impala-reviews mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Matthew Jacobs (Code Review)" <>
Subject [Impala-ASF-CR] IMPALA-5644: Reject queries if min reservation is too large
Date Wed, 16 Aug 2017 23:17:17 GMT
Matthew Jacobs has posted comments on this change.

Change subject: IMPALA-5644: Reject queries if min reservation is too large

Patch Set 2:

File be/src/scheduling/

Line 401:   // Compute the max (over all backends) min_reservation_bytes and the cluster total
> I was wondering about whether it makes sense to report which backend had th
Yeah it's a good idea, I started playing around with doing that earlier but also realized
there wasn't much to do with it. I think what the user really needs is a way to get a good
dump of all the info affecting these decisions as part of the profile. The profile of these
rejected queries will have the "Per Host Min Reservation: " line in the profile, but unfortunately
it may still be hard to figure out what to do with that. We may need a way to see something
like the plan annotated with the post-scheduling information.

Line 430:       int64_t recommended_mem_limit = std::max<int64_t>(
> It seems like this would fit better in ReservationUtil.

Line 432:           max_min_reservation_bytes + ReservationUtil::RESERVATION_MEM_MIN_REMAINING);
> I think the test is only exercising the second MEM_MIN_REMAINING calculatio
File be/src/scheduling/admission-controller.h:

PS2, Line 465: set
> maybe "set to a explanation of why the request was rejected".

To view, visit
To unsubscribe, visit

Gerrit-MessageType: comment
Gerrit-Change-Id: Iabe87ce8f460356cfe4d1be4d7092c5900f9d79b
Gerrit-PatchSet: 2
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-Owner: Matthew Jacobs <>
Gerrit-Reviewer: Dan Hecht <>
Gerrit-Reviewer: Matthew Jacobs <>
Gerrit-Reviewer: Tim Armstrong <>
Gerrit-HasComments: Yes

View raw message