Re: load_region() problem :(

[roemer@informatik.uni-frankfurt.de]

>  Now perhaps someone here can help me 'cause I'm desperate now. Situation is
> that I had a heavy net-session just some hours ago with lots of logins (Benni,
> can you hear me? ;) and daemon calls. This very quickly leads to a terribly
> fragmented memory. Sad enough, but uncureable though.

I cannot remember at the moment whether kmalloc() gets its regions from the
top of memory or from the next free page?

In the latter case fragmentation might be caused by TCP sockets. On socket()
a control structure is allocated using kmalloc(), but is not released
immediatly after the program that has created it exits, because it has to
stay alive for up to 2 minutes in tIMEWAIT state.

The bufferspace in MintNet used for storing packets is also allocated in
32k hunks using kmalloc() and they too aren't necessarily delted when process
exits.

Kay.
--
Kay Roemer              roemer@informatik.uni-frankfurt.de
"If I ever meet ..."    http://www.uni-frankfurt.de/~roemer/
"... myself I'll hit myself so hard I won't know who hit me" (Zaphod)