From: David Miller <davem@davemloft.net>
To: amirv@mellanox.com, amirv.mellanox@gmail.com
Cc: eric.dumazet@gmail.com, edumazet@google.com,
netdev@vger.kernel.org, yevgenyp@mellanox.com,
ogerlitz@mellanox.com, idos@mellanox.com
Subject: Re: [PATCH net-next] net/mlx4_en: remove NETDEV_TX_BUSY
Date: Tue, 07 Oct 2014 13:21:02 -0400 (EDT) [thread overview]
Message-ID: <20141007.132102.2147742408943394634.davem@davemloft.net> (raw)
In-Reply-To: <5433A48E.1040505@gmail.com>
From: Amir Vadai <amirv.mellanox@gmail.com>
Date: Tue, 07 Oct 2014 11:30:06 +0300
> On 10/6/2014 7:30 PM, Eric Dumazet wrote:
>> From: Eric Dumazet <edumazet@google.com>
>>
>> Drivers should avoid NETDEV_TX_BUSY as much as possible.
>>
>> They should stop the tx queue before qdisc even tries to push another
>> packet, to avoid requeues.
>>
>> For a driver supporting skb->xmit_more, this is likely to be a prereq
>> anyway, otherwise we could have a tx deadlock : We need to force a
>> doorbell if TX ring is full.
>>
>> Signed-off-by: Eric Dumazet <edumazet@google.com>
>> ---
>
> Reviewed. Also verified that it fixes the deadlock (by sending a large
> burst - larger than ring size). Before this fix, last packet of the
> burst wasn't sent, therefore no doorbell was rang, and the queue was
> stalled.
>
> BTW, another nice optimization that we hope to send soon, is not to arm
> the CQ unless ringing the doorbell.
>
> Acked-by: Amir Vadai <amirv@mellanox.com>
Applied, thanks everyone.
prev parent reply other threads:[~2014-10-07 17:21 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-10-06 6:15 [PATCH net-next V1 00/14] net/mlx4_en: Optimizations to TX flow Amir Vadai
2014-10-06 6:15 ` [PATCH net-next V1 01/14] net/mlx4_en: Code cleanups in tx path Amir Vadai
2014-10-06 6:15 ` [PATCH net-next V1 02/14] net/mlx4_en: Align tx path structures to cache lines Amir Vadai
2014-10-06 6:15 ` [PATCH net-next V1 03/14] net/mlx4_en: Avoid calling bswap in tx fast path Amir Vadai
2014-10-06 6:15 ` [PATCH net-next V1 04/14] net/mlx4_en: tx_info allocated with kmalloc() instead of vmalloc() Amir Vadai
2014-10-06 6:15 ` [PATCH net-next V1 05/14] net/mlx4_en: Avoid a cache line miss in TX completion for single frag skb's Amir Vadai
2014-10-06 6:15 ` [PATCH net-next V1 06/14] net/mlx4_en: Use prefetch in tx path Amir Vadai
2014-10-06 6:15 ` [PATCH net-next V1 07/14] net/mlx4_en: Avoid false sharing in mlx4_en_en_process_tx_cq() Amir Vadai
2014-10-06 6:15 ` [PATCH net-next V1 08/14] net/mlx4_en: mlx4_en_xmit() reads ring->cons once, and ahead of time to avoid stalls Amir Vadai
2014-10-06 6:15 ` [PATCH net-next V1 09/14] net/mlx4_en: Use local var in tx flow for skb_shinfo(skb) Amir Vadai
2014-10-06 6:15 ` [PATCH net-next V1 10/14] net/mlx4_en: Use local var for skb_headlen(skb) Amir Vadai
2014-10-06 6:16 ` [PATCH net-next V1 11/14] net/mlx4_en: tx_info->ts_requested was not cleared Amir Vadai
2014-10-06 6:16 ` [PATCH net-next V1 12/14] net/mlx4_en: Enable the compiler to make is_inline() inlined Amir Vadai
2014-10-06 6:16 ` [PATCH net-next V1 13/14] ethtool: Ethtool parameter to dynamically change tx_copybreak Amir Vadai
2014-10-06 6:16 ` [PATCH net-next V1 14/14] net/mlx4_en: Use the new tx_copybreak to set inline threshold Amir Vadai
2014-10-06 12:51 ` [PATCH net-next V1 00/14] net/mlx4_en: Optimizations to TX flow Eric Dumazet
2014-10-06 12:54 ` Amir Vadai
2014-10-06 16:30 ` [PATCH net-next] net/mlx4_en: remove NETDEV_TX_BUSY Eric Dumazet
2014-10-07 8:30 ` Amir Vadai
2014-10-07 12:38 ` Eric Dumazet
2014-10-07 17:21 ` David Miller [this message]
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=20141007.132102.2147742408943394634.davem@davemloft.net \
--to=davem@davemloft.net \
--cc=amirv.mellanox@gmail.com \
--cc=amirv@mellanox.com \
--cc=edumazet@google.com \
--cc=eric.dumazet@gmail.com \
--cc=idos@mellanox.com \
--cc=netdev@vger.kernel.org \
--cc=ogerlitz@mellanox.com \
--cc=yevgenyp@mellanox.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).