mridulm commented on code in PR #42357:
URL: https://github.com/apache/spark/pull/42357#discussion_r1295720900
##########
resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/config.scala:
##########
@@ -462,6 +462,30 @@ package object config extends Logging {
.stringConf
.createWithDefault("yarn.io/fpga")
+ private[spark] val YARN_CLIENT_STAT_CACHE_PRELOAD_ENABLED =
+ ConfigBuilder("spark.yarn.client.statCache.preload.enabled")
+ .doc("This configuration enables statCache to be preloaded at YARN client
side. This feature" +
+ " analyzes the pattern of resources paths. If multiple resources shared
the same parent" +
+ " directory, a single <code>listStatus</code> will be invoked on the
parent directory" +
+ " instead of multiple <code>getFileStatus</code> performed on each
individual resources." +
+ " If most resources from a small set of directories, this can
substantially improve job" +
+ " submission time. Enabling this feature may potentially increase client
memory overhead.")
+ .version("4.0.0")
+ .booleanConf
+ .createWithDefault(false)
+
+ private[spark] val YARN_CLIENT_STAT_CACHE_PRELOAD_PER_DIRECTORY_THRESHOLD =
+ ConfigBuilder("spark.yarn.client.statCache.preload.perDirectoryThreshold")
+ .doc("This configuration defines the threshold for the number of
resources in a directory" +
+ " that triggers the activation of the statCache preloading. When the
count of individual" +
Review Comment:
Please do not apply this verbatim :-)
This was illustrative of how to fix it
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
