On Wed, 15 Feb 2012, Alex Elder wrote: > Sage brought to my attention some lockdep reports that > were showing up due to XFS problems last night. I > discussed it on the XFS IRC channel and now have an > XFS patch I would like to test to verify it fixes it. > > But I am not sure what test I can run to reproduce the > problem. The warning came up on the testrados snap workloads, which means they are creating lots of snapshots/clones of objects, and probably triggering lots of sync(2) calls. Other than that, it's going to be some partial file overwrites, sparse files, and copies, and unlinks. We could run the test with filestore logging on to get a better picture of the workload, but I bet you can reproduce it with an ad hoc test (maybe fsx + sync in a loop?). Maybe there's something to infer from the warning itself.. sage -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
