Re: [PATCH] sched: high-res preemption tick

Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

To: Mike Galbraith <efault@...>

Cc: linux-kernel <linux-kernel@...>, Ingo Molnar <mingo@...>, Thomas Gleixner <tglx@...>

Subject: Re: [PATCH] sched: high-res preemption tick

Date: Saturday, October 13, 2007 - 4:55 am

On Sat, 2007-10-13 at 09:18 +0200, Mike Galbraith wrote:
quoted text> On Fri, 2007-10-12 at 22:51 +0200, Peter Zijlstra wrote:
> > Subject: sched: high-res preemption tick
> >=20
> > Use HR-timers (when available) to deliver an accurate preemption tick.
>=20
> This patch further reduced iperf context switching, and boosted
> throughput.
>=20
> iperf -c localhost -P 10 -t 300
>=20
> Previously reported numbers
>=20
> 2.6.23-smp
> [SUM]  0.0-300.0 sec    153 GBytes  4.39 Gbits/sec
> [SUM]  0.0-300.1 sec    148 GBytes  4.23 Gbits/sec
> [SUM]  0.0-300.0 sec    152 GBytes  4.36 Gbits/sec
>=20
> 2.6.23-smp-d (sched-devel)
> [SUM]  0.0-300.0 sec    173 GBytes  4.96 Gbits/sec
> [SUM]  0.0-300.1 sec    173 GBytes  4.96 Gbits/sec
> [SUM]  0.0-300.0 sec    172 GBytes  4.93 Gbits/sec
>=20
> Numbers from fresh pull today
>=20
> 2.6.23-smp-d-hrt
> (re-enable PREEMPT_RESTRICT)

Ah, but HRTICK is not compatible with PREEMPT_RESTRICT, it will be
similar to !WAKEUP_PREEMPT.

quoted text> [SUM]  0.0-300.1 sec    181 GBytes  5.19 Gbits/sec
> [SUM]  0.0-300.0 sec    182 GBytes  5.22 Gbits/sec
> [SUM]  0.0-300.1 sec    182 GBytes  5.22 Gbits/sec
>=20
> 2.6.23-smp-d
> [SUM]  0.0-300.1 sec    174 GBytes  4.97 Gbits/sec
> [SUM]  0.0-300.1 sec    173 GBytes  4.95 Gbits/sec
> [SUM]  0.0-300.1 sec    173 GBytes  4.96 Gbits/sec
>=20
>=20

Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:

[PATCH] sched: high-res preemption tick, Peter Zijlstra, (Fri Oct 12, 4:51 pm)

[RFC][PATCH] sched: SCHED_FIFO watchdog timer, Peter Zijlstra, (Sat Oct 13, 6:51 pm)

Re: [RFC][PATCH] sched: SCHED_FIFO watchdog timer, Kay Sievers, (Mon Oct 15, 5:32 pm)

Re: [RFC][PATCH] sched: SCHED_FIFO watchdog timer, Lennart Poettering, (Mon Oct 15, 10:25 am)

Re: [RFC][PATCH] sched: SCHED_FIFO watchdog timer, Dmitry Adamushko, (Mon Oct 15, 9:26 am)

Re: [RFC][PATCH] sched: SCHED_FIFO watchdog timer, Peter Zijlstra, (Mon Oct 15, 9:57 am)

Re: [PATCH] sched: high-res preemption tick, Mike Galbraith, (Sat Oct 13, 3:18 am)

Re: [PATCH] sched: high-res preemption tick, Peter Zijlstra, (Sat Oct 13, 4:55 am)

Re: [PATCH] sched: high-res preemption tick, Peter Zijlstra, (Sat Oct 13, 5:17 am)

Re: [PATCH] sched: high-res preemption tick, Peter Zijlstra, (Sat Oct 13, 7:13 pm)

Re: [PATCH] sched: high-res preemption tick, Mike Galbraith, (Sun Oct 14, 2:34 am)

Re: [PATCH] sched: high-res preemption tick, Peter Zijlstra, (Sat Oct 13, 7:16 pm)

Re: [PATCH] sched: high-res preemption tick, Mike Galbraith, (Sat Oct 13, 6:11 am)


linux-kernel:
david	Re: Dual-Licensing Linux Kernel with GPL V2 and GPL V3
Heiko Carstens	Re: -mm merge plans for 2.6.23 -- sys_fallocate
Andreas Schwab	Re: [PATCH] [POWERPC] Improve (in\|out)_beXX() asm code
Dave Hansen	Re: [RFC/PATCH] Documentation of kernel messages
git:

linux-netdev:
Gerrit Renker	[PATCH 27/37] dccp: Integration of dynamic feature activation - part 2 (server side)
David Miller	[GIT]: Networking
Jarek Poplawski	Re: [PATCH] pkt_sched: Destroy gen estimators under rtnl_lock().
Jeff Garzik	Re: [bug?] tg3: Failed to load firmware "tigon/tg3_tso.bin"
openbsd-misc:

Re: [PATCH] sched: high-res preemption tick

Online users