Eskimo North

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]


     Ultra1 froze and had to be rebooted at about 8:55 AM PST today

     This is a backbone capacity issue at present.  When the amount of data
requested, mostly web hits, but also people getting e-mail via pop-3, etc,
exceeds the backbone capacity Linux buffers the data and eventually exhausts
all memory on the box.

     I had hoped three T1's would be enough to make it through the busy season
this year (last year we had two) but it's not.  I've got another one coming in
to address reliability problems with Sprint's peering arrangements so that will
provide some relief soon.