OK. That makes sense. The problem is now, that we/I promoted some
formerly arch-private metrics to the global state and that they are now
in different positions in the array. This would explain why Linux/2.5.4
and Linux/2.5.8 now conflict.
roger. if any new metrics were added to the end of the
>
> just as an example. as metric we're added they were put at the end
> of
> the array and backward compatibility was maintained. older gmond
> would
> just ignore data with an index number greater than they knew about
> but
> all the other index numbers where exactly the same.
>
> then we
FYI, I've verified that the latest ganglia snapshot works on FreeBSD 5
(actually 6-CURRENT, but they are mostly the same at the moment.)
I did notice one small bug. If /etc/gmetad.conf doens't exist, you
get a nice warning followed by a core dump instead of an exit.
-- Brooks
--
Any statement
sure you did not want to say "MICRO" here ?
oops. yeh micro.
MICRO again :-)
oops. yeh micro again.
apparently, this is not completely true. As I wrote before, the
current 2.5.8 gmond for Linux (adding cpu_wio and cpu_intr/sintr) does
not live well together with older gmonds on the sa
Hi Matt,
--- Matt Massie <[EMAIL PROTECTED]> wrote:
> I just altered our configure.in script (you'll need to do a cvs
> update)
> to ensure that we have less versioning confusion in the future. Here
> is
> the section of variables that must be altered for each release...
>
> > ## BEGIN RELEA
