Re: I/O Scheduler

2008/8/18 Ingo Weinhold <[email protected]>:
>
>
> You seem to confuse file and block cache.

I actually do.

> Anyway, I haven't really looked
> closer into it, but the explanation you've added to #2631 seems right. I
> cannot say much wrt.

I found it while at bed so I haven't test it yet, but it seems reasonable. :-)
Does the patch looks fine to you?

> #2634; it doesn't look like the new I/O request
> framework is to blame, though. No idea at all regarding #2618; assuming that
> an on-disk structure corruption was detected, the recent I/O changes
> certainly are candidates. If you're able to reproduce it, you can check back
> with an earlier revision (e.g. the one tagged "somewhat stable").

It's not easy to reproduce. It actually happened 2-3 times while download an iso
as I commented in the ticket. I'll see what I can do about it.

>
>> Beside, while we are at it, whats the policy used by the scheduler? :-)
>
> Currently no-op. This will change, but with what strategy (or strategies)
> we'll end up, has to be seen.

Have you had a look at this one?
http://kerneltrap.org/Linux/Budget_Fair_Queuing_IO_Scheduler

Regards,
-- 
Salvatore Benedetto (a.k.a. emitrax)
Student of Computer Engineer
University of Pisa
www.haiku-os.it

-------------------------------------------------------------------------
This SF.Net email is sponsored by the Moblin Your Move Developer's challenge
Build the coolest Linux based applications with Moblin SDK & win great prizes
Grand prize is a trip for two to an Open Source event anywhere in the world
http://moblin-contest.org/redirect.php?banner_id=100&url=/