[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20240816111843.GU632411@kernel.org>
Date: Fri, 16 Aug 2024 12:18:43 +0100
From: Simon Horman <horms@...nel.org>
To: Christoph Paasch <cpaasch@...le.com>
Cc: netdev@...r.kernel.org, Eric Dumazet <edumazet@...gle.com>,
Paolo Abeni <pabeni@...hat.com>, Jakub Kicinski <kuba@...nel.org>,
David Miller <davem@...emloft.net>, Roopa Prabhu <roopa@...dia.com>,
Craig Taylor <cmtaylor@...le.com>
Subject: Re: [PATCH netnext] mpls: Reduce skb re-allocations due to skb_cow()
On Thu, Aug 15, 2024 at 09:12:01AM -0700, Christoph Paasch wrote:
> mpls_xmit() needs to prepend the MPLS-labels to the packet. That implies
> one needs to make sure there is enough space for it in the headers.
>
> Calling skb_cow() implies however that one wants to change even the
> playload part of the packet (which is not true for MPLS). Thus, call
> skb_cow_head() instead, which is what other tunnelling protocols do.
>
> Running a server with this comm it entirely removed the calls to
> pskb_expand_head() from the callstack in mpls_xmit() thus having
> significant CPU-reduction, especially at peak times.
Hi Christoph and Craig,
Including some performance data here would be nice.
> Cc: Roopa Prabhu <roopa@...dia.com>
> Reported-by: Craig Taylor <cmtaylor@...le.com>
> Signed-off-by: Christoph Paasch <cpaasch@...le.com>
And one minor nit, which I do not think warrants a repost:
netnext -> net-next.
In any case, this looks good to me.
Reviewed-by: Simon Horman <horms@...nel.org>
Powered by blists - more mailing lists