On 10/18/2010 11:54 AM, Hans Schillstrom wrote:
On Monday 18 October 2010 10:59:25 Daniel Lezcano wrote:
On 10/08/2010 01:16 PM, Hans Schillstrom wrote:
This part contains the include files
where include/net/netns/ip_vs.h is new and contains all moved vars.
SUMMARY
include/net/ip_vs.h | 136 ++++---
include/net/net_namespace.h | 2 +
include/net/netns/ip_vs.h | 112 +++++
Signed-off-by:Hans Schillstrom<hans.schillstrom@xxxxxxxxxxxx>
---
[ ... ]
#ifdef CONFIG_IP_VS_IPV6
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index bd10a79..b59cdc5 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -15,6 +15,7 @@
#include<net/netns/ipv4.h>
#include<net/netns/ipv6.h>
#include<net/netns/dccp.h>
+#include<net/netns/ip_vs.h>
#include<net/netns/x_tables.h>
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
#include<net/netns/conntrack.h>
@@ -91,6 +92,7 @@ struct net {
struct sk_buff_head wext_nlevents;
#endif
struct net_generic *gen;
+ struct netns_ipvs *ipvs;
};
IMHO, it would be better to use the net_generic infra-structure instead
of adding a new field in the netns structure.
I realized that to, but the performance penalty is quite high with net_generic :-(
But on the other hand if you are going to backport it, (without recompiling the kernel)
you gonna need it!
Hmm, yes. We don't want to have the init_net_ns performances to be impacted.
You use here a pointer which will be dereferenced like the net_generic,
I don't think there will be
a big difference between using net_generic and using a pointer in the
net namespace structure.
The difference is the id usage, but this one is based on the idr which
is quite fast.
We should experiment a bit here to compare both solutions.
IMHO, we can (1) create a non-pointer netns_ipvs field in the net
namespace structure or (2) use a pointer [with net_generic].
(1) is the faster but with the drawback of having a bigger memory
footprint even if the ipvs module is not loaded.
In this case we have to take care of what we store in the netns_ipvs
structure, that is reduce the per namespace table and so. At the first
glance, I think we can reduce this to the sysctls and a very few data,
for example using global tables tagged with the namespace and we don't
break the cacheline alignment optimization.
(2) is slower but as the memory is allocated and freed when the module
is loaded/unloaded. What I don't like with this approach is we add some
overhead even if the netns is not compiled in the kernel.
My sugestion, take both with a configuration switch like:
(i.e. avoid the rcu locking)
--- net/ip_vs.h ---
...
extern int ip_vs_net_id; /* net id for ip_vs */
static inline struct netns_ipvs * net_ipvs(struct net* net, int id) {
#ifdef CONFIG_IP_VS_FAST_NETNS
return net->ipvs;
#else
return (struct netns_ipvs *)net_generic(net, id);
#endif
}
...
and where you need the netns_ipvs struct ptr,
[snip]
struct ip_vs_conn *ip_vs_conn_in_get(struct net *net, ....
{
struct netns_ipvs *ipvs = net_ipvs(net, ip_vs_net_id);
...
It is a nice way to wrap both solutions but at this point I don't think
it is worth to add a 3rd option to compile ipvs.
--
To unsubscribe from this list: send the line "unsubscribe netfilter-devel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
