From: Robert Olsson <Robert.Olsson@data.slu.se>
To: dipankar@in.ibm.com
Cc: Robert Olsson <Robert.Olsson@data.slu.se>,
Andrea Arcangeli <andrea@suse.de>,
"David S. Miller" <davem@redhat.com>,
kuznet@ms2.inr.ac.ru, linux-kernel@vger.kernel.org,
netdev@oss.sgi.com, paulmck@us.ibm.com, akpm@osdl.org
Subject: Re: route cache DoS testing and softirqs
Date: Tue, 6 Apr 2004 14:55:19 +0200 [thread overview]
Message-ID: <16498.43191.733850.18276@robur.slu.se> (raw)
In-Reply-To: <20040405212220.GH4003@in.ibm.com>
[-- Attachment #1: message body text --]
[-- Type: text/plain, Size: 961 bytes --]
Dipankar Sarma writes:
> Looks better atleast. Can you apply the following patch (rs-throttle-rcu)
> on top of rcu-softirq.patch in your tree and see if helps a little bit more ?
> Please make sure to set the kernel paramenters rcupdate.maxbatch to 4
> and rcupdate.plugticks to 0. You can make sure of those parameters
> by looking at dmesg (rcu prints them out during boot). I just merged
> it, but have not tested this patch yet.
OK!
Well not tested yet but I don't think we will get rid overflow totally in my
setup. I've done a little experimental patch so *all* softirq's are run via
ksoftirqd.
total droppped tsquz throttl bh_enbl ksoftird irqexit other
009bee0c 00000000 00004aa7 00000000 00000000 0336a637 00000078 00000000
0054d381 00000000 00004ca0 00000000 00000000 032f8e48 00000000 00000000
I still see dst overflows. But the priority of the ksoftird's can now control
the user apps behavior even during softirq DoS.
[-- Attachment #2: softirq_limit-040405.pat --]
[-- Type: application/octet-stream, Size: 1481 bytes --]
--- kernel/softirq.c.orig 2004-03-11 03:55:24.000000000 +0100
+++ kernel/softirq.c 2004-04-05 12:52:40.000000000 +0200
@@ -58,6 +58,14 @@
wake_up_process(tsk);
}
+static inline int can_run_ksoftirqd(void)
+{
+ /* Interrupts are disabled: no need to stop preemption */
+ struct task_struct *tsk = __get_cpu_var(ksoftirqd);
+
+ return tsk && !(tsk->state & (TASK_DEAD | TASK_ZOMBIE));
+}
+
/*
* We restart softirq processing MAX_SOFTIRQ_RESTART times,
* and we fall back to softirqd after that.
@@ -69,7 +77,7 @@
*/
#define MAX_SOFTIRQ_RESTART 10
-asmlinkage void do_softirq(void)
+asmlinkage void __do_softirq(int from_ksoftirqd)
{
int max_restart = MAX_SOFTIRQ_RESTART;
__u32 pending;
@@ -86,6 +94,9 @@
struct softirq_action *h;
local_bh_disable();
+
+ if (from_ksoftirqd && can_run_ksoftirqd())
+ goto done;
restart:
/* Reset the pending bitmask before enabling irqs */
local_softirq_pending() = 0;
@@ -106,6 +117,7 @@
pending = local_softirq_pending();
if (pending && --max_restart)
goto restart;
+done:
if (pending)
wakeup_softirqd();
__local_bh_enable();
@@ -114,6 +126,11 @@
local_irq_restore(flags);
}
+asmlinkage void do_softirq(void)
+{
+ __do_softirq(0);
+}
+
EXPORT_SYMBOL(do_softirq);
void local_bh_enable(void)
@@ -324,7 +341,7 @@
__set_current_state(TASK_RUNNING);
while (local_softirq_pending()) {
- do_softirq();
+ __do_softirq(1);
cond_resched();
}
[-- Attachment #3: message body text --]
[-- Type: text/plain, Size: 19 bytes --]
Cheers.
--ro
next prev parent reply other threads:[~2004-04-06 12:55 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2004-03-29 18:45 route cache DoS testing and softirqs Dipankar Sarma
2004-03-29 22:29 ` Andrea Arcangeli
2004-03-30 5:06 ` Srivatsa Vaddagiri
2004-03-30 5:35 ` Srivatsa Vaddagiri
2004-03-30 15:11 ` Andrea Arcangeli
2004-03-31 2:36 ` Rusty Russell
2004-03-30 14:43 ` Dipankar Sarma
2004-03-30 19:53 ` Dipankar Sarma
2004-03-30 20:47 ` Andrea Arcangeli
2004-03-30 21:06 ` Dipankar Sarma
2004-03-30 21:27 ` Andrea Arcangeli
2004-03-30 21:29 ` Robert Olsson
2004-03-31 7:36 ` Dipankar Sarma
2004-03-30 20:05 ` kuznet
2004-03-30 20:28 ` Dipankar Sarma
2004-04-01 6:00 ` kuznet
2004-03-30 21:14 ` Andrea Arcangeli
2004-03-30 21:30 ` David S. Miller
2004-03-30 21:37 ` Andrea Arcangeli
2004-03-30 22:22 ` David S. Miller
2004-03-30 22:49 ` Andrea Arcangeli
2004-03-31 20:46 ` Dipankar Sarma
2004-03-31 21:31 ` Andrea Arcangeli
2004-03-31 21:52 ` Dipankar Sarma
2004-03-30 22:33 ` Robert Olsson
2004-03-31 17:10 ` Dipankar Sarma
2004-03-31 18:46 ` Robert Olsson
2004-03-31 20:37 ` Dipankar Sarma
2004-03-31 21:28 ` Andrea Arcangeli
2004-03-31 21:43 ` Dipankar Sarma
2004-04-05 17:11 ` Robert Olsson
2004-04-05 21:22 ` Dipankar Sarma
2004-04-06 12:55 ` Robert Olsson [this message]
2004-04-06 19:52 ` Dipankar Sarma
2004-04-07 15:23 ` Robert Olsson
2004-04-07 19:48 ` Dipankar Sarma
2004-04-08 13:29 ` kuznet
2004-04-08 14:07 ` Robert Olsson
2004-03-31 22:36 ` Robert Olsson
2004-03-31 22:52 ` Andrea Arcangeli
2004-04-01 6:43 ` kuznet
2004-04-01 13:16 ` Andrea Arcangeli
2004-04-08 13:38 ` kuznet
2004-04-01 13:44 ` Robert Olsson
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=16498.43191.733850.18276@robur.slu.se \
--to=robert.olsson@data.slu.se \
--cc=akpm@osdl.org \
--cc=andrea@suse.de \
--cc=davem@redhat.com \
--cc=dipankar@in.ibm.com \
--cc=kuznet@ms2.inr.ac.ru \
--cc=linux-kernel@vger.kernel.org \
--cc=netdev@oss.sgi.com \
--cc=paulmck@us.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;
as well as URLs for NNTP newsgroup(s).