Messages in this thread | | | From | Rusty Russell <> | Subject | Re: [TRIVIAL] kstrdup | Date | Sun, 20 Apr 2003 18:05:40 +1000 |
| |
In message <1050755240.3277.3.camel@dhcp22.swansea.linux.org.uk> you write: > On Sad, 2003-04-19 at 05:48, Jeff Garzik wrote: > > And? It's still slower. > > You are arguing over a 1 instruction, probably sub 1 clock scheduling > matter on a call which is not used on any fast or common path. If you > shaved 1 clock off the timer handling instead you'd make a lot more > difference..
Hey, if we have 50 million machines running 2.6 for three years, this optimization saves 100 clock cycles per boot (most kstrdups are device init), and machines boot once a month, and average 1GHz, that's three minutes of saved time.
I think Jeff and I should start the kstrdup sourceforge project immediately...
Cheers, Rusty. -- Anyone who quotes me in their sig is an idiot. -- Rusty Russell. - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |