Re: Notebooks
Alan Cox (alan@lxorguk.ukuu.org.uk)
Wed, 19 Aug 1998 16:15:17 +0100 (BST)
> I think only for the initial packet. There doesn't seem to be a bailout
> mechanism further up the TCP "stack". A task with a connected stream
> socket, failing to read (busy doing something else), can quickly consume
> all available buffers if the connected peer keeps sending fragmented data.
Nope. Read the code. We account on memory usage, we enforce both window
limits and also absolute per socket memory quotas. We always have done
Alan
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.altern.org/andrebalsa/doc/lkml-faq.html