"David S. Miller" wrote:
> Please try this 2.2.x patch. It fixes the 2.2.x performance
> problem with your example code for me.
Will try when I get back from vacation. Thanks for the quick response!
- Dan
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of
> On both 2.2.14 and 2.2.16, pipe and socketpair are nice and speedy.
> close() is fine for pipes, but at 8000 socketpairs, each call to close()
> takes 14 *milliseconds* at 100% cpu usage. What's up with that?
Welcome to the world of mark sweep garbage collection. The folks who allowed
file
Please try this 2.2.x patch. It fixes the 2.2.x performance
problem with your example code for me.
--- ./include/net/af_unix.h.~1~ Fri Apr 11 21:30:23 1997
+++ ./include/net/af_unix.h Tue Oct 17 00:04:32 2000
@@ -7,7 +7,7 @@
typedef struct sock unix_socket;
extern void unix_gc(void);
Date:Mon, 16 Oct 2000 22:09:03 -0700
From: Dan Kegel <[EMAIL PROTECTED]>
I wrote a little benchmark to call either pipe() or socketpair()
8000 times, then close() on all the fds produced by pipe or
socketpair. On both 2.2.14 and 2.2.16, pipe and socketpair are
nice and
I wrote a little benchmark to call either pipe() or socketpair()
8000 times, then close() on all the fds produced by pipe or socketpair.
On both 2.2.14 and 2.2.16, pipe and socketpair are nice and speedy.
close() is fine for pipes, but at 8000 socketpairs, each call to close()
takes 14
5 matches
Mail list logo