalpha.com/external-collab/keydb-pro-6 into keydbpro_collab
Former-commit-id: e077756b140855cb5a7e60567abf845dbfbc162d
2021-04-07 15:14:59 +00:00
John Sully
d832ebb221 Merge branch 'keydbpro' of https://gitlab.eqalpha.com/external-collab/keydb-pro-6 into keydbpro_collab
Former-commit-id: e077756b140855cb5a7e60567abf845dbfbc162d
2021-04-07 15:14:59 +00:00
Wen Hui
dfbfe4c558 use getPositiveLongFromObjectOrReply for positive check of args (#8750)
just a cleanup
2021-04-07 10:28:53 +03:00
Wen Hui
d96f47cf06
use getPositiveLongFromObjectOrReply for positive check of args (#8750)
just a cleanup
2021-04-07 10:28:53 +03:00
Yang Bodong
79793c3d55 Fix out of range confusing error messages (XAUTOCLAIM, RPOP count) (#8746)
Fix out of range error messages to be clearer (avoid mentioning 9223372036854775807)
* Fix XAUTOCLAIM COUNT option confusing error msg
* Fix other RPOP and alike error message to mention positive
2021-04-07 10:01:28 +03:00
Yang Bodong
4c14e8668c
Fix out of range confusing error messages (XAUTOCLAIM, RPOP count) (#8746)
Fix out of range error messages to be clearer (avoid mentioning 9223372036854775807)
* Fix XAUTOCLAIM COUNT option confusing error msg
* Fix other RPOP and alike error message to mention positive
2021-04-07 10:01:28 +03:00
jsully
c168c8fbbf Merge branch 'flash_read_perf' into 'keydbpro'
Flash read perf

See merge request external-collab/keydb-pro-6!1

Former-commit-id: f6d7277f307b78f079dd99bf532cd26a7b62018d
2021-04-07 06:12:55 +00:00