lkml.org 
[lkml]   [1999]   [Apr]   [3]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: Indirect IO in Linux, some figures


On Sat, 3 Apr 1999, Douglas Gilbert wrote:

[ ... ]

> The last row times seem to be swamped by the overhead of the 51,200
> READ BUFFER SCSI commands involved. So when the best time is taken into
> account this suggests a SCSI command overhead of about 1.2 milliseconds
> (seems a bit low to me). If this time is subtracted from the 420

If 1.2 milli-second is the latency of a SCSI command you observed as seen
from the application program, excluding data phase and head seeking time,
then it seems just extremally high to me. If by 'low' you meant 'bad',
then indeed it is bad.

Something between 100 micro-seconds and 300 micro-seconds is what we can
expect with recent SCSI hardware. More than 100 micro-seconds latency
will probably not allow FAST-40 to give a significant thoughtput increase
against FAST-20 for real life because of the average IO size not being
that large.

Gérard.






-
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/

\
 
 \ /
  Last update: 2005-03-22 13:51    [W:0.038 / U:0.236 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site