[Xen-devel] [Patch] Remove timeout in blktap's main tapdisk select loop

["Stephen C. Tweedie" <sct@xxxxxxxxxx>]

tapdisk was using a 1msec select() timeout in its main event loop.  On
timeout, the loop does nothing except repeat, so the timeout achieves
nothing; worse, on a machine with HZ set to less than 1000, a msec
timeout returns immediately, sending tapdisk into a 100%-CPU-
utilisation loop.

Simply remove the timeout entirely; everything still works fine, and
much more efficiently when idle.

Signed-off-by: Stephen Tweedie <sct@xxxxxxxxxx>

diff -r aeba3dd98fbb -r 49d429529228 tools/blktap/drivers/tapdisk.c
--- a/tools/blktap/drivers/tapdisk.c    Thu Sep 28 18:05:08 2006 +0100
+++ b/tools/blktap/drivers/tapdisk.c    Thu Sep 28 23:24:43 2006 +0100
@@ -271,7 +271,6 @@ static int read_msg(char *buf)
        int length, len, msglen, tap_fd, *io_fd;
        char *ptr, *path;
        image_t *img;
-       struct timeval timeout;
        msg_hdr_t *msg;
        msg_newdev_t *msg_dev;
        msg_pid_t *msg_pid;
@@ -579,8 +578,7 @@ int main(int argc, char *argv[])
 {
        int len, msglen, ret;
        char *p, *buf;
-       fd_set readfds, writefds;
-       struct timeval timeout;
+       fd_set readfds, writefds;       
        fd_list_entry_t *ptr;
        struct tap_disk *drv;
        struct td_state *s;
@@ -622,12 +620,9 @@ int main(int argc, char *argv[])
                /*Set all tap fds*/
                LOCAL_FD_SET(&readfds);
 
-               timeout.tv_sec = 0; 
-               timeout.tv_usec = 1000; 
-
                /*Wait for incoming messages*/
                ret = select(maxfds + 1, &readfds, (fd_set *) 0, 
-                            (fd_set *) 0, &timeout);
+                            (fd_set *) 0, NULL);
 
                if (ret > 0) 
                {



_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel