All of lore.kernel.org
 help / color / mirror / Atom feed
From: Paul Turner <pjt@google.com>
To: linux-kernel@vger.kernel.org
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>,
	Ingo Molnar <mingo@elte.hu>,
	Srivatsa Vaddagiri <vatsa@in.ibm.com>,
	Chris Friesen <cfriesen@nortel.com>,
	Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>,
	Pierre Bourdon <pbourdon@excellency.fr>,
	Paul Turner <pjt@google.com>,
	Bharata B Rao <bharata@linux.vnet.ibm.com>,
	Karl Rister <kmr@us.ibm.com>,
	Balbir Singh <balbir@linux.vnet.ibm.com>,
	David Miller <davem@davemloft.net>
Subject: [tg_shares_up rewrite v3 07/11] sched: add sysctl_sched_shares_window
Date: Thu, 11 Nov 2010 19:24:12 -0800	[thread overview]
Message-ID: <20101112032701.869302582@google.com> (raw)
In-Reply-To: 20101112032405.657789056@google.com

[-- Attachment #1: sched-tg-add-shares_window_sysctl.patch --]
[-- Type: text/plain, Size: 2326 bytes --]

Introduce a new sysctl for the shares window and disambiguate it from
sched_time_avg.

A 10ms window appears to be a good compromise between accuracy and performance.

Signed-off-by: Paul Turner <pjt@google.com>

---
 include/linux/sched.h |    1 +
 kernel/sched_fair.c   |    9 ++++++++-
 kernel/sysctl.c       |    7 +++++++
 3 files changed, 16 insertions(+), 1 deletion(-)

Index: kernel/sched_fair.c
===================================================================
--- kernel/sched_fair.c.orig
+++ kernel/sched_fair.c
@@ -89,6 +89,13 @@ unsigned int normalized_sysctl_sched_wak
 
 const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
 
+/*
+ * The exponential sliding  window over which load is averaged for shares
+ * distribution.
+ * (default: 10msec)
+ */
+unsigned int __read_mostly sysctl_sched_shares_window = 10000000UL;
+
 static const struct sched_class fair_sched_class;
 
 /**************************************************************
@@ -688,7 +695,7 @@ account_entity_dequeue(struct cfs_rq *cf
 #if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED
 static void update_cfs_load(struct cfs_rq *cfs_rq)
 {
-	u64 period = sched_avg_period();
+	u64 period = sysctl_sched_shares_window;
 	u64 now, delta;
 	unsigned long load = cfs_rq->load.weight;
 
Index: include/linux/sched.h
===================================================================
--- include/linux/sched.h.orig
+++ include/linux/sched.h
@@ -1883,6 +1883,7 @@ extern unsigned int sysctl_sched_migrati
 extern unsigned int sysctl_sched_nr_migrate;
 extern unsigned int sysctl_sched_time_avg;
 extern unsigned int sysctl_timer_migration;
+extern unsigned int sysctl_sched_shares_window;
 
 int sched_proc_update_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *length,
Index: kernel/sysctl.c
===================================================================
--- kernel/sysctl.c.orig
+++ kernel/sysctl.c
@@ -337,6 +337,13 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 	{
+		.procname	= "sched_shares_window",
+		.data		= &sysctl_sched_shares_window,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
 		.procname	= "timer_migration",
 		.data		= &sysctl_timer_migration,
 		.maxlen		= sizeof(unsigned int),

-- 


  parent reply	other threads:[~2010-11-12  3:32 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-11-12  3:24 [tg_shares_up rewrite v3 00/11] reduce overhead for tg->shares distribution Paul Turner
2010-11-12  3:24 ` [tg_shares_up rewrite v3 01/11] sched: rewrite tg_shares_up Paul Turner
2010-11-12 11:10   ` Peter Zijlstra
2010-11-12  3:24 ` [tg_shares_up rewrite v3 02/11] sched: on-demand (active) cfs_rq list Paul Turner
2010-11-12  3:24 ` [tg_shares_up rewrite v3 03/11] sched: make tg_shares_up() walk on-demand Paul Turner
2010-11-12  3:24 ` [tg_shares_up rewrite v3 04/11] sched: fix load corruption from update_cfs_shares Paul Turner
2010-11-12  3:24 ` [tg_shares_up rewrite v3 05/11] sched: fix update_cfs_load synchronization Paul Turner
2010-11-12  3:24 ` [tg_shares_up rewrite v3 06/11] sched: hierarchal order on shares update list Paul Turner
2010-11-12  3:24 ` Paul Turner [this message]
2010-11-12  3:24 ` [tg_shares_up rewrite v3 08/11] sched: update shares on idle_balance Paul Turner
2010-11-12  3:24 ` [tg_shares_up rewrite v3 09/11] sched: demand based update_cfs_load() Paul Turner
2010-11-12 10:53   ` Peter Zijlstra
2010-11-12 12:12     ` Peter Zijlstra
2010-11-13  1:01     ` Paul Turner
2010-11-13  2:42       ` Paul Turner
2010-11-13 22:45         ` Peter Zijlstra
2010-11-12  3:24 ` [tg_shares_up rewrite v3 10/11] sched: allow update_cfs_load to update global load Paul Turner
2010-11-12  3:24 ` [tg_shares_up rewrite v3 11/11] sched: update tg->shares after cpu.shares write Paul Turner

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=20101112032701.869302582@google.com \
    --to=pjt@google.com \
    --cc=a.p.zijlstra@chello.nl \
    --cc=balbir@linux.vnet.ibm.com \
    --cc=bharata@linux.vnet.ibm.com \
    --cc=cfriesen@nortel.com \
    --cc=davem@davemloft.net \
    --cc=kmr@us.ibm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=pbourdon@excellency.fr \
    --cc=svaidy@linux.vnet.ibm.com \
    --cc=vatsa@in.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.