From: Ben Hutchings <bhutchings@solarflare.com>
To: amirv@mellanox.co.il
Cc: Tom Herbert <therbert@google.com>,
oren@mellanox.co.il, liranl@mellanox.co.il,
netdev@vger.kernel.org, Diego Crupnicoff <Diego@Mellanox.com>
Subject: Re: RFS issue: no HW filter for paused stream
Date: Wed, 21 Sep 2011 16:09:02 +0100 [thread overview]
Message-ID: <1316617742.2760.18.camel@bwh-desktop> (raw)
In-Reply-To: <4E783855.4020907@dev.mellanox.co.il>
On Tue, 2011-09-20 at 09:53 +0300, Amir Vadai wrote:
> This will unset the current CPU of the rflow that belongs to the desired
> CPU.
> The problem is when the stream resumes and it goes to the wrong RXQ - in
> our HW, it will be according to RSS, as long as there is no specific
> flow steering rule for the stream.
Sorry, yes. Told you I didn't test my patch!
> We need to unset the current CPU of the rflow of the actual RXQ that the
> packet arrived at:
[...]
> Or even better, not set it in the first place - but I'm not sure I
> undersdtand the implications on RPS:
>
> diff --git a/net/core/dev.c b/net/core/dev.c
> index 4b9981c..748acdb 100644
> --- a/net/core/dev.c
> +++ b/net/core/dev.c
> @@ -2654,7 +2654,7 @@ set_rps_cpu(struct net_device *dev, struct sk_buff
> *skb,
> {
> u16 tcpu;
>
> - tcpu = rflow->cpu = next_cpu;
> + tcpu = next_cpu;
> if (tcpu != RPS_NO_CPU) {
> #ifdef CONFIG_RFS_ACCEL
> struct netdev_rx_queue *rxqueue;
>
>
But that means we never move the flow to a new CPU in the non-
accelerated case. So maybe the proper change would be:
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2652,10 +2652,7 @@ static struct rps_dev_flow *
set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
struct rps_dev_flow *rflow, u16 next_cpu)
{
- u16 tcpu;
-
- tcpu = rflow->cpu = next_cpu;
- if (tcpu != RPS_NO_CPU) {
+ if (next_cpu != RPS_NO_CPU) {
#ifdef CONFIG_RFS_ACCEL
struct netdev_rx_queue *rxqueue;
struct rps_dev_flow_table *flow_table;
@@ -2683,16 +2680,16 @@ set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
goto out;
old_rflow = rflow;
rflow = &flow_table->flows[flow_id];
- rflow->cpu = next_cpu;
rflow->filter = rc;
if (old_rflow->filter == rflow->filter)
old_rflow->filter = RPS_NO_FILTER;
out:
#endif
rflow->last_qtail =
- per_cpu(softnet_data, tcpu).input_queue_head;
+ per_cpu(softnet_data, next_cpu).input_queue_head;
}
+ rflow->cpu = next_cpu;
return rflow;
}
--- END ---
--
Ben Hutchings, Staff Engineer, Solarflare
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.
next prev parent reply other threads:[~2011-09-21 15:09 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <CAP7N4Kfd9TOPr_V6+R9yVtK80eGWbkAvPE8BStG0+WhvJHaLGg@mail.gmail.com>
2011-09-19 6:05 ` RFS issue: no HW filter for paused stream Amir Vadai
2011-09-19 15:13 ` Tom Herbert
2011-09-19 15:52 ` Ben Hutchings
2011-09-20 6:53 ` Amir Vadai
2011-09-21 15:09 ` Ben Hutchings [this message]
2011-09-22 6:11 ` Amir Vadai
2011-09-27 23:42 ` Ben Hutchings
2011-10-02 7:59 ` 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=1316617742.2760.18.camel@bwh-desktop \
--to=bhutchings@solarflare.com \
--cc=Diego@Mellanox.com \
--cc=amirv@mellanox.co.il \
--cc=liranl@mellanox.co.il \
--cc=netdev@vger.kernel.org \
--cc=oren@mellanox.co.il \
--cc=therbert@google.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).