home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.arch
- Path: sparky!uunet!mcsun!sunic!ugle.unit.no!alf.uib.no!dsfys1.fi.uib.no!iversen
- From: iversen@dsfys1.fi.uib.no (Per Steinar Iversen)
- Subject: Re: IDE faster than Mips SCSI disk
- Message-ID: <1992Nov9.111601.27585@alf.uib.no>
- Lines: 48
- Sender: iversen@vsfys1.fi.uib.no (Per Steinar Iversen)
- Reply-To: iversen@vsfys1.fi.uib.no
- Organization: Department of Physics, University of Bergen, Norway
- References: <1992Nov6.033942.21194@ntuix.ntu.ac.sg> <MAD.92Nov7220823@amber.math.keio.ac.jp> <k2.721260853@woodstock> <6215@tuegate.tue.nl> <k2.721304278@woodstock>
- Date: Mon, 9 Nov 92 11:16:01 GMT
- Lines: 48
-
-
- In article <k2.721304278@woodstock>, k2@bl.physik.tu-muenchen.de (Klaus Steinberger) writes:
-
- >tgcpwd@rw9.urc.tue.nl (Wim van Dorst) writes:
- >
- >>Klaus Steinberger writes:
- >>> 1520363 bytes/second for writing the file
- >>> 1736771 bytes/second for reading the file
- >
- >>Others have written results for ordinary 386s with plain IDE disk
- >>in the range of 200-500 kB/s. I tried it at my home PC and I got
- >>similar results.
- >
- >>However, I always thought that those VAX/VMS machines at work were
- >>awfully slow. So I tried iozone there too. It compiled without a
- >>glitch, and gave results in various machines (workstations up to
- >>large VAX-6410s) with various disks (RA type, RF type, other)
- >>results in the range 15-40 kB/s.
- >
- >>What does this mean: Are the disks really that slow? Is the VMS
- >>version of iozone different? Is the OS that significant?
- >I did the same test with same results, and I suspect its due to
- >a very bad implementation off the read/write call emulation in VAXCRTL .
- >
- >I did have VMS Posix running on my VAX, and it gives indeed better
- >results. I'm seeing results in the 200 - 300 kBytes/sec range.
- >(A little MVIII, with SMD disks, platter rate around 2Mb/sec).
- >I did not know how well the Posix environment did emulate Unix
- >system calls, so I think native VMS programs with their ugly $QIO
- >interface will see better rates.
- >
-
- I too have tried IOZONE with/without POSIX 1.0. In general the Posix environment
- is 3-6 times faster then under VMS. Most likely the problem is in VAXC, I can
- read/write files with VAX FORTRAN, under ordinary VMS, at rates close to that
- found when the disks are mounted on Unix boxes - without any "ugly $QIO"s
- at all.
-
- -psi
-
- +------------------------------------------------------------------------------+
- ! Per Steinar Iversen ! Internet: iversen@vsfys1.fi.uib.no !
- ! Fysisk Institutt ! BITnet: iversen@cernvm.bitnet !
- ! Universitetet i Bergen ! HEPnet: VSFYS::IVERSEN (VSFYS=21.341=21845) !
- ! Allegaten 55 ! Phone: +47 5212770 !
- ! N-5007 Bergen ! Fax: +47 5318334 !
- ! NORWAY ! !
- +------------------------------------------------------------------------------+
-