Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 2 Jan 2018 12:47:14 -0800
From:      Freddie Cash <fjwcash@gmail.com>
To:        Michael Grimm <trashcan@ellael.org>
Cc:        "Bjoern A. Zeeb" <bzeeb-lists@lists.zabbadoz.net>, freebsd-net <freebsd-net@freebsd.org>, freebsd-pf@freebsd.org
Subject:   Re: [SOLVED] performance issue within VNET jail
Message-ID:  <CAOjFWZ7Z_L-sKHk=-sBSv9a36O20QQ6peyekTZBexOO7jPtS4g@mail.gmail.com>
In-Reply-To: <CAOjFWZ7uyxgwoZBnGFacJO=7Uzji9mFJcZF87ogc%2B5b=6kVa9A@mail.gmail.com>
References:  <4F5EE3F6-0163-4435-8726-56B0D4AE9FAF@ellael.org> <B6446660-9FD2-4C28-A3A2-8AC99624C7FF@sigsegv.be> <8102F5FD-DCFC-4EF8-A443-9E6C9EB1F467@ellael.org> <DB5DE737-7171-4953-AF98-45F1BE7AF09E@sigsegv.be> <8C8A172B-4D4F-4066-8B94-EF5F59E2D345@ellael.org> <5A3D67EC.6010907@grosbein.net> <53687746-C487-4712-AA52-DE86CE70FDEF@ellael.org> <AD46E22E-8230-47FD-A14D-FDA9E0753746@lists.zabbadoz.net> <5FD6CE98-601B-46B7-B598-83BE5A31200A@ellael.org> <CAOjFWZ621TL5dA%2BRnpXR_PU=1MV-kcaEXrvh2iD616H1RGHcLQ@mail.gmail.com> <CAOjFWZ7uyxgwoZBnGFacJO=7Uzji9mFJcZF87ogc%2B5b=6kVa9A@mail.gmail.com>

next in thread | previous in thread | raw e-mail | index | archive | help
On Dec 23, 2017 6:06 AM, "Michael Grimm" <trashcan@ellael.org> wrote:


I will skip these questions for the time being, because I did solve my
issue 15 minutes before your mail ;-) And I feel sorry for all your now
"wasted" efforts in trying to help me.

As I am using vtnet interface in a cloud environment (Public Cloud by OVH)
I did read the vtnet(4) man pages and stumbled about "LOADER TUNABLES" like=
:

        hw.vtnet.lro_disable
        hw.vtnet.X.lro_disable
             This tunable disables LRO.  The default value is 0.

Well, without knowing and understanding the implications of those loader
tunables I did disabled them step by step, and bingo, setting =E2=80=A6

        hw.vtnet.lro_disable=3D"1"

=E2=80=A6 in /boot/loader.conf" and performance is back from KB/s to MB/s.



I really do not understand what I have done and why it is working and
whether that will have negative implications for my servers. Perhaps
someone of you experts could help me understand it.


I don't know all the specifics, but PF and IPFW really like to work on
individual packets from NICs, especially when doing NAT. They don't play
well with batched receives via LRO and batch transmits via TSO. Disabling
those on the NICs being used for packet filtering greatly improves
throughout. Not sure about PF man page, but pretty sure the IPFW man page
mentions disabling those.



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CAOjFWZ7Z_L-sKHk=-sBSv9a36O20QQ6peyekTZBexOO7jPtS4g>