From owner-freebsd-current@freebsd.org Tue May 26 23:39:17 2020 Return-Path: Delivered-To: freebsd-current@mailman.nyi.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2610:1c1:1:606c::19:1]) by mailman.nyi.freebsd.org (Postfix) with ESMTP id 73A5C2F70DE for ; Tue, 26 May 2020 23:39:17 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: from mail-qt1-f171.google.com (mail-qt1-f171.google.com [209.85.160.171]) (using TLSv1.3 with cipher TLS_AES_128_GCM_SHA256 (128/128 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256 client-signature RSA-PSS (2048 bits) client-digest SHA256) (Client CN "smtp.gmail.com", Issuer "GTS CA 1O1" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 49Wr5b4sB9z497Q for ; Tue, 26 May 2020 23:39:15 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: by mail-qt1-f171.google.com with SMTP id j32so2830972qte.10 for ; Tue, 26 May 2020 16:39:15 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=MqdpMvcQZrFJ4ykeh64eMpsOnvJnbDfIWNWgizs6QE4=; b=PjKeOq+jVNutMkyhvnxRMF41GmVh9pa69phtY+yenuQ4YbrziqjRMYNNZcj2QRp/Yj dsaxUUKcXv+qW+aOIIgG2G78Xf7CBEuy154VPfVRSMklG0BvyTCOnVS4WrnEs9QhnFHT IHWykK5uQoFnUAxXxg1CxRxk8cd9Yfk9GIPKXy3fq5lMNXxbCnvYJwjtHgSMq50WPb7S ysaQdCV9ep9lwMzmNMhB8SyROCpW8PpFtKwYVNRSFzo2MMyOFSbR10Z0eHK62nTYGMjq jDyOo+0owNFzhO4fAHfOgFDjFo98oUF9pL3SLfVI9Imqzn/fv9n3P7asbLdQJW2X1pCb cQOw== X-Gm-Message-State: AOAM530zBp71GY9DgwP6BeSLcKEaOzYgVbbczUHeXxQuTPOkPJzQvMKF OwB2hSDVVAv5s5BJJMasZIJbV1/qZWwNQWsn8Vk= X-Google-Smtp-Source: ABdhPJwPvmyQM1sbbgTnSJHbV5Db7tIMAOoyQOh3iQvSIu+19qD9lxYB4snTuTaQZ0j08P/gYHYLbZ9IDxqj7TvsVvc= X-Received: by 2002:ac8:c8b:: with SMTP id n11mr1458766qti.49.1590536354650; Tue, 26 May 2020 16:39:14 -0700 (PDT) MIME-Version: 1.0 References: <3e491993-aa46-9e16-0105-b79cbee6b2a3@selasky.org> In-Reply-To: <3e491993-aa46-9e16-0105-b79cbee6b2a3@selasky.org> From: Adrian Chadd Date: Tue, 26 May 2020 16:39:00 -0700 Message-ID: Subject: Re: iflib and options RSS is a no go for igbX To: Hans Petter Selasky Cc: FreeBSD Current Content-Type: text/plain; charset="UTF-8" X-Rspamd-Queue-Id: 49Wr5b4sB9z497Q X-Spamd-Bar: -- Authentication-Results: mx1.freebsd.org; dkim=none; dmarc=none; spf=pass (mx1.freebsd.org: domain of adrianchadd@gmail.com designates 209.85.160.171 as permitted sender) smtp.mailfrom=adrianchadd@gmail.com X-Spamd-Result: default: False [-2.48 / 15.00]; FROM_NEQ_ENVFROM(0.00)[adrian@freebsd.org,adrianchadd@gmail.com]; ARC_NA(0.00)[]; RCVD_TLS_ALL(0.00)[]; FROM_HAS_DN(0.00)[]; R_SPF_ALLOW(-0.20)[+ip4:209.85.128.0/17]; NEURAL_HAM_LONG(-1.00)[-0.995]; MIME_GOOD(-0.10)[text/plain]; PREVIOUSLY_DELIVERED(0.00)[freebsd-current@freebsd.org]; DMARC_NA(0.00)[freebsd.org]; TO_MATCH_ENVRCPT_SOME(0.00)[]; TO_DN_ALL(0.00)[]; NEURAL_HAM_SHORT(-0.46)[-0.464]; RCPT_COUNT_TWO(0.00)[2]; RCVD_IN_DNSWL_NONE(0.00)[209.85.160.171:from]; NEURAL_HAM_MEDIUM(-1.02)[-1.019]; FORGED_SENDER(0.30)[adrian@freebsd.org,adrianchadd@gmail.com]; RWL_MAILSPIKE_POSSIBLE(0.00)[209.85.160.171:from]; R_DKIM_NA(0.00)[]; FREEMAIL_ENVFROM(0.00)[gmail.com]; ASN(0.00)[asn:15169, ipnet:209.85.128.0/17, country:US]; MIME_TRACE(0.00)[0:+]; TAGGED_FROM(0.00)[]; RCVD_COUNT_TWO(0.00)[2] X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.33 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 26 May 2020 23:39:17 -0000 reply to all this time: On Tue, 26 May 2020 at 02:03, Hans Petter Selasky wrote: > > Hi, > > I just found a bug where outgoing TCP connections over igb0 doesn't work > because likely the software computed hash is wrong, so the incoming > packets get dropped because they are received on the wrong queue. > > It is the management port, so I'm just using this hack for now: > > dev.igb.0.iflib.override_nrxqs=1 > dev.igb.0.iflib.override_ntxqs=1 Did iflib + RSS get broken? Cause it used to work just fine when I was still doing networking stuff at norse, and igb was one of the supported pieces of hardware I fixed up RSS on. The trick was literally making sure the tcp/udp l3 / l4 hash configuration was setup right (which it was by default for at least igb, where RSS worked!) and the hardware programmed in the right RSS key. Outbound connections would work fine, but they wouldn't be created in the local RSS CPU because you didn't know the details until you finished creating a socket. But all the hijinx were done behind the scenes so things got lined up in the right queues. I can go setup my second PC this week (I have PTO!) and go see if I have any PCIe igb hardware here. I /think/ I do but it's fibre. -adrian