| Message ID | 1335939762-1912-19-git-send-email-horms@verge.net.au |
|---|---|
| State | Accepted |
| Headers | show |
Hi David, The IPVS people needs this patch for net-next to allow to tune the socket buffer for ipvs_sync (the state synchronization that they do from kernel-space). This exports sysctl_wmem_max and sysctl_rmem_max living in net/core/sock.c. So far, they've been using global socket tuning to make them bigger (this avoids overruning the socket under high peak of state-change synchronization). I think this is out of my scope (since it's out of the netfilter tree). Would you acknowledge it, please? On Wed, May 02, 2012 at 03:22:42PM +0900, Simon Horman wrote: > From: Hans Schillstrom <hans.schillstrom@ericsson.com> > > To build ip_vs as a module sysctl_rmem_max and sysctl_wmem_max > needs to be exported. > The dependency was added by "ipvs: wakeup master thread" patch > > Signed-off-by: Hans Schillstrom <hans.schillstrom@ericsson.com> > Signed-off-by: Simon Horman <horms@verge.net.au> > --- > net/core/sock.c | 2 ++ > 1 file changed, 2 insertions(+) > > diff --git a/net/core/sock.c b/net/core/sock.c > index c7e60ea..ac3131a 100644 > --- a/net/core/sock.c > +++ b/net/core/sock.c > @@ -258,7 +258,9 @@ static struct lock_class_key af_callback_keys[AF_MAX]; > > /* Run time adjustable parameters. */ > __u32 sysctl_wmem_max __read_mostly = SK_WMEM_MAX; > +EXPORT_SYMBOL(sysctl_wmem_max); > __u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX; > +EXPORT_SYMBOL(sysctl_rmem_max); > __u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX; > __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; > > -- > 1.7.10 > -- To unsubscribe from this list: send the line "unsubscribe netfilter-devel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
From: Pablo Neira Ayuso <pablo@netfilter.org> Date: Sun, 6 May 2012 22:54:12 +0200 > Hi David, > > The IPVS people needs this patch for net-next to allow to tune the > socket buffer for ipvs_sync (the state synchronization that they do > from kernel-space). This exports sysctl_wmem_max and sysctl_rmem_max > living in net/core/sock.c. So far, they've been using global socket > tuning to make them bigger (this avoids overruning the socket under > high peak of state-change synchronization). > > I think this is out of my scope (since it's out of the netfilter > tree). > > Would you acknowledge it, please? Feel free to merge it via your tree: Acked-by: David S. Miller <davem@davemloft.net> -- To unsubscribe from this list: send the line "unsubscribe netfilter-devel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
diff --git a/net/core/sock.c b/net/core/sock.c index c7e60ea..ac3131a 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -258,7 +258,9 @@ static struct lock_class_key af_callback_keys[AF_MAX]; /* Run time adjustable parameters. */ __u32 sysctl_wmem_max __read_mostly = SK_WMEM_MAX; +EXPORT_SYMBOL(sysctl_wmem_max); __u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX; +EXPORT_SYMBOL(sysctl_rmem_max); __u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX; __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;