home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!portal!cup.portal.com!Tony-Preston
- From: Tony-Preston@cup.portal.com (ANTHONY FRANCIS PRESTON)
- Newsgroups: comp.sys.amiga.hardware
- Subject: Re: Hard disk performance speeds
- Message-ID: <72123@cup.portal.com>
- Date: Mon, 21 Dec 92 07:12:08 PST
- Organization: The Portal System (TM)
- References: <etam.723533542@sfu.ca> <37954@cbmvax.commodore.com>
- Lines: 15
-
-
- I wrote a "pessimistic" benchmark that did four tests to measure the
- speed of a disk drive/partition. What it did was create a file, do
- a sequential write(to create the file), sequential read of the file,
- randow read, and random write. While it was doing this, it would
- time all the reads and writes and compute the minimum, maximum, and
- average access time for the file. It would do a small, medium, and
- large block size. It took two or more drive/partitions as arguments
- and compared the second drive on to the results for the first drive
- and sort of a relative performance indicator. I would use the RAM:
- as the first drive and other drives would be compared to it. It
- was a 'pessimistic' benchmark(or should I say realistic) since it
- gave information with all the file system overhead included. If you
- have a fragmented drive, the results would be worse than an unfragmented
- one. It wasn't complex, I could post it if anyone is interested.
-