Hi Sage, On Wed, 2010-10-27 at 23:06 -0600, Sage Weil wrote: > Hi Jim, > > It turns out Henry's problem was actually cause by a bad fix on my part, > d91f2438 in ceph-client.git. (Unfortunately that made it into 2.6.36!) > Reverting that commit fixed things for him. > > I pushed that revert to the ceph-client.git master branch, or you can > revert it yourself. master also includes everything that's been merged > for 2.6.37-rc1, so you may want to revert it yourself and keep the 2.6.36 > stuff. > > In any case, please let us know if it fixes your problem. Thanks, reverting d91f2438 fixes my problem. To be clear, I'm running 2.6.36 + for-linus (as of commit efa4c1206ea) + d91f2438 reverted against unstable branch server code as of commit c1a6ee574b. -- Jim > In the > meantime, I'll try to figure out what it was I thought I was fixing in the > first place! :( > > sage > > > On Tue, 26 Oct 2010, Jim Schutt wrote: > > > > > Hi, > > > > On Tue, 2010-10-26 at 13:25 -0600, Sage Weil wrote: > > > On Tue, 26 Oct 2010, Jim Schutt wrote: > > > > Hi, > > > > > > > > I'm testing a file system with 10 osd daemons, > > > > 1 mds daemon, 1 mon daemon. > > > > > > > > Client code is 2.6.36 + current for-linus branch > > > > Server code is unstable branch, 2a3e73bb325f. > > > > > > > > After mounting 64 clients, I had each write its own 512 MiB > > > > file with dd, with all files being created in the same directory. > > > > > > > > A few seconds after they completed, from another client (not one > > > > of the 64 writers) I did "ls -l" on the directory holding the > > > > new files. > > > > > > > > After several minutes, it still hasn't returned; > > > > all the daemons are still running. > > > > > > This looks just like a client bug I'm tracking down with Henry Chang. > > > I'll try again to reproduce it in my environment (as that should speed > > > up > > > the debugging process anyway!). > > > > Cool! Let me know if it turns out there's some way for > > me to help further on this. > > > > -- Jim > > > > > > > > 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 > > > > > -- 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
