Add in application timeline to profiling tool #2760
Merged
Conversation
This file contains 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
revans2
added
the
task
|
build |
Signed-off-by: Robert (Bobby) Evans <bobby@apache.org>
|
build |
|
would be nice to have some sort of tests, perhaps unit tests that verify the slots as well as negative tests, what does this do with truncated log files, etc. |
|
@tgravescs I added in a test and moved away from using SQL to gather the data for the timeline. |
|
build |
tgravescs
reviewed
Jun 21, 2021
| scheduleCallback: (A, Int) => Unit, | ||
| errorOnMissingSlot: Boolean, | ||
| slotsFreeUntil: mutable.Buffer[Long]): Unit = { | ||
| toSchedule.toSeq.sortWith{ |
There was a problem hiding this comment.
Suggested change
| toSchedule.toSeq.sortWith{ | |
| toSchedule.toSeq.sortWith { |
tools/src/main/scala/com/nvidia/spark/rapids/tool/profiling/GenerateTimeline.scala
Outdated
Show resolved
Hide resolved
tools/src/main/scala/com/nvidia/spark/rapids/tool/profiling/GenerateTimeline.scala
Outdated
Show resolved
Hide resolved
| // TITLE | ||
| // EXEC(s) | TASK TIMING | ||
| // STAGES | STAGE TIMING | ||
| // STAGE RANGES | STAGE RANGE TIMING |
There was a problem hiding this comment.
perhaps we should clarify what stage range means vs just stages, from just looking at the output graph it was unclear to me until I read the code
|
build |
|
@tgravescs I think I have addressed all of your comments. |
tgravescs
approved these changes
Jun 23, 2021
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Outdated suggestions cannot be applied.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.
This adds in application timeline generation the the profiling tool. It is helpful in understanding what was running and where to know if a stage was long because it was preempted by another stage or if there was skew, etc. This really helped me see the high startup overhead, even if it is not reflected in benchmark numbers because the benchmarks start on the SQL query, not when setting up the data.
I used this to help debug some data/time skew issues.