pd-server v3.0.0-rc.2

• Enable the Region storage by default to store the Region metadata #1524
• Fix the issue that hot Region scheduling is preempted by another scheduler #1522
• Fix the issue that the priority for the leader does not take effect #1533
• Add the gRPC interface for ScanRegions #1535
• Push operators actively #1536
• Add the store limit mechanism for separately controlling the speed of operators for each store #1474
• Fix the issue of inconsistent Config status #1476

pd-server v2.1.10

• Fix the issue that the priority of the leader does not take effect #1533

pd-server v2.1.9

• Support the GetOperator service #1514
• Improve leader election related logs #1529

pd-server v3.0.0-rc.1

• Upgrade ETCD #1452
  • Unify the log format of etcd and PD server
  • Fix the issue of failing to elect Leader by PreVote
  • Support fast dropping the “propose” and “read” requests that are to fail to avoid blocking the subsequent requests
  • Fix the deadlock issue of Lease

• Fix the issue that a hot store makes incorrect statistics of keys #1487
• Support forcibly rebuilding a PD cluster from a single PD node
• #1485
• Fix the issue that regionScatterer might generate an invalid OperatorStep
• #1482
• Fix the too short timeout issue of the MergeRegion operator #1495
• Support giving high priority to hot region scheduling #1492
• Add the metrics for recording the time of handling TSO requests on the PD server side #1502
• Add the corresponding Store ID and Address to the metrics related to the store #1507
• Support the GetOperator service #1477
• Fix the issue that the error cannot be sent in the Heartbeat stream because the store cannot be found #1522

pd-server v2.1.8

• Fix the issue that regionScatterer might generate an invalid OperatorStep #1482
• Fix the issue that a hot store makes incorrect statistics of keys #1487
• Fix the issue that too short timeout of MergeRegion causes unfinished merge process #1495
• Add the time metrics of the PD server handling TSO requests #1502

pd-server v2.1.7

• Fix the issue that the transferring leader step cannot be created in the balance-region when the number of replicas is one #1462

pd-server v3.0.0-beta.1

• Unify the log format for easy collection and analysis by tools
• Simulator
  • Support different heartbeat intervals in different stores #1418
  • Add a case about importing data #1263
• Make hotspot scheduling configurable #1412
• Add the store address as the dimension monitoring item to replace the previous Store ID #1429
• Optimize the GetStores overhead to speed up the Region inspection cycle #1410
• Add an interface to delete the Tombstone Store #1472

pd-server v2.1.5

• Provide the ExcludeTombstoneStores option in the GetAllStores interface to remove the Tombstone store from the returned result #1444

pd-server v2.1.3

• Fix the Watch issue related to leader election #1396

pd-server v3.0.0-beta

• Add RegionStorage to store Region metadata separately #1237
• Add shuffle hot Region scheduler #1361
• Add scheduling parameter related metrics #1406
• Add cluster label related metrics #1402
• Add the importing data simulator #1263
• Fix the Watch issue about leader election #1396