130def7897
fix: make sure both conditions are true before better master exists is executed
2021-12-06 13:50:31 -08:00
951bc4acd7
fix: do not call better master exists until the long lived stateless processes have settled into their desired locations
2021-12-06 13:12:27 -08:00
a4fff19320
Revert "fix: long lived stateless processes need to be the last comparison criteria to avoid better master exists from changing behavior from the original recruitment"
...
This reverts commit b55b095ed0
2021-12-05 20:26:13 -08:00
b55b095ed0
fix: long lived stateless processes need to be the last comparison criteria to avoid better master exists from changing behavior from the original recruitment
2021-12-05 20:18:03 -08:00
ff47013158
fix: check if the master has been killed while waiting for getNextBMEpoch
2021-12-04 17:08:23 -08:00
557186ed17
Merge pull request #5909 from sfc-gh-jfu/jfu-cc-request-dbinfo
...
Change dbinfo broadcast to be explicitly requested by the worker registration message
2021-11-16 15:01:42 -08:00
964d0209ca
Merge pull request #5637 from sfc-gh-ljoswiak/features/data-loss-prevention
...
Data loss protection when joining new cluster
2021-11-15 15:26:32 -08:00
51b8ccf7d3
Merge remote-tracking branch 'apple/master' into notify-client-lib-changes
2021-11-10 18:40:34 +01:00
74cf64fe0f
Sync cluster ID through ServerDBInfo
2021-11-09 12:29:48 -08:00
3e2c65bb11
Allow tlog to join another cluster but retain its data
2021-11-09 12:29:48 -08:00
30867750b5
Add protection against storage and tlog data deletion when joining a new cluster
2021-11-09 12:29:47 -08:00
00f4bd8536
Check ccInterface against serverDbInfo's cc and make broadcast unconditional for first registration
2021-11-08 12:43:02 -05:00
4e8625ccc0
retain old behaviour along with explicit request
2021-11-03 17:23:07 -04:00
59f0a2c3e5
Change dbinfo broadcast to be explicitly requested by the worker registration message
2021-11-03 15:51:21 -04:00
ee00135a6b
skip good recruitment errors when doing simulation only validation
2021-11-01 13:24:15 -07:00
78e36e7590
fix: simulation only validation could throw errors which would impact the behavior of the cluster controller
2021-11-01 13:24:15 -07:00
ddf235713e
strengthen assert
2021-10-28 16:40:30 -07:00
4d8ee2ed33
fix: simple recruitment could succeed with less than the required replication factor
2021-10-28 16:38:04 -07:00
875824b186
MVC2.0: Notify clients about relevant changes of client libraries
2021-10-27 23:43:40 +02:00
0ff8ddc2b6
Merge branch 'master' into blob_full_clean
2021-10-25 13:38:48 -05:00
e882eb33fc
Abstract the cluster file into a cluster connection record that can be backed by something other than the filesystem.
2021-10-22 11:05:18 -07:00
773886515e
Merge branch 'feature-range-feed' into blob_full_clean
2021-10-22 11:07:51 -05:00
912ef76f1c
cleanup before merge
2021-10-18 17:11:14 -05:00
5466bdb569
Gate more entry points to BM recruitment.
2021-10-18 15:04:22 -04:00
507a09893c
Add ClientCount to ClusterControllerMetrics ( #5748 )
2021-10-17 20:47:11 -07:00
5f0ec0612a
Merge branch 'feature-range-feed' into blob_full
2021-10-13 15:44:35 -05:00
2ec8781224
Merge knobs into one.
2021-10-13 14:00:37 -04:00
5a6a052c55
Add a knob to gate blob-related work.
2021-10-13 09:48:02 -04:00
645cfc85a0
fix remote health variables declaration order
2021-10-07 21:54:25 -07:00
6540b6eec5
Some improvements for grey failure failover
2021-10-07 20:42:55 -07:00
c07a07dbbe
Take uptime into account when making failover decision
2021-10-07 11:19:34 -07:00
62197faa46
Add more comments to the code
2021-10-07 11:19:34 -07:00
c0fbe5471f
Implement the core logic of grey failure triggered failover
2021-10-07 11:19:34 -07:00
282f9d35cd
Cleanup comments and debugging code.
2021-10-04 11:07:08 -04:00
4d54669ccd
Recruit the blob workers via blob manager.
...
In this PR, the blob manager now recruits blob workers
(via communication with the cluster controller). Blob workers
are onboarded as blob worker processes enter the cluster.
2021-10-04 11:07:08 -04:00
c523964ff7
Fix roll trace event issue
...
Description
Testing
2021-09-24 09:53:32 -07:00
8427e40cbe
Fix roll trace event issue
...
Description
Testing
2021-09-24 09:53:32 -07:00
48990058a3
Fix roll trace event issue
...
Description
Testing
2021-09-24 09:53:32 -07:00
e28fef6264
Fix failover logic in checkRecoveryStalled: failover only when remote is enabled
2021-09-23 20:12:22 -07:00
5fa6c687d6
Add blob manager as a singleton.
2021-09-23 10:45:37 -04:00
95c004f80b
Add missing namespace qualifier to vector.
2021-09-22 16:57:04 -05:00
2b9dfc1371
Simplify count increments.
2021-09-22 16:56:59 -05:00
4530e746d6
Address PR comments.
...
Adds comment for constant and changes method name for `setonDb`.
2021-09-22 16:56:49 -05:00
4a71f3d0f8
Fix recruitment bug.
2021-09-22 16:56:44 -05:00
72edcd8d73
Address PR comments.
...
Revert knob name change, fix comparison between new and old
recruitments, and get rid of empty `if` block.
2021-09-22 16:56:34 -05:00
10807ddebc
Rename function to be more clear.
2021-09-22 16:56:27 -05:00
0b6fecddbc
Refactor logic for recruiting singletons.
...
This commit refactors the logic for recruiting singletons,
which is done by the ClusterController. This allows for far
easier additions of new singletons in the future, and also
cleans up the code.
Also, the logic for recruiting DD was changed to mirror
the logic for recruiting RK. Although the logic for RK
allows there to be many RKs existing at once, the moveKeysLock
mechanism used by DD still prevents multiple DDs existing at once.
2021-09-22 16:56:18 -05:00
90e102cfd2
Add missing namespace qualifier to vector.
2021-09-20 16:43:08 -05:00
0f898fe138
Simplify count increments.
2021-09-20 14:26:42 -05:00
bac9d4cca8
Address PR comments.
...
Adds comment for constant and changes method name for `setonDb`.
2021-09-20 14:26:42 -05:00
Evan Tschannen