Lamar Owen wrote: <snip> : /dev/hda: : Timing buffered disk reads: 170 MB in 3.02 seconds = 56.26 MB/sec : : /dev/hdb: : Timing buffered disk reads: 172 MB in 3.03 seconds = 56.70 MB/sec : : /dev/hde: : Timing buffered disk reads: 170 MB in 3.01 seconds = 56.55 MB/sec : : /dev/hdg: : Timing buffered disk reads: 170 MB in 3.01 seconds = 56.51 MB/sec : : /dev/md0: : Timing buffered disk reads: 372 MB in 3.01 seconds = 123.77 MB/sec Thanks very much Lamar. I understand most of what you wrote in your very detailed email. Your numbers, above, are something like what I would expect. Why do you suppose I get such a low number for my /dev/md0: sda: ~56 MB/sec sdb: ~71 MB/sec sdc: ~75 MB/sec md0: ~65 MB/sec True, I only have three SATA devices (the box won't take a 4th). I don't think this is a case of bus saturation. The 3 Sata cables all go to the motherboard (Dell Precision 490 workstation, not sure what Mobo it is, SATA chipset is Intel 631/632 SATA AHCI) but when I run the two fast drives in RAID0 mode `hdparm -t /dev/md0' gives ~140MB/sec. (I take it you have not adjusted the "read-ahead" parms of the disks or md0? I found that it dramatically increases hdparm numbers, but I suspect there is a downside---something about "no free lunches".) Dean
