[Dxspider-support] Cluster hangs
T3
T3 at semarg.ath.cx
Sun Mar 6 14:16:06 GMT 2005
I think were going tin the wrong direction with this
the problem are the hangups, hangups are caused from extreme fast access
of cluster files, and the slow perl.
*if* thats what the problem is, im seeing more excess traffic slam the
cluster
while its trying to process spots
ive been watching backbone traffic and the PC16 and 17 are out of
control along with dupe file access
its next to impossible to RF backbone link now even at 9.6K to another
cluster, My 9.6K radio is
having trouble with the excess backbone fat. If this don't get cleared
up. I'll be forced to Jump
ship to another flavor of cluster. to try to save these expensive radio
equipment.
what ive been seeing for a year now in windows (and dealing with it) is
now going on in Linux Clusters
Yes we made some improvement, but its starting to look like we steped
backwards a couple of
steps with the basic platform, forgetting the heavy usage during contest
time.
Tony
N1LDY
dg8lav at amsat.org wrote:
>Hi!
>
>
>>Yes happening here - but only during periods of very high spot activity.
>>It
>>happened during the ARRL CW contest and then not since until the ARRL SSB
>>contest this weekend when it has occurred twice so far. I'm on the same
>>build as you but I am running in Windows.
>>
>>
>
>yes, it's a problem with the "high" load of the system. Perl is not very fast in
>case of high volumes of datas. Maybe a memory leak?
>
>I had two hang up yesterday and i noticed a very high counter of dupes and
>cluster loops at the same time. The load on the unix machines had 12.2 at the
>top, which is very high (normal is 0.3).
>
>73s Karl
>dg8lav
>
>
>
More information about the Dxspider-support
mailing list