[Gluster-devel] Shall we revert quota-anon-fd.t?

Justin Clift justin at gluster.org
Wed Jun 11 23:12:47 UTC 2014


On 11/06/2014, at 9:01 AM, Vijay Bellur wrote:
<snip>
> I have seen dd being in uninterruptible sleep on b.g.o. There are also instances [1] where anon-fd-nfs has run for close to 6000+ seconds. This definitely points to the nfs deadlock.

A few of the rackspace regression runs seem to be getting
stuck on bug/bug-1095097.t.  They run forever, never finishing:

  [19:18:01] ./tests/bugs/bug-1095097.t ........................ ok       16 s
  8+0 records in
  8+0 records out
  41943040 bytes (42 MB) copied, 0.304967 s, 138 MB/s
  8+0 records in
  8+0 records out
  41943040 bytes (42 MB) copied, 0.395341 s, 106 MB/s
  1+0 records in
  1+0 records out
  1024 bytes (1.0 kB) copied, 0.00233259 s, 439 kB/s
  4+0 records in
  4+0 records out
  20971520 bytes (21 MB) copied, 0.333085 s, 63.0 MB/s
  1+0 records in
  1+0 records out
  5242880 bytes (5.2 MB) copied, 0.0986338 s, 53.2 MB/s

I've been aborting these ones manually, after its obvious they're
not working.

Could this weird behaviour be related to what you're mentioning
above?

+ Justin

Example ones for anyone interested:

  http://build.gluster.org/job/rackspace-regression/90/console
  http://build.gluster.org/job/rackspace-regression/88/console

--
GlusterFS - http://www.gluster.org

An open source, distributed file system scaling to several
petabytes, and handling thousands of clients.

My personal twitter: twitter.com/realjustinclift



More information about the Gluster-devel mailing list