Re: disk performance still wrecked in 2.4!

From: Jens Axboe (axboe@suse.de)
Date: Fri Jun 30 2000 - 17:43:28 EDT

Next message: Robinson, Daniel: "Intercepting Packets"

Previous message: Theodore Y. Ts'o: "Re: a joint letter on low latency and Linux"
In reply to: Andre Hedrick: "Re: disk performance still wrecked in 2.4!"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

On Fri, Jun 30 2000, Andre Hedrick wrote:
> there is an ata patch that allows for setting the elevator to "noop"
> at compile time only, plus a few other fixes.

... which makes performance even worse on disk I/O. The noop 'elevator'
is mainly meant to be used for intelligent I/O devices that have no
benefit from request reordering. Even on a decent SCSI disk with a
TCQ depth of 32, the noop elevator still performs considerably worse
than a strict ascending sorter.

-- * Jens Axboe <axboe@suse.de> * SuSE Labs

- 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/

Next message: Robinson, Daniel: "Intercepting Packets"
Previous message: Theodore Y. Ts'o: "Re: a joint letter on low latency and Linux"
In reply to: Andre Hedrick: "Re: disk performance still wrecked in 2.4!"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

This archive was generated by hypermail 2b29 : Fri Jun 30 2000 - 18:34:59 EDT