admin/milvus
1
0
Fork 0
mirror of https://gitee.com/milvus-io/milvus.git synced 2026-01-07 03:13:22 +08:00
Code Issues Packages Projects Releases Wiki Activity
milvus/internal/datacoord
History
yihao.dai 5b78ef0a49
fix: Fix delete data loss due to duplicate binlogID (#40960) 
With concurrenct L0 compaction
(https://github.com/milvus-io/milvus/pull/36816), delta logs might be
written to the same L1 segment, causing logID duplication when using the
incremental beginLogID. This PR removes the beginLogID mechanism and
instead passes a log ID range, where the number of IDs in the range
equals the number of compaction segment binlogs multiplied by an
expansion factor.

issue: https://github.com/milvus-io/milvus/issues/40207

---------

Signed-off-by: bigsheeper <yihao.dai@zilliz.com>
2025-04-01 10:36:22 +08:00
..
allocator
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
broker
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
session
enhance: Merge IndexNode and DataNode (#40272)
2025-03-13 14:26:11 +08:00
.mockery.yaml
enhance: Support detailed manual compaction criterion (#40892)
2025-03-25 20:06:22 +08:00
analyze_meta_test.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
analyze_meta.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
build_index_policy.go
Format the code (#27275)
2023-09-21 09:45:27 +08:00
channel_manager_factory.go
fix: drop collection failed if enable streaming service (#37444)
2024-11-07 10:26:26 +08:00
channel_manager_test.go
fix: Fix channel not balance on datanodes (#40422)
2025-03-11 14:56:16 +08:00
channel_manager.go
fix: Fix channel not balance on datanodes (#40422)
2025-03-11 14:56:16 +08:00
channel_store_test.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
channel_store.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
channel.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
cluster_test.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
cluster.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
compaction_l0_view_test.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
compaction_l0_view.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
compaction_policy_clustering_test.go
enhance: Optimize datacoord meta mutex (#40552)
2025-03-25 13:46:25 +08:00
compaction_policy_clustering.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
compaction_policy_l0_test.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
compaction_policy_l0.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
compaction_policy_single_test.go
enhance: Optimize datacoord meta mutex (#40552)
2025-03-25 13:46:25 +08:00
compaction_policy_single.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
compaction_queue_test.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
compaction_queue.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
compaction_task_clustering_test.go
enhance: move object storage client creation to pkg package (#40440)
2025-03-12 20:38:07 +08:00
compaction_task_clustering.go
fix: Fix delete data loss due to duplicate binlogID (#40960)
2025-04-01 10:36:22 +08:00
compaction_task_l0_test.go
fix: Fix delete data loss due to duplicate binlogID (#40960)
2025-04-01 10:36:22 +08:00
compaction_task_l0.go
fix: Fix delete data loss due to duplicate binlogID (#40960)
2025-04-01 10:36:22 +08:00
compaction_task_meta_test.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
compaction_task_meta.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
compaction_task_mix_test.go
fix: Fix delete data loss due to duplicate binlogID (#40960)
2025-04-01 10:36:22 +08:00
compaction_task_mix.go
fix: Fix delete data loss due to duplicate binlogID (#40960)
2025-04-01 10:36:22 +08:00
compaction_task.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
compaction_test.go
enhance: Replace currRows with NumOfRows (#40074)
2025-03-10 12:16:03 +08:00
compaction_trigger_test.go
fix: Fix delete data loss due to duplicate binlogID (#40960)
2025-04-01 10:36:22 +08:00
compaction_trigger_v2_test.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
compaction_trigger_v2.go
fix: Fix delete data loss due to duplicate binlogID (#40960)
2025-04-01 10:36:22 +08:00
compaction_trigger.go
fix: Fix delete data loss due to duplicate binlogID (#40960)
2025-04-01 10:36:22 +08:00
compaction_util.go
fix: Fix delete data loss due to duplicate binlogID (#40960)
2025-04-01 10:36:22 +08:00
compaction_view.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
compaction.go
fix: Negative -1 executing compaction tasks (#39954)
2025-02-25 18:07:55 +08:00
const.go
enhance: pass partition key scalar info if enabled when build vector index (#29931)
2024-01-24 00:04:55 +08:00
errors_test.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
errors.go
Refine DataCoord status (#27262)
2023-09-26 17:15:27 +08:00
garbage_collector_test.go
enhance: Optimize datacoord meta mutex (#40552)
2025-03-25 13:46:25 +08:00
garbage_collector.go
fix: Set task version for stats task (#40035)
2025-02-27 17:49:59 +08:00
go_channel_singleton.go
fix: Fix improper use of offset in HybridSearch (#36244)
2024-09-13 22:05:15 +08:00
handler_test.go
fix: use correct delete checkpoint to prevent premature data cleanup (#40366)
2025-03-12 15:00:08 +08:00
handler.go
fix: use correct delete checkpoint to prevent premature data cleanup (#40366)
2025-03-12 15:00:08 +08:00
import_checker_test.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
import_checker.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
import_job.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
import_meta_test.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
import_meta.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
import_scheduler_test.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
import_scheduler.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
import_task.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
import_util_test.go
enhance: Replace currRows with NumOfRows (#40074)
2025-03-10 12:16:03 +08:00
import_util.go
enhance: Replace currRows with NumOfRows (#40074)
2025-03-10 12:16:03 +08:00
index_engine_version_manager_test.go
fix: Add scalar index engine version for compatibility (#39204)
2025-01-15 12:25:00 +08:00
index_engine_version_manager.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
index_meta_test.go
enhance: Refine task meta with key lock (#40613)
2025-03-14 15:44:22 +08:00
index_meta.go
enhance: Optimize datacoord meta mutex (#40552)
2025-03-25 13:46:25 +08:00
index_service_test.go
fix: Fix json index not equal filter (#40647)
2025-03-27 23:06:23 +08:00
index_service.go
fix: json path should be empty string if it's root (#40611)
2025-03-14 16:50:16 +08:00
job_manager_test.go
enhance: Optimize datacoord meta mutex (#40552)
2025-03-25 13:46:25 +08:00
job_manager.go
enhance: Optimize Task Scheduling to Enable Concurrent Execution (#40251)
2025-03-02 18:38:00 +08:00
knapsack_test.go
enhance: try compact small segments first if they may compose a full segment (#37709)
2024-12-02 16:12:38 +08:00
knapsack.go
fix: Pass Knapsnak ptr to avoid compact multiple times (#40400)
2025-03-06 15:42:03 +08:00
meta_test.go
enhance: Optimize datacoord meta mutex (#40552)
2025-03-25 13:46:25 +08:00
meta_util.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
meta.go
fix: Fix delete data loss due to duplicate binlogID (#40960)
2025-04-01 10:36:22 +08:00
metrics_info_test.go
enhance: Refine task meta with key lock (#40613)
2025-03-14 15:44:22 +08:00
metrics_info.go
enhance: Merge IndexNode and DataNode (#40272)
2025-03-13 14:26:11 +08:00
mock_channel_manager.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
mock_channel_store.go
fix: ChannelManager concurret Release and Watch bug (#38590)
2024-12-19 22:50:47 +08:00
mock_cluster.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
mock_compaction_meta.go
fix: Fix delete data loss due to duplicate binlogID (#40960)
2025-04-01 10:36:22 +08:00
mock_compaction_plan_context.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
mock_handler.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
mock_index_engine_version_manager.go
fix: Add scalar index engine version for compatibility (#39204)
2025-01-15 12:25:00 +08:00
mock_segment_manager.go
fix: auto flush all segment that is not created by streaming service (#40767)
2025-03-26 16:32:22 +08:00
mock_stats_job_manager.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
mock_sub_cluster.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
mock_test.go
enhance: Merge IndexNode and DataNode (#40272)
2025-03-13 14:26:11 +08:00
mock_trigger_manager.go
feat: support to replicate import msg (#39171)
2025-02-16 00:08:13 +08:00
mock_trigger.go
enhance: Support detailed manual compaction criterion (#40892)
2025-03-25 20:06:22 +08:00
OWNERS
[skip ci]Update OWNERS files (#11898)
2021-11-16 15:41:11 +08:00
partition_stats_meta_test.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
partition_stats_meta.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
policy_test.go
fix: Fix channel not balance on datanodes (#40422)
2025-03-11 14:56:16 +08:00
policy.go
fix: Fix channel not balance on datanodes (#40422)
2025-03-11 14:56:16 +08:00
README.md
[skip ci]Change etcd to lowercase (#9983)
2021-10-15 18:58:37 +08:00
segment_allocation_policy_test.go
enhance: Add channel seal policy based on blocking l0 (#40505)
2025-03-10 16:28:04 +08:00
segment_allocation_policy.go
enhance: Add channel seal policy based on blocking l0 (#40505)
2025-03-10 16:28:04 +08:00
segment_info_test.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
segment_info.go
enhance: Replace currRows with NumOfRows (#40074)
2025-03-10 12:16:03 +08:00
segment_manager_test.go
enhance: Replace currRows with NumOfRows (#40074)
2025-03-10 12:16:03 +08:00
segment_manager.go
fix: auto flush all segment that is not created by streaming service (#40767)
2025-03-26 16:32:22 +08:00
segment_operator_test.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
segment_operator.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
server_test.go
enhance: Support detailed manual compaction criterion (#40892)
2025-03-25 20:06:22 +08:00
server.go
enhance: Merge IndexNode and DataNode (#40272)
2025-03-13 14:26:11 +08:00
services_test.go
fix: auto flush all segment that is not created by streaming service (#40767)
2025-03-26 16:32:22 +08:00
services.go
fix: auto flush all segment that is not created by streaming service (#40767)
2025-03-26 16:32:22 +08:00
stats_task_meta_test.go
enhance: Refine task meta with key lock (#40613)
2025-03-14 15:44:22 +08:00
stats_task_meta.go
enhance: Resolve existing lint issues (#40797)
2025-03-20 19:36:11 +08:00
sync_segments_scheduler_test.go
enhance: Optimize datacoord meta mutex (#40552)
2025-03-25 13:46:25 +08:00
sync_segments_scheduler.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
task_analyze.go
enhance: Refine task meta with key lock (#40613)
2025-03-14 15:44:22 +08:00
task_index.go
enhance: Refine task meta with key lock (#40613)
2025-03-14 15:44:22 +08:00
task_queue.go
enhance: Optimize Task Scheduling to Enable Concurrent Execution (#40251)
2025-03-02 18:38:00 +08:00
task_scheduler_test.go
enhance: Optimize datacoord meta mutex (#40552)
2025-03-25 13:46:25 +08:00
task_scheduler.go
fix: Set task queue time before enqueue (#40815)
2025-03-21 19:36:15 +08:00
task_stats_test.go
enhance: Refine task meta with key lock (#40613)
2025-03-14 15:44:22 +08:00
task_stats.go
fix: Fix delete data loss due to duplicate binlogID (#40960)
2025-04-01 10:36:22 +08:00
types.go
enhance: Refine task meta with key lock (#40613)
2025-03-14 15:44:22 +08:00
util_test.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00
util.go
enhance: Use v2 package name for pkg module (#39990)
2025-02-22 23:15:58 +08:00

README.md

Data Coordinator

Data cooridnator(datacoord for short) is the component to organize DataNodes and segments allocations.

Dependency

  • KV store: a kv store has all the meta info datacoord needs to operate. (etcd)
  • Message stream: a message stream to communicate statistics information with data nodes. (Pulsar)
  • Root Coordinator: timestamp, id and meta source.
  • Data Node(s): could be an instance or a cluster, actual worker group handles data modification operations.