Date: Sun, 6 Jun 2004 15:12:49 -0500 From: Alan Cox <alc@cs.rice.edu> To: Alexander Leidinger <Alexander@Leidinger.net> Cc: current@freebsd.org Subject: Re: comments in the page coloring options in /sys/conf/NOTES Message-ID: <20040606201249.GH24461@cs.rice.edu> In-Reply-To: <20040606142446.2900a97e@Magellan.Leidinger.net> References: <20040606142446.2900a97e@Magellan.Leidinger.net>
next in thread | previous in thread | raw e-mail | index | archive | help
On Sun, Jun 06, 2004 at 02:24:46PM +0200, Alexander Leidinger wrote: > Hi, > > the comments about the page coloring in the VM system seem to talk about > L2/L1 cache size combinations, e.g. PQ_CACHESIZE=512 for a 512k/16k > cache. The comment above the PQ_CACHESIZE line just talks about the size > of the L2 cache. > > If it indeed talks about L2/L1 combinations, we should make it explicit. > And what about a 512k/8k combination? > > If it just talks about the L2 cache size, what is the meaning of the > second number? My recent commit fixed a "syntax" error in the comments, specifically, a reference to a missing macro. The comments are, however, still "semantically" broken: 1. Cache size alone does not correctly determine the number of colors, except for direct map caches. The correct formula is (cache size in bytes / page size in bytes) / degree of cache associativity Thus, the comments would lead one to configure his/her system with too many colors. (Relative to configuring a system with too few colors, this is not so bad.) 2. The references to L1 should be removed. They are historical leftovers. To conclude, I would be thrilled if someone wanted to work on automating this. I don't think it's reasonable to expect users to configure this. Alan
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20040606201249.GH24461>