issue: #46087, #46327
The previous implementation only checked if there were any ready
delegators before updating the current target. This could lead to
partial target updates when only some channels had ready delegators.
This regression was introduced by #46088, which removed the check for
all channels being ready. This fix ensures that
shouldUpdateCurrentTarget returns true only when ALL channels have been
successfully synced, preventing incomplete target updates that could
cause query inconsistencies.
Added unit tests to cover:
- All channels synced scenario (should return true)
- Partial channels synced scenario (should return false)
- No ready delegators scenario (should return false)
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
issue: #46087
The previous implementation checked if the total number of ready
delegators >= replicaNum per channel. This could cause target updates to
block indefinitely when dynamically increasing replicas, because some
replicas might lack nodes while the total count still met the threshold.
This change switches to a replica-based check approach:
- Iterate through each replica individually
- For each replica, verify all channels have at least one ready
delegator
- Only sync delegators from fully ready replicas
- Skip replicas that are not ready (e.g., missing nodes for some
channels)
This ensures target updates can proceed with ready replicas while
replicas that lack nodes during dynamic scaling are gracefully skipped.
---------
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
issue: #44014
- Because the session of querynode and streamingnode is different.
- So when streamingnode session down first, a streaming query node will
be treated as querynode.
- Use label but not streaming node session to fix it.
Signed-off-by: chyezh <chyezh@outlook.com>
issue: https://github.com/milvus-io/milvus/issues/41690
This commit implements partial search result functionality when query
nodes go down, improving system availability during node failures. The
changes include:
- Enhanced load balancing in proxy (lb_policy.go) to handle node
failures with retry support
- Added partial search result capability in querynode delegator and
distribution logic
- Implemented tests for various partial result scenarios when nodes go
down
- Added metrics to track partial search results in querynode_metrics.go
- Updated parameter configuration to support partial result required
data ratio
- Replaced old partial_search_test.go with more comprehensive
partial_result_on_node_down_test.go
- Updated proto definitions and improved retry logic
These changes improve query resilience by returning partial results to
users when some query nodes are unavailable, ensuring that queries don't
completely fail when a portion of data remains accessible.
---------
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
issue: https://github.com/milvus-io/milvus/issues/41690
- Merge leader view and channel management into ChannelDistManager,
allowing a channel to have multiple delegators.
- Improve shard leader switching to ensure a single replica only has one
shard leader per channel. The shard leader handles all resource loading
and query requests.
- Refine the serviceable mechanism: after QC completes loading, sync the
query view to the delegator. The delegator then determines its
serviceable status based on the query view.
- When a delegator encounters forwarding query or deletion failures,
mark the corresponding segment as offline and transition it to an
unserviceable state.
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
issue: #40292
related to #39552
- Fix incorrect delete checkpoint usage in SyncDistribution
- Change checkpoint parameter from action.GetCheckpoint() to
action.GetDeleteCP() in SyncTargetVersion call
- This resolves the issue where delete buffer data was being cleaned
prematurely due to wrong checkpoint reference
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
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>
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>
When there're a lot of loaded collections, they would occupy the target
observer scheduler’s pool. This prevents loading collections from
updating the current target in time, slowing down the load process.
This PR adds a separate target dispatcher for loading collections.
issue: https://github.com/milvus-io/milvus/issues/37166
---------
Signed-off-by: bigsheeper <yihao.dai@zilliz.com>
issue: #33550
cause concurrent issue may occur between remove parition in target
manager and sync segment list to delegator. when it happens, some
segment may be released in delegator, and those segment may also be
synced to delegator, which cause delegator become unserviceable due to
lack of necessary segments, then search/query fails.
this PR make sure that all write access to target_manager will be
executed in serial to avoid the concurrent issues.
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
See also #34234
`LoadPartitions` does not guarantee the current target has loading
partitions if there are some partitions already loaded before.
This PR check current target contains the partition to load when
advancing loading percentage to 100.
Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
issue: #32910
* split replica's node list to channels when create replicas
* balance nodes among channels when node change happens
* implement channel level balance, let balance happens in channel level
Signed-off-by: Wei Liu <wei.liu@zilliz.com>
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>
- Add `taskDispatcher` to submit and run task async safely
- Change `LeaderObeserver` and `TargetObserver` schedule and manual check action to submitting task into dispatcher
- Fix logic problem in collection observer when manual check return false
See also #27494
Signed-off-by: Congqi Xia <congqi.xia@zilliz.com>
