* [PATCH net-next-2.6] net: rfs: enable RFS before first data packet is received
@ 2011-06-15 2:15 Eric Dumazet
2011-06-16 23:50 ` Ben Hutchings
0 siblings, 1 reply; 5+ messages in thread
From: Eric Dumazet @ 2011-06-15 2:15 UTC (permalink / raw)
To: Tom Herbert, David Miller; +Cc: netdev, Ben Hutchings, jamal
First packet received on a passive tcp flow is not correctly RFS
steered.
One sock_rps_record_flow() call is missing in inet_accept()
But before that, we also must record rxhash when child socket is setup.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
CC: Tom Herbert <therbert@google.com>
CC: Ben Hutchings <bhutchings@solarflare.com>
CC: Jamal Hadi Salim <hadi@cyberus.ca>
---
Netconf2011 workshop ;)
net/ipv4/af_inet.c | 1 +
net/ipv4/tcp_ipv4.c | 1 +
2 files changed, 2 insertions(+)
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 83673d2..0600f0f 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -676,6 +676,7 @@ int inet_accept(struct socket *sock, struct socket *newsock, int flags)
lock_sock(sk2);
+ sock_rps_record_flow(sk2);
WARN_ON(!((1 << sk2->sk_state) &
(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_CLOSE)));
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 617dee3..955b8e6 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1594,6 +1594,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
goto discard;
if (nsk != sk) {
+ sock_rps_save_rxhash(nsk, skb->rxhash);
if (tcp_child_process(sk, nsk, skb)) {
rsk = nsk;
goto reset;
^ permalink raw reply related [flat|nested] 5+ messages in thread
* Re: [PATCH net-next-2.6] net: rfs: enable RFS before first data packet is received
2011-06-15 2:15 [PATCH net-next-2.6] net: rfs: enable RFS before first data packet is received Eric Dumazet
@ 2011-06-16 23:50 ` Ben Hutchings
2011-06-17 3:38 ` David Miller
0 siblings, 1 reply; 5+ messages in thread
From: Ben Hutchings @ 2011-06-16 23:50 UTC (permalink / raw)
To: Eric Dumazet; +Cc: Tom Herbert, David Miller, netdev, jamal
On Wed, 2011-06-15 at 04:15 +0200, Eric Dumazet wrote:
> First packet received on a passive tcp flow is not correctly RFS
> steered.
>
> One sock_rps_record_flow() call is missing in inet_accept()
>
> But before that, we also must record rxhash when child socket is setup.
>
> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
> CC: Tom Herbert <therbert@google.com>
> CC: Ben Hutchings <bhutchings@solarflare.com>
> CC: Jamal Hadi Salim <hadi@cyberus.ca>
> ---
> Netconf2011 workshop ;)
>
> net/ipv4/af_inet.c | 1 +
> net/ipv4/tcp_ipv4.c | 1 +
> 2 files changed, 2 insertions(+)
>
> diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
> index 83673d2..0600f0f 100644
> --- a/net/ipv4/af_inet.c
> +++ b/net/ipv4/af_inet.c
> @@ -676,6 +676,7 @@ int inet_accept(struct socket *sock, struct socket *newsock, int flags)
>
> lock_sock(sk2);
>
> + sock_rps_record_flow(sk2);
> WARN_ON(!((1 << sk2->sk_state) &
> (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_CLOSE)));
>
> diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
> index 617dee3..955b8e6 100644
> --- a/net/ipv4/tcp_ipv4.c
> +++ b/net/ipv4/tcp_ipv4.c
> @@ -1594,6 +1594,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
> goto discard;
>
> if (nsk != sk) {
> + sock_rps_save_rxhash(nsk, skb->rxhash);
> if (tcp_child_process(sk, nsk, skb)) {
> rsk = nsk;
> goto reset;
>
I haven't tried this, but it looks reasonable to me.
What about IPv6? The logic in tcp_v6_do_rcv() looks very similar.
Ben.
--
Ben Hutchings, Senior Software 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.
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [PATCH net-next-2.6] net: rfs: enable RFS before first data packet is received
2011-06-16 23:50 ` Ben Hutchings
@ 2011-06-17 3:38 ` David Miller
2011-06-17 13:45 ` [PATCH v2] " Eric Dumazet
0 siblings, 1 reply; 5+ messages in thread
From: David Miller @ 2011-06-17 3:38 UTC (permalink / raw)
To: bhutchings; +Cc: eric.dumazet, therbert, netdev, hadi
From: Ben Hutchings <bhutchings@solarflare.com>
Date: Fri, 17 Jun 2011 00:50:46 +0100
> On Wed, 2011-06-15 at 04:15 +0200, Eric Dumazet wrote:
>> @@ -1594,6 +1594,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
>> goto discard;
>>
>> if (nsk != sk) {
>> + sock_rps_save_rxhash(nsk, skb->rxhash);
>> if (tcp_child_process(sk, nsk, skb)) {
>> rsk = nsk;
>> goto reset;
>>
>
> I haven't tried this, but it looks reasonable to me.
>
> What about IPv6? The logic in tcp_v6_do_rcv() looks very similar.
Indeed ipv6 side needs the same fix.
Eric please add that part and resubmit. And in fact I might stick
this into net-2.6 instead of net-next-2.6
Thanks!
^ permalink raw reply [flat|nested] 5+ messages in thread
* [PATCH v2] net: rfs: enable RFS before first data packet is received
2011-06-17 3:38 ` David Miller
@ 2011-06-17 13:45 ` Eric Dumazet
2011-06-17 19:27 ` David Miller
0 siblings, 1 reply; 5+ messages in thread
From: Eric Dumazet @ 2011-06-17 13:45 UTC (permalink / raw)
To: David Miller; +Cc: bhutchings, therbert, netdev, hadi
Le jeudi 16 juin 2011 à 23:38 -0400, David Miller a écrit :
> From: Ben Hutchings <bhutchings@solarflare.com>
> Date: Fri, 17 Jun 2011 00:50:46 +0100
>
> > On Wed, 2011-06-15 at 04:15 +0200, Eric Dumazet wrote:
> >> @@ -1594,6 +1594,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
> >> goto discard;
> >>
> >> if (nsk != sk) {
> >> + sock_rps_save_rxhash(nsk, skb->rxhash);
> >> if (tcp_child_process(sk, nsk, skb)) {
> >> rsk = nsk;
> >> goto reset;
> >>
> >
> > I haven't tried this, but it looks reasonable to me.
> >
> > What about IPv6? The logic in tcp_v6_do_rcv() looks very similar.
>
> Indeed ipv6 side needs the same fix.
>
> Eric please add that part and resubmit. And in fact I might stick
> this into net-2.6 instead of net-next-2.6
>
OK, here is the net-2.6 based one then, thanks !
[PATCH v2] net: rfs: enable RFS before first data packet is received
First packet received on a passive tcp flow is not correctly RFS
steered.
One sock_rps_record_flow() call is missing in inet_accept()
But before that, we also must record rxhash when child socket is setup.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
CC: Tom Herbert <therbert@google.com>
CC: Ben Hutchings <bhutchings@solarflare.com>
CC: Jamal Hadi Salim <hadi@cyberus.ca>
---
V2: add ipv6 support, as Ben noticed.
net/ipv4/af_inet.c | 1 +
net/ipv4/tcp_ipv4.c | 1 +
net/ipv6/tcp_ipv6.c | 1 +
3 files changed, 3 insertions(+)
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 9c19260..eae1f67 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -676,6 +676,7 @@ int inet_accept(struct socket *sock, struct socket *newsock, int flags)
lock_sock(sk2);
+ sock_rps_record_flow(sk2);
WARN_ON(!((1 << sk2->sk_state) &
(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_CLOSE)));
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a7d6671..708dc20 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1589,6 +1589,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
goto discard;
if (nsk != sk) {
+ sock_rps_save_rxhash(nsk, skb->rxhash);
if (tcp_child_process(sk, nsk, skb)) {
rsk = nsk;
goto reset;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index d1fd287..87551ca 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1644,6 +1644,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
* the new socket..
*/
if(nsk != sk) {
+ sock_rps_save_rxhash(nsk, skb->rxhash);
if (tcp_child_process(sk, nsk, skb))
goto reset;
if (opt_skb)
^ permalink raw reply related [flat|nested] 5+ messages in thread
* Re: [PATCH v2] net: rfs: enable RFS before first data packet is received
2011-06-17 13:45 ` [PATCH v2] " Eric Dumazet
@ 2011-06-17 19:27 ` David Miller
0 siblings, 0 replies; 5+ messages in thread
From: David Miller @ 2011-06-17 19:27 UTC (permalink / raw)
To: eric.dumazet; +Cc: bhutchings, therbert, netdev, hadi
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Fri, 17 Jun 2011 15:45:15 +0200
> [PATCH v2] net: rfs: enable RFS before first data packet is received
>
> First packet received on a passive tcp flow is not correctly RFS
> steered.
>
> One sock_rps_record_flow() call is missing in inet_accept()
>
> But before that, we also must record rxhash when child socket is setup.
>
> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Applied.
^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2011-06-17 19:27 UTC | newest]
Thread overview: 5+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2011-06-15 2:15 [PATCH net-next-2.6] net: rfs: enable RFS before first data packet is received Eric Dumazet
2011-06-16 23:50 ` Ben Hutchings
2011-06-17 3:38 ` David Miller
2011-06-17 13:45 ` [PATCH v2] " Eric Dumazet
2011-06-17 19:27 ` David Miller
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).