Please don't reply to lustre-devel. Instead, comment in Bugzilla by using the following link: https://bugzilla.lustre.org/show_bug.cgi?id=11229
Created an attachment (id=9479) Please don't reply to lustre-devel. Instead, comment in Bugzilla by using the following link: --> (https://bugzilla.lustre.org/attachment.cgi?id=9479&action=view) fix EOF condition in llog_lvfs_next_block My new test 30 found an unrelated bug: Feb 1 13:48:23 cfs21 kernel: Lustre: lustre-client-c568e2b8.llite: set param max_read_ahead_whole_mb to 10 Feb 1 13:48:23 cfs21 kernel: Lustre: 22735:0:(llog.c:278:llog_process()) invalid length 0 in llog record for index -83819167/60 This happens when llog_process tries to read past the end of valid data; it doesn't actually mess anything up, but does generate scary error messages. The attached patch fixes it. _______________________________________________ Lustre-devel mailing list [email protected] https://mail.clusterfs.com/mailman/listinfo/lustre-devel
