Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Wed, 13 Jun 2018 18:57:16 +0200
From:   Michal Kubecek <mkubecek@suse.cz>
To:     netdev@vger.kernel.org
Cc:     Eric Dumazet <edumazet@google.com>,
        Yuchung Cheng <ycheng@google.com>,
        Ilpo Jarvinen <ilpo.jarvinen@helsinki.fi>,
        linux-kernel@vger.kernel.org
Subject: Re: [RFC PATCH RESEND] tcp: avoid F-RTO if SACK and timestamps are
 disabled
Message-ID: <20180613165716.4fy7ufk7jnk3r67r@unicorn.suse.cz>
References: <20180613164802.99B89A09E2@unicorn.suse.cz>
 <20180613165543.0F92DA09E2@unicorn.suse.cz>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20180613165543.0F92DA09E2@unicorn.suse.cz>
User-Agent: NeoMutt/20170912 (1.9.0)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Wed, Jun 13, 2018 at 06:55:43PM +0200, Michal Kubecek wrote:
> When F-RTO algorithm (RFC 5682) is used on connection without both SACK and
> timestamps (either because of (mis)configuration or because the other
> endpoint does not advertise them), specific pattern loss can make RTO grow
> exponentially until the sender is only able to send one packet per two
> minutes (TCP_RTO_MAX).
> 
> One way to reproduce is to
> 
>   - make sure the connection uses neither SACK nor timestamps
>   - let tp->reorder grow enough so that lost packets are retransmitted
>     after RTO (rather than when high_seq - snd_una > reorder * MSS)
>   - let the data flow stabilize
>   - drop multiple sender packets in "every second" pattern
>   - either there is no new data to send or acks received in response to new
>     data are also window updates (i.e. not dupacks by definition)
> 
> In this scenario, the sender keeps cycling between retransmitting first
> lost packet (step 1 of RFC 5682), sending new data by (2b) and timing out
> again. In this loop, the sender only gets
> 
>   (a) acks for retransmitted segments (possibly together with old ones)
>   (b) window updates
> 
> Without timestamps, neither can be used for RTT estimator and without SACK,
> we have no newly sacked segments to estimate RTT either. Therefore each
> timeout doubles RTO and without usable RTT samples so that there is nothing
> to counter the exponential growth.
> 
> While disabling both SACK and timestamps doesn't make any sense, the
> resulting behaviour is so pathological that it deserves an improvement.
> (Also, both can be disabled on the other side.) Avoid F-RTO algorithm in
> case both SACK and timestamps are disabled so that the sender falls back to
> traditional slow start retransmission.
> 
> Signed-off-by: Michal Kubecek <mkubecek@suse.cz>

I was able to illustrate the issue using a packetdrill script. It cheats
a bit by setting net.ipv4.tcp_reordering to 30 so that it we can get to
the issue more quickly. In this case, we don't have more data to send
but it's not essential; the issue can be reproduced even with sending of
new data in F-RTO, it would only make everything more complicated.

I was able to run the same script on kernels 4.17-rc6, 4.12 (SLE15) and
4.4 (SLE12-SP2). Kernel 3.12 required minor modifications but not in the
important part (the slow start is a bit slower there).

---------------------------------------------------------------------------
--tolerance_usecs=10000

// flush cached TCP metrics
0.000  `ip tcp_metrics flush all`
+0.000 `sysctl -q net.ipv4.tcp_reordering=20`


// establish a connection
+0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+0.000 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+0.000 setsockopt(3, SOL_SOCKET, SO_SNDBUF, [131072], 4) = 0
+0.000 bind(3, ..., ...) = 0
+0.000 listen(3, 1) = 0

+0.100 < S 0:0(0) win 40000 <mss 1000>
+0.000 > S. 0:0(0) ack 1 <mss 1460>
+0.100 < . 1:1(0) ack 1 win 40000
+0.000 accept(3, ..., ...) = 4

// Send 10 data segments.
+0.100 write(4, ..., 30000) = 30000
// For some reason (unknown yet), GSO packets are only 2000 bytes long
+0.000 > . 1:2001(2000) ack 1
+0.000 > . 2001:4001(2000) ack 1
+0.000 > . 4001:6001(2000) ack 1
+0.000 > . 6001:8001(2000) ack 1
+0.000 > . 8001:10001(2000) ack 1
+0.100 < . 1:1(0) ack 2001 win 38000
+0.000 > . 10001:12001(2000) ack 1
+0.000 > . 12001:14001(2000) ack 1
+0.001 < . 1:1(0) ack 4001 win 36000
+0.000 > . 14001:16001(2000) ack 1
+0.000 > . 16001:18001(2000) ack 1
+0.001 < . 1:1(0) ack 6001 win 34000
+0.000 > . 18001:20001(2000) ack 1
+0.000 > . 20001:22001(2000) ack 1
+0.001 < . 1:1(0) ack 8001 win 32000
+0.000 > . 22001:24001(2000) ack 1
+0.000 > . 24001:26001(2000) ack 1
+0.001 < . 1:1(0) ack 10001 win 30000
+0.000 > . 26001:28001(2000) ack 1
+0.000 > P. 28001:30001(2000) ack 1

// loss of 12001:13001, 14001:15001, ..., 28001:29001
+0.100 < . 1:1(0) ack 12001 win 30000	// original ack
+0.000 < . 1:1(0) ack 12001 win 30000	// 13001:14001
+0.000 < . 1:1(0) ack 12001 win 30000	// 15001:16001
+0.000 < . 1:1(0) ack 12001 win 30000	// 17001:18001
+0.000 < . 1:1(0) ack 12001 win 30000	// 19001:20001
+0.000 < . 1:1(0) ack 12001 win 30000	// 21001:22001
+0.000 < . 1:1(0) ack 12001 win 30000	// 13001:24001
+0.000 < . 1:1(0) ack 12001 win 30000	// 25001:26001
+0.000 < . 1:1(0) ack 12001 win 30000	// 27001:28001
+0.000 < . 1:1(0) ack 12001 win 30000	// 29001:30001

// RTO 300ms
+0.270~+0.330 > . 12001:13001(1000) ack 1
+0.100 < . 1:1(0) ack 14001 win 38000
// RTO 600ms
+0.540~+0.660 > . 14001:15001(1000) ack 1
+0.100 < . 1:1(0) ack 16001 win 38000
// RTO 1200ms
+1.050~+1.350 > . 16001:17001(1000) ack 1
+0.100 < . 1:1(0) ack 18001 win 38000
// RTO 2400ms
+2.100~+2.700 > . 18001:19001(1000) ack 1
+0.100 < . 1:1(0) ack 20001 win 38000
// RTO 4800ms
+4.200~+5.400 > . 20001:21001(1000) ack 1
+0.100 < . 1:1(0) ack 22001 win 38000
// RTO 9600ms
+8.400~+10.800 > . 22001:23001(1000) ack 1
+0.100 < . 1:1(0) ack 24001 win 38000
// RTO 19200ms
+16.800~+21.600 > . 24001:25001(1000) ack 1

+1.000 `sysctl -q net.ipv4.tcp_reordering=3`
---------------------------------------------------------------------------

And this is what happens on current snapshot of master branch with
either net.ipv4.tcp_frto=0 or with the RFC patch:

---------------------------------------------------------------------------
--tolerance_usecs=10000

// flush cached TCP metrics
0.000  `ip tcp_metrics flush all`
+0.000 `sysctl -q net.ipv4.tcp_reordering=20`


// establish a connection
+0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+0.000 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+0.000 setsockopt(3, SOL_SOCKET, SO_SNDBUF, [131072], 4) = 0
+0.000 bind(3, ..., ...) = 0
+0.000 listen(3, 1) = 0

+0.100 < S 0:0(0) win 40000 <mss 1000>
+0.000 > S. 0:0(0) ack 1 <mss 1460>
+0.100 < . 1:1(0) ack 1 win 40000
+0.000 accept(3, ..., ...) = 4

// Send 10 data segments.
+0.100 write(4, ..., 30000) = 30000
// For some reason (unknown yet), GSO packets are only 2000 bytes long
+0.000 > . 1:2001(2000) ack 1
+0.000 > . 2001:4001(2000) ack 1
+0.000 > . 4001:6001(2000) ack 1
+0.000 > . 6001:8001(2000) ack 1
+0.000 > . 8001:10001(2000) ack 1
+0.100 < . 1:1(0) ack 2001 win 38000
+0.000 > . 10001:12001(2000) ack 1
+0.000 > . 12001:14001(2000) ack 1
+0.001 < . 1:1(0) ack 4001 win 36000
+0.000 > . 14001:16001(2000) ack 1
+0.000 > . 16001:18001(2000) ack 1
+0.001 < . 1:1(0) ack 6001 win 34000
+0.000 > . 18001:20001(2000) ack 1
+0.000 > . 20001:22001(2000) ack 1
+0.001 < . 1:1(0) ack 8001 win 32000
+0.000 > . 22001:24001(2000) ack 1
+0.000 > . 24001:26001(2000) ack 1
+0.001 < . 1:1(0) ack 10001 win 30000
+0.000 > . 26001:28001(2000) ack 1
+0.000 > P. 28001:30001(2000) ack 1

// loss of 12001:13001, 14001:15001, ..., 28001:29001
+0.100 < . 1:1(0) ack 12001 win 30000	// original ack
+0.000 < . 1:1(0) ack 12001 win 30000	// 13001:14001
+0.000 < . 1:1(0) ack 12001 win 30000	// 15001:16001
+0.000 < . 1:1(0) ack 12001 win 30000	// 17001:18001
+0.000 < . 1:1(0) ack 12001 win 30000	// 19001:20001
+0.000 < . 1:1(0) ack 12001 win 30000	// 21001:22001
+0.000 < . 1:1(0) ack 12001 win 30000	// 13001:24001
+0.000 < . 1:1(0) ack 12001 win 30000	// 25001:26001
+0.000 < . 1:1(0) ack 12001 win 30000	// 27001:28001
+0.000 < . 1:1(0) ack 12001 win 30000	// 29001:30001

// RTO 300ms
+0.270~+0.330 > . 12001:13001(1000) ack 1
+0.100 < . 1:1(0) ack 14001 win 38000

+0.000 > . 14001:16001(2000) ack 1
+0.000 > . 16001:17001(1000) ack 1
+0.100 < . 1:1(0) ack 16001 win 38000

+0.000 > . 17001:18001(1000) ack 1
+0.000 > . 18001:20001(2000) ack 1
+0.000 > . 20001:21001(1000) ack 1
+0.100 < . 1:1(0) ack 18001 win 38000
+0.001 < . 1:1(0) ack 20001 win 36000
+0.001 < . 1:1(0) ack 21001 win 35000

+0.000 > . 21001:22001(1000) ack 1
+0.000 > . 22001:24001(2000) ack 1
+0.000 > . 24001:25001(1000) ack 1
+0.000 > . 25001:26001(1000) ack 1
+0.000 > . 26001:28001(2000) ack 1
+0.000 > . 28001:29001(1000) ack 1
+0.000 > P. 29001:30001(1000) ack 1
+0.100 < . 1:1(0) ack 22001 win 38000
+0.001 < . 1:1(0) ack 24001 win 36000
+0.001 < . 1:1(0) ack 26001 win 34000
+0.001 < . 1:1(0) ack 28001 win 32000
+0.001 < . 1:1(0) ack 30001 win 30000

+1.000 `sysctl -q net.ipv4.tcp_reordering=3`
---------------------------------------------------------------------------

Michal Kubecek