All of lore.kernel.org
 help / color / mirror / Atom feed
From: Mat Martineau <mathew.j.martineau at linux.intel.com>
To: mptcp at lists.01.org
Subject: [MPTCP] Re: [PATCH net-next 2/6] mptcp: implement wmem reservation
Date: Mon, 30 Nov 2020 15:43:33 -0800	[thread overview]
Message-ID: <7d93fc11-4993-802e-e318-157226f91cf6@linux.intel.com> (raw)
In-Reply-To: e1726dbf86cee84d76098f42774be3abe2c367c7.1606413118.git.pabeni@redhat.com

[-- Attachment #1: Type: text/plain, Size: 1075 bytes --]

On Fri, 27 Nov 2020, Paolo Abeni wrote:

> This leverages the previous commit to reserve the wmem
> required for the sendmsg() operation when the msk socket
> lock is first acquired.
> Some heuristics are used to get a reasonable [over] estimation of
> the whole memory required. If we can't forward alloc such amount
> fallback to a reasonable small chunk, otherwise enter the wait
> for memory path.
>
> When sendmsg() needs more memory it looks at wmem_reserved
> first and if that is exhausted, move more space from
> sk_forward_alloc.
>
> The reserved memory is not persistent and is released at the
> next socket unlock via the release_cb().
>
> Overall this will simplify the next patch.
>
> Acked-by: Florian Westphal <fw(a)strlen.de>
> Signed-off-by: Paolo Abeni <pabeni(a)redhat.com>
> ---
> net/mptcp/protocol.c | 92 ++++++++++++++++++++++++++++++++++++++++----
> net/mptcp/protocol.h |  1 +
> 2 files changed, 86 insertions(+), 7 deletions(-)

Reviewed-by: Mat Martineau <mathew.j.martineau(a)linux.intel.com>

--
Mat Martineau
Intel

WARNING: multiple messages have this Message-ID (diff)
From: Mat Martineau <mathew.j.martineau@linux.intel.com>
To: Paolo Abeni <pabeni@redhat.com>
Cc: netdev@vger.kernel.org, Jakub Kicinski <kuba@kernel.org>,
	mptcp@lists.01.org, Eric Dumazet <edumazet@google.com>
Subject: Re: [PATCH net-next 2/6] mptcp: implement wmem reservation
Date: Mon, 30 Nov 2020 15:43:33 -0800 (PST)	[thread overview]
Message-ID: <7d93fc11-4993-802e-e318-157226f91cf6@linux.intel.com> (raw)
In-Reply-To: <e1726dbf86cee84d76098f42774be3abe2c367c7.1606413118.git.pabeni@redhat.com>

On Fri, 27 Nov 2020, Paolo Abeni wrote:

> This leverages the previous commit to reserve the wmem
> required for the sendmsg() operation when the msk socket
> lock is first acquired.
> Some heuristics are used to get a reasonable [over] estimation of
> the whole memory required. If we can't forward alloc such amount
> fallback to a reasonable small chunk, otherwise enter the wait
> for memory path.
>
> When sendmsg() needs more memory it looks at wmem_reserved
> first and if that is exhausted, move more space from
> sk_forward_alloc.
>
> The reserved memory is not persistent and is released at the
> next socket unlock via the release_cb().
>
> Overall this will simplify the next patch.
>
> Acked-by: Florian Westphal <fw@strlen.de>
> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
> ---
> net/mptcp/protocol.c | 92 ++++++++++++++++++++++++++++++++++++++++----
> net/mptcp/protocol.h |  1 +
> 2 files changed, 86 insertions(+), 7 deletions(-)

Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>

--
Mat Martineau
Intel

             reply	other threads:[~2020-11-30 23:43 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-11-30 23:43 Mat Martineau [this message]
2020-11-30 23:43 ` [PATCH net-next 2/6] mptcp: implement wmem reservation Mat Martineau
  -- strict thread matches above, loose matches on Subject: below --
2020-12-01  2:34 [MPTCP] Re: [PATCH net-next 0/6] mptcp: avoid workqueue usage for data Jakub Kicinski
2020-12-01  2:34 ` Jakub Kicinski
2020-11-30 23:45 [MPTCP] Re: [PATCH net-next 6/6] mptcp: use mptcp release_cb for delayed tasks Mat Martineau
2020-11-30 23:45 ` Mat Martineau
2020-11-30 23:44 [MPTCP] Re: [PATCH net-next 5/6] mptcp: avoid a few atomic ops in the rx path Mat Martineau
2020-11-30 23:44 ` Mat Martineau
2020-11-30 23:44 [MPTCP] Re: [PATCH net-next 4/6] mptcp: allocate TX skbs in msk context Mat Martineau
2020-11-30 23:44 ` Mat Martineau
2020-11-30 23:43 [MPTCP] Re: [PATCH net-next 3/6] mptcp: protect the rx path with the msk socket spinlock Mat Martineau
2020-11-30 23:43 ` Mat Martineau
2020-11-30 23:43 [MPTCP] Re: [PATCH net-next 1/6] mptcp: open code mptcp variant for lock_sock Mat Martineau
2020-11-30 23:43 ` Mat Martineau
2020-11-27 10:10 [MPTCP] [PATCH net-next 6/6] mptcp: use mptcp release_cb for delayed tasks Paolo Abeni
2020-11-27 10:10 ` Paolo Abeni
2020-11-27 10:10 [MPTCP] [PATCH net-next 5/6] mptcp: avoid a few atomic ops in the rx path Paolo Abeni
2020-11-27 10:10 ` Paolo Abeni
2020-11-27 10:10 [MPTCP] [PATCH net-next 4/6] mptcp: allocate TX skbs in msk context Paolo Abeni
2020-11-27 10:10 ` Paolo Abeni
2020-11-27 10:10 [MPTCP] [PATCH net-next 3/6] mptcp: protect the rx path with the msk socket spinlock Paolo Abeni
2020-11-27 10:10 ` Paolo Abeni
2020-11-27 10:10 [MPTCP] [PATCH net-next 2/6] mptcp: implement wmem reservation Paolo Abeni
2020-11-27 10:10 ` Paolo Abeni
2020-11-27 10:10 [MPTCP] [PATCH net-next 1/6] mptcp: open code mptcp variant for lock_sock Paolo Abeni
2020-11-27 10:10 ` Paolo Abeni
2020-11-27 10:10 [MPTCP] [PATCH net-next 0/6] mptcp: avoid workqueue usage for data Paolo Abeni
2020-11-27 10:10 ` Paolo Abeni

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=7d93fc11-4993-802e-e318-157226f91cf6@linux.intel.com \
    --to=unknown@example.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.