[DRBD-user] how long does drbd device do sync

Lars Ellenberg lars.ellenberg at linbit.com
Thu May 10 14:10:33 CEST 2007

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, May 10, 2007 at 01:05:54PM +0100, Mark Watts wrote:
> 
> > > It can be one of the following three:
> > >
> > >    C: write IO is reported as completed, if we know it has
> > >       reached _both_ local and remote DISK.
> > >       * for critical transactional data.
> >
> >        * for most cases.
> 
> Most ?

what is your question?

> > >    B: write IO is reported as completed, if it has reached
> > >       local DISK and remote buffer cache.
> >
> >        * for cases were you can live with possible data loss
> >          of the last few milliseconds in case of failover
> >
> > we should improve our documented recommendations :)
> >
> > >    A: write IO is reported as completed, if it has reached
> > >       local DISK and local tcp send buffer. (see also sndbuf-size)
> > >       * for high latency networks
> > >
> > > If you choose C, then write a file to the DRBD'd filesystem,
> > > the write won't
> >
> > and then fsync! otherwise the write goes
> > just into the local nodes cache,
> > and drbd knows nothing about it yet...
> 
> Do you bypass this requirement my mounting your filesystem sync ?

maybe (read: if your filesystem and kernel and whatnot behave like
I interpret what is described in the man page of mount).
but you don't want to do that for performance reasons.
you want to fix your application instead,
to do fsync where fsync is necessary.

-- 
: Lars Ellenberg                            Tel +43-1-8178292-0  :
: LINBIT Information Technologies GmbH      Fax +43-1-8178292-82 :
: Vivenotgasse 48, A-1120 Vienna/Europe    http://www.linbit.com :
__
please use the "List-Reply" function of your email client.



More information about the drbd-user mailing list