545e8de401
fix: promote leader task failed when segment only exist on current target ( #30794 )
...
issue: #30150
`checkLeaderTaskStale` will check segment whether exist on next current
for leaderTask's growing action, which will cause promote leader task
failed when segment only exist on current target
This PR will check segment for both current or next target.
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2024-02-28 13:14:59 +08:00
6dd7297178
fix: Skip generate balance task when target not ready ( #30724 )
...
issue: #30723
This PR skip generate balance task when collection's target isn't ready.
also refine the check stale logic in query coord's scheduler, if channel
exist in current or next target, task won't be canceled.
---------
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2024-02-23 10:32:53 +08:00
7b91fa3db8
fix: Make leader checker generate leader task instead of segment task ( #30258 )
...
See also #30150
For leader view distribution with offline nodes, a release task can
never be sent to querynode due to targetNode online check logic. Even
the request is dispatched, normal release task does not have "force"
flag when calling `delegator.ReleaseSegment`.
This PR adds a new type of querycoord task: LeaderTask, the
responsibility of which is to rectify leader view distribtion.
---------
Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-02-21 11:08:51 +08:00
57bd3e2181
fix: Leader checker canot submit load task ( #30067 )
...
issue: #29841
if segment loaded, submit load segment task for it isn't permitted, to
avoid load segment twice. but this logic blocks the leader checker to
correct leader view by `LoadSegment`
This PR remove the segment loaded check, to fix that leader checker
cann't submit load task
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2024-01-17 19:12:54 +08:00
043ac87be0
fix: Balance channel may cause channel not availble error ( #28829 )
...
issue: #28831
release old delegator before new delegator update it's distribution may
cause `channel not availble` error
This PR will block release old delgator before new delegator finish
`syncDistribution`
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2023-12-01 10:08:34 +08:00
70995383bf
enhance: modify log to avoid ambiguity and improve readability ( #28331 )
...
Signed-off-by: yah01 <yah2er0ne@outlook.com>
2023-11-10 14:32:20 +08:00
90e2c63d9e
Fix getting incorrect CPU num ( #28146 )
...
Signed-off-by: yah01 <yang.cen@zilliz.com>
2023-11-06 06:02:16 +08:00
852be152de
Change task sourceID to stringer interface ( #27965 )
...
Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2023-10-27 01:08:12 +08:00
e0222b2ce3
refine target manager code style ( #27883 )
...
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2023-10-25 00:44:12 +08:00
a8ce1b6686
Refine QueryCoord stopping ( #27371 )
...
Signed-off-by: yah01 <yah2er0ne@outlook.com>
2023-09-27 16:27:27 +08:00
26f06dd732
Format the code ( #27275 )
...
Signed-off-by: SimFG <bang.fu@zilliz.com>
2023-09-21 09:45:27 +08:00
edde3cf1c7
Add tracer for querycoord tasks ( #27058 )
...
Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2023-09-14 09:59:19 +08:00
f9c060e0d2
Treat balance task with released source segment as stale ( #26453 )
...
Signed-off-by: yah01 <yah2er0ne@outlook.com>
2023-08-22 17:12:22 +08:00
9723787141
Calculate memory usage without page cache ( #26389 )
...
Signed-off-by: yah01 <yah2er0ne@outlook.com>
2023-08-16 17:04:17 +08:00
7d61355ab0
Refactor log for Query ( #26310 )
...
Signed-off-by: Enwei Jiao <enwei.jiao@zilliz.com>
2023-08-14 18:57:32 +08:00
df26b909f0
Fix panic while saw the failed task status ( #26082 )
...
Signed-off-by: yah01 <yang.cen@zilliz.com>
2023-08-02 13:47:05 +08:00
2180ef180c
Record only failed task error ( #26033 )
...
Signed-off-by: yah01 <yang.cen@zilliz.com>
2023-08-01 10:11:05 +08:00
efcaa07fe9
Implement Stringer for task related enums ( #25860 )
...
Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2023-07-24 13:57:00 +08:00
1045c88102
Support replace indexed field in QueryCoord ( #25747 )
...
Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2023-07-19 21:22:58 +08:00
224515eaa3
Add segment dist containing condition for loading segment ( #25736 )
...
Signed-off-by: yah01 <yang.cen@zilliz.com>
2023-07-19 15:02:58 +08:00
228c0df3f7
Skip record ChannelNotFound error while loading segment ( #25669 )
...
Signed-off-by: yah01 <yang.cen@zilliz.com>
2023-07-18 11:53:18 +08:00
b09e7aeaf7
support detailed task metrics( #23414 ) ( #24507 )
...
Signed-off-by: MrPresent-Han <chun.han@zilliz.com>
2023-05-30 14:59:28 +08:00
b517bc9e6a
refine balance mechanism including:( #23454 ) ( #23763 ) ( #23791 )
...
1. balance granuity to replica to avoid influence unrelated replicas
2. avoid balance back and forth
Signed-off-by: MrPresent-Han <jamesharden11122@gmail.com>
2023-05-04 12:22:40 +08:00
c9d0c157ec
Move some modules from internal to public package ( #22572 )
...
Signed-off-by: jaime <yun.zhang@zilliz.com>
2023-04-06 19:14:32 +08:00
afd874b736
enhance segment balance by considering global rowCount(##22914) ( #23056 )
...
Signed-off-by: MrPresent-Han <jamesharden11122@gmail.com>
Co-authored-by: xiaofan-luan <xiaofan.luan@zilliz.com>
2023-04-03 14:16:25 +08:00
ae0f467c02
Fix segment/channel may be re-loaded/subscribed ( #22969 )
...
Signed-off-by: yah01 <yang.cen@zilliz.com>
2023-03-27 18:28:00 +08:00
3d8f0156c7
Refine scheduler & executor of QueryCoord ( #22761 )
...
Signed-off-by: yah01 <yang.cen@zilliz.com>
2023-03-16 17:43:55 +08:00
1a4732bb19
Use new errors to handle load failures cache ( #22672 )
...
Signed-off-by: yah01 <yang.cen@zilliz.com>
2023-03-10 17:15:54 +08:00
697dedac7e
Use cockroachdb/errors to replace other error pkg ( #22390 )
...
Signed-off-by: Enwei Jiao <enwei.jiao@zilliz.com>
2023-02-26 11:31:49 +08:00
2146af1fb2
Return insufficient memory error when load failed ( #21574 )
...
Signed-off-by: bigsheeper <yihao.dai@zilliz.com>
2023-01-10 20:35:39 +08:00
396a85c926
Fix the number of executing tasks may break the limit ( #21318 )
...
Signed-off-by: yah01 <yang.cen@zilliz.com>
2022-12-20 20:33:27 +08:00
ddd29ea6ab
Optimize scheduler, increase merge tasks probability ( #20922 )
...
Signed-off-by: yah01 <yang.cen@zilliz.com>
Signed-off-by: yah01 <yang.cen@zilliz.com>
2022-12-01 16:25:16 +08:00
060649b8aa
Refactor task scheduler and executor ( #20828 )
...
Make the performance able to scale out
Signed-off-by: yah01 <yang.cen@zilliz.com>
Signed-off-by: yah01 <yang.cen@zilliz.com>
2022-11-30 13:57:15 +08:00
cc371d6801
Task/Action won't finish util the RPC returned ( #20669 )
...
Signed-off-by: yah01 <yang.cen@zilliz.com>
Signed-off-by: yah01 <yang.cen@zilliz.com>
2022-11-17 17:55:09 +08:00
1177ed1a33
fix duplicate watch channel task ( #20667 )
...
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2022-11-17 15:05:08 +08:00
a82c235599
Scheduler should returns err if the queue is full ( #20465 )
...
Signed-off-by: yah01 <yang.cen@zilliz.com>
Signed-off-by: yah01 <yang.cen@zilliz.com>
2022-11-11 17:55:05 +08:00
a68cec85af
Refine QueryCoordV2 metrics ( #20461 )
...
Signed-off-by: yah01 <yang.cen@zilliz.com>
Signed-off-by: yah01 <yang.cen@zilliz.com>
2022-11-10 15:01:04 +08:00
f925fa7661
fix check segment stale task ( #20401 )
...
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2022-11-08 19:43:05 +08:00
c5cd92d36e
update target ( #19296 )
...
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2022-11-07 19:37:04 +08:00
4112c667d0
Refine task's priority ( #20364 )
...
Signed-off-by: yah01 <yang.cen@zilliz.com>
Signed-off-by: yah01 <yang.cen@zilliz.com>
2022-11-07 14:53:02 +08:00
c08f11420f
Fix Release tasks may end with incorrect status ( #20263 )
...
If the resource has been removed, the release tasks should end with
Succeeded status, not stale
Signed-off-by: yah01 <yang.cen@zilliz.com>
Signed-off-by: yah01 <yang.cen@zilliz.com>
2022-11-03 15:01:35 +08:00
0b939c5735
Check whether ubsubscribe/release task is stale ( #20165 )
...
Signed-off-by: yah01 <yang.cen@zilliz.com>
Signed-off-by: yah01 <yang.cen@zilliz.com>
2022-11-01 12:33:35 +08:00
1c71844b8d
Add license header ( #19678 )
...
Signed-off-by: yah01 <yang.cen@zilliz.com>
Signed-off-by: yah01 <yang.cen@zilliz.com>
2022-10-11 11:39:22 +08:00
e6c7286bee
Remove task timeout ( #19583 )
...
Signed-off-by: yah01 <yang.cen@zilliz.com>
Signed-off-by: yah01 <yang.cen@zilliz.com>
2022-09-30 19:48:55 +08:00
9dcee37e1c
Skip canceled tasks ( #19513 )
...
Signed-off-by: yah01 <yang.cen@zilliz.com>
Signed-off-by: yah01 <yang.cen@zilliz.com>
2022-09-28 19:58:54 +08:00
377f856833
Fix balance may confuse leader observer ( #19435 )
...
Signed-off-by: yah01 <yang.cen@zilliz.com>
Signed-off-by: yah01 <yang.cen@zilliz.com>
2022-09-28 12:10:54 +08:00
6ba52366c5
Fix load segments can't be retried ( #19414 )
...
Signed-off-by: yah01 <yang.cen@zilliz.com>
Signed-off-by: yah01 <yang.cen@zilliz.com>
2022-09-26 10:54:52 +08:00
2cfacbba8d
Fix leader observer confused with replicas ( #19392 )
...
With 2 replicas, the same segment was loaded on 2 nodes in different
replicas, leader observer will sync the latest one (by version) to the
other one.
Signed-off-by: yah01 <yang.cen@zilliz.com>
Signed-off-by: yah01 <yang.cen@zilliz.com>
2022-09-23 15:16:51 +08:00
97aa2bd84f
Merge load segment tasks to improve performance ( #19234 )
...
Signed-off-by: yah01 <yang.cen@zilliz.com>
Signed-off-by: yah01 <yang.cen@zilliz.com>
2022-09-21 14:42:51 +08:00
626854cf0c
Refactor QueryCoord ( #18836 )
...
Signed-off-by: sunby <bingyi.sun@zilliz.com>
Co-authored-by: yah01 <yang.cen@zilliz.com>
Co-authored-by: Wei Liu <wei.liu@zilliz.com>
Co-authored-by: Congqi Xia <congqi.xia@zilliz.com>
Signed-off-by: sunby <bingyi.sun@zilliz.com>
Co-authored-by: sunby <bingyi.sun@zilliz.com>
Co-authored-by: yah01 <yang.cen@zilliz.com>
Co-authored-by: Wei Liu <wei.liu@zilliz.com>
Co-authored-by: Congqi Xia <congqi.xia@zilliz.com>
2022-09-15 18:48:32 +08:00
wei liu
congqixia
yah01
yah01
SimFG
Enwei Jiao
MrPresent-Han
jaime
bigsheeper
Bingyi Sun