From: Slava Ovsiienko <viacheslavo@mellanox.com>
To: Ferruh Yigit <ferruh.yigit@intel.com>,
Matan Azrad <matan@mellanox.com>, "dev@dpdk.org" <dev@dpdk.org>
Cc: Raslan Darawsheh <rasland@mellanox.com>,
Thomas Monjalon <thomas@monjalon.net>
Subject: Re: [dpdk-dev] [PATCH] net/mlx5: fix inline packet size for ConnectX-4LX
Date: Fri, 21 Feb 2020 09:51:14 +0000 [thread overview]
Message-ID: <AM4PR05MB32652DC6C992021267AE9791D2120@AM4PR05MB3265.eurprd05.prod.outlook.com> (raw)
In-Reply-To: <ed3efe3f-973f-ed09-cb2a-a2fec42b053c@intel.com>
> -----Original Message-----
> From: Ferruh Yigit <ferruh.yigit@intel.com>
> Sent: Friday, February 21, 2020 11:44
> To: Slava Ovsiienko <viacheslavo@mellanox.com>; Matan Azrad
> <matan@mellanox.com>; dev@dpdk.org
> Cc: Raslan Darawsheh <rasland@mellanox.com>; Thomas Monjalon
> <thomas@monjalon.net>
> Subject: Re: [PATCH] net/mlx5: fix inline packet size for ConnectX-4LX
>
> On 2/21/2020 7:39 AM, Slava Ovsiienko wrote:
> >> -----Original Message-----
> >> From: Matan Azrad <matan@mellanox.com>
> >> Sent: Friday, February 21, 2020 9:38
> >> To: Slava Ovsiienko <viacheslavo@mellanox.com>; dev@dpdk.org
> >> Cc: Raslan Darawsheh <rasland@mellanox.com>; Thomas Monjalon
> >> <thomas@monjalon.net>; ferruh.yigit@intel.com
> >> Subject: RE: [PATCH] net/mlx5: fix inline packet size for
> >> ConnectX-4LX
> >>
> >>
> >>
> >> From: Viacheslav Ovsiienko
> >>> This patch does extra inline packet size check to tune the
> >>> ConnectX-4LX performance in the legacy Multi-Packet Write mode.
> >>>
> >>> Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
> >>
> >> Slava, Don't you think we want it for stable releases?
> > Yes, thanks for reminding, just forgot "cc: stable", will send to stable ML.
>
> Is the fixed commit known? (fixes line)
Yes, sorry for missed "Fixes" tag
It should be:
Fixes: 7593cf1d3500 ("net/mlx5: fix legacy multi-packet write session")
With best regards, Slava
>
> >
> >>
> >> Besides it:
> >> Acked-by: Matan Azrad <matan@mellanox.com>
> >>
> >>> drivers/net/mlx5/mlx5_rxtx.c | 2 ++
> >>> 1 file changed, 2 insertions(+)
> >>>
> >>> diff --git a/drivers/net/mlx5/mlx5_rxtx.c
> >>> b/drivers/net/mlx5/mlx5_rxtx.c index b55db4f..0df811b 100644
> >>> --- a/drivers/net/mlx5/mlx5_rxtx.c
> >>> +++ b/drivers/net/mlx5/mlx5_rxtx.c
> >>> @@ -4281,6 +4281,8 @@ enum mlx5_txcmp_code {
> >>> loc->mbuf->ol_flags & PKT_TX_DYNF_NOINLINE)
> >>> goto pointer_empw;
> >>> if (MLX5_TXOFF_CONFIG(MPW)) {
> >>> + if (dlen > txq->inlen_send)
> >>> + goto pointer_empw;
> >>> tlen = dlen;
> >>> if (part == room) {
> >>> /* Open new inline MPW session. */
> >>> --
> >>> 1.8.3.1
> >
next prev parent reply other threads:[~2020-02-21 9:51 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-02-20 21:18 Viacheslav Ovsiienko
2020-02-21 7:37 ` Matan Azrad
2020-02-21 7:39 ` Slava Ovsiienko
2020-02-21 9:44 ` Ferruh Yigit
2020-02-21 9:51 ` Slava Ovsiienko [this message]
2020-02-21 10:07 ` Ferruh Yigit
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=AM4PR05MB32652DC6C992021267AE9791D2120@AM4PR05MB3265.eurprd05.prod.outlook.com \
--to=viacheslavo@mellanox.com \
--cc=dev@dpdk.org \
--cc=ferruh.yigit@intel.com \
--cc=matan@mellanox.com \
--cc=rasland@mellanox.com \
--cc=thomas@monjalon.net \
/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).