Repository navigation
HIVE-30262: LlapTaskSchedulerService writes 8 INFO lines per task attempt, a quarter of the Tez AM log on large DAGs - #6965
Open
abstractdog wants to merge 1 commit into
Conversation
…empt, a quarter of the Tez AM log on large DAGs
|
This branch has not been deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What changes were proposed in this pull request?
Moves the 8 per-task-attempt INFO messages in
LlapTaskSchedulerServiceto DEBUG: 5 on its own logger and 3 on theGuaranteedTaskslogger.constructPendingTaskCountsLogMessage(),NodeInfo.toShortString()) are now behindisDebugEnabled()guards.GuaranteedTasksuse parameterized logging.Why are the changes needed?
These 8 lines are written for every task attempt. In the Tez AM they came to 32 % of log lines and 25 % of bytes: 308 MB in 24 minutes for one 162k-attempt TPC-DS SF10000 run. Five of them are written under the scheduler's write lock. Details and measurements are in HIVE-30262.
Does this PR introduce any user-facing change?
Yes, only in the Tez AM log. At the default INFO level the per-attempt scheduler lines are no longer written. Setting
org.apache.hadoop.hive.llap.tezplugins.LlapTaskSchedulerServiceand/orGuaranteedTasksto DEBUG brings them back.How was this patch tested?
mvn test -pl llap-tez -Dtest=TestLlapTaskSchedulerServicepasses. The change only touches log levels, so no new tests were added.