OK, On Fri, 2007-09-14 at 08:56 -0500, Bruce Allen wrote: ... > Eamonn: could you please build the latest version of smartmontools from > CVS HEAD source and see if the problem exists in that version? Then write > back. I don't think this will help but want to eliminate obvious things. > I built the latest version which reports itself as 5.38 from cvs. The results, as you suspected, were no different. The setup : The system is setup with sda and sdb being partitioned as follows : /dev/sda1 * 1 243 1951866 fd Linux raid autodetect /dev/sda2 244 1459 9767520 fd Linux raid autodetect /dev/sda3 1460 1824 2931862+ fd Linux raid autodetect /dev/sda4 1825 19452 141596910 5 Extended /dev/sda5 1825 7295 43945776 fd Linux raid autodetect /dev/sda6 7296 19452 97651071 fd Linux raid autodetect raid1 mirrors are then setup between the corresponding partitions on the two disks. The results : using either 5.37 or 5.38, issuing a smartctl -t long on either one of the disk devices allows filesystem access at full speed, and issuing a smartctl -X on the disk returns inside a second. All is well: time dd if=/dev/zero of=file bs=1k count=1024 1024+0 records in 1024+0 records out 1048576 bytes (1.0 MB) copied, 0.00488519 seconds, 215 MB/s Starting an extended self-test on *both* disks, however, and filesystem access is *extremely* slow, which may be why the violations are happening, although I didn't leave it running long enough to impact the box: time dd if=/dev/zero of=file bs=1k count=1024 1024+0 records in 1024+0 records out 1048576 bytes (1.0 MB) copied, 0.00505913 seconds, 207 MB/s real 0m9.107s user 0m0.000s sys 0m0.004s Now, I'm asking the guy who runs the system as to when I can test the smartd, but I'm guessing from this that the results will be exactly the same. Comments? Cheers, Eamonn -- This message has been scanned for viruses and dangerous content by MailScanner, and is believed to be clean. - To unsubscribe from this list: send the line "unsubscribe linux-ide" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html