Note: "permalinks" may not be as permanent as we would like,
direct links of old sources may well be a few messages off.
On Thu, Sep 10, 2009 at 05:44:42PM +0200, Gianluca Cecchi wrote: > tried the "drbdadm attach r0" command but I get: > > Sep 10 17:38:45 virtfedbis kernel: block drbd0: disk( Diskless -> Attaching > ) > Sep 10 17:38:45 virtfedbis kernel: block drbd0: Found 6 transactions (244 > active extents) in activity log. > Sep 10 17:38:45 virtfedbis kernel: block drbd0: Method to ensure write > ordering: barrier > Sep 10 17:38:45 virtfedbis kernel: block drbd0: max_segment_size ( = BIO > size ) = 32768 > Sep 10 17:38:45 virtfedbis kernel: block drbd0: recounting of set bits took > additional 2 jiffies > Sep 10 17:38:45 virtfedbis kernel: block drbd0: 0 KB (0 bits) marked > out-of-sync by on disk bit-map. > Sep 10 17:38:45 virtfedbis kernel: block drbd0: Marked additional 920 MB as > out-of-sync based on AL. > Sep 10 17:38:45 virtfedbis kernel: end_request: I/O error, dev cciss/c0d0, > sector 0 this is interessting. "should not happen", and happens below drbd. so something actually is not as it should be at the cciss level, or at some other involved hardware level. > Sep 10 17:38:45 virtfedbis kernel: block drbd0: meta data flush failed with > status -95, disabling md-flushes > Sep 10 17:38:45 virtfedbis kernel: block drbd0: disk( Attaching -> > Negotiating ) > Sep 10 17:38:45 virtfedbis kernel: block drbd0: drbd_sync_handshake: > Sep 10 17:38:45 virtfedbis kernel: block drbd0: self > FFEDAA5E725D8157:13925DF660B57F5D:0DB564243F5AA9A3:377245292BBD1112 > bits:235520 flags:0 > Sep 10 17:38:45 virtfedbis kernel: block drbd0: peer > A0332E51B243BEE1:FFEDAA5E725D8157:13925DF660B57F5D:0DB564243F5AA9A3 > bits:105320 flags:0 > Sep 10 17:38:45 virtfedbis kernel: block drbd0: uuid_compare()=-1 by rule 50 > Sep 10 17:38:45 virtfedbis kernel: block drbd0: conn( Connected -> WFBitMapT > ) disk( Negotiating -> Outdated ) > Sep 10 17:38:45 virtfedbis kernel: block drbd0: conn( WFBitMapT -> > WFSyncUUID ) > Sep 10 17:38:45 virtfedbis kernel: block drbd0: helper command: > /sbin/drbdadm before-resync-target minor-0 > Sep 10 17:38:45 virtfedbis kernel: block drbd0: helper command: > /sbin/drbdadm before-resync-target minor-0 exit code 0 (0x0) > Sep 10 17:38:45 virtfedbis kernel: block drbd0: conn( WFSyncUUID -> > SyncTarget ) disk( Outdated -> Inconsistent ) > Sep 10 17:38:45 virtfedbis kernel: block drbd0: Began resync as SyncTarget > (will sync 1363360 KB [340840 bits set]). > Sep 10 17:38:48 virtfedbis kernel: block drbd0: Resync aborted. > Sep 10 17:38:48 virtfedbis kernel: block drbd0: conn( SyncTarget -> > Connected ) disk( Inconsistent -> Failed ) > Sep 10 17:38:48 virtfedbis kernel: block drbd0: Local IO failed. > Detaching... detaches "without visible reason"... I've seen similar symptoms before, and it could be worked around by disabling offloading settings on the NICs used for the replication ;) I know, that interaction sounds a bit far-fetched, but those are the facts. # to view offload settings ethtool -k eth7 # to switch them all off: ethtool -K eth7 rx off tx off sg off tso off -- : Lars Ellenberg : LINBIT | Your Way to High Availability : DRBD/HA support and consulting http://www.linbit.com DRBD® and LINBIT® are registered trademarks of LINBIT, Austria. __ please don't Cc me, but send to list -- I'm subscribed