Hi,
Here's a simple patch to change sockets_in_use to make use of
per-cpu areas.
I have couple of questions though...
1. Was this var made per-cpu just to avoid atomic_t or locking
or are there real life workloads which cause too many sock_alloc
and sock_releases to cause cacheline bouncing?
2. Is this var required? since we can just sum up all proto->stats.inuse
and remove this var altogether? (This var is read only for /proc
reporting)
Thanks,
Kiran
diff -ruN -X dontdiff linux-2.5.52/net/socket.c sockets_in_use-2.5.52/net/socket.c
--- linux-2.5.52/net/socket.c Mon Dec 16 07:37:53 2002
+++ sockets_in_use-2.5.52/net/socket.c Mon Dec 23 11:48:44 2002
@@ -189,10 +189,7 @@
* Statistics counters of the socket lists
*/
-static union {
- int counter;
- char __pad[SMP_CACHE_BYTES];
-} sockets_in_use[NR_CPUS] __cacheline_aligned = {{0}};
+static DEFINE_PER_CPU(int, sockets_in_use);
/*
* Support routines. Move socket addresses back and forth across the kernel/user
@@ -475,7 +472,8 @@
inode->i_uid = current->fsuid;
inode->i_gid = current->fsgid;
- sockets_in_use[smp_processor_id()].counter++;
+ get_cpu_var(sockets_in_use)++;
+ put_cpu_var(sockets_in_use);
return sock;
}
@@ -511,7 +509,8 @@
if (sock->fasync_list)
printk(KERN_ERR "sock_release: fasync list not empty!\n");
- sockets_in_use[smp_processor_id()].counter--;
+ get_cpu_var(sockets_in_use)--;
+ put_cpu_var(sockets_in_use);
if (!sock->file) {
iput(SOCK_INODE(sock));
return;
@@ -1851,7 +1850,7 @@
int counter = 0;
for (cpu = 0; cpu < NR_CPUS; cpu++)
- counter += sockets_in_use[cpu].counter;
+ counter += per_cpu(sockets_in_use, cpu);
/* It can be negative, by the way. 8) */
if (counter < 0)
-
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/
This archive was generated by hypermail 2b29 : Mon Dec 23 2002 - 22:00:32 EST