Note: "permalinks" may not be as permanent as we would like,
direct links of old sources may well be a few messages off.
On Mon, Apr 14, 2008 at 06:47:09AM +0000, Chris Picton wrote: > Hi all > > I am trying to find out what would happen in the following situation: > > 1. GFS writes to its GNBD device. > GNBD client node writes to GNBD server node. > GNBD server writes to DRBD-primary. > DRBD begins to write to itself and to DRBD-secondary. > > Before DRBD completes the write to DRBD-secondary (thus, before it > returns since writes are synchronous) the DRBD-primary node looses power. > > The GNBD server dies with the power loss. > GNBD client node drops connection to the GNBD server. > > > 2. Heartbeat notices the death of DRBD-primary, switches the DRBD- > secondary to DRBD-primary, re-exports /dev/drbd0 via GNBD, and re-creates > the virtual IP which the GNBD client was connecting to. > > 3. The GNBD client writing on behalf of GFS reconnects. > > > Now, what happens to the write originally going to the DRBD volume? Will > the GNBD-client retry the write? I'm not too familiar with the GNBD client. but I guess it just has to retry, DRBD or not. if the GNBD connection is interrupted for server goes down/reboots/network has a hickup/switch reboots/whatever, and gets re-established: the GNBD needs to retry any pending write. Same for iSCSI or any other network storage. -- : Lars Ellenberg http://www.linbit.com : : DRBD/HA support and consulting sales at linbit.com : : LINBIT Information Technologies GmbH Tel +43-1-8178292-0 : : Vivenotgasse 48, A-1120 Vienna/Europe Fax +43-1-8178292-82 : __ please don't Cc me, but send to list -- I'm subscribed