Re: [DATAPOINT] how max_readahead settings affect streaming throughput

From: Rik van Riel (riel@conectiva.com.br)
Date: Thu Oct 04 2001 - 18:51:21 EST

Next message: Linus Torvalds: "Re: [announce] [patch] limiting IRQ load, irq-rewrite-2.4.11-B5"
Previous message: Linus Torvalds: "Re: Context switch times"
In reply to: Roger Larsson: "[DATAPOINT] how max_readahead settings affect streaming throughput"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

On Fri, 5 Oct 2001, Roger Larsson wrote:

> I question the decision to use 124 kB as default read ahead maximum.

> The example cited was a FTP server serving 100 clients. With standard
> readahead it would give 12.8 MB readahead

[snip]

Ideally the readahead code would scale itself to use as much
memory is available, but no more and without putting pressure
on the working set too much.

I have some ideas on how to implement this and will start
testing them as soon as I have a nice test program for this.

regards,

Rik

-- DMCA, SSSCA, W3C? Who cares? http://thefreeworld.net/ (volunteers needed)

http://www.surriel.com/ http://distro.conectiva.com/

- 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/

Next message: Linus Torvalds: "Re: [announce] [patch] limiting IRQ load, irq-rewrite-2.4.11-B5"
Previous message: Linus Torvalds: "Re: Context switch times"
In reply to: Roger Larsson: "[DATAPOINT] how max_readahead settings affect streaming throughput"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

This archive was generated by hypermail 2b29 : Sun Oct 07 2001 - 21:00:34 EST