From: Andrew Morton <akpm@osdl.org>
To: Brad Laue <brad@brad-x.com>
Cc: linux-kernel@vger.kernel.org
Subject: Re: ksoftirqd using mysteriously high amounts of CPU time
Date: Thu, 11 Mar 2004 02:08:32 -0800 [thread overview]
Message-ID: <20040311020832.1aa25177.akpm@osdl.org> (raw)
In-Reply-To: <40503120.9000008@brad-x.com>
Brad Laue <brad@brad-x.com> wrote:
>
> Brad Laue wrote:
> > Hopefully the attached shows some irregularity. If not, I'll have to
> > reply back in a few weeks when the problem recurs over the course of time.
>
> And without further ado, the attachment. It's been a long day. :)
It beats me. Something must be waking up ksoftirqd all the time.
If you have time, could you please apply the below, then wait for ksoftirqd
to go bad again and then run:
dmesg -c
echo 1 > /proc/sys/debug/0 ; sleep 1; echo 0 > /proc/sys/debug/0
dmesg -s 1000000 > /tmp/foo
and then send foo?
diff -puN include/linux/kernel.h~proc-sys-debug include/linux/kernel.h
--- 25/include/linux/kernel.h~proc-sys-debug 2004-02-25 23:12:56.000000000 -0800
+++ 25-akpm/include/linux/kernel.h 2004-02-25 23:12:57.000000000 -0800
@@ -214,6 +214,8 @@ extern void dump_stack(void);
1; \
})
+extern int proc_sys_debug[8];
+
#endif /* __KERNEL__ */
#define SI_LOAD_SHIFT 16
diff -puN -L kernel/ksyms.c /dev/null /dev/null
diff -puN kernel/sysctl.c~proc-sys-debug kernel/sysctl.c
--- 25/kernel/sysctl.c~proc-sys-debug 2004-02-25 23:12:56.000000000 -0800
+++ 25-akpm/kernel/sysctl.c 2004-02-25 23:21:37.000000000 -0800
@@ -849,7 +849,26 @@ static ctl_table fs_table[] = {
{ .ctl_name = 0 }
};
+int proc_sys_debug[8];
+EXPORT_SYMBOL(proc_sys_debug);
+
static ctl_table debug_table[] = {
+ {1, "0", &proc_sys_debug[0], sizeof(int), 0644, NULL,
+ &proc_dointvec_minmax, &sysctl_intvec, NULL, NULL, NULL},
+ {2, "1", &proc_sys_debug[1], sizeof(int), 0644, NULL,
+ &proc_dointvec_minmax, &sysctl_intvec, NULL, NULL, NULL},
+ {3, "2", &proc_sys_debug[2], sizeof(int), 0644, NULL,
+ &proc_dointvec_minmax, &sysctl_intvec, NULL, NULL, NULL},
+ {4, "3", &proc_sys_debug[3], sizeof(int), 0644, NULL,
+ &proc_dointvec_minmax, &sysctl_intvec, NULL, NULL, NULL},
+ {5, "4", &proc_sys_debug[4], sizeof(int), 0644, NULL,
+ &proc_dointvec_minmax, &sysctl_intvec, NULL, NULL, NULL},
+ {6, "5", &proc_sys_debug[5], sizeof(int), 0644, NULL,
+ &proc_dointvec_minmax, &sysctl_intvec, NULL, NULL, NULL},
+ {7, "6", &proc_sys_debug[6], sizeof(int), 0644, NULL,
+ &proc_dointvec_minmax, &sysctl_intvec, NULL, NULL, NULL},
+ {8, "7", &proc_sys_debug[7], sizeof(int), 0644, NULL,
+ &proc_dointvec_minmax, &sysctl_intvec, NULL, NULL, NULL},
{ .ctl_name = 0 }
};
_
kernel/softirq.c | 7 ++++++-
1 files changed, 6 insertions(+), 1 deletion(-)
diff -puN kernel/softirq.c~a kernel/softirq.c
--- 25/kernel/softirq.c~a 2004-03-11 02:05:20.000000000 -0800
+++ 25-akpm/kernel/softirq.c 2004-03-11 02:06:02.000000000 -0800
@@ -54,8 +54,13 @@ static inline void wakeup_softirqd(void)
/* Interrupts are disabled: no need to stop preemption */
struct task_struct *tsk = __get_cpu_var(ksoftirqd);
- if (tsk && tsk->state != TASK_RUNNING)
+ if (tsk && tsk->state != TASK_RUNNING) {
+ if (proc_sys_debug[0]) {
+ printk("%s wakes ksoftirqd\n", current->comm);
+ dump_stack();
+ }
wake_up_process(tsk);
+ }
}
/*
_
next prev parent reply other threads:[~2004-03-11 10:08 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2004-03-10 21:16 Brad Laue
2004-03-10 23:57 ` Andrew Morton
2004-03-11 8:45 ` Brad Laue
2004-03-11 9:28 ` Brad Laue
2004-03-11 10:08 ` Andrew Morton [this message]
2004-03-11 14:05 ` Yury V. Umanets
2004-03-11 17:22 ` Brad Laue
2004-03-11 18:09 ` Yury V. Umanets
2004-03-11 18:21 ` Brad Laue
2004-03-11 18:24 ` Brad Laue
2004-03-12 17:51 ` Brad Laue
2004-03-11 14:00 ` Yury V. Umanets
[not found] <Pine.LNX.4.21.0403111916570.3466-100000@linux08.ece.utexas.edu>
2004-03-12 7:06 ` Brad Laue
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=20040311020832.1aa25177.akpm@osdl.org \
--to=akpm@osdl.org \
--cc=brad@brad-x.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®