[DRBD-user] recovering from "Local IO failed. Detaching..."

Lars Ellenberg lars.ellenberg at linbit.com
Wed Sep 16 17:23:21 CEST 2009

Note: "permalinks" may not be as permanent as we would like,
direct links of old sources may well be a few messages off.


On Wed, Sep 16, 2009 at 04:20:12PM +0200, Gianluca Cecchi wrote:
> With drbd git installed on peer and rebooting it, while maintaining the
> source as 8.3.3rc2 it succeeds in synchronization now.

ok.

> Do the messages regarding " local disk flush failed with status -95" suggest
> to anyway applying all the changes:
> no-disk-barrier;
> no-disk-flushes;
> no-md-flushes;

yes.

> drawbacks about these?

well, since barriers or flushes apparently are not supported
(95: EOPNOTSUPP), DRBD will disable them after the first failure,
effectively enabling the "no-*" options above, falling back to
"drain" method.

the regression has been in this "detect first barrier failure,
retry and enable fallback" code. I tried to fix a potential endless
loop, thereby introducing that regression by a typo.

> Let's go and see if it is stable now....

keep us posted.

-- 
: 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



More information about the drbd-user mailing list