[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <alpine.OSX.2.23.453.2006261424430.66996@redsall-mobl2.amr.corp.intel.com>
Date: Fri, 26 Jun 2020 14:25:19 -0700 (PDT)
From: Mat Martineau <mathew.j.martineau@...ux.intel.com>
To: Paolo Abeni <pabeni@...hat.com>
cc: netdev@...r.kernel.org, "David S. Miller" <davem@...emloft.net>,
Jakub Kicinski <kuba@...nel.org>, mptcp@...ts.01.org,
Eric Dumazet <edumazet@...gle.com>
Subject: Re: [MPTCP] [PATCH net-next v2 2/4] mptcp: refactor token
container
On Fri, 26 Jun 2020, Paolo Abeni wrote:
> Replace the radix tree with a hash table allocated
> at boot time. The radix tree has some shortcoming:
> a single lock is contented by all the mptcp operation,
> the lookup currently use such lock, and traversing
> all the items would require a lock, too.
>
> With hash table instead we trade a little memory to
> address all the above - a per bucket lock is used.
>
> To hash the MPTCP sockets, we re-use the msk' sk_node
> entry: the MPTCP sockets are never hashed by the stack.
> Replace the existing hash proto callbacks with a dummy
> implementation, annotating the above constraint.
>
> Additionally refactor the token creation to code to:
>
> - limit the number of consecutive attempts to a fixed
> maximum. Hitting a hash bucket with a long chain is
> considered a failed attempt
>
> - accept() no longer can fail to token management.
>
> - if token creation fails at connect() time, we do
> fallback to TCP (before the connection was closed)
>
> v1 -> v2:
> - fix "no newline at end of file" - Jakub
>
> Signed-off-by: Paolo Abeni <pabeni@...hat.com>
> ---
> net/mptcp/protocol.c | 45 ++++---
> net/mptcp/protocol.h | 14 ++-
> net/mptcp/subflow.c | 19 ++-
> net/mptcp/token.c | 271 ++++++++++++++++++++++++++++++-------------
> 4 files changed, 236 insertions(+), 113 deletions(-)
Reviewed-by: Mat Martineau <mathew.j.martineau@...ux.intel.com>
--
Mat Martineau
Intel
Powered by blists - more mailing lists