From: Amir Vadai <amirv.mellanox@gmail.com>
To: Eric Dumazet <eric.dumazet@gmail.com>, Amir Vadai <amirv@mellanox.com>
Cc: "David S. Miller" <davem@davemloft.net>,
Or Gerlitz <ogerlitz@mellanox.com>,
Yevgeny Petrilin <yevgenyp@mellanox.com>,
netdev@vger.kernel.org, Eugenia Emantayev <eugenia@mellanox.com>
Subject: Re: [PATCH net-next 01/12] net/mlx4_en: Reuse mapped memory in RX flow
Date: Tue, 10 Dec 2013 11:47:05 +0200 [thread overview]
Message-ID: <52A6E319.20407@gmail.com> (raw)
In-Reply-To: <1386602236.30495.328.camel@edumazet-glaptop2.roam.corp.google.com>
On 09/12/2013 17:17, Eric Dumazet wrote:
> On Mon, 2013-12-09 at 11:44 +0200, Amir Vadai wrote:
>
>> We get optimal performance when rx rings are mapped 1:1 to cpu's - IRQ
>> affinity is set to this CPU, and memory is allocated on the NUMA node
>> close to it (ring->numa_node)
>> In order to do that, we will post a patch soon to use
>> irq_set_affinity_hint() in order to hint the irq balancer. Till this
>> patch is applied, users should set irq affinity through sysfs and
>> disable the irq balancer.
>
> Point is : You have nothing to do to affine memory allocations.
>
> The big problem is correct IRQ affinity, which as you said is addressed
> in a different way/patch
>
> If the IRQ is properly setup, automatically or by irq affinities,
> then memory will be allocated on the right node, its properly done
> by all memory allocators.
>
> The xxx_alloc_node() variants in the fast path are therefore not needed,
> and not using them avoids catastrophic results if affinities are not
> properly set.
You are right. Will be fixed in V1 too.
We'll use xxx_alloc_node() on the initialization phase, but on the fast
path let the kernel choose the NUMA node.
>
>
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
next prev parent reply other threads:[~2013-12-10 9:47 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-12-08 12:35 [PATCH net-next 00/12] net/mlx4: Mellanox driver update 08-12-2013 Amir Vadai
2013-12-08 12:35 ` [PATCH net-next 01/12] net/mlx4_en: Reuse mapped memory in RX flow Amir Vadai
2013-12-08 19:20 ` Eric Dumazet
2013-12-09 9:44 ` Amir Vadai
2013-12-09 15:17 ` Eric Dumazet
2013-12-10 9:47 ` Amir Vadai [this message]
2013-12-08 12:35 ` [PATCH net-next 02/12] net/mlx4_core: Remove zeroed out of explicit QUERY_FUNC_CAP fields Amir Vadai
2013-12-08 12:35 ` [PATCH net-next 03/12] net/mlx4_core: Rename " Amir Vadai
2013-12-08 12:35 ` [PATCH net-next 04/12] net/mlx4_core: Introduce nic_info new flag in QUERY_FUNC_CAP Amir Vadai
2013-12-08 12:35 ` [PATCH net-next 05/12] net/mlx4_core: Expose physical port id as PF/VF capability Amir Vadai
2013-12-08 12:35 ` [PATCH net-next 06/12] net/mlx4_en: Implement ndo_get_phys_port_id Amir Vadai
2013-12-08 12:35 ` [PATCH net-next 07/12] net/mlx4_en: Configure the XPS queue mapping on driver load Amir Vadai
2013-12-08 15:28 ` Sergei Shtylyov
2013-12-08 15:42 ` Amir Vadai
2013-12-08 12:35 ` [PATCH net-next 08/12] net/mlx4_core: Set CQE/EQE size to 64B by default Amir Vadai
2013-12-08 12:35 ` [PATCH net-next 09/12] net/mlx4_en: Ignore irrelevant hypervisor events Amir Vadai
2013-12-08 12:35 ` [PATCH net-next 10/12] net/mlx4_en: Add NAPI support for transmit side Amir Vadai
2013-12-08 19:22 ` Eric Dumazet
2013-12-09 10:07 ` Amir Vadai
2013-12-08 12:35 ` [PATCH net-next 11/12] net/mlx4_en: Fix Supported/Advertised link mode reported by ethtool Amir Vadai
2013-12-08 12:35 ` [PATCH net-next 12/12] net/mlx4_core: Check port number for validity before accessing data Amir Vadai
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=52A6E319.20407@gmail.com \
--to=amirv.mellanox@gmail.com \
--cc=amirv@mellanox.com \
--cc=davem@davemloft.net \
--cc=eric.dumazet@gmail.com \
--cc=eugenia@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).