From: Ravikiran G Thirumalai <kiran@scalex86.org>
To: linux-kernel@vger.kernel.org
Cc: Ingo Molnar <mingo@elte.hu>, shai@scalex86.org
Subject: [rfc] [patch 2/2 ] Sysctl to turn on/off private futex hash tables for private futexes
Date: Fri, 20 Mar 2009 21:52:51 -0700 [thread overview]
Message-ID: <20090321045251.GB7278@localdomain> (raw)
In-Reply-To: <20090321044637.GA7278@localdomain>
The following patch introduces a sysctl to control whether process private
hashtable will be used for process private futexes.
Signed-off-by: Ravikiran Thirumalai <kiran@scalex86.org>
Signed-off-by: Shai Fultheim <shai@scalex86.org>
Index: linux-2.6.28.6/include/linux/futex.h
===================================================================
--- linux-2.6.28.6.orig/include/linux/futex.h 2009-03-18 16:59:27.000000000 -0800
+++ linux-2.6.28.6/include/linux/futex.h 2009-03-18 17:49:02.000000000 -0800
@@ -179,6 +179,7 @@ static inline void exit_pi_state_list(st
#ifdef CONFIG_PROCESS_PRIVATE_FUTEX
extern void free_futex_htb(struct mm_struct *mm);
+extern int sysctl_private_hash;
#else
static inline void free_futex_htb(struct mm_struct *mm)
{
Index: linux-2.6.28.6/kernel/futex.c
===================================================================
--- linux-2.6.28.6.orig/kernel/futex.c 2009-03-18 17:36:04.000000000 -0800
+++ linux-2.6.28.6/kernel/futex.c 2009-03-18 17:57:13.000000000 -0800
@@ -154,14 +154,16 @@ void free_futex_htb(struct mm_struct *mm
static void alloc_htb(struct mm_struct *mm)
{
- struct futex_hash_bucket *htb;
int i;
+ struct futex_hash_bucket *htb = NULL;
/*
* Allocate and install a private hash table of the
* same size as the global hash table. We fall
- * back onto the global hash on allocation failure
+ * back onto the global hash on allocation failure, or
+ * if private futexes are disabled.
*/
- htb = kmalloc(sizeof(futex_queues), GFP_KERNEL);
+ if (sysctl_private_hash)
+ htb = kmalloc(sizeof(futex_queues), GFP_KERNEL);
if (!htb)
htb = futex_queues;
else {
@@ -183,6 +185,8 @@ static void alloc_htb(struct mm_struct *
}
+int sysctl_private_hash;
+
static struct futex_hash_bucket *get_futex_hashtable(union futex_key *key)
{
struct mm_struct *mm;
Index: linux-2.6.28.6/kernel/sysctl.c
===================================================================
--- linux-2.6.28.6.orig/kernel/sysctl.c 2009-03-18 16:59:27.000000000 -0800
+++ linux-2.6.28.6/kernel/sysctl.c 2009-03-18 17:49:02.000000000 -0800
@@ -48,6 +48,7 @@
#include <linux/acpi.h>
#include <linux/reboot.h>
#include <linux/ftrace.h>
+#include <linux/futex.h>
#include <asm/uaccess.h>
#include <asm/processor.h>
@@ -799,6 +800,19 @@ static struct ctl_table kern_table[] = {
.strategy = &sysctl_intvec,
},
#endif
+#ifdef CONFIG_PROCESS_PRIVATE_FUTEX
+ {
+ .ctl_name = CTL_UNNUMBERED,
+ .procname = "private_futex_hashtable",
+ .data = &sysctl_private_hash,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec_minmax,
+ .strategy = &sysctl_intvec,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
+#endif
#ifdef CONFIG_COMPAT
{
.ctl_name = KERN_COMPAT_LOG,
Index: linux-2.6.28.6/Documentation/sysctl/kernel.txt
===================================================================
--- linux-2.6.28.6.orig/Documentation/sysctl/kernel.txt 2009-02-17 09:29:27.000000000 -0800
+++ linux-2.6.28.6/Documentation/sysctl/kernel.txt 2009-03-20 12:14:15.000000000 -0800
@@ -281,6 +281,25 @@ send before ratelimiting kicks in.
==============================================================
+private_futex_hashtable:
+
+This sysctl can be used to enable processes to use a per-process
+private hash table for private futexes. Private futexes
+are typically used in threaded workloads. When this option is
+off, which is the default, threads waiting on futexes get
+hashed onto a global hash table. On large core count machines
+this turns out to be bad for performance if the workload
+consist of multiple unrelated threaded processes. Turning
+this option on will enable processes to use a private hash
+for private futexes, improving performance.
+
+Valid options are 0 and 1. A value of 0 turns off process private
+futex hash tables and a value of 1 enables private futex hash
+tables. This option will only affect processes that get created
+after the option gets changed.
+
+==============================================================
+
randomize-va-space:
This option can be used to select the type of process address
next prev parent reply other threads:[~2009-03-21 4:53 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-03-21 4:46 [rfc] [patch 1/2 ] Process private hash tables for private futexes Ravikiran G Thirumalai
2009-03-21 4:52 ` Ravikiran G Thirumalai [this message]
2009-03-21 9:07 ` Eric Dumazet
2009-03-21 11:55 ` [PATCH] futex: Dynamically size futexes hash table Eric Dumazet
2009-03-21 16:28 ` Ingo Molnar
2009-03-22 4:54 ` [rfc] [patch 1/2 ] Process private hash tables for private futexes Ravikiran G Thirumalai
2009-03-22 8:17 ` Eric Dumazet
2009-03-23 20:28 ` Ravikiran G Thirumalai
2009-03-23 21:57 ` Eric Dumazet
2009-03-24 3:19 ` Ravikiran G Thirumalai
2009-03-24 3:33 ` Ravikiran G Thirumalai
2009-03-24 5:31 ` Eric Dumazet
2009-03-24 7:04 ` Eric Dumazet
2009-04-23 17:30 ` Darren Hart
2009-03-21 11:35 ` Andrew Morton
2009-03-22 4:15 ` Ravikiran G Thirumalai
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=20090321045251.GB7278@localdomain \
--to=kiran@scalex86.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=shai@scalex86.org \
/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).