On Monday 28 Apr 2014 13:32:05 I wrote: > On Thursday 24 Apr 2014 13:57:19 I wrote: > > So far I've done these things: > > > > 1. Wiped the whole system and restored from backup (heavy overkill, but I > > wanted everything to be in the same, consistent state). > > 2. Run bad-blocks tests on all partitions (though all but / and /boot are > > in logical volumes - I don't know to what extent that will have affected > > the results). > > --->8 > > Looking at bad-blocks again, I see from gkrellm that 'mkfs.ext4 -cc -L Atom > /dev/vg7/atom' writes the test patterns to both the underlying physical > disks, but it only reads back from one of them
... so it isn't much use on a virtual disk. Well, that was a long weekend. The symptoms grew stranger and stranger, until I eventually discovered a problem with IRQ 16. /proc/interrupts includes this line: 16: 0 302525 0 0 IO-APIC-fasteoi ehci_hcd:usb1, nouveau The source file /usr/src/linux/kernel/irq/spurious.c says: /* * If 99,900 of the previous 100,000 interrupts have not been handled * then assume that the IRQ is stuck in some manner. Drop a diagnostic * and try to turn the IRQ off. * * (The other 100-of-100,000 interrupts may have been a correctly * functioning device sharing an IRQ with the failing one) */ ...and suggests booting with irqpoll. So I added irqpoll to the kernel command line. It seemed to make no difference at the time, but I haven't had any recurrence in the last two days. I see though that, according to gkrellm, I have core temps of 52 - 56C and the graphics card shows 59C. That shouldn't be hot enough to start raising spurious interrupts: the nVidia web site says to expect around 105C as a limit. Perhaps I should find a different slot for the Quadro FX580 card, to separate it from the usb interface. So, many hours and much rebuilding later, I've installed a new chroot for the Atom and it seems to be working as expected. Actually, I reinstalled the entire system to be safe, including re-creating the physical and logical volumes on the two SATA disks. The question still remaining is what caused millions of spurious interrupts over a period of a week or so and then subsided. This is an Asus P7P55D motherboard (http://www.asus.com/Motherboards/P7P55D/). -- Regards Peter
