Re: Can O_SYNC be implemented by using fsync?

From: Alan Cox (alan@lxorguk.ukuu.org.uk)
Date: Thu May 18 2000 - 05:50:17 EST


> Linus's argument at the time was "well, do we need it, or is fsync
> fast enough now?" If anyone is prepared to put performance numbers
> on it, now is the time to put your paws in the air. :-)
>
> How complex is the code? Ideally, O_SYNC should be as fast as
> possible, even on very large files -- if the code is simple and small
> enough, I would go for it...

O_SYNC needs to be disk fast, and it needs to issue all the blocks then parallel
wait for them in order to get maximum performance.

Alan

-
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 : Tue May 23 2000 - 21:00:15 EST