Hello, J. R. Okajima & List I think I have encircled the issue:
The Problem disappears when I boot the server into Kernel 3.2 instead of 3.16. So your indication given below was right. It does not disappear when I change nfs export options from sync to async, as mentioned in some (older) internet threads. I'll try to file a bug report with debian, I think. Wolfgang Rosner Am Montag, 9. Februar 2015 18:26:14 schrieben Sie: > > it's all on a single ext4, ordinary consumer type SATA HD > > > > root@.....# mount > > ..... > > /dev/sda2 on / type ext4 (rw,relatime,errors=remount-ro,data=ordered) > > On my debian-3.16.7-ckt2-1~bpo70+1 kernel, I can see ext4 via nfs4 > blocked a long time. It blocked at open(O_TRUNC) and sleep_on_page(). > While I don't investigate deeper yet, this version of ext4 or > io-scheduler is suspcious. But what I saw might be different from your > problem. > > If you can, try another version of kernel or ext4. For example, > - another debian kernel > - use ext2 instead of ext4 > > I will try other tests more. -- ------------------------------------------------------------------------------ Dive into the World of Parallel Programming. The Go Parallel Website, sponsored by Intel and developed in partnership with Slashdot Media, is your hub for all things parallel software development, from weekly thought leadership blogs to news, videos, case studies, tutorials and more. Take a look and join the conversation now. http://goparallel.sourceforge.net/
