f3ecf14601
change midShardSize type and other details
2020-08-12 17:49:12 +00:00
0cceda9908
solve distributor present bug
2020-08-11 21:54:52 +00:00
696e77c94e
query midShardSize from proxy
2020-08-10 20:13:44 +00:00
df9149fea4
ignore transaction tag of immediate transactions
2020-08-07 23:36:17 +00:00
13307679c5
use median shard size"
2020-08-05 03:57:25 +00:00
b903e60cb7
fix monitorDDMetricsChanges bugs
2020-08-03 17:12:36 +00:00
d1cc87452c
merge with master; solve conflicts; solve initialization;
2020-08-02 22:44:07 +00:00
c3a629588f
add client transaction tag sample
2020-07-31 19:08:42 +00:00
a49cb41de7
Merge branch 'release-6.3'
...
# Conflicts:
# CMakeLists.txt
# cmake/ConfigureCompiler.cmake
# fdbserver/Knobs.cpp
# fdbserver/StorageCache.actor.cpp
# fdbserver/storageserver.actor.cpp
# flow/ThreadHelper.actor.h
# flow/serialize.h
# tests/CMakeLists.txt
2020-07-29 00:31:55 -07:00
819e3ab3e8
Merge branch 'ratekeeper'
2020-07-28 16:48:50 +00:00
48a0fb5154
ask DD for shard info
2020-07-25 04:08:12 +00:00
ab0d8b0626
Merge pull request #3509 from sfc-gh-anoyes/anoyes/remove-using-relops
...
Remove using namespace std::rel_ops
2020-07-22 11:58:25 -07:00
638f586f78
Remove unnecessary override
2020-07-21 11:05:46 -07:00
83c5a30f62
Add encapsulation to TCTeamInfo and ParallelTCInfo
2020-07-21 11:05:41 -07:00
9a2ce4c981
Make IDataDistributionTeam const-correct
2020-07-21 11:05:34 -07:00
b2a3b4fd83
Merge branch 'master' into mengxu/merge-6.3-PR
2020-07-20 11:34:18 -07:00
1ba9b6b07f
DD:Change SendRelocateToDDQx100 to SendRelocateToDDQueue
2020-07-17 14:10:17 -07:00
098cdfb558
Replace actor_cancelled error with dd_cancelled
2020-07-16 20:26:07 -07:00
ba3c631350
Remove spammy trace
2020-07-16 10:33:24 -07:00
638e612a97
Improve coding style and trace events
2020-07-16 10:25:42 -07:00
acbb389862
Debug and fix very rare crash in TeamTracker
...
teamTracker only works when all DDTeamCollections are valid.
However, teamTracker can be triggered by zeroTeamSignalling event
after a DDTeamCollection is destructed and the other DDTeamCollection has not been
destructed yet.
This causes teamTracker to uses a pointer to the destructed DDTeamCollection and thus
has mysterious failure.
2020-07-16 10:23:02 -07:00
47ae66bd61
Merge branch 'master' into mengxu/tmp-minor-comment-PR
...
Resolve conflict at waitFailureClient
2020-07-13 16:17:50 -07:00
ef8c1060a2
Merge branch 'master' into mengxu/tmp-merge-6.3
2020-07-13 10:15:56 -07:00
6f2e12be42
Minor improvement on comments
2020-07-12 18:32:47 -07:00
f470ba8316
Remove using namespace std::rel_ops
...
This causes the following to not compile anymore
\#include <utility>
\#include <vector>
using namespace std::rel_ops;
int main() {
std::vector<int> xs;
return xs.rbegin() != xs.rend();
}
See https://godbolt.org/z/s1977n
2020-07-10 22:58:15 +00:00
b09dddc07e
Merge branch 'release-6.2' into merge-release-6.2-into-release-6.3
...
# Conflicts:
# cmake/ConfigureCompiler.cmake
# documentation/sphinx/source/downloads.rst
# fdbrpc/FlowTransport.actor.cpp
# fdbrpc/fdbrpc.vcxproj
# fdbserver/DataDistributionQueue.actor.cpp
# fdbserver/Knobs.cpp
# fdbserver/Knobs.h
# fdbserver/LogSystemPeekCursor.actor.cpp
# fdbserver/MasterProxyServer.actor.cpp
# fdbserver/Status.actor.cpp
# fdbserver/storageserver.actor.cpp
# flow/flow.vcxproj
2020-07-10 15:06:34 -07:00
5e02fd490e
fix: the check for if a teamCollection was tracking a source server was unreliable, leading to scenarios where we would temporarily replicate a shard less than teamSIze
2020-06-29 10:02:27 -07:00
cf13e00a8f
Merge remote-tracking branch 'origin/release-6.3' into fdb_cache_wo_allocator
2020-06-01 17:38:31 -07:00
6ce574f5ad
Merge remote-tracking branch 'upstream/release-6.3' into add-data-distribution-metrics
2020-05-17 23:36:52 -07:00
c2bc75516f
Merge branch 'release-6.3' of github.com:apple/foundationdb into features/trace-roles
2020-05-14 10:34:53 -07:00
48b1b20f67
Fixed a crash related to destruction order in data distribution
2020-05-10 23:14:19 -07:00
ef724bf939
Merge remote-tracking branch 'upstream/master' into add-data-distribution-metrics
2020-05-08 18:39:28 -07:00
e8b62e48f4
Rename DDMetrics to DDMetricsRef
2020-05-08 17:17:27 -07:00
5f9b127e56
Emit traces regularly about role assignment
...
We are currently emitting Role transition traces when a role starts and
when it ends. While this is useful for debugging, it doesn't work well
with tools that inject data and might potentially miss some trace lines.
We do decorate each trace lines with the roles assigned to that
particular process, however, this is not sufficient for tools that can
make use of the UID -> Role mapping
2020-05-08 16:27:57 -07:00
f4d30f8dce
Fix the compilation error.
2020-05-06 19:09:40 -07:00
94570ea590
Data distributor now waitfails caches
2020-05-06 10:35:56 -07:00
aed2d34bcb
Merge branch 'master' into feature-proxy-load-balance
...
# Conflicts:
# fdbclient/NativeAPI.actor.cpp
# fdbserver/MasterProxyServer.actor.cpp
# flow/Knobs.cpp
2020-05-01 09:19:39 -07:00
b7f5f3be48
merge in master
2020-04-28 13:11:47 -07:00
0c84ad4bc6
Merge pull request #2917 from bnamasivayam/fail-slow-ss
...
Mark the storage servers that are continually lagging as unhealthy
2020-04-22 23:18:35 -07:00
d5bef6fc32
Update fdbserver/DataDistribution.actor.cpp
2020-04-22 09:45:56 -07:00
ba3e2af473
Merge commit '5288033bcfe40c3ade97c8bf2d04cf31b3f16cb1' into feature-tree-broadcast
2020-04-17 15:17:37 -07:00
33efb9ec97
code cleanup based on review comments
2020-04-17 15:05:01 -07:00
1439de37b5
Convert GetRangeLimits() -> TOO_MANY + ASSERT().
2020-04-12 18:23:14 -07:00
ce4493f679
many bug fixes
2020-04-10 13:45:16 -07:00
6916434f7d
Addressed review comments
2020-04-08 10:48:32 -07:00
69ef8a127b
Add a backstop mechanism to stop failing too many storage servers when they fall behind.
2020-04-06 23:37:11 -07:00
6078fd1b18
Convert UID to Tag in keyServers to reduce txnStateStore size
2020-04-05 14:30:09 -07:00
73272fc72e
Version difference is now the diff between TLog versions and SS version.
2020-04-03 19:04:43 -07:00
a70bfcc3c8
Remove unnecessary comment.
2020-03-31 18:33:12 -07:00
b1c3893d40
Fix some corner case bugs exposed by simulation.
...
In one case, when a SS joins the cluster and DD doesn't find any healthy server to form a team with the newly added server, then the SS does not get added to any team even when the other servers get healthy.
Another is an extreme case where a data center is down, and a SS in the active DC joins and then dies immediately but not before DD adds it to a destination team for a relocating shard which will result in DD waiting indefinitely for the dead data center to come back up for the cluster to be fully recovered.
2020-03-31 18:33:12 -07:00
Xiaoxi Wang