From mboxrd@z Thu Jan 1 00:00:00 1970 From: Yuchung Cheng Subject: Re: [REGRESSION] Warning in tcp_fastretrans_alert() of net/ipv4/tcp_input.c Date: Mon, 18 Sep 2017 11:01:42 -0700 Message-ID: References: <10035198.1vE6NFrMDO@natalenko.name> <40697505.YK5nrFG7Le@natalenko.name> Mime-Version: 1.0 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable Cc: Neal Cardwell , "David S. Miller" , Alexey Kuznetsov , Hideaki YOSHIFUJI , Netdev To: Oleksandr Natalenko Return-path: Received: from mail-wr0-f169.google.com ([209.85.128.169]:46414 "EHLO mail-wr0-f169.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752858AbdIRSCY (ORCPT ); Mon, 18 Sep 2017 14:02:24 -0400 Received: by mail-wr0-f169.google.com with SMTP id o42so1189895wrb.3 for ; Mon, 18 Sep 2017 11:02:24 -0700 (PDT) In-Reply-To: <40697505.YK5nrFG7Le@natalenko.name> Sender: netdev-owner@vger.kernel.org List-ID: On Mon, Sep 18, 2017 at 10:59 AM, Oleksandr Natalenko wrote: > OK. Should I keep FACK disabled? Yes since it is disabled in the upstream by default. Although you can experiment FACK enabled additionally. Do we know the crash you first experienced is tied to this issue? > > On pond=C4=9Bl=C3=AD 18. z=C3=A1=C5=99=C3=AD 2017 19:51:21 CEST Yuchung C= heng wrote: >> Can you try this patch to verify my theory with tcp_recovery=3D0 and 1? = thanks >> >> diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c >> index 5af2f04f8859..9253d9ee7d0e 100644 >> --- a/net/ipv4/tcp_input.c >> +++ b/net/ipv4/tcp_input.c >> @@ -2381,6 +2381,7 @@ static void tcp_undo_cwnd_reduction(struct sock >> *sk, bool unmark_loss) >> } >> tp->snd_cwnd_stamp =3D tcp_time_stamp; >> tp->undo_marker =3D 0; >> + WARN_ON(tp->retrans_out); >> } >