Note: "permalinks" may not be as permanent as we would like,
direct links of old sources may well be a few messages off.
On 04/19/2011 08:52 AM, Jesse Angell wrote: > I've done some more testing and /dev/sdc appears to be completely healthy. I can fsck it without an issues. No write errors appear until drbd tries to sync. All IO tests I've done work without issue and no errors. > > I replaced the raid card and rebuilt the array and it tests healthy. The moment I try to connect with drbd though -- and those write errors start appearing and it won't become uptodate. > > Any ideas? Sure - would it be feasible to replace each and every disk in the faulty array? It doesn't seem conceivable that DRBD somehow conjures errors that aren't visible under different usage patterns. And even if it's the case after all, you want to get rid of that hardware. Regards, Felix