To further qualify my claims about XFS vs ReiserFS I did an even smaller
test (although still using the same ~600MB file size).
Computers involved:
o Gusi server (same as used in original tests)
o Spolario workstation (Pentium II MMX 400MHz, Linux 2.4.7-xfs)
Info on Spolario:
o hdparm -tT /dev/hda results:
buffer cache reads: 114.29 MB/sec
buffer disk reads: 16.54 MB/sec
As usual, this was done over a 100Mbps switched link, with no other ports
busy. Neither computer was doing anything significant except participate
in the testing.
Procedure:
o transfer Gusi (XFS) --> Spolario
o copy file from XFS partition on Gusi to ReiserFS partition on Gusi
o transfer Gusi (ReiserFS) --> Spolario
o transfer Gusi (XFS) --> Spolario
Results:
Gusi (XFS) --> Spolario [PASS 1] = 7.60 M/s
Gusi (ReiserFS) --> Spolario = 7.03 M/s
Gusi (XFS) --> Spolario [PASS 2] = 7.15 M/s
You will notice that there seems to be no difference in speed due to
caching since we're transferring a file that is significantly greater than
physical memory (672333824 bytes).
Conclusion:
Again we reject the hypothesis that ReiserFS is significantly faster than
XFS in _reading_ a large file (~600MB).
Nota bene:
To those attempting to do similar FTP tests, *PLEASE* use lftp. I do not
know if there is a significant difference in the report metrics of various
ftp clients. Maybe some use 1000k = 1M while others use 1024k = 1M? I
cannot be sure, but for consistency maybe we can use the same client which
does the timing of the transfer, anyway.
--> Jijo
PS- now off to do my schoolwork that I was supposed to do, anyway. <smile>
--
Federico Sevilla III :: [EMAIL PROTECTED]
Network Administrator :: The Leather Collection, Inc.
_
Philippine Linux Users Group. Web site and archives at http://plug.linux.org.ph
To leave: send "unsubscribe" in the body to [EMAIL PROTECTED]
To subscribe to the Linux Newbies' List: send "subscribe" in the body to
[EMAIL PROTECTED]
