Ceph

A whole bunch of nodes have inconsistent PG::Info and log bounds. I don't have logs, so I'm not sure how it happened.

2011-05-20 08:18:22.512454 7fd5374d2720 osd2 10735 pg[4.5( v 933'33 lc 897'29 (933'33,933'33]+backlog n=15 ec=183 les=10589 10665/10696/10696) [] r=0 (info mismatch, log(0'0,0'0]) lcod 0'0 mlcod 0'0 inactive] read_log 0~1506
2011-05-20 08:18:22.512639 7fd5374d2720 osd2 10735 pg[4.5( v 933'33 lc 897'29 (933'33,933'33]+backlog n=15 ec=183 les=10589 10665/10696/10696) [] r=0 (log bound mismatch, actual=[183'1,897'29]) lcod 0'0 mlcod 0'0 inactive] read_log checking for missing items over interval (89
7'29,933'33]
2011-05-20 08:18:22.512667 7fd5374d2720 osd2 10735 pg[4.5( v 933'33 lc 897'29 (933'33,933'33]+backlog n=15 ec=183 les=10589 10665/10696/10696) [] r=0 (log bound mismatch, actual=[183'1,897'29]) lcod 0'0 mlcod 0'0 inactive] read_log done

this is on latest stable branch