Now that I have run through the 32 bit windows portion of the benchmark for the customer, I want to compare to our default way of shipping the units. So I fired up our default CF load, rebuilt the RAID. Simple little test runs, nothing to see here (no tuning yet)
The really simple minded tests … how quickly can we pull from the disk and the buffer cache.
root@jrs8:~/mdadm-2.6.6# hdparm -tT /dev/md0 /dev/md0: Timing cached reads: 8862 MB in 2.00 seconds = 4436.59 MB/sec Timing buffered disk reads: 3038 MB in 3.01 seconds = 1007.76 MB/sec
Now lets write 336 GB.
root@jrs8:/big# dd if=/dev/zero of=/big/big_file bs=32M count=10000 oflag=direct 10000+0 records in 10000+0 records out 335544320000 bytes (336 GB) copied, 281.305 seconds, 1.2 GB/s
and read it back
root@jrs8:/big# dd if=/big/big_file of=/dev/null bs=32M iflag=direct 10000+0 records in 10000+0 records out 335544320000 bytes (336 GB) copied, 245.411 seconds, 1.4 GB/s root@jrs8:/big#
Yeah, it really is a 336 GB file
root@jrs8:~# ls -alF /big total 327680004 drwxr-xr-x 2 root root 21 2008-06-22 16:43 ./ drwxr-xr-x 22 root root 4096 2008-03-12 16:29 ../ -rw-r--r-- 1 root root 335544320000 2008-06-22 16:48 big_file
More tuning to do, will report back later on. First we have a benchmark to set up …