[GIT PULL nf-next] IPVS

[GIT PULL nf-next] IPVS

[Simon Horman]

Hi Pablo,

please consider pulling
git://git.kernel.org/pub/scm/linux/kernel/git/horms/ipvs-next.git master
to obtain and enhancement to the SH scheduelr from Michael Maixim.

Michael Maxim (1):
      IPVS: Modify the SH scheduler to use weights

 net/netfilter/ipvs/Kconfig    |   15 +++++++++++++++
 net/netfilter/ipvs/ip_vs_sh.c |   20 ++++++++++++++++++--
 2 files changed, 33 insertions(+), 2 deletions(-)

[PATCH] IPVS: Modify the SH scheduler to use weights

[Simon Horman]

From: Michael Maxim <mike@okcupid.com>

Modify the algorithm to build the source hashing hash table to add
extra slots for destinations with higher weight. This has the effect
of allowing an IPVS SH user to give more connections to hosts that
have been configured to have a higher weight.

Signed-off-by: Michael Maxim <mike@okcupid.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/Kconfig    |   15 +++++++++++++++
 net/netfilter/ipvs/ip_vs_sh.c |   20 ++++++++++++++++++--
 2 files changed, 33 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
index 70bd1d0..af4c0b8 100644
--- a/net/netfilter/ipvs/Kconfig
+++ b/net/netfilter/ipvs/Kconfig
@@ -232,6 +232,21 @@ config	IP_VS_NQ
 	  If you want to compile it in kernel, say Y. To compile it as a
 	  module, choose M here. If unsure, say N.
 
+comment 'IPVS SH scheduler'
+
+config IP_VS_SH_TAB_BITS
+	int "IPVS source hashing table size (the Nth power of 2)"
+	range 4 20
+	default 8
+	---help---
+	  The source hashing scheduler maps source IPs to destinations
+	  stored in a hash table. This table is tiled by each destination
+	  until all slots in the table are filled. When using weights to
+	  allow destinations to receive more connections, the table is
+	  tiled an amount proportional to the weights specified. The table
+	  needs to be large enough to effectively fit all the destinations
+	  multiplied by their respective weights.
+
 comment 'IPVS application helper'
 
 config	IP_VS_FTP
diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c
index 33815f4..e0ca520 100644
--- a/net/netfilter/ipvs/ip_vs_sh.c
+++ b/net/netfilter/ipvs/ip_vs_sh.c
@@ -30,6 +30,11 @@
  * server is dead or overloaded, the load balancer can bypass the cache
  * server and send requests to the original server directly.
  *
+ * The weight destination attribute can be used to control the
+ * distribution of connections to the destinations in servernode. The
+ * greater the weight, the more connections the destination
+ * will receive.
+ *
  */
 
 #define KMSG_COMPONENT "IPVS"
@@ -99,9 +104,11 @@ ip_vs_sh_assign(struct ip_vs_sh_bucket *tbl, struct ip_vs_service *svc)
 	struct ip_vs_sh_bucket *b;
 	struct list_head *p;
 	struct ip_vs_dest *dest;
+	int d_count;
 
 	b = tbl;
 	p = &svc->destinations;
+	d_count = 0;
 	for (i=0; i<IP_VS_SH_TAB_SIZE; i++) {
 		if (list_empty(p)) {
 			b->dest = NULL;
@@ -113,14 +120,23 @@ ip_vs_sh_assign(struct ip_vs_sh_bucket *tbl, struct ip_vs_service *svc)
 			atomic_inc(&dest->refcnt);
 			b->dest = dest;
 
-			p = p->next;
+			IP_VS_DBG_BUF(6, "assigned i: %d dest: %s weight: %d\n",
+				      i, IP_VS_DBG_ADDR(svc->af, &dest->addr),
+				      atomic_read(&dest->weight));
+
+			/* Don't move to next dest until filling weight */
+			if (++d_count >= atomic_read(&dest->weight)) {
+				p = p->next;
+				d_count = 0;
+			}
+
 		}
 		b++;
 	}
+
 	return 0;
 }
 
-
 /*
  *      Flush all the hash buckets of the specified table.
  */
-- 
1.7.6.3

Re: [PATCH] IPVS: Modify the SH scheduler to use weights

[Pablo Neira Ayuso]

On Wed, Dec 07, 2011 at 05:07:03PM +0900, Simon Horman wrote:
> From: Michael Maxim <mike@okcupid.com>
> 
> Modify the algorithm to build the source hashing hash table to add
> extra slots for destinations with higher weight. This has the effect
> of allowing an IPVS SH user to give more connections to hosts that
> have been configured to have a higher weight.
> 
> Signed-off-by: Michael Maxim <mike@okcupid.com>
> Signed-off-by: Simon Horman <horms@verge.net.au>
> ---
>  net/netfilter/ipvs/Kconfig    |   15 +++++++++++++++
>  net/netfilter/ipvs/ip_vs_sh.c |   20 ++++++++++++++++++--
>  2 files changed, 33 insertions(+), 2 deletions(-)
> 
> diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
> index 70bd1d0..af4c0b8 100644
> --- a/net/netfilter/ipvs/Kconfig
> +++ b/net/netfilter/ipvs/Kconfig
> @@ -232,6 +232,21 @@ config	IP_VS_NQ
>  	  If you want to compile it in kernel, say Y. To compile it as a
>  	  module, choose M here. If unsure, say N.
>  
> +comment 'IPVS SH scheduler'
> +
> +config IP_VS_SH_TAB_BITS
> +	int "IPVS source hashing table size (the Nth power of 2)"
> +	range 4 20
> +	default 8
> +	---help---
> +	  The source hashing scheduler maps source IPs to destinations
> +	  stored in a hash table. This table is tiled by each destination
> +	  until all slots in the table are filled. When using weights to
> +	  allow destinations to receive more connections, the table is
> +	  tiled an amount proportional to the weights specified. The table
> +	  needs to be large enough to effectively fit all the destinations
> +	  multiplied by their respective weights.

Hm, does this really belong to this patch?

> +
>  comment 'IPVS application helper'
>  
>  config	IP_VS_FTP
> diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c
> index 33815f4..e0ca520 100644
> --- a/net/netfilter/ipvs/ip_vs_sh.c
> +++ b/net/netfilter/ipvs/ip_vs_sh.c
> @@ -30,6 +30,11 @@
>   * server is dead or overloaded, the load balancer can bypass the cache
>   * server and send requests to the original server directly.
>   *
> + * The weight destination attribute can be used to control the
> + * distribution of connections to the destinations in servernode. The
> + * greater the weight, the more connections the destination
> + * will receive.
> + *
>   */
>  
>  #define KMSG_COMPONENT "IPVS"
> @@ -99,9 +104,11 @@ ip_vs_sh_assign(struct ip_vs_sh_bucket *tbl, struct ip_vs_service *svc)
>  	struct ip_vs_sh_bucket *b;
>  	struct list_head *p;
>  	struct ip_vs_dest *dest;
> +	int d_count;
>  
>  	b = tbl;
>  	p = &svc->destinations;
> +	d_count = 0;
>  	for (i=0; i<IP_VS_SH_TAB_SIZE; i++) {
>  		if (list_empty(p)) {
>  			b->dest = NULL;
> @@ -113,14 +120,23 @@ ip_vs_sh_assign(struct ip_vs_sh_bucket *tbl, struct ip_vs_service *svc)
>  			atomic_inc(&dest->refcnt);
>  			b->dest = dest;
>  
> -			p = p->next;
> +			IP_VS_DBG_BUF(6, "assigned i: %d dest: %s weight: %d\n",
> +				      i, IP_VS_DBG_ADDR(svc->af, &dest->addr),
> +				      atomic_read(&dest->weight));
> +
> +			/* Don't move to next dest until filling weight */
> +			if (++d_count >= atomic_read(&dest->weight)) {
> +				p = p->next;
> +				d_count = 0;
> +			}
> +
>  		}
>  		b++;
>  	}
> +
>  	return 0;
>  }
>  
> -

While at it, would you remove this unnecessary deletions/additions.

Thanks!

Re: [PATCH] IPVS: Modify the SH scheduler to use weights

[Mike Maxim]

The reason I put that in is because the size of that table becomes
more relevant/important if you decide to use the weights in the manner
the patch lets you. It would be conceivable that someone might need to
increase the size of that table to accommodate their configuration, so
I thought it would be handy to be able to do that through the regular
configuration system instead of editing the source.

On Wed, Dec 7, 2011 at 6:30 AM, Pablo Neira Ayuso <pablo@netfilter.org> wrote:
> On Wed, Dec 07, 2011 at 05:07:03PM +0900, Simon Horman wrote:
>> From: Michael Maxim <mike@okcupid.com>
>>
>> Modify the algorithm to build the source hashing hash table to add
>> extra slots for destinations with higher weight. This has the effect
>> of allowing an IPVS SH user to give more connections to hosts that
>> have been configured to have a higher weight.
>>
>> Signed-off-by: Michael Maxim <mike@okcupid.com>
>> Signed-off-by: Simon Horman <horms@verge.net.au>
>> ---
>>  net/netfilter/ipvs/Kconfig    |   15 +++++++++++++++
>>  net/netfilter/ipvs/ip_vs_sh.c |   20 ++++++++++++++++++--
>>  2 files changed, 33 insertions(+), 2 deletions(-)
>>
>> diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
>> index 70bd1d0..af4c0b8 100644
>> --- a/net/netfilter/ipvs/Kconfig
>> +++ b/net/netfilter/ipvs/Kconfig
>> @@ -232,6 +232,21 @@ config   IP_VS_NQ
>>         If you want to compile it in kernel, say Y. To compile it as a
>>         module, choose M here. If unsure, say N.
>>
>> +comment 'IPVS SH scheduler'
>> +
>> +config IP_VS_SH_TAB_BITS
>> +     int "IPVS source hashing table size (the Nth power of 2)"
>> +     range 4 20
>> +     default 8
>> +     ---help---
>> +       The source hashing scheduler maps source IPs to destinations
>> +       stored in a hash table. This table is tiled by each destination
>> +       until all slots in the table are filled. When using weights to
>> +       allow destinations to receive more connections, the table is
>> +       tiled an amount proportional to the weights specified. The table
>> +       needs to be large enough to effectively fit all the destinations
>> +       multiplied by their respective weights.
>
> Hm, does this really belong to this patch?
>
>> +
>>  comment 'IPVS application helper'
>>
>>  config       IP_VS_FTP
>> diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c
>> index 33815f4..e0ca520 100644
>> --- a/net/netfilter/ipvs/ip_vs_sh.c
>> +++ b/net/netfilter/ipvs/ip_vs_sh.c
>> @@ -30,6 +30,11 @@
>>   * server is dead or overloaded, the load balancer can bypass the cache
>>   * server and send requests to the original server directly.
>>   *
>> + * The weight destination attribute can be used to control the
>> + * distribution of connections to the destinations in servernode. The
>> + * greater the weight, the more connections the destination
>> + * will receive.
>> + *
>>   */
>>
>>  #define KMSG_COMPONENT "IPVS"
>> @@ -99,9 +104,11 @@ ip_vs_sh_assign(struct ip_vs_sh_bucket *tbl, struct ip_vs_service *svc)
>>       struct ip_vs_sh_bucket *b;
>>       struct list_head *p;
>>       struct ip_vs_dest *dest;
>> +     int d_count;
>>
>>       b = tbl;
>>       p = &svc->destinations;
>> +     d_count = 0;
>>       for (i=0; i<IP_VS_SH_TAB_SIZE; i++) {
>>               if (list_empty(p)) {
>>                       b->dest = NULL;
>> @@ -113,14 +120,23 @@ ip_vs_sh_assign(struct ip_vs_sh_bucket *tbl, struct ip_vs_service *svc)
>>                       atomic_inc(&dest->refcnt);
>>                       b->dest = dest;
>>
>> -                     p = p->next;
>> +                     IP_VS_DBG_BUF(6, "assigned i: %d dest: %s weight: %d\n",
>> +                                   i, IP_VS_DBG_ADDR(svc->af, &dest->addr),
>> +                                   atomic_read(&dest->weight));
>> +
>> +                     /* Don't move to next dest until filling weight */
>> +                     if (++d_count >= atomic_read(&dest->weight)) {
>> +                             p = p->next;
>> +                             d_count = 0;
>> +                     }
>> +
>>               }
>>               b++;
>>       }
>> +
>>       return 0;
>>  }
>>
>> -
>
> While at it, would you remove this unnecessary deletions/additions.
>
> Thanks!

Re: [PATCH] IPVS: Modify the SH scheduler to use weights

[Simon Horman]

On Wed, Dec 07, 2011 at 10:24:09AM -0500, Mike Maxim wrote:
> The reason I put that in is because the size of that table becomes
> more relevant/important if you decide to use the weights in the manner
> the patch lets you. It would be conceivable that someone might need to
> increase the size of that table to accommodate their configuration, so
> I thought it would be handy to be able to do that through the regular
> configuration system instead of editing the source.

Hi Mike,

I agree, but I think its also reasonable to consider IP_VS_SH_TAB_BITS as
a separate change.

Could you

1. Split the patch into a Kconfig patch and a ip_vs_sh.c patch
2. Remove spurious line additions from the resulting patches?

> 
> On Wed, Dec 7, 2011 at 6:30 AM, Pablo Neira Ayuso <pablo@netfilter.org> wrote:
> > On Wed, Dec 07, 2011 at 05:07:03PM +0900, Simon Horman wrote:
> >> From: Michael Maxim <mike@okcupid.com>
> >>
> >> Modify the algorithm to build the source hashing hash table to add
> >> extra slots for destinations with higher weight. This has the effect
> >> of allowing an IPVS SH user to give more connections to hosts that
> >> have been configured to have a higher weight.
> >>
> >> Signed-off-by: Michael Maxim <mike@okcupid.com>
> >> Signed-off-by: Simon Horman <horms@verge.net.au>
> >> ---
> >>  net/netfilter/ipvs/Kconfig    |   15 +++++++++++++++
> >>  net/netfilter/ipvs/ip_vs_sh.c |   20 ++++++++++++++++++--
> >>  2 files changed, 33 insertions(+), 2 deletions(-)
> >>
> >> diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
> >> index 70bd1d0..af4c0b8 100644
> >> --- a/net/netfilter/ipvs/Kconfig
> >> +++ b/net/netfilter/ipvs/Kconfig
> >> @@ -232,6 +232,21 @@ config   IP_VS_NQ
> >>         If you want to compile it in kernel, say Y. To compile it as a
> >>         module, choose M here. If unsure, say N.
> >>
> >> +comment 'IPVS SH scheduler'
> >> +
> >> +config IP_VS_SH_TAB_BITS
> >> +     int "IPVS source hashing table size (the Nth power of 2)"
> >> +     range 4 20
> >> +     default 8
> >> +     ---help---
> >> +       The source hashing scheduler maps source IPs to destinations
> >> +       stored in a hash table. This table is tiled by each destination
> >> +       until all slots in the table are filled. When using weights to
> >> +       allow destinations to receive more connections, the table is
> >> +       tiled an amount proportional to the weights specified. The table
> >> +       needs to be large enough to effectively fit all the destinations
> >> +       multiplied by their respective weights.
> >
> > Hm, does this really belong to this patch?
> >
> >> +
> >>  comment 'IPVS application helper'
> >>
> >>  config       IP_VS_FTP
> >> diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c
> >> index 33815f4..e0ca520 100644
> >> --- a/net/netfilter/ipvs/ip_vs_sh.c
> >> +++ b/net/netfilter/ipvs/ip_vs_sh.c
> >> @@ -30,6 +30,11 @@
> >>   * server is dead or overloaded, the load balancer can bypass the cache
> >>   * server and send requests to the original server directly.
> >>   *
> >> + * The weight destination attribute can be used to control the
> >> + * distribution of connections to the destinations in servernode. The
> >> + * greater the weight, the more connections the destination
> >> + * will receive.
> >> + *
> >>   */
> >>
> >>  #define KMSG_COMPONENT "IPVS"
> >> @@ -99,9 +104,11 @@ ip_vs_sh_assign(struct ip_vs_sh_bucket *tbl, struct ip_vs_service *svc)
> >>       struct ip_vs_sh_bucket *b;
> >>       struct list_head *p;
> >>       struct ip_vs_dest *dest;
> >> +     int d_count;
> >>
> >>       b = tbl;
> >>       p = &svc->destinations;
> >> +     d_count = 0;
> >>       for (i=0; i<IP_VS_SH_TAB_SIZE; i++) {
> >>               if (list_empty(p)) {
> >>                       b->dest = NULL;
> >> @@ -113,14 +120,23 @@ ip_vs_sh_assign(struct ip_vs_sh_bucket *tbl, struct ip_vs_service *svc)
> >>                       atomic_inc(&dest->refcnt);
> >>                       b->dest = dest;
> >>
> >> -                     p = p->next;
> >> +                     IP_VS_DBG_BUF(6, "assigned i: %d dest: %s weight: %d\n",
> >> +                                   i, IP_VS_DBG_ADDR(svc->af, &dest->addr),
> >> +                                   atomic_read(&dest->weight));
> >> +
> >> +                     /* Don't move to next dest until filling weight */
> >> +                     if (++d_count >= atomic_read(&dest->weight)) {
> >> +                             p = p->next;
> >> +                             d_count = 0;
> >> +                     }
> >> +
> >>               }
> >>               b++;
> >>       }
> >> +
> >>       return 0;
> >>  }
> >>
> >> -
> >
> > While at it, would you remove this unnecessary deletions/additions.
> >
> > Thanks!
> --
> To unsubscribe from this list: send the line "unsubscribe lvs-devel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> 
--
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

Re: [PATCH] IPVS: Modify the SH scheduler to use weights

[Simon Horman]

On Thu, Dec 08, 2011 at 09:40:09AM +0900, Simon Horman wrote:
> On Wed, Dec 07, 2011 at 10:24:09AM -0500, Mike Maxim wrote:
> > The reason I put that in is because the size of that table becomes
> > more relevant/important if you decide to use the weights in the manner
> > the patch lets you. It would be conceivable that someone might need to
> > increase the size of that table to accommodate their configuration, so
> > I thought it would be handy to be able to do that through the regular
> > configuration system instead of editing the source.
> 
> Hi Mike,
> 
> I agree, but I think its also reasonable to consider IP_VS_SH_TAB_BITS as
> a separate change.
> 
> Could you
> 
> 1. Split the patch into a Kconfig patch and a ip_vs_sh.c patch
> 2. Remove spurious line additions from the resulting patches?

Scratch that, please follow Pablo's request.

Re: [PATCH] IPVS: Modify the SH scheduler to use weights

[Mike Maxim]

No problem, I'll send out the new patch now. Thanks!

On Wed, Dec 7, 2011 at 8:11 PM, Simon Horman <horms@verge.net.au> wrote:
> On Thu, Dec 08, 2011 at 09:40:09AM +0900, Simon Horman wrote:
>> On Wed, Dec 07, 2011 at 10:24:09AM -0500, Mike Maxim wrote:
>> > The reason I put that in is because the size of that table becomes
>> > more relevant/important if you decide to use the weights in the manner
>> > the patch lets you. It would be conceivable that someone might need to
>> > increase the size of that table to accommodate their configuration, so
>> > I thought it would be handy to be able to do that through the regular
>> > configuration system instead of editing the source.
>>
>> Hi Mike,
>>
>> I agree, but I think its also reasonable to consider IP_VS_SH_TAB_BITS as
>> a separate change.
>>
>> Could you
>>
>> 1. Split the patch into a Kconfig patch and a ip_vs_sh.c patch
>> 2. Remove spurious line additions from the resulting patches?
>
> Scratch that, please follow Pablo's request.
> --
> To unsubscribe from this list: send the line "unsubscribe lvs-devel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH] IPVS: Modify the SH scheduler to use weights

[Pablo Neira Ayuso]

On Wed, Dec 07, 2011 at 10:24:09AM -0500, Mike Maxim wrote:
> The reason I put that in is because the size of that table becomes
> more relevant/important if you decide to use the weights in the manner
> the patch lets you. It would be conceivable that someone might need to
> increase the size of that table to accommodate their configuration, so
> I thought it would be handy to be able to do that through the regular
> configuration system instead of editing the source.

That explains that chunk.

Would you mind resubmitting the patch including this description in the
patch and removing the unnecessary line deletion / addition?

Thanks!

Re: [PATCH] IPVS: Modify the SH scheduler to use weights

[Simon Horman]

On Wed, Dec 07, 2011 at 12:30:38PM +0100, Pablo Neira Ayuso wrote:
> On Wed, Dec 07, 2011 at 05:07:03PM +0900, Simon Horman wrote:
> > From: Michael Maxim <mike@okcupid.com>
> > 
> > Modify the algorithm to build the source hashing hash table to add
> > extra slots for destinations with higher weight. This has the effect
> > of allowing an IPVS SH user to give more connections to hosts that
> > have been configured to have a higher weight.
> > 
> > Signed-off-by: Michael Maxim <mike@okcupid.com>
> > Signed-off-by: Simon Horman <horms@verge.net.au>
> > ---
> >  net/netfilter/ipvs/Kconfig    |   15 +++++++++++++++
> >  net/netfilter/ipvs/ip_vs_sh.c |   20 ++++++++++++++++++--
> >  2 files changed, 33 insertions(+), 2 deletions(-)
> > 
> > diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
> > index 70bd1d0..af4c0b8 100644
> > --- a/net/netfilter/ipvs/Kconfig
> > +++ b/net/netfilter/ipvs/Kconfig
> > @@ -232,6 +232,21 @@ config	IP_VS_NQ
> >  	  If you want to compile it in kernel, say Y. To compile it as a
> >  	  module, choose M here. If unsure, say N.
> >  
> > +comment 'IPVS SH scheduler'
> > +
> > +config IP_VS_SH_TAB_BITS
> > +	int "IPVS source hashing table size (the Nth power of 2)"
> > +	range 4 20
> > +	default 8
> > +	---help---
> > +	  The source hashing scheduler maps source IPs to destinations
> > +	  stored in a hash table. This table is tiled by each destination
> > +	  until all slots in the table are filled. When using weights to
> > +	  allow destinations to receive more connections, the table is
> > +	  tiled an amount proportional to the weights specified. The table
> > +	  needs to be large enough to effectively fit all the destinations
> > +	  multiplied by their respective weights.
> 
> Hm, does this really belong to this patch?

It seemed reasonable to me, as it is related to the main purpose of
the patch. But I'm happy to split it out into a separate patch.

> 
> > +
> >  comment 'IPVS application helper'
> >  
> >  config	IP_VS_FTP
> > diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c
> > index 33815f4..e0ca520 100644
> > --- a/net/netfilter/ipvs/ip_vs_sh.c
> > +++ b/net/netfilter/ipvs/ip_vs_sh.c
> > @@ -30,6 +30,11 @@
> >   * server is dead or overloaded, the load balancer can bypass the cache
> >   * server and send requests to the original server directly.
> >   *
> > + * The weight destination attribute can be used to control the
> > + * distribution of connections to the destinations in servernode. The
> > + * greater the weight, the more connections the destination
> > + * will receive.
> > + *
> >   */
> >  
> >  #define KMSG_COMPONENT "IPVS"
> > @@ -99,9 +104,11 @@ ip_vs_sh_assign(struct ip_vs_sh_bucket *tbl, struct ip_vs_service *svc)
> >  	struct ip_vs_sh_bucket *b;
> >  	struct list_head *p;
> >  	struct ip_vs_dest *dest;
> > +	int d_count;
> >  
> >  	b = tbl;
> >  	p = &svc->destinations;
> > +	d_count = 0;
> >  	for (i=0; i<IP_VS_SH_TAB_SIZE; i++) {
> >  		if (list_empty(p)) {
> >  			b->dest = NULL;
> > @@ -113,14 +120,23 @@ ip_vs_sh_assign(struct ip_vs_sh_bucket *tbl, struct ip_vs_service *svc)
> >  			atomic_inc(&dest->refcnt);
> >  			b->dest = dest;
> >  
> > -			p = p->next;
> > +			IP_VS_DBG_BUF(6, "assigned i: %d dest: %s weight: %d\n",
> > +				      i, IP_VS_DBG_ADDR(svc->af, &dest->addr),
> > +				      atomic_read(&dest->weight));
> > +
> > +			/* Don't move to next dest until filling weight */
> > +			if (++d_count >= atomic_read(&dest->weight)) {
> > +				p = p->next;
> > +				d_count = 0;
> > +			}
> > +
> >  		}
> >  		b++;
> >  	}
> > +
> >  	return 0;
> >  }
> >  
> > -
> 
> While at it, would you remove this unnecessary deletions/additions.

Sure.

[GIT PULL nf-next] IPVS

[Simon Horman]

Hi Pablo,

please consider pulling
git://git.kernel.org/pub/scm/linux/kernel/git/horms/ipvs-next.git master
to obtain and enhancement to the SH scheduelr from Michael Maixim.

This patch includes the changes that you requested; A note about the
Kconfig change in the changelog and removal of whitespace-only changes.

Michael Maxim (1):
      IPVS: Modify the SH scheduler to use weights

 net/netfilter/ipvs/Kconfig    |   15 +++++++++++++++
 net/netfilter/ipvs/ip_vs_sh.c |   18 +++++++++++++++++-
 2 files changed, 32 insertions(+), 1 deletions(-)

[PATCH] IPVS: Modify the SH scheduler to use weights

[Simon Horman]

From: Michael Maxim <mike@okcupid.com>

Modify the algorithm to build the source hashing hash table to add
extra slots for destinations with higher weight. This has the effect
of allowing an IPVS SH user to give more connections to hosts that
have been configured to have a higher weight.

The reason for the Kconfig change is because the size of the hash table
becomes more relevant/important if you decide to use the weights in the
manner this patch lets you. It would be conceivable that someone might
need to increase the size of that table to accommodate their
configuration, so it will be handy to be able to do that through the
regular configuration system instead of editing the source.

Signed-off-by: Michael Maxim <mike@okcupid.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
 net/netfilter/ipvs/Kconfig    |   15 +++++++++++++++
 net/netfilter/ipvs/ip_vs_sh.c |   18 +++++++++++++++++-
 2 files changed, 32 insertions(+), 1 deletions(-)

diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
index 70bd1d0..af4c0b8 100644
--- a/net/netfilter/ipvs/Kconfig
+++ b/net/netfilter/ipvs/Kconfig
@@ -232,6 +232,21 @@ config	IP_VS_NQ
 	  If you want to compile it in kernel, say Y. To compile it as a
 	  module, choose M here. If unsure, say N.
 
+comment 'IPVS SH scheduler'
+
+config IP_VS_SH_TAB_BITS
+	int "IPVS source hashing table size (the Nth power of 2)"
+	range 4 20
+	default 8
+	---help---
+	  The source hashing scheduler maps source IPs to destinations
+	  stored in a hash table. This table is tiled by each destination
+	  until all slots in the table are filled. When using weights to
+	  allow destinations to receive more connections, the table is
+	  tiled an amount proportional to the weights specified. The table
+	  needs to be large enough to effectively fit all the destinations
+	  multiplied by their respective weights.
+
 comment 'IPVS application helper'
 
 config	IP_VS_FTP
diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c
index 33815f4..069e8d4 100644
--- a/net/netfilter/ipvs/ip_vs_sh.c
+++ b/net/netfilter/ipvs/ip_vs_sh.c
@@ -30,6 +30,11 @@
  * server is dead or overloaded, the load balancer can bypass the cache
  * server and send requests to the original server directly.
  *
+ * The weight destination attribute can be used to control the
+ * distribution of connections to the destinations in servernode. The
+ * greater the weight, the more connections the destination
+ * will receive.
+ *
  */
 
 #define KMSG_COMPONENT "IPVS"
@@ -99,9 +104,11 @@ ip_vs_sh_assign(struct ip_vs_sh_bucket *tbl, struct ip_vs_service *svc)
 	struct ip_vs_sh_bucket *b;
 	struct list_head *p;
 	struct ip_vs_dest *dest;
+	int d_count;
 
 	b = tbl;
 	p = &svc->destinations;
+	d_count = 0;
 	for (i=0; i<IP_VS_SH_TAB_SIZE; i++) {
 		if (list_empty(p)) {
 			b->dest = NULL;
@@ -113,7 +120,16 @@ ip_vs_sh_assign(struct ip_vs_sh_bucket *tbl, struct ip_vs_service *svc)
 			atomic_inc(&dest->refcnt);
 			b->dest = dest;
 
-			p = p->next;
+			IP_VS_DBG_BUF(6, "assigned i: %d dest: %s weight: %d\n",
+				      i, IP_VS_DBG_ADDR(svc->af, &dest->addr),
+				      atomic_read(&dest->weight));
+
+			/* Don't move to next dest until filling weight */
+			if (++d_count >= atomic_read(&dest->weight)) {
+				p = p->next;
+				d_count = 0;
+			}
+
 		}
 		b++;
 	}
-- 
1.7.6.3