Peter Gordon wrote:
On Sat, 2005-12-31 at 12:15 -0600, Les Mikesell wrote:
Writes also always go through cache and sensible operating systems will sort the write-back into seek order to avoid threshing the head around in the process. So, if you think you have a speed problem caused by your disk, the quick fix is normally to add more RAM.
It iss interesting to note, also, that Ext3's default "ordered" data writing mode does precisely this, from what I've read. It first commits the metadata transactions to the journal, then flushes the data to the disk in large blocks of writes, then commits the journal transactions to the disk.
Extents-based and delayed write allocation (for on-disk contiguity of file data) are also being worked on (though, due to possible on-disk changes of the filesystem format, this could end up becoming "ext4" or similar). Please see the following page for more information: http://ext2.sourceforge.net/2005-ols/paper-html/node18.html
Thanks for the link Peter, I found the reading interesting. The information clears up some questions if the fragmentation problem and dealing with large files is being addressed. It seems that work is ongoing.
Jim