Note: "permalinks" may not be as permanent as we would like,
direct links of old sources may well be a few messages off.
On Tue, Mar 08, 2011 at 04:51:19PM -0500, Cory Coager wrote: > On 03/08/2011 03:34 PM, Cory Coager wrote: > >Yes, that was quite a book to read. Sounds like a big mess that > >is still unresolved. I guess I should hope that my only problem > >is a broken NIC and not something else going on. I'm going to try > >to add some NIC's to the server when I find a time window and see > >if that fixes the problem. > Question, would disabling receive/transmit offloading on the NIC be > a sufficient enough test to rule out a bad NIC? A sufficient test to rule out a bad NIC was to upgrade to drbd 8.3.10, and see if the sending side (primary) logs "Digest mismatch, buffer modified by upper layers during write: ..." for every digest-mismatch on the receiving side. -- : Lars Ellenberg : LINBIT | Your Way to High Availability : DRBD/HA support and consulting http://www.linbit.com