public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: "Stephan Bärwolf" <stephan.baerwolf@tu-ilmenau.de>
To: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Nikhil Rao <ncrao@google.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Mike Galbraith <efault@gmx.de>,
	"Nikunj A. Dadhania" <nikunj@linux.vnet.ibm.com>,
	Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>,
	linux-kernel@vger.kernel.org
Subject: [PATCH] sched: fix/optimise calculation of weight-inverse
Date: Wed, 11 May 2011 18:03:29 +0200	[thread overview]
Message-ID: <4DCAB351.4010204@tu-ilmenau.de> (raw)

[-- Attachment #1: Type: text/plain, Size: 2077 bytes --]

If the inverse loadweight should be zero, function "calc_delta_mine"
calculates the inverse of "lw->weight" (in 32bit integer ops).

This calculation is actually a little bit impure (because it is
inverting something around "lw-weight"+1), especially when
"lw->weight" becomes smaller. (This could explain some aritmetical
issues for small shares...)

The correct inverse would be 1/lw->weight multiplied by
"WMULT_CONST" for fixcomma-scaling it into integers.
(So WMULT_CONST/lw->weight ...)

For safety it is also important to check if division by zero
could happen...

The old, impure algorithm took two divisions for inverting lw->weight,
the new, more exact one only takes one and an additional unlikely-if.

Signed-off-by: Stephan Baerwolf <stephan.baerwolf@tu-ilmenau.de>
---
 kernel/sched.c |   12 +++++++++---
 1 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/kernel/sched.c b/kernel/sched.c
index 312f8b9..bb55996 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1307,15 +1307,21 @@ calc_delta_mine(unsigned long delta_exec,
unsigned long weight,
 {
     u64 tmp;
 
+    tmp = (u64)delta_exec * weight;
+
+    // actually we would have to trap - division by zero - but we stay
and pretend the limit of the operation...
+    if (unlikely(lw->weight == 0)) {
+        if (unlikely(tmp == ((u64)0))) return (unsigned long)0;
+        else return (unsigned long)LONG_MAX;
+    }
+
     if (!lw->inv_weight) {
         if (BITS_PER_LONG > 32 && unlikely(lw->weight >= WMULT_CONST))
             lw->inv_weight = 1;
         else
-            lw->inv_weight = 1 + (WMULT_CONST-lw->weight/2)
-                / (lw->weight+1);
+            lw->inv_weight = WMULT_CONST / lw->weight;
     }
 
-    tmp = (u64)delta_exec * weight;
     /*
      * Check whether we'd overflow the 64-bit multiplication:
      */
-- 
1.7.3.4



--
Dipl.-Inf. Stephan Bärwolf
Ilmenau University of Technology, Integrated Communication Systems Group
Phone: +49 (0)3677 69 2821,  FAX: +49 (0)3677 69 1614
Email: stephan.baerwolf@tu-ilmenau.de,
Web: http://www.tu-ilmenau.de/iks



[-- Attachment #2: 0001-sched-fix-optimise-calculation-of-weight-inverse.patch --]
[-- Type: text/plain, Size: 1981 bytes --]

>From 46d3b89632aee75643b2ef9ea9ccd3085c631211 Mon Sep 17 00:00:00 2001
From: Stephan Baerwolf <stephan.baerwolf@tu-ilmenau.de>
Date: Wed, 11 May 2011 17:36:26 +0200
Subject: [PATCH] sched: fix/optimise calculation of weight-inverse

If the inverse loadweight should be zero, function "calc_delta_mine"
calculates the inverse of "lw->weight" (in 32bit integer ops).

This calculation is actually a little bit impure (because it is
inverting something around "lw-weight"+1), especially when
"lw->weight" becomes smaller. (This could explain some aritmetical
issues for small shares...)

The correct inverse would be 1/lw->weight multiplied by
"WMULT_CONST" for fixcomma-scaling it into integers.
(So WMULT_CONST/lw->weight ...)

For safety it is also important to check if division by zero
could happen...

The old, impure algorithm took two divisions for inverting lw->weight,
the new, more exact one only takes one and an additional unlikely-if.

Signed-off-by: Stephan Baerwolf <stephan.baerwolf@tu-ilmenau.de>
---
 kernel/sched.c |   12 +++++++++---
 1 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/kernel/sched.c b/kernel/sched.c
index 312f8b9..bb55996 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1307,15 +1307,21 @@ calc_delta_mine(unsigned long delta_exec, unsigned long weight,
 {
 	u64 tmp;
 
+	tmp = (u64)delta_exec * weight;
+
+	// actually we would have to trap - division by zero - but we stay and pretend the limit of the operation...
+	if (unlikely(lw->weight == 0)) {
+		if (unlikely(tmp == ((u64)0))) return (unsigned long)0;
+		else return (unsigned long)LONG_MAX;
+	}
+
 	if (!lw->inv_weight) {
 		if (BITS_PER_LONG > 32 && unlikely(lw->weight >= WMULT_CONST))
 			lw->inv_weight = 1;
 		else
-			lw->inv_weight = 1 + (WMULT_CONST-lw->weight/2)
-				/ (lw->weight+1);
+			lw->inv_weight = WMULT_CONST / lw->weight;
 	}
 
-	tmp = (u64)delta_exec * weight;
 	/*
 	 * Check whether we'd overflow the 64-bit multiplication:
 	 */
-- 
1.7.3.4


             reply	other threads:[~2011-05-11 16:09 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-05-11 16:03 Stephan Bärwolf [this message]
2011-05-11 16:20 ` [PATCH] sched: fix/optimise calculation of weight-inverse Ingo Molnar
2011-05-11 16:43   ` Peter Zijlstra
2011-05-11 17:35     ` Stephan Bärwolf
2011-05-11 19:49       ` 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=4DCAB351.4010204@tu-ilmenau.de \
    --to=stephan.baerwolf@tu-ilmenau.de \
    --cc=efault@gmx.de \
    --cc=linux-kernel@vger.kernel.org \
    --cc=ncrao@google.com \
    --cc=nikunj@linux.vnet.ibm.com \
    --cc=peterz@infradead.org \
    --cc=torvalds@linux-foundation.org \
    --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