Just Launched: You can now import projects and releases from Google Code onto SourceForge
We are excited to release new functionality to enable a 1-click import from Google Code onto the Allura platform on SourceForge. You can import tickets, wikis, source, releases, and more with a few simple steps. Read More
Several times over the last week I've seen something new. aprsd suddenly
begins conuming all the available CPU time on the primary findu machine.
There are three processes sharing in this load. The input queue's
reported by netstat -t are in the 70k range for several connections,
making me think the server isn't processing data from these ports.
However, the server is still processing some data, because the findu
parser (the only connection to the server) is still getting data, there
are no gaps in the database, and the watchdog is not triggered.
When I discover it my first priority is returning the server to a
functioning state, which means executing an aprsd.init stop, and letting
the watchdog restart. I haven't looked too closely at the situation
because if this priority.
Anybody else ever seen anything like it?
On a related issue, is there an update on the filtering plans? The fact
that this filters out long posits is the last remaining thing keeping me
from returning the primary server to duty as http://www.findu.com. I really
would like to do it, the secondary server just doesn't have the disk
throughput the load requires these days...