On Friday 17 October 2014 21.51:19 you wrote:
Hey just a remark, I've not check in kernel changelog but what was a "behaviour" of previous kernel series has now stop
Diverse crash in kernel when a nfs server was under heavy load with ext4 fs (the average io output at that time is around 260MB/s)
I've loaded 3.17.0 three times now and no more messages like below. I guess that 13.2 and factory could benefit also from it ;-) Hum, never seen this. Actually it looks like a memory corruption - we oopsed when dereferencing RDI which has value ff008802f8cf7f98 which looks
On Mon 13-10-14 11:45:47, Bruno Friedmann wrote: like a valid kernel pointer except that the second most significant byte got zeroed-out. Strangely enough R12 contains ffff8802f8cf7f98 which is the address without zeroing. To see how that can happen I'd need to see disassembly of jbd2_journal_try_to_free_buffers(). Anyway it looks like a very recent corruption or maybe event a CPU problem...
Honza
Effectively Jan after 3 days working 3.17 crash and suddenly working ram were declared bad ... Thus I swap out everything and install new motherboard, new cpu, new ram kit .. Let see if now everything will run smoothly :-) This simply confirm, if kernel crash stop screaming against developer and recheck carefully your hardware ;-) Thanks for the explanation you provide. it really help to confirm that old hardware (just 2 years old) was becoming crazy -- Bruno Friedmann Ioda-Net Sàrl www.ioda-net.ch openSUSE Member & Board, fsfe fellowship GPG KEY : D5C9B751C4653227 irc: tigerfoot -- To unsubscribe, e-mail: opensuse-kernel+unsubscribe@opensuse.org To contact the owner, e-mail: opensuse-kernel+owner@opensuse.org