Re: [hybi] Background info: Properties of sendfile()
Greg Wilkins <gregw@webtide.com> Fri, 06 August 2010 04:18 UTC
Return-Path: <gregw@webtide.com>
X-Original-To: hybi@core3.amsl.com
Delivered-To: hybi@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id 77F4B3A6888 for <hybi@core3.amsl.com>; Thu, 5 Aug 2010 21:18:18 -0700 (PDT)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -1.755
X-Spam-Level:
X-Spam-Status: No, score=-1.755 tagged_above=-999 required=5 tests=[AWL=0.222, BAYES_00=-2.599, FM_FORGED_GMAIL=0.622]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id czY6Vz2TNHBt for <hybi@core3.amsl.com>; Thu, 5 Aug 2010 21:18:16 -0700 (PDT)
Received: from mail-fx0-f44.google.com (mail-fx0-f44.google.com [209.85.161.44]) by core3.amsl.com (Postfix) with ESMTP id C7D2B3A68B0 for <hybi@ietf.org>; Thu, 5 Aug 2010 21:18:15 -0700 (PDT)
Received: by fxm16 with SMTP id 16so3043024fxm.31 for <hybi@ietf.org>; Thu, 05 Aug 2010 21:18:46 -0700 (PDT)
MIME-Version: 1.0
Received: by 10.223.114.9 with SMTP id c9mr11979991faq.59.1281068326292; Thu, 05 Aug 2010 21:18:46 -0700 (PDT)
Received: by 10.223.57.12 with HTTP; Thu, 5 Aug 2010 21:18:46 -0700 (PDT)
In-Reply-To: <20100806024316.GK27827@shareable.org>
References: <4C5B1695.6070704@gmx.de> <F8E2F702-9F74-4316-B3B2-D5A731409ABF@apple.com> <4C5B2029.90403@gmx.de> <AANLkTim1WeCRfcPxXUNQcVhb4+t_TtDQDv2bXaxOQ=bk@mail.gmail.com> <01098AD0-FBF4-4A61-B565-947C95722BAA@apple.com> <AANLkTi=qQSND5BvUP5+P=wJ7E8SG6NncGZH8U8+VYwZ0@mail.gmail.com> <20100806004907.GF27827@shareable.org> <C0FC87B7-C51C-4B36-BC16-DBDB0B00A20F@gbiv.com> <20100806012845.GI27827@shareable.org> <AANLkTi=GQOmgtg23XkGSc8NG5RDJP5wVY83P1VcG2AJZ@mail.gmail.com> <20100806024316.GK27827@shareable.org>
Date: Fri, 06 Aug 2010 14:18:46 +1000
Message-ID: <AANLkTin6qt8PQ-AUWOzdFsOdG=P4zDY+b2jPrHDoSxTG@mail.gmail.com>
From: Greg Wilkins <gregw@webtide.com>
To: Jamie Lokier <jamie@shareable.org>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Cc: "Roy T. Fielding" <fielding@gbiv.com>, "hybi@ietf.org" <hybi@ietf.org>
Subject: Re: [hybi] Background info: Properties of sendfile()
X-BeenThere: hybi@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: Server-Initiated HTTP <hybi.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/hybi>, <mailto:hybi-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/hybi>
List-Post: <mailto:hybi@ietf.org>
List-Help: <mailto:hybi-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/hybi>, <mailto:hybi-request@ietf.org?subject=subscribe>
X-List-Received-Date: Fri, 06 Aug 2010 04:18:18 -0000
On 6 August 2010 12:43, Jamie Lokier <jamie@shareable.org> wrote: > Greg Wilkins wrote: >> On 6 August 2010 11:28, Jamie Lokier <jamie@shareable.org> wrote: >> For jetty using java's file mapped buffers, we've encountered 2 key >> problems that cause us to turn it off. > > Little note: Mapped buffers aren't sendfile (unless they aren't what > they sound like; I don't know Java too well). Assuming they're mmap() > plus send(), they are a different technique that achieves _some_ of > the same benefits. Mapped buffers reduce memory use and some copying, > but don't result in sockets sharing the same memory, nor eliminate > copying, nor are they affected in the same way by NIC hardware > acceleration constraints - unless mapped buffers can combine forces with AIO > (which certainly isn't possible on Linux, at least). this is a little off topic, but... The JVM API allows for memory map buffers to be sent to a channel and it is meant to use sendfile like mechanisms so that the file content is sent directly to the interface device. I think the need to memory map to a buffer is a side effect of the java API, which is all about channels and buffers and totally hides file descriptors. It may be that in this case java uses the memory mapped buffer only as a holder of a file descriptor plus offset and length. > For a different perspective, see Roberto Peon's message which has the > same thread parent as yours - he says there's no gain from sendfile. Probably the biggest benefit from the java point of view is not being able to drive the network interface at maximum speed, but rather avoiding using user memory and the garbage collects that result. cheers
- Re: [hybi] hum #3: Message Jamie Lokier
- [hybi] hum #3: Message Salvatore Loreto
- Re: [hybi] hum #3: Message Ian Hickson
- Re: [hybi] hum #3: Message John Tamplin
- Re: [hybi] hum #3: Message Douglas Otis
- Re: [hybi] hum #3: Message Maciej Stachowiak
- Re: [hybi] hum #3: Message Dave Cridland
- Re: [hybi] hum #3: Message Ian Hickson
- Re: [hybi] hum #3: Message Julian Reschke
- Re: [hybi] hum #3: Message John Tamplin
- Re: [hybi] hum #3: Message Jack Moffitt
- Re: [hybi] hum #3: Message Bjoern Hoehrmann
- Re: [hybi] hum #3: Message Willy Tarreau
- Re: [hybi] hum #3: Message Bjoern Hoehrmann
- Re: [hybi] hum #3: Message Maciej Stachowiak
- Re: [hybi] hum #3: Message Julian Reschke
- Re: [hybi] hum #3: Message Roberto Peon
- Re: [hybi] hum #3: Message Maciej Stachowiak
- Re: [hybi] hum #3: Message Jack Moffitt
- Re: [hybi] hum #3: Message Willy Tarreau
- Re: [hybi] hum #3: Message Maciej Stachowiak
- Re: [hybi] hum #3: Message Maciej Stachowiak
- Re: [hybi] hum #3: Message Dave Cridland
- Re: [hybi] hum #3: Message Maciej Stachowiak
- Re: [hybi] hum #3: Message Dave Cridland
- Re: [hybi] hum #3: Message Greg Wilkins
- Re: [hybi] hum #3: Message Dave Cridland
- Re: [hybi] hum #3: Message Jack Moffitt
- Re: [hybi] hum #3: Message Ian Fette (イアンフェッティ)
- Re: [hybi] hum #3: Message Ian Fette (イアンフェッティ)
- [hybi] Background info: Properties of sendfile() Jamie Lokier
- Re: [hybi] hum #3: Message Jamie Lokier
- Re: [hybi] Background info: Properties of sendfil… Roy T. Fielding
- Re: [hybi] Background info: Properties of sendfil… Jamie Lokier
- Re: [hybi] Background info: Properties of sendfil… Greg Wilkins
- Re: [hybi] Background info: Properties of sendfil… Roberto Peon
- Re: [hybi] hum #3: Message Scott Ferguson
- Re: [hybi] Background info: Properties of sendfil… Jamie Lokier
- Re: [hybi] Background info: Properties of sendfil… Greg Wilkins
- Re: [hybi] Background info: Properties of sendfil… Willy Tarreau
- Re: [hybi] Background info: Properties of sendfil… Maciej Stachowiak
- Re: [hybi] Background info: Properties of sendfil… Willy Tarreau
- Re: [hybi] hum #3: Message Pieter Hintjens
- Re: [hybi] hum #3: Message Arman Djusupov
- Re: [hybi] hum #3: Message Pieter Hintjens
- Re: [hybi] hum #3: Message Julian Reschke
- Re: [hybi] hum #3: Message Arman Djusupov
- Re: [hybi] Background info: Properties of sendfil… Jack Moffitt
- Re: [hybi] hum #3: Message John Tamplin
- Re: [hybi] hum #3: Message Arman Djusupov
- Re: [hybi] hum #3: Message Scott Ferguson
- Re: [hybi] hum #3: Message Scott Ferguson
- Re: [hybi] hum #3: Message Patrick McManus
- Re: [hybi] hum #3: Message Scott Ferguson
- Re: [hybi] hum #3: Message Patrick McManus
- Re: [hybi] Background info: Properties of sendfil… Roberto Peon
- Re: [hybi] Background info: Properties of sendfil… Jamie Lokier
- Re: [hybi] hum #3: Message Dave Cridland
- Re: [hybi] hum #3: Message Dave Cridland
- Re: [hybi] hum #3: Message Douglas Otis
- [hybi] Impact of mandatory chunking (was Re: Back… Maciej Stachowiak
- Re: [hybi] Impact of mandatory chunking (was Re: … Jack Moffitt
- Re: [hybi] hum #3: Message Pieter Hintjens
- Re: [hybi] Impact of mandatory chunking (was Re: … Maciej Stachowiak
- Re: [hybi] hum #3: Message Scott Ferguson
- Re: [hybi] hum #3: Message Willy Tarreau
- Re: [hybi] hum #3: Message Scott Ferguson
- Re: [hybi] hum #3: Message Roberto Peon
- Re: [hybi] hum #3: Message Willy Tarreau
- Re: [hybi] hum #3: Message Scott Ferguson
- Re: [hybi] hum #3: Message Pieter Hintjens
- Re: [hybi] hum #3: Message Greg Wilkins
- Re: [hybi] hum #3: Message Pieter Hintjens
- Re: [hybi] hum #3: Message Martin Sustrik
- Re: [hybi] hum(s) followup Maciej Stachowiak
- [hybi] hum(s) followup Salvatore Loreto
- Re: [hybi] hum(s) followup Pieter Hintjens
- Re: [hybi] hum(s) followup Salvatore Loreto