Re: [RFC][PATCH 00/16] sched: Core scheduling

From: Subhra Mazumdar
Date: Thu Feb 21 2019 - 19:36:49 EST



On 2/21/19 6:03 AM, Peter Zijlstra wrote:
On Wed, Feb 20, 2019 at 06:53:08PM -0800, Subhra Mazumdar wrote:
On 2/18/19 9:49 AM, Linus Torvalds wrote:
On Mon, Feb 18, 2019 at 9:40 AM Peter Zijlstra <peterz@xxxxxxxxxxxxx> wrote:
However; whichever way around you turn this cookie; it is expensive and nasty.
Do you (or anybody else) have numbers for real loads?

Because performance is all that matters. If performance is bad, then
it's pointless, since just turning off SMT is the answer.

Linus
I tested 2 Oracle DB instances running OLTP on a 2 socket 44 cores system.
This is on baremetal, no virtualization.
I'm thinking oracle schedules quite a bit, right? Then you get massive
overhead (as shown).

Out of curiosity I ran the patchset from Amazon with the same setup to see
if performance wise it was any better. But it looks equally bad. At 32
users it performed even worse and the idle time increased much more. Only
good thing about it was it was being fair to both the instances as seen in
the low %stdev

Users Baseline %stdev %idle cosched %stdev %idle
16ÂÂÂÂ 1ÂÂÂÂÂÂÂ 2.9ÂÂÂÂ 66ÂÂÂÂ 0.93(-7%)ÂÂ 1.1 69
24ÂÂÂÂ 1ÂÂÂÂÂÂÂ 11.3ÂÂÂ 53ÂÂÂÂ 0.87(-13%)Â 11.2 61
32ÂÂÂÂ 1ÂÂÂÂÂÂÂ 7ÂÂÂÂÂÂ 41ÂÂÂÂ 0.66(-34%)Â 5.3ÂÂÂÂ 54