zecookiez commented on code in PR #50123:
URL: https://github.com/apache/spark/pull/50123#discussion_r2004259876
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/state/StateStoreCoordinator.scala:
##########
@@ -129,10 +210,25 @@ class StateStoreCoordinatorRef private(rpcEndpointRef:
RpcEndpointRef) {
* Class for coordinating instances of [[StateStore]]s loaded in executors
across the cluster,
* and get their locations for job scheduling.
*/
-private class StateStoreCoordinator(override val rpcEnv: RpcEnv)
- extends ThreadSafeRpcEndpoint with Logging {
+private class StateStoreCoordinator(
+ override val rpcEnv: RpcEnv,
+ val sqlConf: SQLConf)
+ extends ThreadSafeRpcEndpoint
+ with Logging {
private val instances = new mutable.HashMap[StateStoreProviderId,
ExecutorCacheTaskLocation]
+ // Stores the latest snapshot upload event for a specific state store
provider instance
+ private val stateStoreLatestUploadedSnapshot =
Review Comment:
Resolved offline - we loop through active instances instead of
stateStoreLatestUploadedSnapshot to account for partitions that have never
uploaded
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
