From owner-freebsd-questions@freebsd.org Fri Oct 2 14:43:42 2015 Return-Path: Delivered-To: freebsd-questions@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id EE31FA0DFED for ; Fri, 2 Oct 2015 14:43:42 +0000 (UTC) (envelope-from merritt.alex@gmail.com) Received: from mail-yk0-x22a.google.com (mail-yk0-x22a.google.com [IPv6:2607:f8b0:4002:c07::22a]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id B236F1C82 for ; Fri, 2 Oct 2015 14:43:42 +0000 (UTC) (envelope-from merritt.alex@gmail.com) Received: by ykdg206 with SMTP id g206so110922714ykd.1 for ; Fri, 02 Oct 2015 07:43:42 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:from:date:message-id:subject:to:content-type; bh=YmufYs625WPRE7YPpY2P8Buj+HlLjkT98ogI9czYVL4=; b=e1zjxhyyWLm7VVMORH1zAo+16FoDcHiTWwp7AVDgrcOcJgPaQT2jJGyWQllVVzfthl eQRszP/Ad9vLaimc24WOfF31PY6eTqEybSXQ4TrQ0zg7kxhzIidObbMiOs6Ac/mt4LgY TsJ2GQj7Kb0Z8ITw270BO5nMPBg6JRuVOfqfg5VyL3V7GLwY4hCQH0QZrUxvZxcuC6AV FnFmJkc/LG483eped/rCeq+SSEYpEo6JDzwBinChBv88Q5xSMkmtZvJnp5fyThssINAA /tSl1MUnDMSqjVq7wlPD+uQs7bPj8skl0I4dV16/hTBOaUXmA0rxRv8LTGbXfe8F+CBB zZjQ== X-Received: by 10.170.124.81 with SMTP id q78mr13691161ykb.124.1443797021956; Fri, 02 Oct 2015 07:43:41 -0700 (PDT) MIME-Version: 1.0 Received: by 10.37.2.194 with HTTP; Fri, 2 Oct 2015 07:43:12 -0700 (PDT) From: Alex Merritt Date: Fri, 2 Oct 2015 10:43:12 -0400 Message-ID: Subject: Explicit superpage allocation To: freebsd-questions Content-Type: text/plain; charset=UTF-8 X-Content-Filtered-By: Mailman/MimeDel 2.1.20 X-BeenThere: freebsd-questions@freebsd.org X-Mailman-Version: 2.1.20 Precedence: list List-Id: User questions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 02 Oct 2015 14:43:43 -0000 Hi all, mmap(2) states with first use of a memory region with backing frames not yet allocated and an appropriate alignment, the kernel will automatically use a larger page when given MAP_ALIGNED_SUPER. Is there a method to explicitly request a specific page size for an anonymous memory region? I want to perform measurements using 2MB-backed regions and 1GB-backed regions, but do not want the kernel to make arbitrary decisions underneath me. I am using 10.2 and Intel hardware. Thanks, Alex