Commit Graph

99 Commits (eb046863485fdf3e130fc60484485c901b81276b)

Author SHA1 Message Date
congqixia cb7f2fa6fd
enhance: Use v2 package name for pkg module (#39990)
Related to #39095

https://go.dev/doc/modules/version-numbers

Update pkg version according to golang dep version convention

---------

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2025-02-22 23:15:58 +08:00
Zhen Ye bb8d1ab3bf
enhance: make new go package to manage proto (#39114)
issue: #39095

---------

Signed-off-by: chyezh <chyezh@outlook.com>
2025-01-10 10:49:01 +08:00
Xiaofan cb6eca8e91
fix: drop partition can not be successful if load failed (#38793)
fix #38649
when partition load failed, the partition drop will also fail due to the
wrong error message

Signed-off-by: xiaofanluan <xiaofan.luan@zilliz.com>
2024-12-30 19:42:52 +08:00
wei liu 25f0c82ceb
fix: Fix update loading collection's load config doesn't work (#38595)
issue: #38594

---------

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2024-12-25 18:02:51 +08:00
jaime 78438ef41e
fix: revert optimize CPU usage for CheckHealth requests (#35589) (#38555)
issue: #35563

Signed-off-by: jaime <yun.zhang@zilliz.com>
2024-12-19 00:38:45 +08:00
jaime 28fdbc4e30
enhance: optimize CPU usage for CheckHealth requests (#35589)
issue: #35563
1. Use an internal health checker to monitor the cluster's health state,
storing the latest state on the coordinator node. The CheckHealth
request retrieves the cluster's health from this latest state on the
proxy sides, which enhances cluster stability.
2. Each health check will assess all collections and channels, with
detailed failure messages temporarily saved in the latest state.
3. Use CheckHealth request instead of the heavy GetMetrics request on
the querynode and datanode

Signed-off-by: jaime <yun.zhang@zilliz.com>
2024-12-17 11:02:45 +08:00
congqixia 051bc280dd
enhance: Make dynamic load/release partition follow targets (#38059)
Related to #37849

---------

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-12-05 16:24:40 +08:00
tinswzy e76802f910
enhance: refine querycoord meta/catalog related interfaces to ensure that each method includes a ctx parameter (#37916)
issue: #35917 
This PR refine the querycoord meta related interfaces to ensure that
each method includes a ctx parameter.

Signed-off-by: tinswzy <zhenyuan.wei@zilliz.com>
2024-11-25 11:14:34 +08:00
congqixia b0bd290a6e
enhance: Use internal json(sonic) to replace std json lib (#37708)
Related to #35020

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-11-18 10:46:31 +08:00
wei liu 266f8ef1f5
fix: Search may return less result after qn recover (#36549)
issue: #36293 #36242
after qn recover, delegator may be loaded in new node, after all segment
has been loaded, delegator becomes serviceable. but delegator's target
version hasn't been synced, and if search/query comes, delegator will
use wrong target version to filter out a empty segment list, which
caused empty search result.

This pr will block delegator's serviceable status until target version
is synced

---------

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2024-11-12 16:34:28 +08:00
congqixia f5b06a3c9f
enhance: Invalidate collection cache when release collection (#37577)
Related to #37395

---------

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-11-12 10:16:29 +08:00
jaime 9d16b972ea
feat: add tasks page into management WebUI (#37002)
issue: #36621

1. Add API to access task runtime metrics, including:
  - build index task
  - compaction task
  - import task
- balance (including load/release of segments/channels and some leader
tasks on querycoord)
  - sync task
2. Add a debug model to the webpage by using debug=true or debug=false
in the URL query parameters to enable or disable debug mode.

Signed-off-by: jaime <yun.zhang@zilliz.com>
2024-10-28 10:13:29 +08:00
jaime 4746f47282
feat: management WebUI homepage (#36822)
issue: #36784
1. Implement an embedded web server for WebUI access.  
2. Complete the homepage development.

Home page demo:
<img width="2177" alt="iShot_2024-10-10_17 57 34"
src="https://github.com/user-attachments/assets/38539917-ce09-4e54-a5b5-7f4f7eaac353">

Signed-off-by: jaime <yun.zhang@zilliz.com>
2024-10-23 11:29:28 +08:00
wei liu 3cd0b26285
enhance: Enable dynamic update loaded collection's replica (#35822)
issue: #35821
After collection loaded, if we need to increase/decrease collection's
replica, we need to release and load it again.

milvus offers 4 solution to update loaded collection's replica, this PR
aims to dynamic change the replica number without release, and after
replica number changed, milvus will execute load replica or release
replica in async, and the replica loaded status can be checked by
getReplicas API.

Notice that if set too much replicas than querynode can afford,the new
replica won't be loaded successfully until enough querynode joins.

---------

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2024-09-25 10:13:18 +08:00
wei liu c84ea5465c
fix: Fix some replicas don't participate in the query after the failure recovery (#35850)
issue: #35846
querycoord will notify proxy to update shard leader cache after
delegator location changes, but during querynode's failure recovery,
some delegator may become unserviceable due to lacking of segments, and
back to serviceable after segment loaded, so we also need to notify
proxy to invalidate shard leader cache when delegator serviceable state
changes.

This PR will maintain querynode's serviceable state during heartbeat,
and notify proxy to invalidate shard leader cache if serviceable state
changes.

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2024-09-03 15:39:03 +08:00
congqixia 09ef3f1b4f
fix: Make sure querycoord observers started once (#35811)
Related to #35809

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-08-29 14:45:00 +08:00
congqixia 2fbc628994
feat: Support field partial load collection (#35416)
Related to #35415

---------

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-08-20 16:49:02 +08:00
wei liu e09dc3be58
enhance: Mark query node as read only after suspend (#35492)
issue: #34985 #35493
after querynode has been suspended, it's not allow to load
segment/channel on it, which means the node is read only. to be
compatible with resource group design, after query node has been
suspend, we remove it from it's original resource group, make it a read
only query node in replica. then two things will happens:
1. it's original resource group will be lacking of query nodes, query
coord will assign new node to it.
2. querycoord will try to move out all segments/channels after querynode
has been suspended

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2024-08-20 14:02:54 +08:00
jaime fcec4c21b9
fix: check collection health(queryable) fail for releasing collection (#34947)
issue: #34946

Signed-off-by: jaime <yun.zhang@zilliz.com>
2024-08-02 17:20:15 +08:00
wei liu 8123bea1ae
enhance: Avoid assign too much segment/channels to new querynode (#34096)
issue: #34095

When a new query node comes online, the segment_checker,
channel_checker, and balance_checker simultaneously attempt to allocate
segments to it. If this occurs during the execution of a load task and
the distribution of the new query node hasn't been updated, the query
coordinator may mistakenly view the new query node as empty. As a
result, it assigns segments or channels to it, potentially overloading
the new query node with more segments or channels than expected.

This PR measures the workload of the executing tasks on the target query
node to prevent assigning an excessive number of segments to it.

---------

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2024-06-27 19:06:05 +08:00
jaime 9630974fbb
enhance: move rocksmq from internal to pkg module (#33881)
issue: #33956

Signed-off-by: jaime <yun.zhang@zilliz.com>
2024-06-25 21:18:15 +08:00
wei liu b13932bb55
enhance: Enable database level replica num and resource groups for loading collection (#33052)
issue: #30040

This PR introduce two database level props:
1. database.replica.number
2. database.resource_groups

User can set those two database props by AlterDatabase API, then can
load collection without specified replica_num and resource groups. then
it will use database level load param when try to load collections.

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2024-05-29 10:59:43 +08:00
wei liu 2013d97243
enhance: Enable to dynamic update balancer policy in querycoord (#33037)
issue: #33036
This PR enable to dynamic update balancer policy without restart
querycoord.

---------

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2024-05-21 14:29:39 +08:00
wei liu a7f6193bfc
fix: query node may stuck at stopping progress (#33104)
issue: #33103 
when try to do stopping balance for stopping query node, balancer will
try to get node list from replica.GetNodes, then check whether node is
stopping, if so, stopping balance will be triggered for this replica.

after the replica refactor, replica.GetNodes only return rwNodes, and
the stopping node maintains in roNodes, so balancer couldn't find
replica which contains stopping node, and stopping balance for replica
won't be triggered, then query node will stuck forever due to
segment/channel doesn't move out.

---------

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2024-05-20 10:21:38 +08:00
chyezh 293f14a8b9
fix: remove redundant replica recover (#32985)
issue: #22288 

- replica recover should be only triggered by replica recover

Signed-off-by: chyezh <chyezh@outlook.com>
2024-05-13 15:25:32 +08:00
chyezh 1c84a1c9b6
fix: lru related issue fixup patch (#32916)
issue: #32206, #32801

- search failure with some assertion, segment not loaded and resource
insufficient.

- segment leak when query segments

---------

Signed-off-by: chyezh <chyezh@outlook.com>
2024-05-10 19:17:30 +08:00
chyezh f06509bf97
fix: get replica should not report error when no querynode serve (#32536)
issue: #30647

- Remove error report if there's no query node serve. It's hard for
programer to use it to do resource management.

- Change resource group `transferNode` logic to keep compatible with old
version sdk.

---------

Signed-off-by: chyezh <chyezh@outlook.com>
2024-04-25 19:25:24 +08:00
congqixia d7ff1bbe5c
enhance: Make querycoordv2 collection observer task driven (#32441)
See also #32440

- Add loadTask in collection observer
- For load collection/partitions, load task shall timeout as a whole
- Change related constructor to load jobs

---------

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-04-22 10:39:22 +08:00
chyezh 48fe977a9d
enhance: declarative resource group api (#31930)
issue: #30647

- Add declarative resource group api

- Add config for resource group management

- Resource group recovery enhancement

---------

Signed-off-by: chyezh <chyezh@outlook.com>
2024-04-15 08:13:19 +08:00
chyezh a2502bde75
enhance: replica manager enhancement (#31496)
issue: #30647 

- ReplicaManager manage read only node now, and always do persistent of
node distribution of replica.

- All segment/channel checker using ReplicaManager to get read-only node
or read-write node, but not ResourceManager.

- ReplicaManager promise that only apply unique querynode to one replica
in same collection now (replicas in same collection never hold same
querynode at same time).

- ReplicaManager promise that fairly node count assignment policy if
multi replicas of collection is assigned to one resource group.

- Move some parameters check into ReplicaManager to avoid data race.

- Allow transfer replica to resource group that already load replica of
same collection

- Allow transfer node between resource groups that load replica of same
collection

---------

Signed-off-by: chyezh <chyezh@outlook.com>
2024-04-05 04:57:16 +08:00
wei liu 92971707de
enhance: Add restful api for devops to execute rolling upgrade (#29998)
issue: #29261
This PR Add restful api for devops to execute rolling upgrade, including
suspend/resume balance and manual transfer segments/channels.

---------

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2024-03-27 16:15:19 +08:00
chyezh ff4237bb90
enhance: add hostname into node info (#30673)
issue: https://github.com/milvus-io/milvus/issues/30647

- Address may be reused in k8s environment. Using hostname can be
better.

Signed-off-by: chyezh <chyezh@outlook.com>
2024-03-15 10:45:06 +08:00
congqixia c886aa29ff
enhance: Use `ListIndexes` instead of `DescribeIndex` for qc broker (#31122)
See also #31103

Since querycoord need index meta information from datacoord only, broker
shall use `ListIndexes` to skip segment index building check logic in
datacoord

This PR is also related to #30538, in which DescribeIndex caused lots of
memory usage and lead to OOM eventually

---------

Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
2024-03-07 21:43:03 +08:00
wei liu 9abc868d15
fix: Remove heartbeat lag logic during get shard leaders (#29999)
issue: #29677 #29838
during get shard leaders, if qeurynode doesn't ack the heartbeat than
10s, querycoord will treat it as unavailable, and won't return shard
leader on it. but when querynode has a full cpu usage, it's easily to
stuck for more than 10s without ack the heartbeat, which cause no shard
leader to search/query.

This PR remove heartbeat lag logic during get shard leaders

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2024-01-17 11:22:52 +08:00
wei liu e98c62abbb
enhance: refactor leader_observer to leader_checker (#29454)
issue: #29453 

sync distribution by rpc will also call loadSegment/releaseSegment,
which may cause all kinds of concurrent case on same segment, such as
concurrent load and release on one segment.
This PR add leader_checker which generate load/release task to correct
the leader view, instead of calling sync distribution by rpc

---------

Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2024-01-05 15:54:55 +08:00
yah01 bfccfcd0ca
enhance: refine error messages (#28424)
- Split the simple reason and full detail
- Refine existing error messages
related: #28422

---------

Signed-off-by: yah01 <yah2er0ne@outlook.com>
2023-11-21 17:02:24 +08:00
yah01 1b90630633
Fix the target updated before version updated to cause data missing (#28250)
Signed-off-by: yah01 <yah2er0ne@outlook.com>
2023-11-08 11:36:22 +08:00
yah01 dc89730a50
Support collection-level mmap control (#26901)
Signed-off-by: yah01 <yah2er0ne@outlook.com>
2023-11-02 23:52:16 +08:00
Filip Haltmayer 6b1a106a31
Moving etcd client into session (#27069)
Signed-off-by: Filip Haltmayer <filip.haltmayer@zilliz.com>
2023-10-27 07:36:12 +08:00
wei liu e0222b2ce3
refine target manager code style (#27883)
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2023-10-25 00:44:12 +08:00
yah01 be980fbc38
Refine state check (#27541)
Signed-off-by: yah01 <yah2er0ne@outlook.com>
2023-10-11 21:01:35 +08:00
yah01 a8ce1b6686
Refine QueryCoord stopping (#27371)
Signed-off-by: yah01 <yah2er0ne@outlook.com>
2023-09-27 16:27:27 +08:00
yah01 6539a5ae2c
Refine DataCoord status (#27262)
Signed-off-by: yah01 <yah2er0ne@outlook.com>
2023-09-26 17:15:27 +08:00
MrPresent-Han 4b12cb8847
fix unstable ut due to unstable sort of unique set (#27302)
Signed-off-by: MrPresent-Han <chun.han@zilliz.com>
2023-09-22 19:07:26 +08:00
SimFG 26f06dd732
Format the code (#27275)
Signed-off-by: SimFG <bang.fu@zilliz.com>
2023-09-21 09:45:27 +08:00
yah01 941a383019
Fix failed to load collection with more than 128 partitions (#26763)
Signed-off-by: yah01 <yah2er0ne@outlook.com>
2023-09-02 00:09:01 +08:00
wei liu 949c320185
remove pull target from qc recover (#26775)
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
2023-09-01 11:17:01 +08:00
Bingyi Sun a3e22786ed
Move meta store to kv catalog (#25915)
Signed-off-by: sunby <sunbingyi1992@gmail.com>
2023-07-31 13:57:04 +08:00
yah01 dc37b4587e
Fix panic if channel not watched while getting shard leaders (#25820)
Signed-off-by: yah01 <yang.cen@zilliz.com>
2023-07-24 14:13:02 +08:00
yah01 948d1f1f4a
Handle errors by merr for QueryCoord (#24926)
Signed-off-by: yah01 <yang.cen@zilliz.com>
2023-07-17 14:59:34 +08:00