From: Antonio Vargas <wind@cocodriloo.com>
To: Con Kolivas <kernel@kolivas.org>
Cc: linux kernel mailing list <linux-kernel@vger.kernel.org>,
Andrew Morton <akpm@osdl.org>, Ingo Molnar <mingo@elte.hu>,
Felipe Alfaro Solana <felipe_alfaro@linuxmail.org>
Subject: Re: [PATCH] O13int for interactivity
Date: Mon, 4 Aug 2003 21:15:13 +0200 [thread overview]
Message-ID: <20030804191513.GB814@wind.cocodriloo.com> (raw)
In-Reply-To: <200308050207.18096.kernel@kolivas.org>
On Tue, Aug 05, 2003 at 02:07:18AM +1000, Con Kolivas wrote:
> Changes:
>
> Reverted the child penalty to 95 as new changes help this from hurting
>
> Changed the logic behind loss of interactive credits to those that burn off
> all their sleep_avg
>
> Now all tasks get proportionately more sleep as their relative bonus drops
> off. This has the effect of detecting a change from a cpu burner to an
> interactive task more rapidly as in O10.
>
> The _major_ change in this patch is that tasks on uninterruptible sleep do not
> earn any sleep avg during that sleep; it is not voluntary sleep so they should
> not get it. This has the effect of stopping cpu hogs from gaining dynamic
> priority during periods of heavy I/O. Very good for the jerks you may
> see in X or audio skips when you start a whole swag of disk intensive cpu hogs
> (eg make -j large number). I've simply dropped all their sleep_avg, but
> weighting it may be more appropriate. This has the side effect that pure
> disk tasks (eg cp) have relatively low priority which is why weighting may
> be better. We shall see.
>
> Please test this one extensively. It should _not_ affect I/O throughput per
> se, but I'd like to see some of the I/O benchmarks on this. I do not want to
> have detrimental effects elsewhere.
>
> patch-O12.3-O13int applies on top of 2.6.0-test2-mm4 that has been
> patched with O12.3int and is available on my site, and a full patch
> against 2.6.0-test2 called patch-test2-O13int is here:
>
> http://kernel.kolivas.org/2.5
>
> patch-O12.3-O13int:
>
> --- linux-2.6.0-test2-mm4-O12.3/kernel/sched.c 2003-08-05 01:30:27.000000000 +1000
> +++ linux-2.6.0-test2-mm4-O13/kernel/sched.c 2003-08-05 01:36:20.000000000 +1000
> @@ -78,7 +78,7 @@
> #define MAX_TIMESLICE (200 * HZ / 1000)
> #define TIMESLICE_GRANULARITY (HZ/40 ?: 1)
> #define ON_RUNQUEUE_WEIGHT 30
> -#define CHILD_PENALTY 90
> +#define CHILD_PENALTY 95
> #define PARENT_PENALTY 100
> #define EXIT_WEIGHT 3
> #define PRIO_BONUS_RATIO 25
> @@ -365,6 +365,9 @@ static void recalc_task_prio(task_t *p,
> unsigned long long __sleep_time = now - p->timestamp;
> unsigned long sleep_time;
>
> + if (!p->sleep_avg)
> + p->interactive_credit--;
> +
> if (__sleep_time > NS_MAX_SLEEP_AVG)
> sleep_time = NS_MAX_SLEEP_AVG;
> else
> @@ -384,17 +387,19 @@ static void recalc_task_prio(task_t *p,
> JIFFIES_TO_NS(JUST_INTERACTIVE_SLEEP(p));
> else {
> /*
> - * Tasks with interactive credits get boosted more
> - * rapidly if their bonus has dropped off. Other
> - * tasks are limited to one timeslice worth of
> - * sleep avg.
> + * The lower the sleep avg a task has the more
> + * rapidly it will rise with sleep time. Tasks
> + * without interactive_credit are limited to
> + * one timeslice worth of sleep avg bonus.
> */
> - if (p->interactive_credit > 0)
> - sleep_time *= (MAX_BONUS + 1 -
> + sleep_time *= (MAX_BONUS + 1 -
> (NS_TO_JIFFIES(p->sleep_avg) *
> MAX_BONUS / MAX_SLEEP_AVG));
> - else if (sleep_time > JIFFIES_TO_NS(task_timeslice(p)))
> - sleep_time = JIFFIES_TO_NS(task_timeslice(p));
> +
> + if (p->interactive_credit < 0 &&
> + sleep_time > JIFFIES_TO_NS(task_timeslice(p)))
> + sleep_time =
> + JIFFIES_TO_NS(task_timeslice(p));
>
> /*
> * This code gives a bonus to interactive tasks.
> @@ -435,20 +440,26 @@ static inline void activate_task(task_t
> recalc_task_prio(p, now);
>
> /*
> - * Tasks which were woken up by interrupts (ie. hw events)
> - * are most likely of interactive nature. So we give them
> - * the credit of extending their sleep time to the period
> - * of time they spend on the runqueue, waiting for execution
> - * on a CPU, first time around:
> + * This checks to make sure it's not an uninterruptible task
> + * that is now waking up.
> */
> - if (in_interrupt())
> - p->activated = 2;
> - else
> - /*
> - * Normal first-time wakeups get a credit too for on-runqueue time,
> - * but it will be weighted down:
> - */
> - p->activated = 1;
> + if (!p->activated){
[1]
> + /*
> + * Tasks which were woken up by interrupts (ie. hw events)
> + * are most likely of interactive nature. So we give them
> + * the credit of extending their sleep time to the period
> + * of time they spend on the runqueue, waiting for execution
> + * on a CPU, first time around:
> + */
> + if (in_interrupt())
> + p->activated = 2;
> + else
> + /*
> + * Normal first-time wakeups get a credit too for on-runqueue
> + * time, but it will be weighted down:
> + */
> + p->activated = 1;
[3]
> + }
>
> p->timestamp = now;
>
> @@ -572,8 +583,15 @@ repeat_lock_task:
> task_rq_unlock(rq, &flags);
> goto repeat_lock_task;
> }
> - if (old_state == TASK_UNINTERRUPTIBLE)
> + if (old_state == TASK_UNINTERRUPTIBLE){
> + /*
> + * Tasks on involuntary sleep don't earn
> + * sleep_avg
> + */
> rq->nr_uninterruptible--;
> + p->timestamp = sched_clock();
> + p->activated = -1;
[2]
> + }
> if (sync)
> __activate_task(p, rq);
> else {
> @@ -1326,7 +1344,6 @@ void scheduler_tick(int user_ticks, int
> p->prio = effective_prio(p);
> p->time_slice = task_timeslice(p);
> p->first_time_slice = 0;
> - p->interactive_credit--;
>
> if (!rq->expired_timestamp)
> rq->expired_timestamp = jiffies;
> @@ -1459,7 +1476,7 @@ pick_next_task:
> queue = array->queue + idx;
> next = list_entry(queue->next, task_t, run_list);
>
> - if (next->activated && next->interactive_credit > 0) {
> + if (next->activated > 0) {
> unsigned long long delta = now - next->timestamp;
>
> if (next->activated == 1)
>
Con, I will probably be wrong, but in [1] you are testing
"activated != 0" and [2] is setting "activated = -1", which
_is_ != 0 and thus would enter the "if->else" branch and
do "activated = 1" in [3].
Perhaps you meant to set "activated = 0" in [2]???
Note I've not read the rest of the scheduler code,
so perhaps the "activated = 0" is in another place...
just in case, I prefer asking.
Greets for your hard work, Antonio.
--
1. Dado un programa, siempre tiene al menos un fallo.
2. Dadas varias lineas de codigo, siempre se pueden acortar a menos lineas.
3. Por induccion, todos los programas se pueden
reducir a una linea que no funciona.
next prev parent reply other threads:[~2003-08-04 17:13 UTC|newest]
Thread overview: 83+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-08-04 16:07 [PATCH] O13int for interactivity Con Kolivas
2003-08-04 18:24 ` Felipe Alfaro Solana
2003-08-04 19:15 ` Antonio Vargas [this message]
2003-08-04 21:32 ` Con Kolivas
2003-08-04 20:11 ` Mike Galbraith
2003-08-04 22:11 ` Con Kolivas
2003-08-05 7:10 ` Mike Galbraith
2003-08-05 2:11 ` Nick Piggin
2003-08-05 2:20 ` Con Kolivas
2003-08-05 2:21 ` Nick Piggin
2003-08-05 3:06 ` Con Kolivas
2003-08-05 3:17 ` Nick Piggin
2003-08-06 18:48 ` Interactivity improvements Timothy Miller
2003-08-06 19:01 ` Mike Fedyk
2003-08-06 20:09 ` Helge Hafting
2003-08-06 21:15 ` Con Kolivas
2003-08-05 3:18 ` [PATCH] O13int for interactivity Con Kolivas
2003-08-05 3:31 ` Nick Piggin
2003-08-05 5:04 ` Con Kolivas
2003-08-05 5:12 ` Nick Piggin
2003-08-05 5:16 ` Con Kolivas
2003-08-05 5:28 ` Nick Piggin
2003-08-05 10:22 ` Con Kolivas
2003-08-05 10:32 ` Nick Piggin
2003-08-05 10:45 ` Con Kolivas
2003-08-05 10:48 ` Nick Piggin
2003-08-05 10:56 ` Con Kolivas
2003-08-05 11:03 ` Nick Piggin
2003-08-05 11:12 ` Con Kolivas
2003-08-05 11:23 ` Nick Piggin
2003-08-05 11:34 ` Con Kolivas
2003-08-05 10:54 ` Arjan van de Ven
2003-08-05 11:10 ` Con Kolivas
2003-08-06 21:33 ` Timothy Miller
2003-08-06 21:33 ` Con Kolivas
2003-08-07 0:27 ` Timothy Miller
2003-08-07 0:27 ` Con Kolivas
2003-08-07 0:44 ` Timothy Miller
2003-08-11 6:48 ` Rob Landley
2003-08-11 15:47 ` William Lee Irwin III
2003-08-12 2:51 ` Nick Piggin
2003-08-12 6:16 ` Mike Galbraith
2003-08-12 7:07 ` Nick Piggin
2003-08-12 7:18 ` Nick Piggin
2003-08-12 9:42 ` Mike Galbraith
2003-08-12 21:11 ` Mike Fedyk
2003-08-13 6:55 ` Mike Galbraith
2003-08-12 9:22 ` Mike Galbraith
2003-08-12 9:37 ` Nick Piggin
2003-08-12 9:48 ` Mike Galbraith
2003-08-12 10:29 ` Rob Landley
2003-08-12 11:08 ` Nick Piggin
2003-08-12 11:35 ` Rob Landley
2003-08-12 11:58 ` Nick Piggin
2003-08-13 2:08 ` jw schultz
2003-08-13 3:07 ` Gene Heskett
2003-08-13 3:24 ` Nick Piggin
2003-08-13 5:24 ` Gene Heskett
2003-08-13 5:43 ` Andrew McGregor
2003-08-13 12:33 ` Gene Heskett
2003-08-14 5:03 ` Andrew McGregor
2003-08-14 10:48 ` Gene Heskett
2003-08-12 15:36 ` Timothy Miller
2003-08-05 6:03 ` Andrew Morton
2003-08-05 7:26 ` Con Kolivas
2003-08-05 8:12 ` Oliver Neukum
2003-08-05 8:20 ` Con Kolivas
2003-08-05 8:27 ` Mike Galbraith
2003-08-05 8:43 ` Con Kolivas
2003-08-05 9:09 ` Mike Galbraith
2003-08-05 9:19 ` Con Kolivas
2003-08-05 10:04 ` Nick Piggin
2003-08-11 6:57 ` Rob Landley
2003-08-11 15:58 ` William Lee Irwin III
2003-08-05 7:53 ` Mike Galbraith
[not found] <gQ4n.5oS.7@gated-at.bofh.it>
[not found] ` <jUl6.5eh.1@gated-at.bofh.it>
[not found] ` <jUuT.5kZ.15@gated-at.bofh.it>
[not found] ` <jWn1.6K1.11@gated-at.bofh.it>
2003-08-13 13:48 ` Pascal Schmidt
2003-08-13 14:50 ` Gene Heskett
-- strict thread matches above, loose matches on Subject: below --
2003-08-06 10:35 Voluspa
2003-08-04 19:12 Voluspa
2003-07-27 15:12 [PATCH] O10int " Con Kolivas
2003-07-28 18:08 ` Valdis.Kletnieks
2003-07-28 18:40 ` Andrew Morton
2003-08-04 18:51 ` [PATCH] O13int " Felipe Alfaro Solana
2003-08-04 18:58 ` Felipe Alfaro Solana
2003-08-04 21:46 ` Con Kolivas
2003-08-04 22:16 ` Felipe Alfaro Solana
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20030804191513.GB814@wind.cocodriloo.com \
--to=wind@cocodriloo.com \
--cc=akpm@osdl.org \
--cc=felipe_alfaro@linuxmail.org \
--cc=kernel@kolivas.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).