Date: Mon, 12 Sep 2011 13:58:23 -0500 (CDT) From: Bob Friesenhahn <bfriesen@simple.dallas.tx.us> To: "K. Macy" <kmacy@freebsd.org> Cc: freebsd-fs@freebsd.org Subject: Re: ZFS-lighttpd2-sendfile, too high IO Message-ID: <alpine.GSO.2.01.1109121356080.12948@freddy.simplesystems.org> In-Reply-To: <CAHM0Q_Piojt=Ob%2BsniMpaO9v1j_mBxCrKXFi6yxWktn2tnnSVQ@mail.gmail.com> References: <freemail.20110912131045.97846.1@xmldata03.freemail.hu> <F959B6B4287E4B7A9C55B34E7A2EDAC9@multiplay.co.uk> <CAHM0Q_Piojt=Ob%2BsniMpaO9v1j_mBxCrKXFi6yxWktn2tnnSVQ@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Mon, 12 Sep 2011, K. Macy wrote: > 2011/9/12 Steven Hartland <killing@multiplay.co.uk>: >> sendfile doesn't work as you might expect on zfs, its not zero copy due to >> the use of none buffer pool memory. >> >> You do get a benefit but it requires double the amount of memory to get it >> so we've disabled sendfile >> under nginx for zfs based hosts for this very reason. > > In my performance testing, sending from mmaped I/O on ZFS was > dramatically faster (> 2x) than sendfile. The problem is that since the zfs ARC and the backing memory used for the mapping are not the same, twice as much memory is used. This would not be good for streaming if the machine is short on RAM. Bob -- Bob Friesenhahn bfriesen@simple.dallas.tx.us, http://www.simplesystems.org/users/bfriesen/ GraphicsMagick Maintainer, http://www.GraphicsMagick.org/
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?alpine.GSO.2.01.1109121356080.12948>