From mboxrd@z Thu Jan  1 00:00:00 1970
To: Fans of the OS Plan 9 from Bell Labs <9fans@9fans.net>
In-reply-to: Your message of "Fri, 08 May 2015 21:24:13 +0200."
	<20150508212413.7466429d@zinc.9fans.fr>
References: <87C61423-7C13-4516-88B5-C2ABA7D32AA9@me.com>
	<A1D8C0A6-BB79-42EB-9874-C3F4A8FCC1F6@9srv.net>
	<CAEAzY38Az=_4Min2vFfXCkNez-7Wka104QiWf=FaafmnJuAAWw@mail.gmail.com>
	<CANUoZoERAwWAMxLYGiAGOihHBwPAq07XyKmiTyCg2tmgvaO44Q@mail.gmail.com>
	<CAOw7k5jven0TcUs6HpreteRxr8vT57rNbAuubUbq2wEiqbv2+A@mail.gmail.com>
	<CANUoZoGXm6bf_Mi_QNJSmHN6U0yb+3CeVcK_r-UA+PFfDE_NQQ@mail.gmail.com>
	<CAOw7k5jBr37Owp1_pvjK4GqLCg-rP7Qut8hDci8ZwZ8nr1O1tw@mail.gmail.com>
	<CANUoZoFAq-h6dhpH+L54egj-jYBAyDYHRxG3cwc6suZdhs_dUQ@mail.gmail.com>
	<CAEAzY3_w3Cm+uAqEH_POW0sGUVods4UxxUPMHYQ9DFOcvbivXg@mail.gmail.com>
	<CANUoZoFWQtQVP1YsRBkr-6haOBn+CWav57-gMDGPjMv+L7Lrzg@mail.gmail.com>
	<bc68096596c6c5f33b7a074e689bdd8a@brasstown.quanstro.net>
	<CANUoZoHG5xya2y0iDOt9nWHgauHFgYmpyVTUT1bRAu-ACD2VBQ@mail.gmail.com>
	<CAOw7k5jF3yCZdgBiB-a+v+gcX4fiREfaE1k+HkxDdSxy4EzkWg@mail.gmail.com>
	<20150508191612.2f080829@zinc.9fans.fr>
	<20150508212413.7466429d@zinc.9fans.fr>
Date: Fri,  8 May 2015 14:19:22 -0700
From: Bakul Shah <bakul@bitblocks.com>
Message-Id: <20150508211922.1118FB82A@mail.bitblocks.com>
Subject: Re: [9fans] fossil+venti performance question
Topicbox-Message-UUID: 503b8184-ead9-11e9-9d60-3106f5b1d025

On Fri, 08 May 2015 21:24:13 +0200 David du Colombier <0intro@gmail.com> wrote:
> On the loopback medium, I suppose this is the opposite issue.
> Since the TCP stack didn't fix the MSS in the incoming
> connection, the programs sent multiple small 1500 bytes
> IP packets instead of large 16384 IP packets, but I don't
> know why it leads to such a slowdown.

Looking at the first few bytes in each dir of the initial TCP
handshake (with tcpdump) I see:

        0x0000:  4500 0030 24da 0000  <= from plan9 to freebsd

        0x0000:  4500 0030 d249 4000  <= from freebsd to plan9

Looks like FreeBSD always sets the DF (don't fragment) bit
(0x40 in byte 6), while plan9 doesn't (byte 6 is 0x00).

May be plan9 should set the DF (don't fragment) bit in the IP
header and try to do path MTU discovery? Either by default or
under some ctl option.