Kim C wrote: > I have suspected that the drive might be dying, though I dont see any > other symptoms, no noise, no syslog messages, no smart logged and no > kernel messages. Well the drive has always been a little funny with smart, > always logged lots of > ( 1)Raw Read Error Rate 0x000f 057 046 006 38919422 > (195)Hardware ECC Recovered 0x001a 057 046 000 38919422 I see lots of "Hardware ECC Recovered" on recent Seagate disks too, but always zero "Raw Read Error Rate". No problems so far with those Seagate disks. > I assume the 100% utilization is from the loop device doing > something(probably en/decrypting) is this wrongly assumed? iostat state > that at 100% utilization big saturation may occur and I guess its that I > see here? Whenever loop driver consumes CPU cycles, it shows up in "sys" section. This can be in context of some process doing write to loop device, or loop helper thread doing encrypting or decrypting. "iowait" is equivalent to "idle" except that in "iowait" some process is waiting for I/O reads or writes to complete. In both cases CPU is free. That iostat data that you posted on Saturday says that loop CPU consumption was 33% or less, and that most of the time loop driver was waiting for disk to compete reads or writes. -- Jari Ruusu 1024R/3A220F51 5B 4B F9 BB D3 3F 52 E9 DB 1D EB E3 24 0E A9 DD - Linux-crypto: cryptography in and on the Linux system Archive: http://mail.nl.linux.org/linux-crypto/
