27350 Commits

Author SHA1 Message Date
Salvatore Sanfilippo
40161553e2
Merge pull request #7096 from ShooterIT/sendfile
Implements sendfile for redis.
2020-05-22 13:55:46 +02:00
Madelyn Olson
8802cbbcde EAGAIN for tls during diskless load 2020-05-22 12:37:59 +02:00
Madelyn Olson
e201f83cee EAGAIN for tls during diskless load 2020-05-22 12:37:59 +02:00
Qu Chen
5d59bbb6d9 Disconnect chained replicas when the replica performs PSYNC with the master always to avoid replication offset mismatch between master and chained replicas. 2020-05-22 12:37:59 +02:00
Qu Chen
58fc456cbd Disconnect chained replicas when the replica performs PSYNC with the master always to avoid replication offset mismatch between master and chained replicas. 2020-05-22 12:37:59 +02:00
hwware
08c70f7dce using moreargs variable 2020-05-22 12:37:59 +02:00
hwware
3febc5c29e using moreargs variable 2020-05-22 12:37:59 +02:00
hwware
5c70dab9fc fix server crash for STRALGO command 2020-05-22 12:37:49 +02:00
hwware
8d67385593 fix server crash for STRALGO command 2020-05-22 12:37:49 +02:00
ShooterIT
e60f63a718 Replace addDeferredMultiBulkLength with addReplyDeferredLen in comment 2020-05-22 12:37:49 +02:00
ShooterIT
7a35eec540 Replace addDeferredMultiBulkLength with addReplyDeferredLen in comment 2020-05-22 12:37:49 +02:00
Yossi Gottlieb
26143c2936 TLS: Improve tls-protocols clarity in redis.conf. 2020-05-22 12:37:49 +02:00
Yossi Gottlieb
f93e1417b9 TLS: Improve tls-protocols clarity in redis.conf. 2020-05-22 12:37:49 +02:00
ShooterIT
9d1265240f Fix reply bytes calculation error
Fix #7275.
2020-05-22 12:37:49 +02:00
ShooterIT
d0c9e44545 Fix reply bytes calculation error
Fix #7275.
2020-05-22 12:37:49 +02:00
zhaozhao.zz
830c674845 Tracking: flag CLIENT_TRACKING_BROKEN_REDIR when redir broken 2020-05-22 12:37:49 +02:00
zhaozhao.zz
1cde6a0603 Tracking: flag CLIENT_TRACKING_BROKEN_REDIR when redir broken 2020-05-22 12:37:49 +02:00
Oran Agra
56d63f4d7d fix a rare active defrag edge case bug leading to stagnation
There's a rare case which leads to stagnation in the defragger, causing
it to keep scanning the keyspace and do nothing (not moving any
allocation), this happens when all the allocator slabs of a certain bin
have the same % utilization, but the slab from which new allocations are
made have a lower utilization.

this commit fixes it by removing the current slab from the overall
average utilization of the bin, and also eliminate any precision loss in
the utilization calculation and move the decision about the defrag to
reside inside jemalloc.

and also add a test that consistently reproduce this issue.
2020-05-22 12:37:49 +02:00
Oran Agra
436be34986 fix a rare active defrag edge case bug leading to stagnation
There's a rare case which leads to stagnation in the defragger, causing
it to keep scanning the keyspace and do nothing (not moving any
allocation), this happens when all the allocator slabs of a certain bin
have the same % utilization, but the slab from which new allocations are
made have a lower utilization.

this commit fixes it by removing the current slab from the overall
average utilization of the bin, and also eliminate any precision loss in
the utilization calculation and move the decision about the defrag to
reside inside jemalloc.

and also add a test that consistently reproduce this issue.
2020-05-22 12:37:49 +02:00
Oran Agra
4f8e19f877 improve DEBUG MALLCTL to be able to write to write only fields.
also support:
  debug mallctl-str thread.tcache.flush VOID
2020-05-22 12:37:49 +02:00
Oran Agra
f9d2ffdc5d improve DEBUG MALLCTL to be able to write to write only fields.
also support:
  debug mallctl-str thread.tcache.flush VOID
2020-05-22 12:37:49 +02:00
hujie
6bb5b6d942 fix clear USER_FLAG_ALLCOMMANDS flag in acl
in ACLSetUserCommandBit, when the command bit overflows, no operation
is performed, so no need clear the USER_FLAG_ALLCOMMANDS flag.

in ACLSetUser, when adding subcommand, we don't need to call
ACLGetCommandID ahead since subcommand may be empty.
2020-05-22 12:37:49 +02:00
hujie
d7968ee920 fix clear USER_FLAG_ALLCOMMANDS flag in acl
in ACLSetUserCommandBit, when the command bit overflows, no operation
is performed, so no need clear the USER_FLAG_ALLCOMMANDS flag.

in ACLSetUser, when adding subcommand, we don't need to call
ACLGetCommandID ahead since subcommand may be empty.
2020-05-22 12:37:49 +02:00
ShooterIT
2478a83ce7 Redis Benchmark: generate random test data
The function of generating random data is designed by antirez. See #7196.
2020-05-22 12:37:49 +02:00
ShooterIT
a902e6b251 Redis Benchmark: generate random test data
The function of generating random data is designed by antirez. See #7196.
2020-05-22 12:37:49 +02:00
hwware
3ffb3ac7ea Redis-Benchmark: avoid potentical memmory leaking 2020-05-22 12:37:49 +02:00
hwware
9564ed7c39 Redis-Benchmark: avoid potentical memmory leaking 2020-05-22 12:37:49 +02:00
WuYunlong
65de5a1a7d Handle keys with hash tag when computing hash slot using tcl cluster client. 2020-05-22 12:37:49 +02:00
WuYunlong
2e41827435 Handle keys with hash tag when computing hash slot using tcl cluster client. 2020-05-22 12:37:49 +02:00
WuYunlong
71036d4cdb Add a test to prove current tcl cluster client can not handle keys with hash tag. 2020-05-22 12:37:49 +02:00
WuYunlong
eb2c8b2c61 Add a test to prove current tcl cluster client can not handle keys with hash tag. 2020-05-22 12:37:49 +02:00
ShooterIT
e113af7448 Use dictSize to get the size of dict in dict.c 2020-05-22 12:37:49 +02:00
ShooterIT
928e6976bb Use dictSize to get the size of dict in dict.c 2020-05-22 12:37:49 +02:00
Madelyn Olson
1d84b89fb6 Converge hash validation for adding and removing 2020-05-22 12:37:49 +02:00
Madelyn Olson
cdcf5af5aa Converge hash validation for adding and removing 2020-05-22 12:37:49 +02:00
Benjamin Sergeant
5d88c23555 do not handle --cluster-yes for cluster fix mode 2020-05-22 12:37:49 +02:00
Benjamin Sergeant
e8b09d2203 do not handle --cluster-yes for cluster fix mode 2020-05-22 12:37:49 +02:00
Benjamin Sergeant
dc2f7e0ad7 fix typo ... 2020-05-22 12:37:49 +02:00
Benjamin Sergeant
57b4fb0d84 fix typo ... 2020-05-22 12:37:49 +02:00
Benjamin Sergeant
902e82efd2 Redis-cli 6.0.1 --cluster-yes doesn't work (fix #7246)
This make it so that all prompts for all redis-cli --cluster commands are automatically answered with a yes.
2020-05-22 12:37:49 +02:00
Benjamin Sergeant
29f25e4111 Redis-cli 6.0.1 --cluster-yes doesn't work (fix #7246)
This make it so that all prompts for all redis-cli --cluster commands are automatically answered with a yes.
2020-05-22 12:37:49 +02:00
Oran Agra
7d8259d151 fix valgrind test failure in replication test
in 00323f342 i added more keys to that test to make it run longer
but in valgrind this now means the test times out, give valgrind more
time.
2020-05-22 12:37:49 +02:00
Oran Agra
00d8b92b89 fix valgrind test failure in replication test
in b4416280c i added more keys to that test to make it run longer
but in valgrind this now means the test times out, give valgrind more
time.
2020-05-22 12:37:49 +02:00
Oran Agra
5e75739bfd add regression test for the race in #7205
with the original version of 6.0.0, this test detects an excessive full
sync.
with the fix in 146201c69, this test detects memory corruption,
especially when using libc allocator with or without valgrind.
2020-05-22 12:37:49 +02:00
Oran Agra
5e17e6276c add regression test for the race in #7205
with the original version of 6.0.0, this test detects an excessive full
sync.
with the fix in 1a7cd2c0e, this test detects memory corruption,
especially when using libc allocator with or without valgrind.
2020-05-22 12:37:49 +02:00
antirez
3d478f2e3f Improve the PSYNC2 test reliability. 2020-05-22 12:37:49 +02:00
antirez
96e7c011e2 Improve the PSYNC2 test reliability. 2020-05-22 12:37:49 +02:00
Salvatore Sanfilippo
51f840fd47 Merge pull request #7305 from madolson/unstable-connection
EAGAIN not handled for TLS during diskless load
2020-05-22 12:25:40 +02:00
Salvatore Sanfilippo
285817b28a
Merge pull request #7305 from madolson/unstable-connection
EAGAIN not handled for TLS during diskless load
2020-05-22 12:25:40 +02:00
Salvatore Sanfilippo
a688552350 Merge pull request #7306 from QuChen88/chained-replica-offset
Disconnect chained replicas when the replica performs PSYNC with the master always to avoid replication offset mismatch between master and chained replicas
2020-05-22 12:23:07 +02:00