home
***
CD-ROM
|
disk
|
FTP
|
other
***
search
/
Usenet 1994 October
/
usenetsourcesnewsgroupsinfomagicoctober1994disk2.iso
/
unix
/
volume22
/
byte-benchmarks
/
part01
/
README
< prev
next >
Wrap
Text File
|
1990-06-07
|
4KB
|
107 lines
Version 2.5 -- 4/17/90 16:45:28
================================================================
To use the new BYTE Unix Benchmarks:
make all
Run
The results are stored in results/log. All logs are accumulated
in results/log.accum. Raw times for each run are stored in
results/times.
Notes:
BSD & Ultrix users will have to change the makefile Define to
from SysV to BSD, and copy pgms/BSDtime.awk to pgms/time.awk.
Be sure to check your compiler options for optimizing. When
optimizing is supposed to be on (most tests), it should be set to
level 1 (generally -O), however different compilers have
different options for "optimizer off." Ultrix for RISC uses -O0;
SCO uses -Od. We have found that the memory tests can get
optimized so that the memory is never really fetched. That is why
we turn the optimizer off for these tests.
BUG ALERT:
BSD4v2 only: The time functions in the memory and and file
access tests appear to be incorrect.
================================================================
You may run individual benchmark programs and groups of programs.
There are also a few options.
Run [<bench> ...] [<group> ...] [-qvd]
-q quiet no output to standard out
-v verbose extra output to standard out
-d debug Run is displayed as it is run
GROUP BENCHMARK EXPLANATION SOURCE
-------- ----------- -------------------- -------------
arithmetic
arithoh arithmetic overhead src/arith.c
register register arithmetic src/arith.c
short short arithmetic src/arith.c
int int arithmetic src/arith.c
long long arithmetic src/arith.c
float float arithmetic src/arith.c
double double arithmetic src/arith.c
system
syscall system call overhead src/syscall.c
pipe pipe throughput src/pipe.c
context1 pipe context switch src/context1.c
spawn process creation src/spawn.c
execl execl call src/execl.c
fstime filesystem throughput src/fstime.c
misc
C compile and link /bin/cc
dc calculations with dc testdir/dc.dat
hanoi recursion src/hanoi.c
dhry
dhry2 dhrystone 2 w/o regs src/dhry.c
dhry2reg dhrystone 2 with regs src/dhry.c
db
dbmscli client/server src/dbmscli.c
dbmserv dbms engine src/dbmserv.c
load
multi.sh load system with pgms/multi.sh
concurrent shell pgms/tst.sh
scripts
===================== RELEASE NOTES =====================================
========================= Jan 90 =============================
Tom Yager has joined the effort here at BYTE; he is responsible
for many refinements in the UNIX benchmarks.
The memory access tests have been deleted from the benchmarks.
The file access tests have been reversed so that the test is run
for a fixed time. The amount of data transfered (written, read,
and copied) is the variable. !WARNING! This test can eat up a
large hunk of disk space.
The initial line of all shell scripts has been changed from the
SCO and XENIX form (:) to the more standard form "#! /bin/sh".
But different systems handle shell switching differently. Check
the documentation on your system and find out how you are
supposed to do it. Or, simpler yet, just run the benchmarks from
the Bourne shell. (You may need to set SHELL=/bin/sh as well.)
The options to Run have not been checked in a while. They may no
longer function. Next time, I'll get back on them. There needs to
be another option added (next time) that halts testing between
each test. !WARNING! Some systems have caches that are not getting flushed
before the next test or iteration is run. This can cause
erroneous values.
========================= Sept 89 =============================
The database (db) programs now have a tuneable message queue space.
queue space. The default set in the Run script is 1024 bytes.
Other major changes are in the format of the times. We now show
Arithmetic and Geometric mean and standard deviation for User
Time, System Time, and Real Time. Generally, in reporting, we
plan on using the Real Time values with the benchs run with one
active user (the bench user). Comments and arguments are requested.
contact: BIX bensmith or rick_g