[DRBD-user] heartbeat

Chip Burke cburke at innova-partners.com
Fri Feb 17 15:40:51 CET 2006

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


The best you will be able to do is to reduce your warning and dead times in
heartbeat. Personally I have a cluster running a warning at 25ms and dead at
100ms. You will always have a slight delay as it takes some time for the IPs
to switch over, the ARP broadcasts to get out, and httpd to start... there
is nothing you can do to speed that up other than get a faster machine. But
it fails over for me in roughly 1-2 seconds. Even when I was testing this
setup on some old Celeron 300s it was less than 5 seconds for a failover.

Chip


-----Original Message-----
From: drbd-user-bounces at lists.linbit.com
[mailto:drbd-user-bounces at lists.linbit.com] On Behalf Of paddy
Sent: Friday, February 17, 2006 9:37 AM
To: drbd-user at lists.linbit.com
Subject: Re: [DRBD-user] heartbeat

On Fri, Feb 17, 2006 at 09:36:06AM +0100, Christophe Mailhebuau wrote:
> Hi,
> 
> I need to reduce the time of resumption of
> service between two waiters apache.
> 
> i test to modify deadtime in ha.cf but waiting is too long, i need a
> realtime reaction

realtime means many different things, please clarify.

you might find something like 

http://en.wikipedia.org/wiki/Real-time_computing

useful


Regards,
Paddy
-- 
Perl 6 will give you the big knob. -- Larry Wall
_______________________________________________
drbd-user mailing list
drbd-user at lists.linbit.com
http://lists.linbit.com/mailman/listinfo/drbd-user





More information about the drbd-user mailing list