netdev - Re: 2.6.24 BUG: soft lockup

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <1206706759.4429.58.camel@localhost>
Date:	Fri, 28 Mar 2008 08:19:19 -0400
From:	jamal <hadi@...erus.ca>
To:	Herbert Xu <herbert@...dor.apana.org.au>
Cc:	"David S. Miller" <davem@...emloft.net>,
	Ingo Molnar <mingo@...e.hu>, Matheos.Worku@....COM,
	jesse.brandeburg@...el.com, jarkao2@...il.com,
	netdev@...r.kernel.org
Subject: Re: 2.6.24 BUG: soft lockup - CPU#X

On Fri, 2008-28-03 at 19:29 +0800, Herbert Xu wrote:

> OK, since we don't really have any good ways of balancing softirq
> events with each other, I've taken Dave's suggestion of checking
> the jiffies as is done with NAPI.  I've kept the need_resched to
> minimise the scheduling latency.

i think the need_resched would be effective.

**** heres something that has not yet resolved in my mind (even for the
NAPI case which was inherited from code that has been there forever).
Theres probably a very simple answer ;->
say we have two machines:
one faster and we decide HZ = 1000 meaning 1ms for a jiffy; the other
slower and we make HZ 100 i.e 10ms jiffy.
Logically, shouldnt the slower machine allocate less time running the
loop since it has less resources? in the above case it would spend 10
times more. 

cheers,
jamal

--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html