From: Robert Olsson Subject: Re: Route cache performance under stress Date: Mon, 2 Jun 2003 18:36:37 +0200 Sender: netdev-bounce@oss.sgi.com Message-ID: <16091.32021.75335.227150@robur.slu.se> References: <20030522.015815.91322249.davem@redhat.com> <20030522.034058.71558626.davem@redhat.com> <20030522114438.GD2961@netnation.com> <20030522.153330.74735095.davem@redhat.com> <20030529205125.GA30058@netnation.com> <16091.11735.721251.925522@robur.slu.se> <20030602151852.GA6070@netnation.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Cc: Robert Olsson , "David S. Miller" , netdev@oss.sgi.com, linux-net@vger.kernel.org, kuznet@ms2.inr.ac.ru Return-path: To: Simon Kirby In-Reply-To: <20030602151852.GA6070@netnation.com> Errors-to: netdev-bounce@oss.sgi.com List-Id: netdev.vger.kernel.org Simon Kirby writes: > This reminds me of the situation we experienced with the dst cache > overflowing in early 2.2 kernels. This was a long time ago, when our > traffic was only about 10 Mbits/second. We had recently upgraded from a > 2.0 kernel. The dst cache was overflowing due to a bug in the garbage > collector, and at the time, no messages were printed. It took me a > _long_ time to figure out why connections to a server I hadn't previously > connected to in a while would only work every so often, and not > immediately like they should. I'm affraid this approach will have a > similar effect, albeit (hopefully) only under an attack. We are given more work than we have resources for (max_size) what else than refuse can we do? But yes we have invested pretty much work already. Also remember we are looking into runs were 100% of incoming traffic has one new dst for every packet. So how is the situation in "real life"? In case of multiple devices at least NAPI gives all devs it's share. > Is it possible to have a dst LRU or a simpler approximation of such and > recycle dst entries rather than deallocating/reallocating them? This > would relieve a lot of work from the garbage collector and avoid the > periodic large garbage collection latency. It could be tuned to only > occur in an attack (I remember Alexey saying that the deferred garbage > collection was implemented to reduce latency in normal opreation). I don't see how this can be done. Others may? Cheers. --ro