linux-kernel - RE: Mainline kernel OLTP performance update

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: <1232392055.25783.9.camel@localhost.localdomain>
Date:	Mon, 19 Jan 2009 14:07:35 -0500
From:	Steven Rostedt <srostedt@...hat.com>
To:	Chris Mason <chris.mason@...cle.com>
Cc:	"Ma, Chinang" <chinang.ma@...el.com>,
	Andrew Morton <akpm@...ux-foundation.org>,
	Matthew Wilcox <matthew@....cx>,
	"Wilcox, Matthew R" <matthew.r.wilcox@...el.com>,
	"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
	"Tripathi, Sharad C" <sharad.c.tripathi@...el.com>,
	"arjan@...ux.intel.com" <arjan@...ux.intel.com>,
	"Kleen, Andi" <andi.kleen@...el.com>,
	"Siddha, Suresh B" <suresh.b.siddha@...el.com>,
	"Chilukuri, Harita" <harita.chilukuri@...el.com>,
	"Styner, Douglas W" <douglas.w.styner@...el.com>,
	"Wang, Peter Xihong" <peter.xihong.wang@...el.com>,
	"Nueckel, Hubert" <hubert.nueckel@...el.com>,
	"linux-scsi@...r.kernel.org" <linux-scsi@...r.kernel.org>,
	Andrew Vasquez <andrew.vasquez@...gic.com>,
	Anirban Chakraborty <anirban.chakraborty@...gic.com>,
	Ingo Molnar <mingo@...hat.com>,
	Thomas Gleixner <tglx@...utronix.de>,
	Peter Zijlstra <peterz@...radead.org>,
	Gregory Haskins <ghaskins@...ell.com>,
	Rusty Russell <rusty@...tcorp.com.au>
Subject: RE: Mainline kernel OLTP performance update


On Mon, 2009-01-19 at 13:55 -0500, Chris Mason wrote:

> I wasn't actually looking at the cost of the checks, even though they do
> look higher (if they are using CONFIG_CPUMASK_OFFSTACK anyway).
> 
> The 2.6.24 code would trigger a rescheduling interrupt only when the
> prio of the inbound task was higher than the running task.
> 
> This workload has a large number of equal priority rt tasks that are not
> bound to a single CPU, and so I think it should trigger more
> preempts/reschedules with the today's check_preempt_equal_prio().

Ah yeah. This is one of the things that shows RT being more "responsive"
but less on performance. An RT task wants to run ASAP even if that means
there's a chance of more interrupts and higher cache misses.

The old way would be much faster in general through put, but I measured
RT tasks taking up to tens of milliseconds to get scheduled. This is
unacceptable for an RT task.

-- Steve


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/