From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-out01.uio.no (mail-out01.uio.no [IPv6:2001:700:100:10::50]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by lists.bufferbloat.net (Postfix) with ESMTPS id 4412C3CB37 for ; Wed, 7 Feb 2024 07:08:44 -0500 (EST) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=ifi.uio.no; s=key2309; h=To:References:Message-Id:Content-Transfer-Encoding:Cc:Date: In-Reply-To:From:Subject:Mime-Version:Content-Type:Sender:Reply-To:Content-ID :Content-Description:Resent-Date:Resent-From:Resent-Sender:Resent-To: Resent-Cc:Resent-Message-ID:List-Id:List-Help:List-Unsubscribe:List-Subscribe :List-Post:List-Owner:List-Archive; bh=OAnOaiL6Wkk3dvlwtJxxwSf6mNkkcBGOAp7wBOqPlmk=; b=3tZVme9/nkECPMxSKfS5olxEPt xaxDGMsDZZQZvBNDQ6HAegD/ZBCIIFOwoJYC/EaNsN9H7TwZs4cDIgX+yOAracUma06cFE8jCHNJS gwTMXHMomOtmZ8+Bqw4zry4HE7wo0n9Z+VVXDOgkVMShtCLEQmAO1rMj4CaV2ndhvYxhlFLeRHEU3 2/svVSeTqX49ZVqP4cLKa7YaD+nrzWFJHf2Kb3ZWeOLFNZBCTZLK0NjfvhR+8egR+yKAX6dxAIFR0 xma/UOxs1qrNPZFdD3lMOBAZSSMZIty/L9qigYLs840Wz4XEMMb/ym6SqNfU7xQxqLZOHguNqbsBQ rotoBqSw==; Received: from mail-mx12.uio.no ([129.240.10.84]) by mail-out01.uio.no with esmtps (TLS1.2) tls TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384 (Exim 4.96.2) (envelope-from ) id 1rXgjJ-00BYwv-1Y; Wed, 07 Feb 2024 13:08:41 +0100 Received: from collaborix.ifi.uio.no ([129.240.69.78] helo=smtpclient.apple) by mail-mx12.uio.no with esmtps (TLS1.2:ECDHE-ECDSA-AES256-GCM-SHA384:256) (Exim 4.96.2) (envelope-from ) id 1rXgjI-0003b4-2z; Wed, 07 Feb 2024 13:08:41 +0100 Content-Type: text/plain; charset=utf-8 Mime-Version: 1.0 (Mac OS X Mail 16.0 \(3696.120.41.1.1\)) From: Michael Welzl In-Reply-To: Date: Wed, 7 Feb 2024 13:08:40 +0100 Cc: Linux Kernel Network Developers , bloat@lists.bufferbloat.net Content-Transfer-Encoding: quoted-printable Message-Id: References: <1BAA689A-D44E-4122-9AD8-25F6D024377E@ifi.uio.no> To: Dave Taht X-Mailer: Apple Mail (2.3696.120.41.1.1) X-UiO-SPF-Received: Received-SPF: neutral (mail-mx12.uio.no: 129.240.69.78 is neither permitted nor denied by domain of ifi.uio.no) client-ip=129.240.69.78; envelope-from=michawe@ifi.uio.no; helo=smtpclient.apple; X-UiO-Spam-info: not spam, SpamAssassin (score=-4.6, required=5.0, autolearn=disabled, KHOP_HELO_FCRDNS=0.4, T_SCC_BODY_TEXT_LINE=-0.01, UIO_MAIL_IS_INTERNAL=-5) X-UiO-Scanned: 2CCAA68EDBB96D2186333327B15102915C74D20E X-UiOonly: 940DBC83520B41C5D4A4388A9D537D71DCC88203 Subject: Re: [Bloat] Trying to *really* understand Linux pacing X-BeenThere: bloat@lists.bufferbloat.net X-Mailman-Version: 2.1.20 Precedence: list List-Id: General list for discussing Bufferbloat List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 07 Feb 2024 12:08:44 -0000 Whoa=E2=80=A6 and now I=E2=80=99m even more afraid :-) My sincere apologies to anyone whose code I may have mis-represented! I = just tried to get it=E2=80=A6 sorry if there are silly mistakes in = there! > On 7 Feb 2024, at 13:05, Dave Taht wrote: >=20 > Dear Michael: >=20 > Thank you for digging deeply into packet pacing, TSQ, etc. I think > there are some interesting new possibilities in probing (especially > during slow start) that could make the core idea even more effective > than it is. I also tend to think that attempting it in various cloudy > environments and virtualization schemes, and with certain drivers, the > side effects are not as well understood as I would like. For example, > AWS's nitro lacks BQL as does virtio-net. >=20 > I think the netdev community, now cc'd, would be interested in your > document and explorations so far, below. I hope for more > enlightenment. >=20 > On Wed, Feb 7, 2024 at 6:57=E2=80=AFAM Michael Welzl via Bloat > wrote: >>=20 >> Dear de-bloaters of buffers, >> Esteemed experts of low delay and pacing! >>=20 >> I have no longer been satisfied with high-level descriptions of how = pacing works in Linux, and how it interacts with TSQ (I=E2=80=99ve seen = some, in various papers, over the years) - but I wanted to REALLY = understand it. So, I have dug through the code. >>=20 >> I documented this experience here: >> = https://docs.google.com/document/d/1-uXnPDcVBKmg5krkG5wYBgaA2yLSFK_kZa7xGD= Wc7XU/edit?usp=3Dsharing >> but it has some holes and may have mistakes. >>=20 >> Actually, my main problem is that I don=E2=80=99t really know what = goes on when I configure a larger IW=E2=80=A6 things seem to get quite = =E2=80=9Coff=E2=80=9D there. Why? Anyone up for solving that riddle? = ;-) >> (see the tests I documented towards the end of the document) >>=20 >> Generally, if someone who has their hands on files such as = tcp_output.c all the time could take a look, and perhaps =E2=80=9Cfill=E2=80= =9D my holes, or improve anything that might be wrong, that would be = fantastic! I think that anyone should be allowed to comment and make = suggestions in this doc. >>=20 >> MANY thanks to whoever finds the time to take a look ! >>=20 >> Cheers, >> Michael >>=20 >> _______________________________________________ >> Bloat mailing list >> Bloat@lists.bufferbloat.net >> https://lists.bufferbloat.net/listinfo/bloat >=20 >=20 >=20 > --=20 > 40 years of net history, a couple songs: > https://www.youtube.com/watch?v=3DD9RGX6QFm5E > Dave T=C3=A4ht CSO, LibreQos