On Fri, 12 Sep 2014 14:15:35 +0200 Marco Schindler <marco.schindler@xxxxxxxxx> wrote: > ok, that’s interesting. > the process id is _not_ mdadm daemon and it looks like the spindown itself is triggering the process. > > ps ax | grep mdadm > 28956 ? Ss 0:00 mdadm --monitor --scan --daemonise --pid-file /var/run/mdadm.pid --syslog > > grep sda /var/log/messages > Sep 12 13:55:04 alina spindown: sda is now inactive. > Sep 12 13:55:09 alina kernel: mdadm(29737): READ block 3907028992 on sda (8 sectors) > Sep 12 13:55:17 alina kernel: mdadm(29737): READ block 3907029152 on sda (8 sectors) > Sep 12 13:55:26 alina kernel: mdadm(29737): READ block 0 on sda (8 sectors) > Sep 12 13:55:26 alina kernel: mdadm(29737): READ block 8 on sda (8 sectors) > Sep 12 13:55:26 alina kernel: mdadm(29737): READ block 8 on sda (8 sectors) > Sep 12 13:55:26 alina kernel: mdadm(29737): READ block 3907029167 on sda (1 sectors) > Sep 12 13:55:26 alina kernel: mdadm(29737): READ block 3907029166 on sda (1 sectors) > Sep 12 13:55:26 alina kernel: mdadm(29737): READ block 0 on sda (1 sectors) > Sep 12 13:55:26 alina kernel: mdadm(29737): READ block 0 on sda (1 sectors) > Sep 12 13:55:26 alina kernel: mdadm(29737): READ block 3907029152 on sda (8 sectors) > Sep 12 13:55:26 alina kernel: mdadm(29737): READ block 0 on sda (8 sectors) > Sep 12 13:55:26 alina kernel: mdadm(29737): READ block 8 on sda (8 sectors) > Sep 12 13:55:26 alina kernel: mdadm(29737): READ block 8 on sda (8 sectors) > Sep 12 13:55:26 alina kernel: mdadm(29737): READ block 8 on sda (8 sectors) > Sep 12 13:56:12 alina spindown: sda is now active. It would help to get "udevadm monitor" info to correlate with this. Presumably some uevent is generated when the spindown happens. udev might respond to this by reading from the device, which defeats the purpose... > > here’s the output of blktrace -d /dev/sda during that time. > https://dl.dropboxusercontent.com/u/3464720/blktrace.tar.bz2 That suggest that something is reading the metadata from the device almost constantly. Mostly a 'kworker' thread. I don't know what would cause that. Let's look at the 'udevadm monitor' trace first and see what that shows. NeilBrown
Attachment:
signature.asc
Description: PGP signature
