2005-04-17 00:20:36 +02:00
|
|
|
/*
|
|
|
|
* IPVS: Weighted Round-Robin Scheduling module
|
|
|
|
*
|
|
|
|
* Authors: Wensong Zhang <wensong@linuxvirtualserver.org>
|
|
|
|
*
|
|
|
|
* 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:
|
|
|
|
* Wensong Zhang : changed the ip_vs_wrr_schedule to return dest
|
|
|
|
* Wensong Zhang : changed some comestics things for debugging
|
|
|
|
* Wensong Zhang : changed for the d-linked destination list
|
|
|
|
* Wensong Zhang : added the ip_vs_wrr_update_svc
|
|
|
|
* Julian Anastasov : fixed the bug of returning destination
|
|
|
|
* with weight 0 when all weights are zero
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
2009-07-30 23:29:44 +02:00
|
|
|
#define KMSG_COMPONENT "IPVS"
|
|
|
|
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
|
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
#include <linux/module.h>
|
|
|
|
#include <linux/kernel.h>
|
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 09:04:11 +01:00
|
|
|
#include <linux/slab.h>
|
2008-02-06 05:00:10 +01:00
|
|
|
#include <linux/net.h>
|
2009-12-22 09:42:06 +01:00
|
|
|
#include <linux/gcd.h>
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
#include <net/ip_vs.h>
|
|
|
|
|
|
|
|
/*
|
|
|
|
* current destination pointer for weighted round-robin scheduling
|
|
|
|
*/
|
|
|
|
struct ip_vs_wrr_mark {
|
|
|
|
struct list_head *cl; /* current list head */
|
|
|
|
int cw; /* current weight */
|
|
|
|
int mw; /* maximum weight */
|
|
|
|
int di; /* decreasing interval */
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
|
|
static int ip_vs_wrr_gcd_weight(struct ip_vs_service *svc)
|
|
|
|
{
|
|
|
|
struct ip_vs_dest *dest;
|
|
|
|
int weight;
|
|
|
|
int g = 0;
|
|
|
|
|
|
|
|
list_for_each_entry(dest, &svc->destinations, n_list) {
|
|
|
|
weight = atomic_read(&dest->weight);
|
|
|
|
if (weight > 0) {
|
|
|
|
if (g > 0)
|
|
|
|
g = gcd(weight, g);
|
|
|
|
else
|
|
|
|
g = weight;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return g ? g : 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Get the maximum weight of the service destinations.
|
|
|
|
*/
|
|
|
|
static int ip_vs_wrr_max_weight(struct ip_vs_service *svc)
|
|
|
|
{
|
|
|
|
struct ip_vs_dest *dest;
|
2009-08-31 14:18:48 +02:00
|
|
|
int new_weight, weight = 0;
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
list_for_each_entry(dest, &svc->destinations, n_list) {
|
2009-08-31 14:18:48 +02:00
|
|
|
new_weight = atomic_read(&dest->weight);
|
|
|
|
if (new_weight > weight)
|
|
|
|
weight = new_weight;
|
2005-04-17 00:20:36 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
return weight;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static int ip_vs_wrr_init_svc(struct ip_vs_service *svc)
|
|
|
|
{
|
|
|
|
struct ip_vs_wrr_mark *mark;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Allocate the mark variable for WRR scheduling
|
|
|
|
*/
|
|
|
|
mark = kmalloc(sizeof(struct ip_vs_wrr_mark), GFP_ATOMIC);
|
2011-08-29 23:17:25 +02:00
|
|
|
if (mark == NULL)
|
2005-04-17 00:20:36 +02:00
|
|
|
return -ENOMEM;
|
2011-08-29 23:17:25 +02:00
|
|
|
|
2005-04-17 00:20:36 +02:00
|
|
|
mark->cl = &svc->destinations;
|
|
|
|
mark->cw = 0;
|
|
|
|
mark->mw = ip_vs_wrr_max_weight(svc);
|
|
|
|
mark->di = ip_vs_wrr_gcd_weight(svc);
|
|
|
|
svc->sched_data = mark;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static int ip_vs_wrr_done_svc(struct ip_vs_service *svc)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* Release the mark variable
|
|
|
|
*/
|
|
|
|
kfree(svc->sched_data);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static int ip_vs_wrr_update_svc(struct ip_vs_service *svc)
|
|
|
|
{
|
|
|
|
struct ip_vs_wrr_mark *mark = svc->sched_data;
|
|
|
|
|
|
|
|
mark->cl = &svc->destinations;
|
|
|
|
mark->mw = ip_vs_wrr_max_weight(svc);
|
|
|
|
mark->di = ip_vs_wrr_gcd_weight(svc);
|
|
|
|
if (mark->cw > mark->mw)
|
|
|
|
mark->cw = 0;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Weighted Round-Robin Scheduling
|
|
|
|
*/
|
|
|
|
static struct ip_vs_dest *
|
|
|
|
ip_vs_wrr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
|
|
|
|
{
|
|
|
|
struct ip_vs_dest *dest;
|
|
|
|
struct ip_vs_wrr_mark *mark = svc->sched_data;
|
|
|
|
struct list_head *p;
|
|
|
|
|
2009-08-02 13:05:41 +02:00
|
|
|
IP_VS_DBG(6, "%s(): Scheduling...\n", __func__);
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
/*
|
|
|
|
* This loop will always terminate, because mark->cw in (0, max_weight]
|
|
|
|
* and at least one server has its weight equal to max_weight.
|
|
|
|
*/
|
|
|
|
write_lock(&svc->sched_lock);
|
|
|
|
p = mark->cl;
|
|
|
|
while (1) {
|
|
|
|
if (mark->cl == &svc->destinations) {
|
|
|
|
/* it is at the head of the destination list */
|
|
|
|
|
|
|
|
if (mark->cl == mark->cl->next) {
|
|
|
|
/* no dest entry */
|
2011-02-11 14:01:12 +01:00
|
|
|
ip_vs_scheduler_err(svc,
|
|
|
|
"no destination available: "
|
|
|
|
"no destinations present");
|
2005-04-17 00:20:36 +02:00
|
|
|
dest = NULL;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
mark->cl = svc->destinations.next;
|
|
|
|
mark->cw -= mark->di;
|
|
|
|
if (mark->cw <= 0) {
|
|
|
|
mark->cw = mark->mw;
|
|
|
|
/*
|
|
|
|
* Still zero, which means no available servers.
|
|
|
|
*/
|
|
|
|
if (mark->cw == 0) {
|
|
|
|
mark->cl = &svc->destinations;
|
2011-02-11 14:01:12 +01:00
|
|
|
ip_vs_scheduler_err(svc,
|
|
|
|
"no destination available");
|
2005-04-17 00:20:36 +02:00
|
|
|
dest = NULL;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
} else
|
|
|
|
mark->cl = mark->cl->next;
|
|
|
|
|
|
|
|
if (mark->cl != &svc->destinations) {
|
|
|
|
/* not at the head of the list */
|
|
|
|
dest = list_entry(mark->cl, struct ip_vs_dest, n_list);
|
|
|
|
if (!(dest->flags & IP_VS_DEST_F_OVERLOAD) &&
|
|
|
|
atomic_read(&dest->weight) >= mark->cw) {
|
|
|
|
/* got it */
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (mark->cl == p && mark->cw == mark->di) {
|
|
|
|
/* back to the start, and no dest is found.
|
|
|
|
It is only possible when all dests are OVERLOADED */
|
|
|
|
dest = NULL;
|
2011-02-11 14:01:12 +01:00
|
|
|
ip_vs_scheduler_err(svc,
|
|
|
|
"no destination available: "
|
|
|
|
"all destinations are overloaded");
|
2005-04-17 00:20:36 +02:00
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2008-09-02 15:55:39 +02:00
|
|
|
IP_VS_DBG_BUF(6, "WRR: server %s:%u "
|
|
|
|
"activeconns %d refcnt %d weight %d\n",
|
|
|
|
IP_VS_DBG_ADDR(svc->af, &dest->addr), ntohs(dest->port),
|
|
|
|
atomic_read(&dest->activeconns),
|
|
|
|
atomic_read(&dest->refcnt),
|
|
|
|
atomic_read(&dest->weight));
|
2005-04-17 00:20:36 +02:00
|
|
|
|
|
|
|
out:
|
|
|
|
write_unlock(&svc->sched_lock);
|
|
|
|
return dest;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
static struct ip_vs_scheduler ip_vs_wrr_scheduler = {
|
|
|
|
.name = "wrr",
|
|
|
|
.refcnt = ATOMIC_INIT(0),
|
|
|
|
.module = THIS_MODULE,
|
2008-08-10 11:18:02 +02:00
|
|
|
.n_list = LIST_HEAD_INIT(ip_vs_wrr_scheduler.n_list),
|
2005-04-17 00:20:36 +02:00
|
|
|
.init_service = ip_vs_wrr_init_svc,
|
|
|
|
.done_service = ip_vs_wrr_done_svc,
|
|
|
|
.update_service = ip_vs_wrr_update_svc,
|
|
|
|
.schedule = ip_vs_wrr_schedule,
|
|
|
|
};
|
|
|
|
|
|
|
|
static int __init ip_vs_wrr_init(void)
|
|
|
|
{
|
|
|
|
return register_ip_vs_scheduler(&ip_vs_wrr_scheduler) ;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void __exit ip_vs_wrr_cleanup(void)
|
|
|
|
{
|
|
|
|
unregister_ip_vs_scheduler(&ip_vs_wrr_scheduler);
|
|
|
|
}
|
|
|
|
|
|
|
|
module_init(ip_vs_wrr_init);
|
|
|
|
module_exit(ip_vs_wrr_cleanup);
|
|
|
|
MODULE_LICENSE("GPL");
|