stubbs@ncr-sd.UUCP (Jan Stubbs) (12/05/85)
IOCALL, A UNIX SYSTEM PERFORMANCE BENCHMARK
The results so far are at the end of this article. Thanks everybody.
Send your results to me directly. The benchmark is a "C" program
which measures Unix kernel performance.
To run it:
cut off top and bottom of this article and put it in iocall.c
cc iocall -o iocall
time iocall
Send all 3 times (user, system, real)
I am reporting the system time only.
"The opinions expressed herein are those of the author".
Jan Stubbs
NCR Corp.
San Diego, CA
619 485-3052
..sdcsvax!ncr-sd!stubbs
------cut here------cut here-------------------------------
/*This benchmark tests speed of Unix system call interface
and speed of cpu doing common Unix io system calls. */
char buf[512];
int fd,count,i,j;
main()
{
fd = creat("/tmp/testfile",0777);
close(fd);
fd = open("/tmp/testfile",2);
unlink("/tmp/testfile");
for (i=0;i<=1000;i++) {
count = write(fd,buf,500);
lseek(fd,0,0);
for (j=0;j<=3;j++)
count = read(fd,buf,100);
}
}
------cut-------cut----cut-----------------------------
IOCALL RESULTS (so far)
SYSTEM UNIX VERSION SYSTEM TIME SECONDS
----------- ---------------- -------------------
DEC Rainbow100 w/NECV20 Venix 18.4
VAX 11/750 4.2 BSD 10.0
VAX 11/750 SV.2 9.4
VAX 11/750 4.3 BSD 9.0
VAX 11/750 research version 8 8.1
ATT 7300 Unix PC SV.2 6.4
Pyramid 90x w/cache OSx2.2 5.8
VAX 11/780 4.2 BSD 5.7
VAX 11/785 4.3 BSD 3.6sean@ukma.UUCP (Sean Casey) (12/05/85)
I think it would be wise to turn the benchmark around and make
higher scores better. It would make it more understandable and
more immediately obvious what the ratios are.
Sean
--
-------------------------------------------------------------------------------
Sean Casey UUCP: sean@ukma.UUCP or
915 Patterson Office Tower {cbosgd,anlams,hasmed}!ukma!sean
University of Kentucky ARPA: ukma!sean@ANL-MCS.ARPA
Lexington, Ky. 40506-0027 BITNET: sean@UKMA.BITNET