Commit Graph

454 Commits (perf)

Author SHA1 Message Date
aoiasd b85118cc03
Fix queryCoord init deadlock when restart (#19402)
Signed-off-by: aoiasd <zhicheng.yue@zilliz.com>

Signed-off-by: aoiasd <zhicheng.yue@zilliz.com>
2022-09-27 12:00:54 +08:00
congqixia 7b4dde4ac4
Add triggerQueue check for handoff verifyReq (#19064) (#19080)
Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2022-09-07 18:18:34 +08:00
zhenshan.cao 815b4d26b8
Execute triggerTask in order of generation time (#19060)
Signed-off-by: zhenshan.cao <zhenshan.cao@zilliz.com>

Signed-off-by: zhenshan.cao <zhenshan.cao@zilliz.com>
2022-09-06 19:23:14 +08:00
Enwei Jiao e9410d8059
fix restart querycoord blocking issue (#18801) (#18947)
Signed-off-by: Enwei Jiao <enwei.jiao@zilliz.com>

Signed-off-by: Enwei Jiao <enwei.jiao@zilliz.com>

Signed-off-by: Enwei Jiao <enwei.jiao@zilliz.com>
2022-09-02 16:27:01 +08:00
wei liu 0733aece2d
fix remove offline nodes in watchDmChannel (#18906)
Signed-off-by: Wei Liu <wei.liu@zilliz.com>

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2022-08-30 19:34:57 +08:00
wei liu a926a7d23a
fix watch dml channel remove offline node (#18886)
Signed-off-by: Wei Liu <wei.liu@zilliz.com>

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2022-08-30 09:38:57 +08:00
Enwei Jiao a9eb72e580
fix GetCompactionState hang (#18850)
Signed-off-by: Enwei Jiao <enwei.jiao@zilliz.com>

Signed-off-by: Enwei Jiao <enwei.jiao@zilliz.com>
2022-08-26 18:00:54 +08:00
wayblink 6929e94065
Fix watchDmChannel may be out-of-date after compaction issue and add context (#18790)
Signed-off-by: wayblink <anyang.wang@zilliz.com>

Signed-off-by: wayblink <anyang.wang@zilliz.com>
2022-08-23 17:44:56 +08:00
Jiquan Long d335c7b591
Fix query cluster metrics (#18725) (#18727)
pick from master and fix #18722
Signed-off-by: longjiquan <jiquan.long@zilliz.com>
2022-08-19 13:58:01 +08:00
Xiaofan 9899a5be98
Remove Load Delta Channel Request (#18394)
Fix #18393

remove watch delta channel task related logic

Co-authored-by: xiaofan-luan <xiaofan.luan@zilliz.com>
Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>

Co-authored-by: Congqi Xia <congqi.xia@zilliz.com>
2022-08-04 17:50:37 +08:00
congqixia b5678f1e6a
Sync patched segmentInfo to etcd (#18383)
Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2022-07-23 21:26:29 +08:00
zhenshan.cao 6521f6da44
Fix segment DmChannel in querycoord for compatibility to 2.0.2 (#18373)
Signed-off-by: zhenshan.cao <zhenshan.cao@zilliz.com>
2022-07-22 21:00:28 +08:00
Xiaofan a34f635bcb
Change handoff handler from timer to ticker (#18358)
Signed-off-by: xiaofan-luan <xiaofan.luan@zilliz.com>
2022-07-21 21:30:27 +08:00
wei liu f132197ae9
fix sync problem during reblance (#18344)
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2022-07-20 15:58:28 +08:00
yah01 94b16a1a85
GetQuerySegmentInfo returns sealed loaded segments (#18255) (#18278)
Signed-off-by: yah01 <yang.cen@zilliz.com>
2022-07-14 20:08:25 +08:00
bigsheeper e8ac366440
Check load request both in impl and task (#18256)
Signed-off-by: bigsheeper <yihao.dai@zilliz.com>
2022-07-14 19:56:26 +08:00
yah01 b93a275f83
Fix QueryCoord unit test stucks (#18197) (#18218)
Signed-off-by: yah01 <yang.cen@zilliz.com>
2022-07-11 14:28:24 +08:00
wayblink a6692a4134
Make VChannelInfo read compatible with 2.0.2 (#18160)
Signed-off-by: wayblink <anyang.wang@zilliz.com>
2022-07-08 14:58:22 +08:00
zhenshan.cao 997e0668c8
Fix bug in metrics (#18144)
Signed-off-by: zhenshan.cao <zhenshan.cao@zilliz.com>
2022-07-08 14:10:22 +08:00
cai.zhang c6bce4e91e
Fix bug for clean etcd in QueryNCoord (#18146)
Signed-off-by: Cai.Zhang <cai.zhang@zilliz.com>
2022-07-07 18:30:22 +08:00
Enwei Jiao 6cb485aa15
fix receive messages before waitToFinish (#18122)
Signed-off-by: Enwei Jiao <enwei.jiao@zilliz.com>
2022-07-07 11:04:21 +08:00
Xiaofan ae84a99746
Change the etcd compareAndSwap interface (#18095)
Signed-off-by: xiaofan-luan <xiaofan.luan@zilliz.com>
2022-07-06 14:36:21 +08:00
bigsheeper e6cfbe8ed1
Improve flow graph node name and log msgID in QueryCoord (#18044)
Signed-off-by: bigsheeper <yihao.dai@zilliz.com>
2022-07-05 16:46:23 +08:00
yah01 cee427b4dd
Fix LoadBalance Sync all segments to shard leaders (#18002) (#18018)
Signed-off-by: yah01 <yang.cen@zilliz.com>
2022-07-01 20:54:18 +08:00
yah01 4e14184f27
Clean segments as releasing collection (#17932) (#18017)
Signed-off-by: yah01 <yang.cen@zilliz.com>
2022-07-01 20:50:19 +08:00
yah01 b1c97b3b3c
Fix the scheduler enqueues concurrent load tasks (#17950) (#18020)
Signed-off-by: yah01 <yang.cen@zilliz.com>

related to #17850
2022-07-01 20:48:19 +08:00
Jiquan Long 1e8e164a18
Fix querycoord ut data race (#17980) (#17983)
Signed-off-by: longjiquan <jiquan.long@zilliz.com>
2022-07-01 14:42:18 +08:00
cai.zhang 8d072181a6
Handle etcd compacted error (#17908)
Signed-off-by: Cai.Zhang <cai.zhang@zilliz.com>
2022-06-30 18:56:20 +08:00
yah01 98d71051e2
Refactor handoff handler (#17806) (#17933)
Signed-off-by: yah01 <yang.cen@zilliz.com>
Co-authored-by: xiaofan-luan <xiaofan.luan@zilliz.com>

Co-authored-by: xiaofan-luan <xiaofan.luan@zilliz.com>

Co-authored-by: xiaofan-luan <xiaofan.luan@zilliz.com>
2022-06-30 13:24:18 +08:00
congqixia 20af4dbe2d
Fix querycoord cannot update deltaChannel info (#17901) (#17906)
Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2022-06-29 16:14:18 +08:00
Bingyi Sun 5b26b310d2
Fix missing dml nodeIDs when recovering from old version (#17800) (#17842)
issue: #17416
Signed-off-by: sunby <bingyi.sun@zilliz.com>

Co-authored-by: sunby <bingyi.sun@zilliz.com>

Co-authored-by: sunby <bingyi.sun@zilliz.com>
2022-06-28 10:14:17 +08:00
wayblink 03027dfe49
Move datacoord related methods from meta to globalMetaBroker (#17847)
Signed-off-by: wayblink <anyang.wang@zilliz.com>
2022-06-28 09:56:17 +08:00
cai.zhang 22b3c27cb1
Fixed the bug that IndexCoord lost some meta information (#17825)
Signed-off-by: Cai.Zhang <cai.zhang@zilliz.com>
2022-06-28 08:52:17 +08:00
yah01 2dd1dc092b
Fix handoff isn't processed correctly (#17738) (#17848)
Signed-off-by: yah01 <yang.cen@zilliz.com>
Co-authored-by: Congqi Xia <congqi.xia@zilliz.com>

Co-authored-by: Congqi Xia <congqi.xia@zilliz.com>

Co-authored-by: Congqi Xia <congqi.xia@zilliz.com>
2022-06-27 23:18:17 +08:00
congqixia 7a10ca02d2
Fix load progress complete before syncReplica (#17845)
Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2022-06-27 20:56:16 +08:00
yah01 0d8e0e1326
SyncReplicaSegments syncs all segments (#17774) (#17790)
Signed-off-by: yah01 <yang.cen@zilliz.com>
2022-06-25 11:20:15 +08:00
yah01 9589eb4345
Fix LoadBalance removes source nodes from DmChannel (#17744) (#17783)
Only NodeDown LoadBalance should remove source nodes

Signed-off-by: yah01 <yang.cen@zilliz.com>
2022-06-24 21:08:15 +08:00
wayblink 6c47ea2f85
Fix: WatchDmChannelsRequest can be too large to save in etcd (#17755)
Signed-off-by: wayblink <anyang.wang@zilliz.com>
2022-06-24 15:12:16 +08:00
yah01 b4f21259ef
Fix SegmentChangeInfo is not set properly (#17701)
Signed-off-by: yah01 <yang.cen@zilliz.com>
2022-06-22 21:08:13 +08:00
yah01 a077bad84a
Make updating replica atomic, balance plan idempotent (#17686)
Signed-off-by: yah01 <yang.cen@zilliz.com>
2022-06-22 13:40:13 +08:00
yah01 1e87b54542
Add the offlines nodes previously crashed to offline nodes channel (#17663)
Signed-off-by: yah01 <yang.cen@zilliz.com>
2022-06-21 16:08:13 +08:00
wayblink f2bd910df5
[skip e2e]Fix log mistake: WatchDmChannels -> WatchDeltaChannels (#17643)
Signed-off-by: wayblink <anyang.wang@zilliz.com>
2022-06-20 15:10:12 +08:00
congqixia 50cecc65ed
Fix mock querynode server session not revoked (#17229)
Revoke mock querynode server session when it's stopped
This PR reduces the running time of TestLoadBalanceIndexedSegmentsAfterNodeDown from 60+ seconds to less than 1+ seconds
Also related to #17212 #17215

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2022-06-18 18:22:12 +08:00
wayblink 074ec3060a
Support return dropped segments info in GetSegmentInfo rpc (#17617)
Signed-off-by: wayblink <anyang.wang@zilliz.com>
2022-06-17 18:24:12 +08:00
congqixia 785a5a757f
Use segment version instead of ref cnt (#17609)
Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2022-06-17 17:38:12 +08:00
congqixia cc3ecc4bd5
Make querycoord channel allocator respect context (#17552)
Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2022-06-17 16:02:12 +08:00
yah01 f5fa93aa0b
Return err if failed to assign segments/channels to nodes (#17616)
Signed-off-by: yah01 <yang.cen@zilliz.com>
2022-06-17 12:42:11 +08:00
yah01 0f87763682
Fix LoadBalance may not update the shard leader (#17608)
This happens probably with concurrent updating replicas,
some goroutines modify the nodes list of replicas,
and the others modify the shard leaders of replicas

Signed-off-by: yah01 <yang.cen@zilliz.com>
2022-06-17 08:58:10 +08:00
yah01 3f42f5f345
Set the task state to TaskFailed if error occurs (#17598)
Signed-off-by: yah01 <yang.cen@zilliz.com>
2022-06-16 19:18:11 +08:00
Xiaofan 1f6fbf91b2
Fix pulsar unsubsribe issue (#17562)
Signed-off-by: xiaofan-luan <xiaofan.luan@zilliz.com>
2022-06-16 17:28:11 +08:00