Hi David
I am chasing NR_CPUS syndrom for your NR_CPUS=4096 machines :)
(Feel free to give me an account on one of them just for fun)
I made this patch but have no idea if it actually works
(only compile tested) because I dont know how to use this
CONFIG_NET_CLS_ROUTE stuff
Thank you
[PATCH] NET : NET_CLS_ROUTE : convert ip_rt_acct to per_cpu variables
ip_rt_acct needs 4096 bytes per cpu to perform some accounting.
It is actually allocated as a single huge array [4096*NR_CPUS]
(rounded up to a power of two)
Converting it to a per cpu variable is wanted to :
- Save space on machines were num_possible_cpus() < NR_CPUS
- Better NUMA placement (each cpu gets memory on its node)
Signed-off-by: Eric Dumazet <[EMAIL PROTECTED]>
include/net/route.h | 2 +-
net/ipv4/ip_input.c | 2 +-
net/ipv4/route.c | 17 ++---------------
3 files changed, 4 insertions(+), 17 deletions(-)
diff --git a/include/net/route.h b/include/net/route.h
index f7ce625..3044fd1 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -103,7 +103,7 @@ struct rt_cache_stat
unsigned int out_hlist_search;
};
-extern struct ip_rt_acct *ip_rt_acct;
+DECLARE_PER_CPU(struct ip_rt_acct[256], ip_rt_acct);
struct in_device;
extern int ip_rt_init(void);
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 5b8a760..82f9a52 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -347,7 +347,7 @@ static int ip_rcv_finish(struct sk_buff *skb)
#ifdef CONFIG_NET_CLS_ROUTE
if (unlikely(skb->dst->tclassid)) {
- struct ip_rt_acct *st = ip_rt_acct + 256*smp_processor_id();
+ struct ip_rt_acct *st = __get_cpu_var(ip_rt_acct);
u32 idx = skb->dst->tclassid;
st[idx&0xFF].o_packets++;
st[idx&0xFF].o_bytes+=skb->len;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index f0b28f9..83b319a 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2855,12 +2855,12 @@ ctl_table ipv4_route_table[] = {
#endif
#ifdef CONFIG_NET_CLS_ROUTE
-struct ip_rt_acct *ip_rt_acct;
+DEFINE_PER_CPU(struct ip_rt_acct [256], ip_rt_acct);
/* This code sucks. But you should have seen it before! --RR */
/* IP route accounting ptr for this logical cpu number. */
-#define IP_RT_ACCT_CPU(i) (ip_rt_acct + i * 256)
+#define IP_RT_ACCT_CPU(i) (per_cpu(ip_rt_acct, i))
#ifdef CONFIG_PROC_FS
static int ip_rt_acct_read(char *buffer, char **start, off_t offset,
@@ -2923,19 +2923,6 @@ int __init ip_rt_init(void)
rt_hash_rnd = (int) ((num_physpages ^ (num_physpages>>8)) ^
(jiffies ^ (jiffies >> 7)));
-#ifdef CONFIG_NET_CLS_ROUTE
- {
- int order;
- for (order = 0;
- (PAGE_SIZE << order) < 256 * sizeof(struct ip_rt_acct) * NR_CPUS;
order++)
- /* NOTHING */;
- ip_rt_acct = (struct ip_rt_acct *)__get_free_pages(GFP_KERNEL, order);
- if (!ip_rt_acct)
- panic("IP: failed to allocate ip_rt_acct\n");
- memset(ip_rt_acct, 0, PAGE_SIZE << order);
- }
-#endif
-
ipv4_dst_ops.kmem_cachep =
kmem_cache_create("ip_dst_cache", sizeof(struct rtable), 0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
-
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
