On Sun, 4 Apr 2004, Alvin Oga wrote: > > On Sun, 4 Apr 2004, Stefan Goessling-Reisemann wrote: > > > Question1 : could this be related to the position of the partition on the > > disk? > > yup > > > How could I verify this? > > wite a block of data to certain cylinders.... starting from cylinder-0 > to cylinder 10,000 ... ( be aware of the zone boundries of ZBR ) > - thruput should be the same within the zone
I wouldn't want to write to random cylinders, because I still nee dthe data on the disk ;-) Can I read directly from specified cylinders/positions on the disk? Is there a tool for testing the throughput from different positions on the disk? > > > Is the hda2 partition always directly > > adjacent to the hda1 partition? > > no .. partitions can start and end anywhere, as long as it doesnt overlap OK, I checked the positions: hda1 (Windows, vfat) is at the beginning of the disk and measures around 28 GB. Then there comes the swap partition hda4 (1 GB) and then actual Linux partition hda2 (ext2, around 9.5 GB). After that there is some free space (around 480 MB) and another small (~8 MB) Win partition, hda3, setup by the service department of the laptop manufacturer. Question: would it make sense to move the Linux partition in front of the swap partition? It would only shift it by around 1 GB. I doubt that it would somehow increase throuput, would it? If so: how can I most securely move whole partitions? I suppose this would involve backing up images, re-partitioning, and restoring the images, right? Thanks and best regards Stefan -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of "unsubscribe". Trouble? Contact [EMAIL PROTECTED]
