percpu_counter_add() uses a default batch size which is quite big
on platforms with 256 cpus. (2*256 -> 512)
This means dst_entries_get_fast() can be off by +/- 2*(nr_cpus^2)
(131072 on servers with 256 cpus)
Reduce the batch size to something more reasonable, and
add logic to ip6_dst_gc() to call dst_entries_get_slow()
before calling the _very_ expensive fib6_run_gc() function.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
return percpu_counter_sum_positive(&dst->pcpuc_entries);
}
+#define DST_PERCPU_COUNTER_BATCH 32
static inline void dst_entries_add(struct dst_ops *dst, int val)
{
- percpu_counter_add(&dst->pcpuc_entries, val);
+ percpu_counter_add_batch(&dst->pcpuc_entries, val,
+ DST_PERCPU_COUNTER_BATCH);
}
static inline int dst_entries_init(struct dst_ops *dst)
{
struct dst_entry *dst;
- if (ops->gc && dst_entries_get_fast(ops) > ops->gc_thresh) {
+ if (ops->gc &&
+ !(flags & DST_NOCOUNT) &&
+ dst_entries_get_fast(ops) > ops->gc_thresh) {
if (ops->gc(ops)) {
- printk_ratelimited(KERN_NOTICE "Route cache is full: "
- "consider increasing sysctl "
- "net.ipv[4|6].route.max_size.\n");
+ pr_notice_ratelimited("Route cache is full: consider increasing sysctl net.ipv6.route.max_size.\n");
return NULL;
}
}
int entries;
entries = dst_entries_get_fast(ops);
+ if (entries > rt_max_size)
+ entries = dst_entries_get_slow(ops);
+
if (time_after(rt_last_gc + rt_min_interval, jiffies) &&
entries <= rt_max_size)
goto out;