This list never ceases to amaze me with very very quick and educating responses John R Pierce <pierce at ...> writes: > > Rajagopal Swaminathan wrote: > > depends on your disk controllers. whats `iostat -x 5` say the IO on > hdb3 and hda3 is doing? (ignore the first sample, its average since avg-cpu: %user %nice %system %iowait %steal %idle 0.13 0.00 31.98 0.00 0.00 67.89 Device: rrqm/s wrqm/s r/s w/s rsec/s wsec/s avgrq-sz avgqu-sz await svctm %util hda 26.40 0.40 4.20 2.20 3660.80 20.80 575.25 2.74 386.97 148.44 95.00 hdb 0.00 24.80 0.00 6.60 0.00 3988.80 604.36 1.43 217.45 143.24 94.54 md2 0.00 0.00 0.00 2.60 0.00 20.80 8.00 0.00 0.00 0.00 0.00 md1 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 md0 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 dm-0 0.00 0.00 0.00 2.60 0.00 20.80 8.00 0.43 163.85 78.08 20.30 I won't claim I understand everyone of the above columns. I am in the process of reading man pages. > > is the md2 filesystem mounted ? Yes. But no users using the system and it is mounted as / (root). So cant unmount it > > 500gb has to be read and written over the SATA channels, which appear to > be in IDE mode (hda instead of sda).... figure 60-80MB/sec peak > sustainable, lets round that to 50MB/sec, so thats 500000/50 == 10000 > seconds if its running at pure wire speed the whole time. if there's > -any- disk contention, it will run MUCH slower. if its only running > 2MB/sec (as indicated) somethinig is fubar with the disk IO, maybe its > in PIO mode, ouch! > So Q1. Where should I look to correct its PIO mode hdparm? BIOS? Q2. If I bring down the system, will the array reconstruction start from beginning or from where it left off before reboot? BTW it is HP ML 110 G5 box with 4 gigs RAM. Thanks Rajagopal