Re: lowlatency-2.2.14-B1 + 2.2.14aa7 fixes crash, but...

From: Benno Senoner (sbenno@gardena.net)
Date: Wed Feb 23 2000 - 12:52:44 EST


On Wed, 23 Feb 2000, Andrea Arcangeli wrote:
> On Wed, 23 Feb 2000, Benno Senoner wrote:
>
> >I was wondering if backing out the inode freeing changes,
> >increases latencies in your tests.
>
> It may be if you are handling an huge number of inodes with most of them
> busy but I think that's certainly not a regular multimedia load.
>
> Andrea

What are you refering to with "multimedia load" ?
Any realtime stuff (like audio playback in my case) needs
deterministic execution times.
And the worst case is the case which we need to analyze.

Therefore if the worst case is 1000ms and the average case 2ms
we are still in a bad situation.
That is why we must find a way to trigger extreme cases.
(like big mem on a slow CPU etc)

Benno.

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



This archive was generated by hypermail 2b29 : Wed Feb 23 2000 - 21:00:33 EST