[Top] [All Lists]

Observation on IDE read operation

Subject: Observation on IDE read operation
From: kernel coder <>
Date: Tue, 17 Jan 2006 04:12:17 -0800
Domainkey-signature: a=rsa-sha1; q=dns; c=nofws; s=beta;; h=received:message-id:date:from:to:subject:mime-version:content-type:content-transfer-encoding:content-disposition; b=jUZl932vBcZ6noXg4fg/cQ+Vsj+dArupcrnr6SR/rZA9iyQPGPfTjPKfSU7WqmWiCWrl+0K3p2zqmWKjc+WSn5Hqx46ZanHqnkrWiM/gZa4ZROn8agKQ9QKdUPkpW+xMcxrF8A/lHuue1/Vs8addrhIL9zFwOsVxit5dN7Bz2DA=
Original-recipient: rfc822;

I was analyzing the IDE i/o mechanism in linux kernel 2.4.32.I
observed following sequence of read requests to read a particular file
with size around 13kb.

1) block no=9706                 number of sectors=20

2) block no=9723                 number of sectors=4

3) block no=9725                 number of sectors=2

4) block no=9726                 number of sectors=2

As u can see 4 different requests were made to read blocks 9706 to
9715 , 9723 to 9724 , 9725 , 9726.

The function __make_request ensures that requests are rearranged and
merged so that consective blocks are read in one request.So please
tell me why separete requests were made for reading blocks 9723 to
9724 , 9725 , 9726 ,when requests from 9724 to 9726 can be merged into

Is it suitable that instead of generating separte requests for reading
 9706 to 9715 and 9723 to 9726 blocks ,just one request for reading
9706 to 9726 blocks is issued.This will cause irrelevant blocks (9716
to 9722) to be read as well but they can be discarded.

 If all data blocks of that particular file are read in one
request,will it increase  the speed of read operation on that file.


<Prev in Thread] Current Thread [Next in Thread>
  • Observation on IDE read operation, kernel coder <=