Bug 1310180 - [RFE] IO threads should be considered in scheduling [NEEDINFO]
Summary: [RFE] IO threads should be considered in scheduling
Keywords:
Status: CLOSED DEFERRED
Alias: None
Product: ovirt-engine
Classification: oVirt
Component: General
Version: 4.0.0
Hardware: Unspecified
OS: Unspecified
unspecified
low vote
Target Milestone: ---
: ---
Assignee: bugs@ovirt.org
QA Contact:
URL:
Whiteboard:
Depends On:
Blocks:
TreeView+ depends on / blocked
 
Reported: 2016-02-19 16:44 UTC by Milan Zamazal
Modified: 2020-04-01 14:51 UTC (History)
5 users (show)

Fixed In Version:
Doc Type: Enhancement
Doc Text:
Clone Of:
Environment:
Last Closed: 2020-04-01 14:48:03 UTC
oVirt Team: SLA
mgoldboi: needinfo? (mgoldboi)
dfediuck: ovirt-future?
rule-engine: planning_ack?
rule-engine: devel_ack?
rule-engine: testing_ack?


Attachments (Terms of Use)

Description Milan Zamazal 2016-02-19 16:44:27 UTC
Description of problem:

Support for IO threads (AKA virtio-blk-dataplane) was added to oVirt some time ago, see https://bugzilla.redhat.com/1214311. This functionality utilizes dedicated threads and thus the number of available CPU cores should be taken into account. AFAIK this is not considered in oVirt scheduling.

Actual results:

Possibly suboptimal resource usage due to higher requirements on the number of CPU cores than expected.

Possible solution:

Inclusion of the number of requested IO threads and the corresponding system resource requirements into scheduling calculations.

Comment 1 Doron Fediuck 2016-02-21 08:05:07 UTC
Can you be more specific about the request;
ie- which calculation should consider the IO threads and in what way?

Comment 2 Milan Zamazal 2016-02-23 10:28:59 UTC
I don't know which CPU related scheduling calculations should be affected, AFAIK IO threads are not counted anywhere.  Initial clue to how to count them is in libvirt documentation: "There should be only 1 or 2 IOThreads per host CPU."

Comment 3 Moran Goldboim 2016-11-30 10:22:12 UTC
please check out with performance team.

Comment 5 Michal Skrivanek 2020-03-19 15:41:36 UTC
We didn't get to this bug for more than 2 years, and it's not being considered for the upcoming 4.4. It's unlikely that it will ever be addressed so I'm suggesting to close it.
If you feel this needs to be addressed and want to work on it please remove cond nack and target accordingly.

Comment 6 Michal Skrivanek 2020-04-01 14:48:03 UTC
ok, closing. Please reopen if still relevant/you want to work on it.

Comment 7 Michal Skrivanek 2020-04-01 14:51:22 UTC
ok, closing. Please reopen if still relevant/you want to work on it.


Note You need to log in before you can comment on or make changes to this bug.