Here's another run that doesn't have a constant number of bytes, so
the bytes/sec might be a little more accurate
~% for BS in 1 512 $(expr 1024 \* 4) $(expr 1024 \* 16) $(expr 1024
\* 64); do dd if=/dev/random of=/dev/null bs=$BS count=1024;
done 1024+0 records in
1024+0 records out
1024 bytes transferred in 0.395678 secs (2588 bytes/sec)
1024+0 records in
1024+0 records out
524288 bytes transferred in 0.791416 secs (662468 bytes/sec)
1024+0 records in
1024+0 records out
4194304 bytes transferred in 6.415680 secs (653758 bytes/sec)
1024+0 records in
1024+0 records out
16777216 bytes transferred in 25.814593 secs (649912 bytes/sec)
1024+0 records in
1024+0 records out
67108864 bytes transferred in 102.280978 secs (656123 bytes/sec)
On 16 Oct 2006, at 10:14, David King wrote:
BTW, David, test (if you have enough time for curiosity) /dev/
urandom (or
wherever the generator is) with different values of 'bs', from very
small to large (1 byte, 512, 4k, 16k, 64k) to see how much it depends
on block size.
bash-2.05b$ time dd if=/dev/urandom bs=1024 count=10240 of=/dev/null
10240+0 records in
10240+0 records out
10485760 bytes transferred in 0.154649 secs (67803598 bytes/sec)
~% cat test_rand_block.sh
#!/usr/local/bin/bash
for BS in 1 512 $(expr 1024 \* 4) $(expr 1024 \* 16) $(expr 1024 \*
64); do
COUNT=$(expr $(expr 1024 \* 64) / $BS)
BYTES=$(expr $COUNT \* $BS)
echo bs=$BS count=$COUNT bytes=$BYTES
dd if=/dev/random of=/dev/null bs=$BS count=$COUNT
echo ------;
done
~% sh test_rand_block.sh
bs=1 count=65536 bytes=65536
65536+0 records in
65536+0 records out
65536 bytes transferred in 25.599306 secs (2560 bytes/sec)
------
bs=512 count=128 bytes=65536
128+0 records in
128+0 records out
65536 bytes transferred in 0.099902 secs (656003 bytes/sec)
------
bs=4096 count=16 bytes=65536
16+0 records in
16+0 records out
65536 bytes transferred in 0.100660 secs (651062 bytes/sec)
------
bs=16384 count=4 bytes=65536
4+0 records in
4+0 records out
65536 bytes transferred in 0.099324 secs (659820 bytes/sec)
------
bs=65536 count=1 bytes=65536
1+0 records in
1+0 records out
65536 bytes transferred in 0.099681 secs (657458 bytes/sec)
------
_______________________________________________
[email protected] mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-hardware
To unsubscribe, send any mail to "freebsd-hardware-
[EMAIL PROTECTED]"
--
David King
Computer Programmer
Ketralnis Systems
_______________________________________________
[email protected] mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-hardware
To unsubscribe, send any mail to "[EMAIL PROTECTED]"
