From nobody Tue Jun 29 06:28:41 2021 X-Original-To: freebsd-net@mlmmj.nyi.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2610:1c1:1:606c::19:1]) by mlmmj.nyi.freebsd.org (Postfix) with ESMTP id 093FA11F5C7A for ; Tue, 29 Jun 2021 06:29:01 +0000 (UTC) (envelope-from lutz@iks-jena.de) Received: from annwfn.iks-jena.de (annwfn.iks-jena.de [IPv6:2001:4bd8::19]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 4GDZLh5CCSz3sql for ; Tue, 29 Jun 2021 06:29:00 +0000 (UTC) (envelope-from lutz@iks-jena.de) X-SMTP-Sender: IPv6:2001:4bd8:0:666:248:54ff:fe12:ee3f Received: from belenus.iks-jena.de (belenus.iks-jena.de [IPv6:2001:4bd8:0:666:248:54ff:fe12:ee3f]) by annwfn.iks-jena.de (8.15.2/8.15.2) with ESMTPS id 15T6SgMg030390 (version=TLSv1 cipher=DHE-RSA-AES256-SHA bits=256 verify=NOT); Tue, 29 Jun 2021 08:28:42 +0200 X-MSA-Host: belenus.iks-jena.de Received: (from lutz@localhost) by belenus.iks-jena.de (8.14.3/8.14.1/Submit) id 15T6Sf4X031665; Tue, 29 Jun 2021 08:28:41 +0200 Date: Tue, 29 Jun 2021 08:28:41 +0200 From: Lutz Donnerhacke To: Rick Macklem Cc: freebsd-net Subject: Re: RFC: NFS trunking (multiple TCP connections for a mount Message-ID: <20210629062841.GC31225@belenus.iks-jena.de> References: List-Id: Networking and TCP/IP with FreeBSD List-Archive: https://lists.freebsd.org/archives/freebsd-net List-Help: List-Post: List-Subscribe: List-Unsubscribe: Sender: owner-freebsd-net@freebsd.org MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: X-message-flag: Please send plain text messages only. Thank you. User-Agent: Mutt/1.5.17 (2007-11-01) X-Rspamd-Queue-Id: 4GDZLh5CCSz3sql X-Spamd-Bar: ---- Authentication-Results: mx1.freebsd.org; none X-Spamd-Result: default: False [-4.00 / 15.00]; REPLY(-4.00)[] X-ThisMailContainsUnwantedMimeParts: N On Tue, Jun 29, 2021 at 12:23:21AM +0000, Rick Macklem wrote: > I don't understand how multiple TCP connections to the same > server IP address will distribute the load across multiple network > interfaces? Sounds like a bandwith-latency-product issue. TCP is prone to stalling at the end of a buffer window (in addition to reassembly and RPC waits). Multiple TCP streams scale linear with the available bandwidth over them. Single RPC messages should not split over multiple streams (causes reorder of segments), but different messages can go in round robin fashion. There is no need to ensure a symmetric path, so that the response comes back on the same stream.