All of lore.kernel.org
 help / color / mirror / Atom feed
From: Shailabh Nagar <nagar@watson.ibm.com>
To: linux-kernel <linux-kernel@vger.kernel.org>
Subject: [Patch 6/8] virtual cpu run time
Date: Wed, 29 Mar 2006 19:54:53 -0500	[thread overview]
Message-ID: <442B2C5D.2020300@watson.ibm.com> (raw)
In-Reply-To: <442B271D.10208@watson.ibm.com>

delayacct-virtcpu.patch

Distinguish between "wall-clock" and "virtual" cpu run times and return
both, at per-task and per-tgid granularity.

Some architectures adjust tsk->utime+tsk->stime to reflect the time that
the kernel wasn't scheduled in hypervised environments and this is the
"wall-clock" cpu run time. "Virtual" cpu run time, on the other hand, does
not account for the kernel being descheduled.

This patch allows the most accurate "virtual" cpu run time, collected by
the schedstats code (now shared with delay accounting code), to be returned
to user space, in addition to the "wall-clock" cpu time that was being exported
earlier. Both these times are useful for workload management in different
situations.

In a non-virtualized environment, or on architectures which do not adjust
tsk->utime/stime, these will effectively be the same value but at different
granularities.


Signed-off-by: Shailabh Nagar <nagar@us.ibm.com>
Signed-off-by: Balbir Singh <balbir@in.ibm.com>

 include/linux/taskstats.h |   10 ++++++++--
 kernel/delayacct.c        |   12 +++++++++---
 2 files changed, 17 insertions(+), 5 deletions(-)

Index: linux-2.6.16/include/linux/taskstats.h
===================================================================
--- linux-2.6.16.orig/include/linux/taskstats.h	2006-03-29 18:13:18.000000000 -0500
+++ linux-2.6.16/include/linux/taskstats.h	2006-03-29 18:13:20.000000000 -0500
@@ -46,8 +46,14 @@ struct taskstats {
 	__u64	swapin_count;
 	__u64	swapin_delay_total;	/* swapin page fault wait*/

-	__u64	cpu_run_total;		/* cpu running time
-					 * no count available/provided */
+	__u64	cpu_run_real_total;	/* cpu "wall-clock" running time
+					 * Potentially accounts for cpu
+					 * virtualization, on some arches
+					 */
+	__u64	cpu_run_virtual_total;	/* cpu "virtual" running time
+					 * Uses time intervals as seen by
+					 * the kernel
+					 */
 };


Index: linux-2.6.16/kernel/delayacct.c
===================================================================
--- linux-2.6.16.orig/kernel/delayacct.c	2006-03-29 18:13:18.000000000 -0500
+++ linux-2.6.16/kernel/delayacct.c	2006-03-29 18:13:20.000000000 -0500
@@ -123,17 +123,18 @@ int __delayacct_add_tsk(struct taskstats
 {
 	nsec_t tmp;
 	struct timespec ts;
-	unsigned long t1,t2;
+	unsigned long t1,t2,t3;

 	/* zero XXX_total,non-zero XXX_count implies XXX stat overflowed */

-	tmp = (nsec_t)d->cpu_run_total ;
+	tmp = (nsec_t)d->cpu_run_real_total ;
 	tmp += (u64)(tsk->utime+tsk->stime)*TICK_NSEC;
-	d->cpu_run_total = (tmp < (nsec_t)d->cpu_run_total)? 0: tmp;
+	d->cpu_run_real_total = (tmp < (nsec_t)d->cpu_run_real_total)? 0: tmp;

 	/* No locking available for sched_info. Take snapshot first. */
 	t1 = tsk->sched_info.pcnt;
 	t2 = tsk->sched_info.run_delay;
+	t3 = tsk->sched_info.cpu_time;

 	d->cpu_count += t1;

@@ -141,6 +142,11 @@ int __delayacct_add_tsk(struct taskstats
 	tmp = (nsec_t)d->cpu_delay_total + timespec_to_ns(&ts);
 	d->cpu_delay_total = (tmp < (nsec_t)d->cpu_delay_total)? 0: tmp;

+	tmp = (nsec_t)d->cpu_run_virtual_total
+		+ (nsec_t)jiffies_to_usecs(t3) * 1000;
+	d->cpu_run_virtual_total = (tmp < (nsec_t)d->cpu_run_virtual_total) ?
+					0 : tmp;
+
 	spin_lock(&tsk->delays->lock);
 	tmp = d->blkio_delay_total + tsk->delays->blkio_delay;
 	d->blkio_delay_total = (tmp < d->blkio_delay_total)? 0: tmp;

  parent reply	other threads:[~2006-03-30  0:55 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-03-30  0:32 [Patch 0/8] per-task delay accounting Shailabh Nagar
2006-03-30  0:35 ` [Patch 1/8] Setup Shailabh Nagar
2006-03-30  5:03   ` Andrew Morton
2006-03-30 15:07     ` Shailabh Nagar
2006-03-30  0:37 ` [Patch 2/8] Block I/O, swapin delays Shailabh Nagar
2006-03-30  5:03   ` Andrew Morton
2006-03-30 15:21     ` Shailabh Nagar
2006-03-30  0:42 ` [Patch 3/8] cpu delays Shailabh Nagar
2006-03-30  5:03   ` Andrew Morton
2006-03-30 16:01     ` Shailabh Nagar
2006-03-30 16:00   ` Dave Hansen
2006-03-30 16:03     ` Shailabh Nagar
2006-03-30  0:48 ` [Patch 4/8] generic netlink utility functions Shailabh Nagar
2006-03-30  0:52 ` [Patch 5/8] generic netlink interface for delay accounting Shailabh Nagar
2006-03-30  5:04   ` Andrew Morton
2006-03-30  6:10     ` Balbir Singh
2006-03-30  6:26       ` Andrew Morton
2006-03-30  6:29         ` Balbir Singh
2006-03-30 16:24       ` Shailabh Nagar
2006-03-30  0:54 ` Shailabh Nagar [this message]
2006-03-30  5:04   ` [Patch 6/8] virtual cpu run time Andrew Morton
2006-03-30 16:10     ` Shailabh Nagar
2006-03-30  0:56 ` [Patch 7/8] proc interface for block I/O delays Shailabh Nagar
2006-03-30  5:04   ` Andrew Morton
2006-03-30  0:59 ` [Patch 8/8] documentation, userspace utility Shailabh Nagar
2006-03-30  5:03 ` [Patch 0/8] per-task delay accounting Andrew Morton
2006-03-30  6:23   ` Balbir Singh
2006-03-30  6:47     ` Andrew Morton
2006-03-30  9:55       ` Paul Jackson
2006-03-30 13:23       ` [Lse-tech] " Dipankar Sarma
2006-03-30 17:23       ` Shailabh Nagar
2006-03-31  2:54         ` Peter Chubb
2006-03-31  5:27           ` Shailabh Nagar
2006-03-31  8:17             ` Peter Chubb
2006-03-31 16:03               ` Shailabh Nagar
     [not found]       ` <442CCF54.3000501@watson.ibm.com>
2006-03-31  7:31         ` Guillaume Thouvenin
2006-03-31 17:01           ` Shailabh Nagar
     [not found]         ` <442D8E39.8080606@engr.sgi.com>
     [not found]           ` <442DED81.5060009@engr.sgi.com>
2006-04-10 17:15             ` Jay Lan
2006-04-10 21:44               ` Shailabh Nagar
2006-04-10 22:33                 ` [Lse-tech] " Jay Lan

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=442B2C5D.2020300@watson.ibm.com \
    --to=nagar@watson.ibm.com \
    --cc=linux-kernel@vger.kernel.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 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.