From mboxrd@z Thu Jan 1 00:00:00 1970 Authentication-Results: passt.top; dmarc=pass (p=quarantine dis=none) header.from=redhat.com Authentication-Results: passt.top; dkim=pass (1024-bit key; unprotected) header.d=redhat.com header.i=@redhat.com header.a=rsa-sha256 header.s=mimecast20190719 header.b=I4kcSL0E; dkim-atps=neutral Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.129.124]) by passt.top (Postfix) with ESMTPS id E08375A026F for ; Wed, 29 Oct 2025 08:39:41 +0100 (CET) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1761723580; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=wRi0RPJTGnQgIt9bRj2AbKAKrIrx0K8hfJLUmOUlT9c=; b=I4kcSL0EErwjxfBEUxxgeJ6OaE+/S3C3+U6cs+hxVDUxXIgb2qJjrytqvl0vzTUUrhNs2n KAMHoRhuoSTWMQa4K1PMTSA8/0SmsBFZcrXabSBPljrs4qWVBIgnhhSc3RGF6TpTChhQFC AJ2V7VFUNOtcTR12POgzuYQmqbAF+2s= Received: from mail-wm1-f72.google.com (mail-wm1-f72.google.com [209.85.128.72]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3, cipher=TLS_AES_256_GCM_SHA384) id us-mta-537-cej-HJPhNlCSeKreqk_Cfg-1; Wed, 29 Oct 2025 03:39:38 -0400 X-MC-Unique: cej-HJPhNlCSeKreqk_Cfg-1 X-Mimecast-MFC-AGG-ID: cej-HJPhNlCSeKreqk_Cfg_1761723577 Received: by mail-wm1-f72.google.com with SMTP id 5b1f17b1804b1-471201dc0e9so39373855e9.2 for ; Wed, 29 Oct 2025 00:39:37 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1761723577; x=1762328377; h=content-transfer-encoding:mime-version:organization:references :in-reply-to:message-id:subject:cc:to:from:date:x-gm-message-state :from:to:cc:subject:date:message-id:reply-to; bh=/FFlVkJ3rg191eH3bjF1JZF2X7gT0kPH+rnQhPypxu0=; b=RqfnJwFgU62ebiDppz7lLwFUPHEJ+Aixqp8oQHRizvNpDHlaAjO24dAHtSXIdx69Kf xcEkSVrL/GKdUfhH34NA5SMjYVJjnYY9QnZiQauUKTCm+hML+YKFfffwHWELAZOsGo96 phbhb/lXBziC6Zkk6fzXzo0Q6l1w1YvUMwbxMVi5Cp5RskZ/9Lpt2hM5uxn/W7e+cdtz lY3B2fvkYsDxPYi6Tiw7sQLHH83eoGq20JsmMT77qoFOp8NsYV+jRtYz6WFn77/Xl+Lq mmTh4GMGpylTLbSvRcIK/wZEGXwqUmwDxPRAUML9IaeRbjsrjo9vFfYv9+wZs4HOspMa HJGg== X-Gm-Message-State: AOJu0YxnAsYnUPVXI/62ffJRcjKQShEioFoUcwLNBiOgZYZ0uzrm/0ZW bigKA0gzjSkmPKt8LNAy5oroA0nT5MwROIC8sywvtltYIXP8NNLIFgAw+xs6hnK4n2oRuGpDfhK CAqDmE8FP66n6MBVdm0GUOunVwTni19GSifTmnazSya/uVkF+WLrzxg== X-Gm-Gg: ASbGncsuvAkLhgEgK1kI3vBIHOrfnlXwcpMlmTdm4vykJGQ+bXeLQBOIebN1DgbHDoL PZ+UpiIsoO8UbBQSqf/rf+ULzhxO7Y6tqW171f0q62wOYwcqzq9N4/z/XBSCY1327HnzzyM7P7X GMoIWZ2be98BjSKaAb4CKRVL95rEarUEMKrQftaReDDDmWQQ+tw+Nq4srXINUr2BmWG5Xmwl6BB tcF9ksFpHSk532+xHOav3gg3hbwmyDdNpgAUndKlTbFl3dHA2ORdefY1847H3W9j4Nj/lInAWq9 rMAgayfkHq4RXkwATCjnc2kNsXv+a8ncg5YXyZ9Dxlp+CtRDrMPLSEkkgV24Qq9NYBMiklpiKD2 naD7cMMQLJQ== X-Received: by 2002:a05:600c:3b15:b0:475:dd89:acb with SMTP id 5b1f17b1804b1-4771e3a88ccmr14801365e9.22.1761723576619; Wed, 29 Oct 2025 00:39:36 -0700 (PDT) X-Google-Smtp-Source: AGHT+IEmZvxWR+40nl8pgu1z0qoBc9U/kA2qqKUDhw7xQUfi8Vvh2OD1UBsBUXpoJlzFkvrJbpHDAQ== X-Received: by 2002:a05:600c:3b15:b0:475:dd89:acb with SMTP id 5b1f17b1804b1-4771e3a88ccmr14801105e9.22.1761723575981; Wed, 29 Oct 2025 00:39:35 -0700 (PDT) Received: from maya.myfinge.rs (ifcgrfdd.trafficplex.cloud. [2a10:fc81:a806:d6a9::1]) by smtp.gmail.com with ESMTPSA id 5b1f17b1804b1-4771e3937b3sm31601895e9.5.2025.10.29.00.39.35 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 29 Oct 2025 00:39:35 -0700 (PDT) Date: Wed, 29 Oct 2025 08:39:29 +0100 From: Stefano Brivio To: Yumei Huang Subject: Re: [PATCH v6 4/4] tcp: Update data retransmission timeout Message-ID: <20251029083929.0dc52bc6@elisabeth> In-Reply-To: References: <20251017062838.21041-1-yuhuang@redhat.com> <20251017062838.21041-5-yuhuang@redhat.com> <20251024010438.16e19757@elisabeth> <20251028124426.534fd236@elisabeth> <20251029053804.711716aa@elisabeth> <20251029080953.4f671f56@elisabeth> Organization: Red Hat X-Mailer: Claws Mail 4.2.0 (GTK 3.24.49; x86_64-pc-linux-gnu) MIME-Version: 1.0 X-Mimecast-Spam-Score: 0 X-Mimecast-MFC-PROC-ID: t_Yk2Y1vM0kgTxwoKW-EDeaGpeVRmk9oqdwZb9U4IZA_1761723577 X-Mimecast-Originator: redhat.com Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Message-ID-Hash: OXASJ2JYGSPU6YIOXFZAHCTGQW3DHPU6 X-Message-ID-Hash: OXASJ2JYGSPU6YIOXFZAHCTGQW3DHPU6 X-MailFrom: sbrivio@redhat.com X-Mailman-Rule-Misses: dmarc-mitigation; no-senders; approved; emergency; loop; banned-address; member-moderation; nonmember-moderation; administrivia; implicit-dest; max-recipients; max-size; news-moderation; no-subject; digests; suspicious-header CC: passt-dev@passt.top, david@gibson.dropbear.id.au X-Mailman-Version: 3.3.8 Precedence: list List-Id: Development discussion and patches for passt Archived-At: Archived-At: List-Archive: List-Archive: List-Help: List-Owner: List-Post: List-Subscribe: List-Unsubscribe: On Wed, 29 Oct 2025 15:32:33 +0800 Yumei Huang wrote: > On Wed, Oct 29, 2025 at 3:10=E2=80=AFPM Stefano Brivio wrote: > > > > On Wed, 29 Oct 2025 13:11:48 +0800 > > Yumei Huang wrote: > > =20 > > > On Wed, Oct 29, 2025 at 12:38=E2=80=AFPM Stefano Brivio wrote: =20 > > > > > > > > On Wed, 29 Oct 2025 11:06:44 +0800 > > > > Yumei Huang wrote: > > > > =20 > > > > > On Tue, Oct 28, 2025 at 7:44=E2=80=AFPM Stefano Brivio wrote: =20 > > > > > > > > > > > > On Tue, 28 Oct 2025 16:09:03 +0800 > > > > > > Yumei Huang wrote: > > > > > > =20 > > > > > > > On Fri, Oct 24, 2025 at 7:04=E2=80=AFAM Stefano Brivio wrote: =20 > > > > > > > > > > > > > > > > On Fri, 17 Oct 2025 14:28:38 +0800 > > > > > > > > Yumei Huang wrote: > > > > > > > > =20 > > > > > > > > > Use an exponential backoff timeout for data retransmissio= n according > > > > > > > > > to RFC 2988 and RFC 6298. Set the initial RTO to one seco= nd as discussed > > > > > > > > > in Appendix A of RFC 6298. > > > > > > > > > > > > > > > > > > Also combine the macros defining the initial RTO for both= SYN and ACK. > > > > > > > > > > > > > > > > > > Signed-off-by: Yumei Huang > > > > > > > > > Reviewed-by: David Gibson > > > > > > > > > --- > > > > > > > > > tcp.c | 27 ++++++++++++--------------- > > > > > > > > > 1 file changed, 12 insertions(+), 15 deletions(-) > > > > > > > > > > > > > > > > > > diff --git a/tcp.c b/tcp.c > > > > > > > > > index 9385132..dc0ec6c 100644 > > > > > > > > > --- a/tcp.c > > > > > > > > > +++ b/tcp.c > > > > > > > > > @@ -179,16 +179,14 @@ > > > > > > > > > * > > > > > > > > > * Timeouts are implemented by means of timerfd timers, = set based on flags: > > > > > > > > > * > > > > > > > > > - * - SYN_TIMEOUT_INIT: if no ACK is received from tap/gu= est during handshake > > > > > > > > > - * (flag ACK_FROM_TAP_DUE without ESTABLISHED event) w= ithin this time, resend > > > > > > > > > - * SYN. It's the starting timeout for the first SYN re= try. If this persists > > > > > > > > > - * for more than TCP_MAX_RETRIES or (tcp_syn_retries + > > > > > > > > > - * tcp_syn_linear_timeouts) times in a row, reset the = connection > > > > > > > > > - * > > > > > > > > > - * - ACK_TIMEOUT: if no ACK segment was received from ta= p/guest, after sending > > > > > > > > > - * data (flag ACK_FROM_TAP_DUE with ESTABLISHED event)= , re-send data from the > > > > > > > > > - * socket and reset sequence to what was acknowledged.= If this persists for > > > > > > > > > - * more than TCP_MAX_RETRIES times in a row, reset the= connection > > > > > > > > > + * - RTO_INIT: if no ACK segment was received from tap/g= uest, either during > > > > > > > > > + * handshake (flag ACK_FROM_TAP_DUE without ESTABLISHE= D event) or after > > > > > > > > > + * sending data (flag ACK_FROM_TAP_DUE with ESTABLISHE= D event), re-send data > > > > > > > > > + * from the socket and reset sequence to what was ackn= owledged. This is the > > > > > > > > > + * timeout for the first retry, in seconds. If this pe= rsists too many times > > > > > > > > > + * in a row, reset the connection: TCP_MAX_RETRIES for= established > > > > > > > > > + * connections, or (tcp_syn_retries + tcp_syn_linear_t= imeouts) during the > > > > > > > > > + * handshake. > > > > > > > > > * > > > > > > > > > * - FIN_TIMEOUT: if a FIN segment was sent to tap/guest= (flag ACK_FROM_TAP_DUE > > > > > > > > > * with TAP_FIN_SENT event), and no ACK is received wi= thin this time, reset > > > > > > > > > @@ -342,8 +340,7 @@ enum { > > > > > > > > > #define WINDOW_DEFAULT 14600 = /* RFC 6928 */ > > > > > > > > > > > > > > > > > > #define ACK_INTERVAL 10 /* = ms */ > > > > > > > > > -#define SYN_TIMEOUT_INIT 1 /* = s */ > > > > > > > > > -#define ACK_TIMEOUT 2 > > > > > > > > > +#define RTO_INIT 1 /* = s, RFC 6298 */ > > > > > > > > > #define FIN_TIMEOUT 60 > > > > > > > > > #define ACT_TIMEOUT 7200 > > > > > > > > > > > > > > > > > > @@ -588,13 +585,13 @@ static void tcp_timer_ctl(const str= uct ctx *c, struct tcp_tap_conn *conn) > > > > > > > > > } else if (conn->flags & ACK_FROM_TAP_DUE) { > > > > > > > > > if (!(conn->events & ESTABLISHED)) { > > > > > > > > > if (conn->retries < c->tcp.syn_line= ar_timeouts) > > > > > > > > > - it.it_value.tv_sec =3D SYN_= TIMEOUT_INIT; > > > > > > > > > + it.it_value.tv_sec =3D RTO_= INIT; > > > > > > > > > else > > > > > > > > > - it.it_value.tv_sec =3D SYN_= TIMEOUT_INIT << > > > > > > > > > + it.it_value.tv_sec =3D RTO_= INIT << > > > > > > > > > (conn->retries - c-= >tcp.syn_linear_timeouts); > > > > > > > > > } > > > > > > > > > else > > > > > > > > > - it.it_value.tv_sec =3D ACK_TIMEOUT; > > > > > > > > > + it.it_value.tv_sec =3D RTO_INIT << = conn->retries; =20 > > > > > > > > > > > > > > > > Same as on 3/4, but here it's clearly more convenient: just= assign > > > > > > > > RTO_INIT, and multiply as needed in the if / else clauses. = =20 > > > > > > > > > > > > > > I guess we can't just assign RTO_INIT. Maybe assign it only = when > > > > > > > retries=3D=3D0, otherwise multiply as it.it_value.tv_sec <<= =3D1. =20 > > > > > > > > > > > > Why can't you do that? Say: > > > > > > > > > > > > it.it_value.tv_sec =3D RTO_INIT > > > > > > if (!(conn->events & ESTABLISHED)) { > > > > > > if (conn->retries >=3D c->tcp.syn_linear_timeou= ts) > > > > > > it.it_value.tv_sec <<=3D (conn->retries= - > > > > > > c->tcp.syn_line= ar_timeouts); > > > > > > > > > > > > but anyway, see below. > > > > > > =20 > > > > > > > But it seems more complicated. What do you think? =20 > > > > > > > > > > > > Or maybe, building on my latest comment to 3/4: > > > > > > > > > > > > int factor =3D conn->retries; > > > > > > > > > > > > if (!(conn->events & ESTABLISHED)) > > > > > > factor -=3D c->tcp.syn_linear_timeouts; > > > > > > > > > > > > it.it_value.tv_sec =3D RTO_INIT << MAX(factor, = 0); > > > > > > > > > > > > ? =20 > > > > > > > > > > Yeah, I understand this part now. > > > > > =20 > > > > > > =20 > > > > > > > > =20 > > > > > > > > > } else if (CONN_HAS(conn, SOCK_FIN_SENT | TAP_FIN_A= CKED)) { > > > > > > > > > it.it_value.tv_sec =3D FIN_TIMEOUT; > > > > > > > > > } else { =20 > > > > > > > > > > > > > > > > The rest of the series looks good to me. > > > > > > > > > > > > > > > > It might be slightly more practical to factor in directly t= he RTO > > > > > > > > clamp, and I don't think it's complicated now that you have= the helper > > > > > > > > from 2/4, but it's not a strong preference from my side, as= the series > > > > > > > > makes sense in any case. =20 > > > > > > > > > > > > > > Reading tcp_rto_max_ms can be easy with the helper. My concer= n is > > > > > > > about the way we get the total time for retries. > > > > > > > > > > > > > > I used to do it like this in v2, > > > > > > > https://archives.passt.top/passt-dev/20251010074700.22177-4-y= uhuang@redhat.com/: > > > > > > > > > > > > > > +#define RETRY_ELAPSED(timeout_init, retries) \ > > > > > > > + ((timeout_init) * ((1 << ((retries) + 1)) - 2)) > > > > > > > > > > > > > > Though the formula is not quite right, we could refine it as = below: > > > > > > > > > > > > > > #define RETRY_ELAPSED(retries) ((RTO_INIT) * ((1 << ((retries= ) + 1)) - 1)) > > > > > > > > > > > > > > Does it make sense to get the time this way? =20 > > > > > > > > > > > > Well, it also depends on c->tcp.syn_linear_timeouts, right? =20 > > > > > > > > > > Not really, it's only used for data retransmission, so > > > > > syn_linear_timeouts is not relevant. =20 > > > > > > > > Hmm, no, why? RFC 6298 covers SYN retries as well, and that's the o= ne > > > > stating: =20 > > > > > > I meant RETRY_ELAPSED was only used for data retransmission, which > > > uses exponential backoff timeout directly, so syn_linear_timeouts was > > > not relevant. =20 > > > > Ah, okay. > > =20 > > > > > > > > (2.5) A maximum value MAY be placed on RTO provided it is at lea= st 60 > > > > seconds. =20 > > > > > > For SYN retries, as we used linear backoff + exponential backoff, and > > > also limited by TCP_MAX_RETRIES, the possible max RTO is far less tha= n > > > 60s. So we didn't clamp it. Do you think we need to clamp it as well?= =20 > > > > If syn_linear_timeouts is 0 and tcp_syn_retries is 7, I guess we'll > > reach 2^0 + 2^1 + 2^2 + 2^3 + 2^4 + 2^5 + 2^6 + 2^7 =3D 247 seconds? Or > > just up to ... + 2^6, that is, 119 seconds? > > > > In any case, what is the difference compared to data retransmissions? = =20 >=20 > You are right. I assumed wrongly that syn_linear_timeouts is always 4. > When it's 0, it's the same as data retransmissions. > > > > Don't we have 3 bits to store the retry count as well, so we're limited > > by TCP_MAX_RETRIES anyway? Looking at patch 1/4 I'd say it's the same > > counter. =20 >=20 > Yes, it's the same counter. I guess you mean we should clamp it as well. I didn't check this part, I thought we already did, but if we don't, we should do that, yes. > > > > ...the only thing that I don't see implemented in this version of t= he > > > > patch is paragraph 5.7: > > > > > > > > (5.7) If the timer expires awaiting the ACK of a SYN segment and= the > > > > TCP implementation is using an RTO less than 3 seconds, th= e RTO > > > > MUST be re-initialized to 3 seconds when data transmission > > > > begins (i.e., after the three-way handshake completes). > > > > > > > > I missed that while reviewing earlier versions. I guess we need to = use > > > > a MAX(x, 3) clamp if (c->conn->events & ESTABLISHED). I think it's > > > > simpler than re-introducing separate starting values (one second an= d > > > > three seconds). =20 > > > > > > I'm not sure I understand here. If the timer expires, didn't we reset > > > the connection directly? We would never get to the data transmission > > > phase? =20 > > > > In the RFC, "the timer expires" indicates one iteration of the timeout > > algorithm, that is, it's the same as our timer (tcp_timer_handler()) > > triggering. =20 >=20 > I see. >=20 > If you agree, I can add a new patch in this series to address the clampin= g. I don't really have a preference, I guess it could be directly in 4/4 or in a separate patch, neither option should complicate things too much. > > The paragraph says "after the three-way handshake completes", so it > > looks like the connection wasn't reset. > > =20 > > > > > Probably I should name it more clearly. > > > > > =20 > > > > > > > > > > > > But in any case, do you really need to calculate that explicitl= y? I was > > > > > > thinking that you can just clamp the value when you use it in > > > > > > tcp_timer_ctl(). > > > > > > > > > > > > If c->tcp.rto_max is DIV_ROUND_CLOSEST(x, 1000), where 'x' is t= he value > > > > > > you read from the kernel, then I guess it's just: > > > > > > > > > > > > --- > > > > > > it.it_value.tv_sec =3D MIN(it.it_value.tv_sec, = c->tcp.rto_max); =20 > > > > > > > > > > After reading the comments in v3 when tcp_rto_max_ms was first > > > > > mentioned again, I realized I got something wrong again. I though= t it > > > > > was for the total timeout for all retries, so I need to calculate= that > > > > > and decide to reset the connection as in v2. =20 > > > > > > > > I think it actually applies to all the retries. > > > > =20 > > > > > Anyway, you are right. We don't need to do that. Thanks for your = patience. > > > > > =20 > > > > > > } ... > > > > > > > > > > > > if (timerfd_settime(conn->timer, 0, &it, NULL)) > > > > > > flow_perror(conn, "failed to set timer"); > > > > > > --- =20 --=20 Stefano