Date: Wed, 10 Apr 2013 22:12:45 +0200 From: Sebastian Feld <sebastian.n.feld@gmail.com> To: Wojciech Puchar <wojtek@wojtek.tensor.gdynia.pl> Cc: freebsd-hackers@freebsd.org, Benjamin Kaduk <kaduk@mit.edu> Subject: Re: Multiple page size support on FreeBSD? Message-ID: <CAHnbEGLt3ngB-Gv6OBYzmm60gtvwpe1fS%2BMYK8OQn7AuBiXhCQ@mail.gmail.com> In-Reply-To: <alpine.BSF.2.00.1304101947470.19441@wojtek.tensor.gdynia.pl> References: <CAHnbEGJuo9Jvskxaog0xLVM_LOse695b4E3fKae7YufOAVZuBg@mail.gmail.com> <alpine.GSO.1.10.1304072319300.9389@multics.mit.edu> <alpine.BSF.2.00.1304081238580.6013@wojtek.tensor.gdynia.pl> <201304101006.13960.jhb@freebsd.org> <alpine.BSF.2.00.1304101947470.19441@wojtek.tensor.gdynia.pl>
next in thread | previous in thread | raw e-mail | index | archive | help
On Wed, Apr 10, 2013 at 7:49 PM, Wojciech Puchar <wojtek@wojtek.tensor.gdynia.pl> wrote: >> How do your tests work? Do you examine PTEs directly to check for >> superpages >> or are you relying on the vm.pmap.pde sysctls? > > > the later. > > anyway - algorithm described on list - that heuristics detects consecutive > page access doesn't really help the urgent case - RANDOM access to large > amount of memory. > > sequential access will get minimal improvement. > > IMHO the only way that really make sens is to add options to madvise to give > kernel information about usage. Solaris has an API to control the usage for large pages, search for MPSS - multiple page size support. It consists of APIs in madvise, and /usr/bin/pagesize -a to list all available page sizes, and other stuff. Since this has been established since at least Solaris 9 (and 10) and is used by database and HPC software, it might be a good starting point.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CAHnbEGLt3ngB-Gv6OBYzmm60gtvwpe1fS%2BMYK8OQn7AuBiXhCQ>