From owner-freebsd-arch@FreeBSD.ORG Fri Aug 19 09:28:24 2011 Return-Path: Delivered-To: freebsd-arch@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id D8C5B1065672 for ; Fri, 19 Aug 2011 09:28:24 +0000 (UTC) (envelope-from lev@FreeBSD.org) Received: from onlyone.friendlyhosting.spb.ru (onlyone.friendlyhosting.spb.ru [IPv6:2a01:4f8:131:60a2::2]) by mx1.freebsd.org (Postfix) with ESMTP id 9DEC18FC0C for ; Fri, 19 Aug 2011 09:28:24 +0000 (UTC) Received: from lion.home.serebryakov.spb.ru (unknown [IPv6:2001:470:923f:1:248b:b3cd:918d:d0d2]) (Authenticated sender: lev@serebryakov.spb.ru) by onlyone.friendlyhosting.spb.ru (Postfix) with ESMTPA id D3BF74AC1C; Fri, 19 Aug 2011 13:28:23 +0400 (MSD) Date: Fri, 19 Aug 2011 13:28:19 +0400 From: Lev Serebryakov X-Priority: 3 (Normal) Message-ID: <1156334334.20110819132819@serebryakov.spb.ru> To: Slawa Olhovchenkov In-Reply-To: <20110819092304.GB92576@zxy.spb.ru> References: <810527321.20110819123700@serebryakov.spb.ru> <20110819092304.GB92576@zxy.spb.ru> MIME-Version: 1.0 Content-Type: text/plain; charset=koi8-r Content-Transfer-Encoding: quoted-printable Cc: freebsd-arch@freebsd.org Subject: Re: FreeBSD problems and preliminary ways to solve X-BeenThere: freebsd-arch@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Discussion related to FreeBSD architecture List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 19 Aug 2011 09:28:24 -0000 Hello, Slawa. You wrote 19 =C1=D7=C7=D5=D3=D4=C1 2011 =C7., 13:23:04: >> There are a few known issues in terms of parallelism -- one is contention >> between the ithread and user thread on per-TCP connection locks. Anothe= r is=20 >> that we still haven't managed to switch to per-CPU statistics for the ne= twork=20 >> stack (which is fairly straight forward in a specific sense, but we'd li= ke a=20 >> proper abstraction for it so we can generalise). > After discussion in other place: may be perfomace improve if > application resheduling on the same core, as processing incoming > IP packet (hot CPU ca=D3he)? Yes, it is exactly what our admins done, and it helps, but if streams will grow (and they WILL) here will be a little space to grow up performance as well. But it is completely offtopic already. --=20 // Black Lion AKA Lev Serebryakov