Re: [PATCH ipvs v2] ipvs: Add simple weighted failover scheduler

[Julian Anastasov <ja@ssi.bg>]

	Hello,

On Tue, 9 Sep 2014, Kenny Mathis wrote:

> Please consider this patch for addition in 3.17
> 
> Add simple weighted IPVS failover support to the Linux kernel. All
> other scheduling modules implement some form of load balancing, while
> this offers a simple failover solution. Connections are directed to
> the appropriate server based solely on highest weight value and server
> availability. Tested functionality with keepalived.
> 
> Signed-off-by: Kenny Mathis <kmathis@chokepoint.net>

	Looks good to me, thanks!

Acked-by: Julian Anastasov <ja@ssi.bg>

	Simon, you can apply it to ipvs-next if there are
no any objections.

> ---
>  net/netfilter/ipvs/Kconfig    |   10 ++++++
>  net/netfilter/ipvs/Makefile   |    1 +
>  net/netfilter/ipvs/ip_vs_fo.c |   79 +++++++++++++++++++++++++++++++++++++++++
>  3 files changed, 90 insertions(+)
>  create mode 100644 net/netfilter/ipvs/ip_vs_fo.c
> 
> diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
> index 0c3b167..3b6929d 100644
> --- a/net/netfilter/ipvs/Kconfig
> +++ b/net/netfilter/ipvs/Kconfig
> @@ -152,6 +152,16 @@ config	IP_VS_WLC
>  	  If you want to compile it in kernel, say Y. To compile it as a
>  	  module, choose M here. If unsure, say N.
>  
> +config  IP_VS_FO
> +		tristate "weighted failover scheduling"
> +	---help---
> +	  The weighted failover scheduling algorithm directs network
> +	  connections to the server with the highest weight that is
> +	  currently available.
> +
> +	  If you want to compile it in kernel, say Y. To compile it as a
> +	  module, choose M here. If unsure, say N.
> +
>  config	IP_VS_LBLC
>  	tristate "locality-based least-connection scheduling"
>  	---help---
> diff --git a/net/netfilter/ipvs/Makefile b/net/netfilter/ipvs/Makefile
> index 34ee602..38b2723 100644
> --- a/net/netfilter/ipvs/Makefile
> +++ b/net/netfilter/ipvs/Makefile
> @@ -26,6 +26,7 @@ obj-$(CONFIG_IP_VS_RR) += ip_vs_rr.o
>  obj-$(CONFIG_IP_VS_WRR) += ip_vs_wrr.o
>  obj-$(CONFIG_IP_VS_LC) += ip_vs_lc.o
>  obj-$(CONFIG_IP_VS_WLC) += ip_vs_wlc.o
> +obj-$(CONFIG_IP_VS_FO) += ip_vs_fo.o
>  obj-$(CONFIG_IP_VS_LBLC) += ip_vs_lblc.o
>  obj-$(CONFIG_IP_VS_LBLCR) += ip_vs_lblcr.o
>  obj-$(CONFIG_IP_VS_DH) += ip_vs_dh.o
> diff --git a/net/netfilter/ipvs/ip_vs_fo.c b/net/netfilter/ipvs/ip_vs_fo.c
> new file mode 100644
> index 0000000..6a2647d
> --- /dev/null
> +++ b/net/netfilter/ipvs/ip_vs_fo.c
> @@ -0,0 +1,79 @@
> +/*
> + * IPVS:        Weighted Fail Over module
> + *
> + * Authors:     Kenny Mathis <kmathis@chokepoint.net>
> + *
> + *              This program is free software; you can redistribute it and/or
> + *              modify it under the terms of the GNU General Public License
> + *              as published by the Free Software Foundation; either version
> + *              2 of the License, or (at your option) any later version.
> + *
> + * Changes:
> + *     Kenny Mathis            :     added initial functionality based on weight
> + *
> + */
> +
> +#define KMSG_COMPONENT "IPVS"
> +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
> +
> +#include <linux/module.h>
> +#include <linux/kernel.h>
> +
> +#include <net/ip_vs.h>
> +
> +/* Weighted Fail Over Module */
> +static struct ip_vs_dest *
> +ip_vs_fo_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
> +		  struct ip_vs_iphdr *iph)
> +{
> +	struct ip_vs_dest *dest, *hweight = NULL;
> +	int hw = 0; /* Track highest weight */
> +
> +	IP_VS_DBG(6, "ip_vs_fo_schedule(): Scheduling...\n");
> +
> +	/* Basic failover functionality
> +	 * Find virtual server with highest weight and send it traffic
> +	 */
> +	list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
> +		if (!(dest->flags & IP_VS_DEST_F_OVERLOAD) &&
> +		    atomic_read(&dest->weight) > hw) {
> +			hweight = dest;
> +			hw = atomic_read(&dest->weight);
> +		}
> +	}
> +
> +	if (hweight) {
> +		IP_VS_DBG_BUF(6, "FO: server %s:%u activeconns %d weight %d\n",
> +			      IP_VS_DBG_ADDR(svc->af, &hweight->addr),
> +			      ntohs(hweight->port),
> +			      atomic_read(&hweight->activeconns),
> +			      atomic_read(&hweight->weight));
> +		return hweight;
> +	}
> +
> +	ip_vs_scheduler_err(svc, "no destination available");
> +	return NULL;
> +}
> +
> +static struct ip_vs_scheduler ip_vs_fo_scheduler = {
> +	.name =			"fo",
> +	.refcnt =		ATOMIC_INIT(0),
> +	.module =		THIS_MODULE,
> +	.n_list =		LIST_HEAD_INIT(ip_vs_fo_scheduler.n_list),
> +	.schedule =		ip_vs_fo_schedule,
> +};
> +
> +static int __init ip_vs_fo_init(void)
> +{
> +	return register_ip_vs_scheduler(&ip_vs_fo_scheduler);
> +}
> +
> +static void __exit ip_vs_fo_cleanup(void)
> +{
> +	unregister_ip_vs_scheduler(&ip_vs_fo_scheduler);
> +	synchronize_rcu();
> +}
> +
> +module_init(ip_vs_fo_init);
> +module_exit(ip_vs_fo_cleanup);
> +MODULE_LICENSE("GPL");
> -- 
> 1.7.9.5

Regards

--
Julian Anastasov <ja@ssi.bg>