From: David Ahern <dsahern@gmail.com>
To: Ido Schimmel <idosch@idosch.org>, netdev@vger.kernel.org
Cc: davem@davemloft.net, kuba@kernel.org, amcohen@nvidia.com,
roopa@nvidia.com, sharpd@nvidia.com, bpoirier@nvidia.com,
mlxsw@nvidia.com, Ido Schimmel <idosch@nvidia.com>
Subject: Re: [PATCH net-next 05/10] net: ipv4: Emit notification when fib hardware flags are changed
Date: Tue, 26 Jan 2021 22:02:50 -0700 [thread overview]
Message-ID: <79194116-6d96-eb13-c845-b5d268df7a82@gmail.com> (raw)
In-Reply-To: <20210126132311.3061388-6-idosch@idosch.org>
On 1/26/21 6:23 AM, Ido Schimmel wrote:
> From: Amit Cohen <amcohen@nvidia.com>
>
> After installing a route to the kernel, user space receives an
> acknowledgment, which means the route was installed in the kernel,
> but not necessarily in hardware.
>
> The asynchronous nature of route installation in hardware can lead to a
> routing daemon advertising a route before it was actually installed in
> hardware. This can result in packet loss or mis-routed packets until the
> route is installed in hardware.
>
> It is also possible for a route already installed in hardware to change
> its action and therefore its flags. For example, a host route that is
> trapping packets can be "promoted" to perform decapsulation following
> the installation of an IPinIP/VXLAN tunnel.
>
> Emit RTM_NEWROUTE notifications whenever RTM_F_OFFLOAD/RTM_F_TRAP flags
> are changed. The aim is to provide an indication to user-space
> (e.g., routing daemons) about the state of the route in hardware.
>
> Introduce a sysctl that controls this behavior.
>
> Keep the default value at 0 (i.e., do not emit notifications) for several
> reasons:
> - Multiple RTM_NEWROUTE notification per-route might confuse existing
> routing daemons.
are you aware of any routing daemons that are affected? Seems like they
should be able to handle redundant notifications
> - Convergence reasons in routing daemons.
> - The extra notifications will negatively impact the insertion rate.
any numbers on the overhead?
> - Not all users are interested in these notifications.
>
> Signed-off-by: Amit Cohen <amcohen@nvidia.com>
> Acked-by: Roopa Prabhu <roopa@nvidia.com>
> Signed-off-by: Ido Schimmel <idosch@nvidia.com>
> ---
> Documentation/networking/ip-sysctl.rst | 20 +++++++++++++++++++
> include/net/netns/ipv4.h | 2 ++
> net/ipv4/af_inet.c | 2 ++
> net/ipv4/fib_trie.c | 27 ++++++++++++++++++++++++++
> net/ipv4/sysctl_net_ipv4.c | 9 +++++++++
> 5 files changed, 60 insertions(+)
>
next prev parent reply other threads:[~2021-01-27 5:20 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-01-26 13:23 [PATCH net-next 00/10] Add notifications when route hardware flags change Ido Schimmel
2021-01-26 13:23 ` [PATCH net-next 01/10] netdevsim: fib: Convert the current occupancy to an atomic variable Ido Schimmel
2021-01-27 4:33 ` David Ahern
2021-01-27 10:51 ` Amit Cohen
2021-01-28 3:42 ` David Ahern
2021-01-26 13:23 ` [PATCH net-next 02/10] netdevsim: fib: Perform the route programming in a non-atomic context Ido Schimmel
2021-01-27 4:36 ` David Ahern
2021-01-26 13:23 ` [PATCH net-next 03/10] net: ipv4: Pass fib_rt_info as const to fib_dump_info() Ido Schimmel
2021-01-27 4:38 ` David Ahern
2021-01-26 13:23 ` [PATCH net-next 04/10] net: ipv4: Publish fib_nlmsg_size() Ido Schimmel
2021-01-27 4:41 ` David Ahern
2021-01-26 13:23 ` [PATCH net-next 05/10] net: ipv4: Emit notification when fib hardware flags are changed Ido Schimmel
2021-01-27 5:02 ` David Ahern [this message]
2021-01-27 11:46 ` Amit Cohen
2021-01-28 3:34 ` David Ahern
2021-01-29 3:04 ` Jakub Kicinski
2021-01-29 3:33 ` David Ahern
2021-01-29 4:15 ` Jakub Kicinski
2021-01-30 15:36 ` Ido Schimmel
2021-01-30 15:11 ` Ido Schimmel
2021-01-26 13:23 ` [PATCH net-next 06/10] net: Pass 'net' struct as first argument to fib6_info_hw_flags_set() Ido Schimmel
2021-01-27 5:08 ` David Ahern
2021-01-26 13:23 ` [PATCH net-next 07/10] net: Do not call fib6_info_hw_flags_set() when IPv6 is disabled Ido Schimmel
2021-01-26 13:23 ` [PATCH net-next 08/10] net: ipv6: Emit notification when fib hardware flags are changed Ido Schimmel
2021-01-27 5:14 ` David Ahern
2021-01-28 3:36 ` David Ahern
2021-01-26 13:23 ` [PATCH net-next 09/10] selftests: Extend fib tests to run with and without flags notifications Ido Schimmel
2021-01-26 13:23 ` [PATCH net-next 10/10] selftests: netdevsim: Add fib_notifications test Ido Schimmel
2021-01-28 3:41 ` David Ahern
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=79194116-6d96-eb13-c845-b5d268df7a82@gmail.com \
--to=dsahern@gmail.com \
--cc=amcohen@nvidia.com \
--cc=bpoirier@nvidia.com \
--cc=davem@davemloft.net \
--cc=idosch@idosch.org \
--cc=idosch@nvidia.com \
--cc=kuba@kernel.org \
--cc=mlxsw@nvidia.com \
--cc=netdev@vger.kernel.org \
--cc=roopa@nvidia.com \
--cc=sharpd@nvidia.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).