From: Simon Horman <horms@verge.net.au>
To: Pablo Neira Ayuso <pablo@netfilter.org>
Cc: lvs-devel@vger.kernel.org, netdev@vger.kernel.org,
netfilter-devel@vger.kernel.org,
Wensong Zhang <wensong@linux-vs.org>,
Julian Anastasov <ja@ssi.bg>, Simon Horman <horms@verge.net.au>
Subject: [PATCH 02/34] ipvs: avoid routing by TOS for real server
Date: Fri, 29 Mar 2013 13:11:19 +0900 [thread overview]
Message-ID: <1364530311-11512-3-git-send-email-horms@verge.net.au> (raw)
In-Reply-To: <1364530311-11512-1-git-send-email-horms@verge.net.au>
From: Julian Anastasov <ja@ssi.bg>
Avoid replacing the cached route for real server
on every packet with different TOS. I doubt that routing
by TOS for real server is used at all, so we should be
better with such optimization.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off by: Hans Schillstrom <hans@schillstrom.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
include/net/ip_vs.h | 1 -
net/netfilter/ipvs/ip_vs_xmit.c | 58 +++++++++++++++++----------------------
2 files changed, 25 insertions(+), 34 deletions(-)
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index bee87ba..64db117 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -753,7 +753,6 @@ struct ip_vs_dest {
/* for destination cache */
spinlock_t dst_lock; /* lock of dst_cache */
struct dst_entry *dst_cache; /* destination cache entry */
- u32 dst_rtos; /* RT_TOS(tos) for dst */
u32 dst_cookie;
union nf_inet_addr dst_saddr;
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index ee6b7a9..4b0bd15 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -57,27 +57,24 @@ enum {
* Destination cache to speed up outgoing route lookup
*/
static inline void
-__ip_vs_dst_set(struct ip_vs_dest *dest, u32 rtos, struct dst_entry *dst,
- u32 dst_cookie)
+__ip_vs_dst_set(struct ip_vs_dest *dest, struct dst_entry *dst, u32 dst_cookie)
{
struct dst_entry *old_dst;
old_dst = dest->dst_cache;
dest->dst_cache = dst;
- dest->dst_rtos = rtos;
dest->dst_cookie = dst_cookie;
dst_release(old_dst);
}
static inline struct dst_entry *
-__ip_vs_dst_check(struct ip_vs_dest *dest, u32 rtos)
+__ip_vs_dst_check(struct ip_vs_dest *dest)
{
struct dst_entry *dst = dest->dst_cache;
if (!dst)
return NULL;
- if ((dst->obsolete || rtos != dest->dst_rtos) &&
- dst->ops->check(dst, dest->dst_cookie) == NULL) {
+ if (dst->obsolete && dst->ops->check(dst, dest->dst_cookie) == NULL) {
dest->dst_cache = NULL;
dst_release(dst);
return NULL;
@@ -104,7 +101,7 @@ __mtu_check_toobig_v6(const struct sk_buff *skb, u32 mtu)
/* Get route to daddr, update *saddr, optionally bind route to saddr */
static struct rtable *do_output_route4(struct net *net, __be32 daddr,
- u32 rtos, int rt_mode, __be32 *saddr)
+ int rt_mode, __be32 *saddr)
{
struct flowi4 fl4;
struct rtable *rt;
@@ -113,7 +110,6 @@ static struct rtable *do_output_route4(struct net *net, __be32 daddr,
memset(&fl4, 0, sizeof(fl4));
fl4.daddr = daddr;
fl4.saddr = (rt_mode & IP_VS_RT_MODE_CONNECT) ? *saddr : 0;
- fl4.flowi4_tos = rtos;
fl4.flowi4_flags = (rt_mode & IP_VS_RT_MODE_KNOWN_NH) ?
FLOWI_FLAG_KNOWN_NH : 0;
@@ -124,7 +120,7 @@ retry:
if (PTR_ERR(rt) == -EINVAL && *saddr &&
rt_mode & IP_VS_RT_MODE_CONNECT && !loop) {
*saddr = 0;
- flowi4_update_output(&fl4, 0, rtos, daddr, 0);
+ flowi4_update_output(&fl4, 0, 0, daddr, 0);
goto retry;
}
IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n", &daddr);
@@ -132,7 +128,7 @@ retry:
} else if (!*saddr && rt_mode & IP_VS_RT_MODE_CONNECT && fl4.saddr) {
ip_rt_put(rt);
*saddr = fl4.saddr;
- flowi4_update_output(&fl4, 0, rtos, daddr, fl4.saddr);
+ flowi4_update_output(&fl4, 0, 0, daddr, fl4.saddr);
loop++;
goto retry;
}
@@ -143,7 +139,7 @@ retry:
/* Get route to destination or remote server */
static struct rtable *
__ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
- __be32 daddr, u32 rtos, int rt_mode, __be32 *ret_saddr)
+ __be32 daddr, int rt_mode, __be32 *ret_saddr)
{
struct net *net = dev_net(skb_dst(skb)->dev);
struct rtable *rt; /* Route to the other host */
@@ -152,19 +148,18 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
if (dest) {
spin_lock(&dest->dst_lock);
- if (!(rt = (struct rtable *)
- __ip_vs_dst_check(dest, rtos))) {
- rt = do_output_route4(net, dest->addr.ip, rtos,
- rt_mode, &dest->dst_saddr.ip);
+ rt = (struct rtable *) __ip_vs_dst_check(dest);
+ if (!rt) {
+ rt = do_output_route4(net, dest->addr.ip, rt_mode,
+ &dest->dst_saddr.ip);
if (!rt) {
spin_unlock(&dest->dst_lock);
return NULL;
}
- __ip_vs_dst_set(dest, rtos, dst_clone(&rt->dst), 0);
- IP_VS_DBG(10, "new dst %pI4, src %pI4, refcnt=%d, "
- "rtos=%X\n",
+ __ip_vs_dst_set(dest, dst_clone(&rt->dst), 0);
+ IP_VS_DBG(10, "new dst %pI4, src %pI4, refcnt=%d\n",
&dest->addr.ip, &dest->dst_saddr.ip,
- atomic_read(&rt->dst.__refcnt), rtos);
+ atomic_read(&rt->dst.__refcnt));
}
daddr = dest->addr.ip;
if (ret_saddr)
@@ -177,7 +172,7 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
* for performance reasons because we do not remember saddr
*/
rt_mode &= ~IP_VS_RT_MODE_CONNECT;
- rt = do_output_route4(net, daddr, rtos, rt_mode, &saddr);
+ rt = do_output_route4(net, daddr, rt_mode, &saddr);
if (!rt)
return NULL;
if (ret_saddr)
@@ -307,7 +302,7 @@ __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest,
if (dest) {
spin_lock(&dest->dst_lock);
- rt = (struct rt6_info *)__ip_vs_dst_check(dest, 0);
+ rt = (struct rt6_info *)__ip_vs_dst_check(dest);
if (!rt) {
u32 cookie;
@@ -320,7 +315,7 @@ __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest,
}
rt = (struct rt6_info *) dst;
cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
- __ip_vs_dst_set(dest, 0, dst_clone(&rt->dst), cookie);
+ __ip_vs_dst_set(dest, dst_clone(&rt->dst), cookie);
IP_VS_DBG(10, "new dst %pI6, src %pI6, refcnt=%d\n",
&dest->addr.in6, &dest->dst_saddr.in6,
atomic_read(&rt->dst.__refcnt));
@@ -449,8 +444,9 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
EnterFunction(10);
- if (!(rt = __ip_vs_get_out_rt(skb, NULL, iph->daddr, RT_TOS(iph->tos),
- IP_VS_RT_MODE_NON_LOCAL, NULL)))
+ rt = __ip_vs_get_out_rt(skb, NULL, iph->daddr, IP_VS_RT_MODE_NON_LOCAL,
+ NULL);
+ if (!rt)
goto tx_error_icmp;
/* MTU checking */
@@ -581,10 +577,9 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
}
if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
- RT_TOS(iph->tos),
IP_VS_RT_MODE_LOCAL |
- IP_VS_RT_MODE_NON_LOCAL |
- IP_VS_RT_MODE_RDR, NULL)))
+ IP_VS_RT_MODE_NON_LOCAL |
+ IP_VS_RT_MODE_RDR, NULL)))
goto tx_error_icmp;
local = rt->rt_flags & RTCF_LOCAL;
/*
@@ -832,10 +827,9 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
EnterFunction(10);
if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
- RT_TOS(tos), IP_VS_RT_MODE_LOCAL |
- IP_VS_RT_MODE_NON_LOCAL |
- IP_VS_RT_MODE_CONNECT,
- &saddr)))
+ IP_VS_RT_MODE_LOCAL |
+ IP_VS_RT_MODE_NON_LOCAL |
+ IP_VS_RT_MODE_CONNECT, &saddr)))
goto tx_error_icmp;
if (rt->rt_flags & RTCF_LOCAL) {
ip_rt_put(rt);
@@ -1067,7 +1061,6 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
EnterFunction(10);
if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
- RT_TOS(iph->tos),
IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_KNOWN_NH, NULL)))
@@ -1223,7 +1216,6 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL;
if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
- RT_TOS(ip_hdr(skb)->tos),
rt_mode, NULL)))
goto tx_error_icmp;
local = rt->rt_flags & RTCF_LOCAL;
--
1.7.10.4
next prev parent reply other threads:[~2013-03-29 4:11 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-03-29 4:11 [GIT PULL nf-next] IPVS optimisations for v3.10 Simon Horman
2013-03-29 4:11 ` [PATCH 01/34] net: add skb_dst_set_noref_force Simon Horman
2013-04-01 12:06 ` Pablo Neira Ayuso
2013-04-01 16:57 ` David Miller
2013-04-01 22:42 ` Pablo Neira Ayuso
2013-04-02 1:11 ` Simon Horman
2013-03-29 4:11 ` Simon Horman [this message]
2013-03-29 4:11 ` [PATCH 03/34] ipvs: prefer NETDEV_DOWN event to free cached dsts Simon Horman
2013-03-29 4:11 ` [PATCH 04/34] ipvs: convert the IP_VS_XMIT macros to functions Simon Horman
2013-03-29 4:11 ` [PATCH 05/34] ipvs: rename functions related to dst_cache reset Simon Horman
2013-03-29 4:11 ` [PATCH 06/34] ipvs: no need to reroute anymore on DNAT over loopback Simon Horman
2013-03-29 14:44 ` Sergei Shtylyov
2013-03-29 21:47 ` Julian Anastasov
2013-03-29 4:11 ` [PATCH 07/34] ipvs: do not use skb_share_check Simon Horman
2013-03-29 4:11 ` [PATCH 08/34] ipvs: consolidate all dst checks on transmit in one place Simon Horman
2013-03-29 4:11 ` [PATCH 09/34] ipvs: optimize dst usage for real server Simon Horman
2013-03-29 4:11 ` [PATCH 10/34] ipvs: convert app locks Simon Horman
2013-03-29 4:11 ` [PATCH 11/34] ipvs: remove rs_lock by using RCU Simon Horman
2013-03-29 4:11 ` [PATCH 12/34] ipvs: convert locks used in persistence engines Simon Horman
2013-03-29 4:11 ` [PATCH 13/34] ipvs: convert connection locking Simon Horman
2013-03-29 4:11 ` [PATCH 14/34] ipvs: reorder keys in connection structure Simon Horman
2013-03-29 4:11 ` [PATCH 15/34] ipvs: avoid kmem_cache_zalloc in ip_vs_conn_new Simon Horman
2013-03-29 4:11 ` [PATCH 16/34] ipvs: change ip_vs_sched_lock to mutex Simon Horman
2013-03-29 4:11 ` [PATCH 17/34] ipvs: preparations for using rcu in schedulers Simon Horman
2013-03-29 4:11 ` [PATCH 18/34] ipvs: add ip_vs_dest_hold and ip_vs_dest_put Simon Horman
2013-03-29 4:11 ` [PATCH 19/34] ipvs: convert dh scheduler to rcu Simon Horman
2013-03-29 4:11 ` [PATCH 20/34] ipvs: convert lblc " Simon Horman
2013-03-29 4:11 ` [PATCH 21/34] ipvs: convert lblcr " Simon Horman
2013-03-29 4:11 ` [PATCH 22/34] ipvs: convert lc " Simon Horman
2013-03-29 4:11 ` [PATCH 23/34] ipvs: convert nq " Simon Horman
2013-03-29 4:11 ` [PATCH 24/34] ipvs: convert rr " Simon Horman
2013-03-29 4:11 ` [PATCH 25/34] ipvs: convert sed " Simon Horman
2013-03-29 4:11 ` [PATCH 26/34] ipvs: convert sh " Simon Horman
2013-03-29 4:11 ` [PATCH 27/34] ipvs: convert wlc " Simon Horman
2013-03-29 4:11 ` [PATCH 28/34] ipvs: convert wrr " Simon Horman
2013-03-29 4:11 ` [PATCH 29/34] ipvs: reorganize dest trash Simon Horman
2013-03-29 4:11 ` [PATCH 30/34] ipvs: do not expect result from done_service Simon Horman
2013-03-29 4:11 ` [PATCH 31/34] ipvs: convert sched_lock to spin lock Simon Horman
2013-03-29 4:11 ` [PATCH 32/34] ipvs: convert dests to rcu Simon Horman
2013-03-29 4:11 ` [PATCH 33/34] ipvs: convert services " Simon Horman
2013-03-29 4:11 ` [PATCH 34/34] ipvs: do not disable bh for long time Simon Horman
2013-04-01 22:41 ` [GIT PULL nf-next] IPVS optimisations for v3.10 Pablo Neira Ayuso
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=1364530311-11512-3-git-send-email-horms@verge.net.au \
--to=horms@verge.net.au \
--cc=ja@ssi.bg \
--cc=lvs-devel@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=netfilter-devel@vger.kernel.org \
--cc=pablo@netfilter.org \
--cc=wensong@linux-vs.org \
/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).