From owner-freebsd-current  Mon Aug 19 13:59: 8 2002
Delivered-To: freebsd-current@freebsd.org
Received: from mx1.FreeBSD.org (mx1.FreeBSD.org [216.136.204.125])
	by hub.freebsd.org (Postfix) with ESMTP
	id 36A4337B400; Mon, 19 Aug 2002 13:59:06 -0700 (PDT)
Received: from apollo.backplane.com (apollo.backplane.com [216.240.41.2])
	by mx1.FreeBSD.org (Postfix) with ESMTP
	id 3A1BA43E91; Mon, 19 Aug 2002 13:59:04 -0700 (PDT)
	(envelope-from dillon@apollo.backplane.com)
Received: from apollo.backplane.com (localhost [127.0.0.1])
	by apollo.backplane.com (8.12.5/8.12.4) with ESMTP id g7JKx3dc079177;
	Mon, 19 Aug 2002 13:59:03 -0700 (PDT)
	(envelope-from dillon@apollo.backplane.com)
Received: (from dillon@localhost)
	by apollo.backplane.com (8.12.5/8.12.4/Submit) id g7JKx2j4079175;
	Mon, 19 Aug 2002 13:59:02 -0700 (PDT)
	(envelope-from dillon)
Date: Mon, 19 Aug 2002 13:59:02 -0700 (PDT)
From: Matthew Dillon <dillon@apollo.backplane.com>
Message-Id: <200208192059.g7JKx2j4079175@apollo.backplane.com>
To: Bruce Evans <bde@zeta.org.au>
Cc: "Semen A. Ustimenko" <semenu@FreeBSD.ORG>,
	<freebsd-current@FreeBSD.ORG>, Maxim Konovalov <maxim@FreeBSD.ORG>,
	Robert Watson <rwatson@FreeBSD.ORG>, <dg@FreeBSD.ORG>
Subject: Re: sendfile() change (Was: Re: cvs commit: src/sys/kern uipc_syscalls.c)
References:  <20020820040605.N20882-100000@gamplex.bde.org>
Sender: owner-freebsd-current@FreeBSD.ORG
Precedence: bulk
List-ID: <freebsd-current.FreeBSD.ORG>
List-Archive: <http://docs.freebsd.org/mail/> (Web Archive)
List-Help: <mailto:majordomo@FreeBSD.ORG?subject=help> (List Instructions)
List-Subscribe: <mailto:majordomo@FreeBSD.ORG?subject=subscribe%20freebsd-current>
List-Unsubscribe: <mailto:majordomo@FreeBSD.ORG?subject=unsubscribe%20freebsd-current>
X-Loop: FreeBSD.ORG


:>     call VOP_GETPAGES() on a block of pages instead of just one.  I'm
:>     guessing that is not being done because it's about 100 lines of code
:>     to do it right.  It's easier just to call vn_rdwr() and let the
:>     system do the clustering.
:
:This argument seems to apply to exec_map_first_pages() too.  It does
:its own blocking to get up to VM_INITIAL_PAGEIN (normally 16) pages
:using only about 50 lines of code, but does this slightly wrong.  It
:doesn't honor the device limit of si_iosize_max, unlike filesystem
:code.  This used to break exec on zip drives (si_iosize_max used to
:be 32K, but VM_INITIAL_PAGEIN pages is 64K bytes on i386's).
:
:Bruce

    Yes, it definitely applies.  The vm_page_grab() can be replaced
    with a vm_page_lookup() sequence similar to what we find in 
    do_sendfile(), and everything inside the 'if ((ma[0]->valid & ...' 
    can be ripped out and replaced with a single vn_rdwr() call, 
    if (error) test, and then loop back up to the vm_page_lookup().

    There are enough parallels between the sendfile code and
    the exec_map_first_page() code that a significant portion of
    both procedures could be shifted to its own procedure which does
    the read-ahead and returns a single, valid, busied page.

    I am not volunteering to do this, though, I already have a full plate.

					-Matt
					Matthew Dillon 
					<dillon@backplane.com>

To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-current" in the body of the message