Csaba Ringhofer has posted comments on this change. ( 
http://gerrit.cloudera.org:8080/21257 )

Change subject: IMPALA-12980: Translate CpuAsk into admission control slots
......................................................................


Patch Set 14:

(3 comments)

http://gerrit.cloudera.org:8080/#/c/21257/11//COMMIT_MSG
Commit Message:

http://gerrit.cloudera.org:8080/#/c/21257/11//COMMIT_MSG@19
PS11, Line 19: stances
             : scheduled in this e
> Rephrased this paragraph.
Thanks for the explanation!


http://gerrit.cloudera.org:8080/#/c/21257/14//COMMIT_MSG
Commit Message:

http://gerrit.cloudera.org:8080/#/c/21257/14//COMMIT_MSG@17
PS14, Line 17: underestimation query overadmission. For example, assume an 
executor
nit: missing "and"?


http://gerrit.cloudera.org:8080/#/c/21257/11/tests/custom_cluster/test_executor_groups.py
File tests/custom_cluster/test_executor_groups.py:

http://gerrit.cloudera.org:8080/#/c/21257/11/tests/custom_cluster/test_executor_groups.py@1245
PS11, Line 1245:     #   CoreCount={total=16 
trace=F15:3+F01:1+F14:3+F03:1+F13:3+F05:1+F12:3+F07:1},
> patch set 14 adds processing-cost-plan-admission-slots.test
Thanks for adding the new plan, now the fragment numbers make sense!

One thing I noticed is that runtime filters do not seem to be accounted for. 
RF000/RF001 are produced in F11, which depends on F12/F07. Meanwhile F05 
consumes these filters, so F13/F05 can't run in parallel to F12/F07. Is this 
how it is intended to work?

About the cost of fragments:
"F00:PLAN FRAGMENT [RANDOM] hosts=3 instances=3 (adjusted from 384)"
Is my understanding correct that this is the case where based on the cost we 
wanted to run more instances, but it was clamped to the maximum number of 
instances in hosts, so this is why fragments that only process a couple of rows 
have the same "weight" (number of instances) as fragments that process a lot of 
rows? So if F00 actually got 384 instances then it could become more dominant 
than the current dominant fragment set.



--
To view, visit http://gerrit.cloudera.org:8080/21257
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings

Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-MessageType: comment
Gerrit-Change-Id: I338ca96555bfe8d07afce0320b3688a0861663f2
Gerrit-Change-Number: 21257
Gerrit-PatchSet: 14
Gerrit-Owner: Riza Suminto <[email protected]>
Gerrit-Reviewer: Abhishek Rawat <[email protected]>
Gerrit-Reviewer: Csaba Ringhofer <[email protected]>
Gerrit-Reviewer: Impala Public Jenkins <[email protected]>
Gerrit-Reviewer: Kurt Deschler <[email protected]>
Gerrit-Reviewer: Riza Suminto <[email protected]>
Gerrit-Reviewer: Wenzhe Zhou <[email protected]>
Gerrit-Comment-Date: Wed, 17 Apr 2024 14:16:01 +0000
Gerrit-HasComments: Yes

Reply via email to