From: Peter Zijlstra <a.p.zijlstra@chello.nl>
To: Ingo Molnar <mingo@elte.hu>, Mike Galbraith <efault@gmx.de>,
Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>,
dhaval@linux.vnet.ibm.com, tong.n.li@intel.com
Cc: linux-kernel@vger.kernel.org, Peter Zijlstra <a.p.zijlstra@chello.nl>
Subject: [PATCH 6/7] sched: fair: optimize sched_slice()
Date: Mon, 18 Feb 2008 10:55:41 +0100 [thread overview]
Message-ID: <20080218095625.579955000@chello.nl> (raw)
In-Reply-To: 20080218095535.629736000@chello.nl
[-- Attachment #1: sched-opt-sched_slice.patch --]
[-- Type: text/plain, Size: 1824 bytes --]
Cache the divide in the hope we can avoid doing it in steady state optertion.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
kernel/sched.c | 2 ++
kernel/sched_debug.c | 1 +
kernel/sched_fair.c | 6 ++----
3 files changed, 5 insertions(+), 4 deletions(-)
Index: linux-2.6/kernel/sched.c
===================================================================
--- linux-2.6.orig/kernel/sched.c
+++ linux-2.6/kernel/sched.c
@@ -1225,11 +1225,13 @@ calc_delta_mine(unsigned long delta_exec
static inline void update_load_add(struct load_weight *lw, unsigned long inc)
{
lw->weight += inc;
+ lw->inv_weight = 0;
}
static inline void update_load_sub(struct load_weight *lw, unsigned long dec)
{
lw->weight -= dec;
+ lw->inv_weight = 0;
}
/*
Index: linux-2.6/kernel/sched_debug.c
===================================================================
--- linux-2.6.orig/kernel/sched_debug.c
+++ linux-2.6/kernel/sched_debug.c
@@ -137,6 +137,7 @@ void print_cfs_rq(struct seq_file *m, in
SPLIT_NS(spread0));
SEQ_printf(m, " .%-30s: %ld\n", "nr_running", cfs_rq->nr_running);
SEQ_printf(m, " .%-30s: %ld\n", "load", cfs_rq->load.weight);
+ SEQ_printf(m, " .%-30s: %ld\n", "load^-1", cfs_rq->load.inv_weight);
#ifdef CONFIG_SCHEDSTATS
SEQ_printf(m, " .%-30s: %d\n", "bkl_count",
rq->bkl_count);
Index: linux-2.6/kernel/sched_fair.c
===================================================================
--- linux-2.6.orig/kernel/sched_fair.c
+++ linux-2.6/kernel/sched_fair.c
@@ -374,10 +374,8 @@ static u64 sched_slice(struct cfs_rq *cf
goto out;
for_each_sched_entity(se) {
- cfs_rq = cfs_rq_of(se);
-
- slice *= se->load.weight;
- do_div(slice, cfs_rq->load.weight);
+ slice = calc_delta_mine(slice,
+ se->load.weight, &cfs_rq_of(se)->load);
}
out:
--
next prev parent reply other threads:[~2008-02-18 10:00 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-02-18 9:55 [PATCH 0/7] Single RQ group scheduling Peter Zijlstra
2008-02-18 9:55 ` [PATCH 1/7] sched: cleanup old and rarely used debug features Peter Zijlstra
2008-02-18 9:55 ` [PATCH 2/7] sched: fair-group scheduling vs latency Peter Zijlstra
2008-02-18 9:55 ` [PATCH 3/7] sched: fair-group: de-couple load-balancing from the rb-trees Peter Zijlstra
2008-02-18 9:55 ` [PATCH 4/7] sched: fair-group: single RQ approach Peter Zijlstra
2008-02-18 9:55 ` [PATCH 5/7] sched: remove sysctl_sched_batch_wakeup_granularity Peter Zijlstra
2008-02-18 9:55 ` Peter Zijlstra [this message]
2008-02-18 9:55 ` [PATCH 7/7] sched: fair: vruntime spread Peter Zijlstra
2008-02-19 6:10 ` [PATCH 0/7] Single RQ group scheduling Mike Galbraith
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=20080218095625.579955000@chello.nl \
--to=a.p.zijlstra@chello.nl \
--cc=dhaval@linux.vnet.ibm.com \
--cc=efault@gmx.de \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=tong.n.li@intel.com \
--cc=vatsa@linux.vnet.ibm.com \
/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