lkml.org 
[lkml]   [2002]   [Jul]   [12]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
Subject[patch trivial 2.5.25] dst.c cleanup -- dst_total
dst_total  is read only #if RT_CACHE_DEBUG >=2 , but is incremented and
decremented during dst_alloc and dst_destroy. Following patch conditions
the atomic_inc and atomic_decs to dst_total with RT_CACHE_DEBUG >= 2

dst_alloc routine (which incements dst_total) shows up with the tests
suggested by Dave Miller for measuring RCU route cache changes.
Profile ticks reduce by 15 % for dst_alloc on a 4 way with the foll
patch (with the default -- RT_CACHE_DEBUG = 0 ).

-Kiran


--- linux-2.5.25-pure/net/core/dst.c Sat Jul 6 05:12:31 2002
+++ linux-2.5.25/net/core/dst.c Fri Jul 12 13:23:09 2002
@@ -29,7 +29,9 @@
* 4) All operations modify state, so a spinlock is used.
*/
static struct dst_entry *dst_garbage_list;
+#if RT_CACHE_DEBUG >= 2
static atomic_t dst_total = ATOMIC_INIT(0);
+#endif
static spinlock_t dst_lock = SPIN_LOCK_UNLOCKED;

static unsigned long dst_gc_timer_expires;
@@ -108,7 +110,9 @@
dst->lastuse = jiffies;
dst->input = dst_discard;
dst->output = dst_blackhole;
+#if RT_CACHE_DEBUG >= 2
atomic_inc(&dst_total);
+#endif
atomic_inc(&ops->entries);
return dst;
}
@@ -158,7 +162,9 @@
dst->ops->destroy(dst);
if (dst->dev)
dev_put(dst->dev);
+#if RT_CACHE_DEBUG >= 2
atomic_dec(&dst_total);
+#endif
kmem_cache_free(dst->ops->kmem_cachep, dst);
}

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
\
 
 \ /
  Last update: 2005-03-22 13:22    [W:0.034 / U:2.232 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site