From: Peter Zijlstra <a.p.zijlstra@chello.nl>
To: Ingo Molnar <mingo@elte.hu>
Cc: linux-kernel@vger.kernel.org, Gautham R Shenoy <ego@in.ibm.com>,
Andreas Herrmann <andreas.herrmann3@amd.com>,
Balbir Singh <balbir@in.ibm.com>,
Peter Zijlstra <a.p.zijlstra@chello.nl>
Subject: [RFC][PATCH 02/14] sched: SD_PREFER_SIBLING
Date: Thu, 03 Sep 2009 15:21:47 +0200 [thread overview]
Message-ID: <20090903132212.224601306@chello.nl> (raw)
In-Reply-To: 20090903132145.482814810@chello.nl
[-- Attachment #1: sched-lb-2.patch --]
[-- Type: text/plain, Size: 3932 bytes --]
Do the placement thing using SD flags
XXX: consider degenerate bits
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
include/linux/sched.h | 29 +++++++++++++++--------------
kernel/sched.c | 14 +++++++++++++-
2 files changed, 28 insertions(+), 15 deletions(-)
Index: linux-2.6/include/linux/sched.h
===================================================================
--- linux-2.6.orig/include/linux/sched.h
+++ linux-2.6/include/linux/sched.h
@@ -808,18 +808,19 @@ enum cpu_idle_type {
#define SCHED_LOAD_SCALE_FUZZ SCHED_LOAD_SCALE
#ifdef CONFIG_SMP
-#define SD_LOAD_BALANCE 1 /* Do load balancing on this domain. */
-#define SD_BALANCE_NEWIDLE 2 /* Balance when about to become idle */
-#define SD_BALANCE_EXEC 4 /* Balance on exec */
-#define SD_BALANCE_FORK 8 /* Balance on fork, clone */
-#define SD_WAKE_IDLE 16 /* Wake to idle CPU on task wakeup */
-#define SD_WAKE_AFFINE 32 /* Wake task to waking CPU */
-#define SD_WAKE_BALANCE 64 /* Perform balancing at task wakeup */
-#define SD_SHARE_CPUPOWER 128 /* Domain members share cpu power */
-#define SD_POWERSAVINGS_BALANCE 256 /* Balance for power savings */
-#define SD_SHARE_PKG_RESOURCES 512 /* Domain members share cpu pkg resources */
-#define SD_SERIALIZE 1024 /* Only a single load balancing instance */
-#define SD_WAKE_IDLE_FAR 2048 /* Gain latency sacrificing cache hit */
+#define SD_LOAD_BALANCE 0x0001 /* Do load balancing on this domain. */
+#define SD_BALANCE_NEWIDLE 0x0002 /* Balance when about to become idle */
+#define SD_BALANCE_EXEC 0x0004 /* Balance on exec */
+#define SD_BALANCE_FORK 0x0008 /* Balance on fork, clone */
+#define SD_WAKE_IDLE 0x0010 /* Wake to idle CPU on task wakeup */
+#define SD_WAKE_AFFINE 0x0020 /* Wake task to waking CPU */
+#define SD_WAKE_BALANCE 0x0040 /* Perform balancing at task wakeup */
+#define SD_SHARE_CPUPOWER 0x0080 /* Domain members share cpu power */
+#define SD_POWERSAVINGS_BALANCE 0x0100 /* Balance for power savings */
+#define SD_SHARE_PKG_RESOURCES 0x0200 /* Domain members share cpu pkg resources */
+#define SD_SERIALIZE 0x0400 /* Only a single load balancing instance */
+#define SD_WAKE_IDLE_FAR 0x0800 /* Gain latency sacrificing cache hit */
+#define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */
enum powersavings_balance_level {
POWERSAVINGS_BALANCE_NONE = 0, /* No power saving load balance */
@@ -839,7 +840,7 @@ static inline int sd_balance_for_mc_powe
if (sched_smt_power_savings)
return SD_POWERSAVINGS_BALANCE;
- return 0;
+ return SD_PREFER_SIBLING;
}
static inline int sd_balance_for_package_power(void)
@@ -847,7 +848,7 @@ static inline int sd_balance_for_package
if (sched_mc_power_savings | sched_smt_power_savings)
return SD_POWERSAVINGS_BALANCE;
- return 0;
+ return SD_PREFER_SIBLING;
}
/*
Index: linux-2.6/kernel/sched.c
===================================================================
--- linux-2.6.orig/kernel/sched.c
+++ linux-2.6/kernel/sched.c
@@ -3803,9 +3803,13 @@ static inline void update_sd_lb_stats(st
const struct cpumask *cpus, int *balance,
struct sd_lb_stats *sds)
{
+ struct sched_domain *child = sd->child;
struct sched_group *group = sd->groups;
struct sg_lb_stats sgs;
- int load_idx;
+ int load_idx, prefer_sibling = 0;
+
+ if (child && child->flags & SD_PREFER_SIBLING)
+ prefer_sibling = 1;
init_sd_power_savings_stats(sd, sds, idle);
load_idx = get_sd_load_idx(sd, idle);
@@ -3825,6 +3829,14 @@ static inline void update_sd_lb_stats(st
sds->total_load += sgs.group_load;
sds->total_pwr += group->__cpu_power;
+ /*
+ * In case the child domain prefers tasks go to siblings
+ * first, lower the group capacity to one so that we'll try
+ * and move all the excess tasks away.
+ */
+ if (prefer_sibling)
+ sgs.group_capacity = 1;
+
if (local_group) {
sds->this_load = sgs.avg_load;
sds->this = group;
--
next prev parent reply other threads:[~2009-09-03 13:23 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-09-03 13:21 [RFC][PATCH 00/14] load-balancing and cpu_power -v3 Peter Zijlstra
2009-09-03 13:21 ` [RFC][PATCH 01/14] sched: restore __cpu_power to a straight sum of power Peter Zijlstra
2009-09-03 13:21 ` Peter Zijlstra [this message]
2009-09-03 13:21 ` [RFC][PATCH 03/14] sched: update the cpu_power sum during load-balance Peter Zijlstra
2009-09-03 13:21 ` [RFC][PATCH 04/14] sched: add smt_gain Peter Zijlstra
2009-09-03 13:21 ` [RFC][PATCH 05/14] sched: dynamic cpu_power Peter Zijlstra
2009-09-03 13:21 ` [RFC][PATCH 06/14] sched: scale down cpu_power due to RT tasks Peter Zijlstra
2009-09-03 13:21 ` [RFC][PATCH 07/14] sched: try to deal with low capacity Peter Zijlstra
2009-09-03 13:21 ` [RFC][PATCH 08/14] sched: remove reciprocal for cpu_power Peter Zijlstra
2009-09-03 13:59 ` Peter Zijlstra
2009-09-03 13:21 ` [RFC][PATCH 09/14] x86: move APERF/MPERF into a X86_FEATURE Peter Zijlstra
2009-09-03 13:21 ` [RFC][PATCH 10/14] x86: generic aperf/mperf code Peter Zijlstra
2009-09-04 9:19 ` Thomas Renninger
2009-09-04 9:25 ` Peter Zijlstra
2009-09-04 9:27 ` Peter Zijlstra
2009-09-04 9:34 ` Thomas Renninger
2009-09-04 14:22 ` Dave Jones
2009-09-04 14:42 ` Peter Zijlstra
2009-09-04 17:45 ` H. Peter Anvin
2009-09-03 13:21 ` [RFC][PATCH 11/14] sched: provide arch_scale_freq_power Peter Zijlstra
2009-09-03 13:21 ` [RFC][PATCH 12/14] x86: sched: provide arch implementations using aperf/mperf Peter Zijlstra
2009-09-03 13:21 ` [RFC][PATCH 13/14] sched: cleanup wake_idle power saving Peter Zijlstra
2009-09-03 13:21 ` [RFC][PATCH 14/14] sched: cleanup wake_idle Peter Zijlstra
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=20090903132212.224601306@chello.nl \
--to=a.p.zijlstra@chello.nl \
--cc=andreas.herrmann3@amd.com \
--cc=balbir@in.ibm.com \
--cc=ego@in.ibm.com \
--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