Home » Mailing list archives » linux-kernel » 2007 » April » 19

Re: [ck] Announce - Staircase Deadline cpu scheduler v0.41

Previous thread: Re: [Announce] [patch] Modular Scheduler Core and Completely Fair Scheduler [CFS] by Michael K. Edwards on Wednesday, April 18, 2007 - 3:13 pm. (1 message)

Next thread: Remaining straight forward kthread API conversions... by Eric W. Biederman on Thursday, April 19, 2007 - 2:52 am. (216 messages)
[view original message]
From: Con Kolivas <kernel@...>
To: linux kernel mailing list <linux-kernel@...>, ck list <ck@...>
Subject: Announce - Staircase Deadline cpu scheduler v0.41
Date: Wednesday, April 18, 2007 - 7:59 pm

Since there is so much work currently ongoing with alternative cpu schedulers,

as a standard for comparison with the alternative virtual deadline fair

designs I've addressed a few issues in the Staircase Deadline cpu scheduler

which improve behaviour likely in a noticeable fashion and released version

0.41.


http://ck.kolivas.org/patches/staircase-deadline/2.6.20.7-sd-0.41.patch

http://ck.kolivas.org/patches/staircase-deadline/2.6.21-rc7-sd-0.41.patch


and an incremental for those on 0.40:

http://ck.kolivas.org/patches/staircase-deadline/2.6.21-rc7/sched-implem...


Remember to renice X to -10 for nicest desktop behaviour :)


Have fun.


--

-ck

-
[view original message]
From: Con Kolivas <kernel@...>
To: <ck@...>, Nick Piggin <npiggin@...>, Ingo Molnar <mingo@...>, Matt Mackall <mpm@...>, Peter Williams <pwil3058@...>, Mike Galbraith <efault@...>, Bill Huey <billh@...>, William Lee Irwin III <wli@...>, Gene Heskett <gene.heskett@...>, Willy Tarreau <w@...>
Cc: linux kernel mailing list <linux-kernel@...>
Subject: Re: [ck] Announce - Staircase Deadline cpu scheduler v0.41
Date: Wednesday, April 18, 2007 - 8:41 pm

Oops forgot to cc a few people


Nick you said I should still have something to offer so here it is.

Peter you said you never saw this design (it's a dual array affair sorry).

Gene and Willy you were some of the early testers that noticed the advantages

of the earlier designs,

Matt you did lots of great earlier testing.

WLI you inspired a lot of design ideas.

Mike you were the stick.

And a few others I've forgotten to mention and include.


--

-ck

-
[view original message]
From: Mike Galbraith <efault@...>
To: Con Kolivas <kernel@...>
Cc: <ck@...>, Nick Piggin <npiggin@...>, Ingo Molnar <mingo@...>, Matt Mackall <mpm@...>, Peter Williams <pwil3058@...>, Bill Huey <billh@...>, William Lee Irwin III <wli@...>, Gene Heskett <gene.heskett@...>, Willy Tarreau <w@...>, linux kernel mailing list <linux-kernel@...>
Subject: Re: [ck] Announce - Staircase Deadline cpu scheduler v0.41
Date: Thursday, April 19, 2007 - 2:59 am

(dirty job, somebody has to do it)


-
[view original message]
From: Con Kolivas <kernel@...>
To: <ck@...>, Al Boldi <a1426z@...>
Cc: Nick Piggin <npiggin@...>, Ingo Molnar <mingo@...>, Matt Mackall <mpm@...>, Peter Williams <pwil3058@...>, Mike Galbraith <efault@...>, Bill Huey <billh@...>, William Lee Irwin III <wli@...>, Gene Heskett <gene.heskett@...>, Willy Tarreau <w@...>, linux kernel mailing list <linux-kernel@...>
Subject: Announce - Staircase Deadline cpu scheduler v0.42
Date: Wednesday, April 18, 2007 - 10:12 pm

Version 0.42


http://ck.kolivas.org/patches/staircase-deadline/2.6.21-rc7-sd-0.42.patch


--

-ck

-
[view original message]
From: Willy Tarreau <w@...>
To: Con Kolivas <kernel@...>
Cc: <ck@...>, Al Boldi <a1426z@...>, Nick Piggin <npiggin@...>, Ingo Molnar <mingo@...>, Matt Mackall <mpm@...>, Peter Williams <pwil3058@...>, Mike Galbraith <efault@...>, Bill Huey <billh@...>, William Lee Irwin III <wli@...>, Gene Heskett <gene.heskett@...>, linux kernel mailing list <linux-kernel@...>
Subject: Re: Announce - Staircase Deadline cpu scheduler v0.42
Date: Thursday, April 19, 2007 - 8:55 am

Will give it a shoot ASAP, probably this week-end. I'm too short in time this

week.


Regards,

Willy


-
[view original message]
From: Con Kolivas <kernel@...>
To: Willy Tarreau <w@...>
Cc: <ck@...>, Al Boldi <a1426z@...>, Nick Piggin <npiggin@...>, Ingo Molnar <mingo@...>, Matt Mackall <mpm@...>, Peter Williams <pwil3058@...>, Mike Galbraith <efault@...>, Bill Huey <billh@...>, William Lee Irwin III <wli@...>, Gene Heskett <gene.heskett@...>, linux kernel mailing list <linux-kernel@...>
Subject: Re: Announce - Staircase Deadline cpu scheduler v0.42
Date: Thursday, April 19, 2007 - 9:39 am

Great, thanks. By then there will almost certainly be a 0.43 so no rush.


--

-ck

-
[view original message]
From: Nick Piggin <npiggin@...>
To: Con Kolivas <kernel@...>
Cc: <ck@...>, Al Boldi <a1426z@...>, Ingo Molnar <mingo@...>, Matt Mackall <mpm@...>, Peter Williams <pwil3058@...>, Mike Galbraith <efault@...>, Bill Huey <billh@...>, William Lee Irwin III <wli@...>, Gene Heskett <gene.heskett@...>, Willy Tarreau <w@...>, linux kernel mailing list <linux-kernel@...>
Subject: Re: Announce - Staircase Deadline cpu scheduler v0.42
Date: Wednesday, April 18, 2007 - 11:22 pm

OK, I run some tests later today...

-
[view original message]
From: Con Kolivas <kernel@...>
To: Nick Piggin <npiggin@...>
Cc: <ck@...>, Al Boldi <a1426z@...>, Ingo Molnar <mingo@...>, Matt Mackall <mpm@...>, Peter Williams <pwil3058@...>, Mike Galbraith <efault@...>, Bill Huey <billh@...>, William Lee Irwin III <wli@...>, Gene Heskett <gene.heskett@...>, Willy Tarreau <w@...>, linux kernel mailing list <linux-kernel@...>
Subject: Re: Announce - Staircase Deadline cpu scheduler v0.42
Date: Thursday, April 19, 2007 - 5:40 am

Thank you very much.


--

-ck

-
[view original message]
From: Nick Piggin <npiggin@...>
To: Con Kolivas <kernel@...>
Cc: <ck@...>, Al Boldi <a1426z@...>, Ingo Molnar <mingo@...>, Matt Mackall <mpm@...>, Peter Williams <pwil3058@...>, Mike Galbraith <efault@...>, Bill Huey <billh@...>, William Lee Irwin III <wli@...>, Gene Heskett <gene.heskett@...>, Willy Tarreau <w@...>, linux kernel mailing list <linux-kernel@...>
Subject: Re: Announce - Staircase Deadline cpu scheduler v0.42
Date: Thursday, April 19, 2007 - 6:22 am

lmbench numbers are roughly comparable to mainline (lmbench seems to be

a bit erratic, but there isn't the obvious drop that cfs has).


Didn't worry about hackbench ;)


kbuild:

2.6.21-rc7

508.87user 32.47system 2:17.82elapsed 392%CPU

509.05user 32.25system 2:17.84elapsed 392%CPU

508.75user 32.26system 2:17.83elapsed 392%CPU

508.63user 32.17system 2:17.88elapsed 392%CPU

509.01user 32.26system 2:17.90elapsed 392%CPU

509.08user 32.20system 2:17.95elapsed 392%CPU


2.6.21-rc7-sd42

512.78user 31.99system 2:18.41elapsed 393%CPU

512.55user 31.90system 2:18.57elapsed 392%CPU

513.05user 31.78system 2:18.48elapsed 393%CPU

512.46user 32.06system 2:18.63elapsed 392%CPU

512.78user 31.81system 2:18.49elapsed 393%CPU

512.41user 32.08system 2:18.70elapsed 392%CPU


sd42 is doing about 745 context switches per second here, and perfomance is

slightly below mainline. But it isn't doing badly.


507.87user 32.53system 2:17.50elapsed 392%CPU

508.47user 32.40system 2:17.56elapsed 393%CPU

508.59user 32.27system 2:17.53elapsed 393%CPU 


A few runs with rr_interval at 100 show that ctxsw numbers drop to 587, and

performance is up to slightly above mainline.


With the results I've got so far with all scedulers (actually I didn't try

nicksched with a small timeslice, but I'm sure it would give the expected

result)... I'd say 5ms might be too small a timeslice. Even 15ms will hurt

some people I think.


Although we could arguably tolerate this kind of regression, my box only

has 1MB caches, and kbuild is naturally context switching at over 500 per

second anyway. On something with bigger caches and less context switchy /

more cache sensitive workloads, the regression could be quite a bit worse.


(not directed at anyone in particular, but food for thought)

-
[view original message]
From: Con Kolivas <kernel@...>
To: Nick Piggin <npiggin@...>
Cc: <ck@...>, Al Boldi <a1426z@...>, Ingo Molnar <mingo@...>, Matt Mackall <mpm@...>, Peter Williams <pwil3058@...>, Mike Galbraith <efault@...>, Bill Huey <billh@...>, William Lee Irwin III <wli@...>, Gene Heskett <gene.heskett@...>, Willy Tarreau <w@...>, linux kernel mailing list <linux-kernel@...>
Subject: Re: Announce - Staircase Deadline cpu scheduler v0.42
Date: Thursday, April 19, 2007 - 7:53 am

Great.


Not bad. It's always impossible to know where the sweet spot will lie with

these things. Basically the higher the better.... for this one thing of 


Well they're nice numbers indeed. I don't even need to leave the maximum at

100ms but I seriously doubt we'd see much improvement beyond there... I'm

sure some renderfarm might enjoy values of 1 second though (like my -ck

patchet already offers in compute mode for old fashioned staircase cpu 


On 4x (that's what your hardware was IIRC) SD would be setting it to 15ms.

Mainline would be timeslice granularity setting 4x to about 40ms. Pulling a

number out of my rear end generator I'd say 20ms for SD should make it close 


Heck if I'm going to keep offering SD as an alternative for comparison I may

as well use the food you've offered me. I guess I better work on a v0.43 with

some more of these very easy to do tweaks then. Thanks!


--

-ck

-
Previous thread: Re: [Announce] [patch] Modular Scheduler Core and Completely Fair Scheduler [CFS] by Michael K. Edwards on Wednesday, April 18, 2007 - 3:13 pm. (1 message)

Next thread: Remaining straight forward kthread API conversions... by Eric W. Biederman on Thursday, April 19, 2007 - 2:52 am. (216 messages)