Date: Wed, 26 Aug 1998 04:19:40 +0000 (GMT) From: Terry Lambert <tlambert@primenet.com> To: ben@rosengart.com Cc: tlambert@primenet.com, mike@smith.net.au, michaelh@cet.co.jp, gpalmer@FreeBSD.ORG, chuckr@glue.umd.edu, freebsd-current@FreeBSD.ORG Subject: Re: Threads across processors Message-ID: <199808260419.VAA01004@usr07.primenet.com> In-Reply-To: <Pine.GSO.4.02.9808252219230.16068-100000@echonyc.com> from "Snob Art Genre" at Aug 25, 98 10:23:47 pm
next in thread | previous in thread | raw e-mail | index | archive | help
> > A dirty little secret is that SYSV SHM in FreeBSD is much faster > > than mmap, because pages backed by anonymous pages instead of a > > vnode pager object do not have to be written through... > > What about this? From mmap(2): > > MAP_ANON Map anonymous memory not associated with any specific file. > The file descriptor used for creating MAP_ANON must be -1. > The offset parameter is ignored. Memory mapped this way can only be shared between a parent process and children, and then only if marked for inheritance. This is a hell of a lot less useful that SYSV SHM, especially if the memory is to be attached by a non-child process for the purpose of status reporting and/or control (for example). Terry Lambert terry@lambert.org --- Any opinions in this posting are my own and not those of my present or previous employers. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-current" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199808260419.VAA01004>