> On 15 Sep 2017, at 02:39, Two Spirit <twospirit6905@xxxxxxxxx> wrote: > >> the unfound object is the tail object of mds log. what I did was finding the position of latest valid log entry and set log write_pos to it > > Thanks for the help. The file system came back up after the scrub, I > mounted it, started copying files back on to it and within 1-2 hours > the file system went back degraded. Is this possibly due to the same > bug you found with mds not replay? Do I need to wait for a patch to > continue testing this? What do you mean fs degraded, mds damaged or mds crashed? Your fs hasn’t been completely fixed. It’s possible that mds encountered some inconsistent metatda. I didn’t find any bug in mds replay code. you had an unfound mds log object. mds were supposed to go to damaged state in that case. ping me at the same irc channel Regards Yan, Zheng-- 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
