Okay, I have committed some parts of the diff and made a couple of other tweaks
which were sometimes causing it to hang. Please test the diff below instead.
Index: fdm.c
===================================================================
RCS file: /cvsroot/fdm/fdm/fdm.c,v
retrieving revision 1.183
diff -u -p -r1.183 fdm.c
--- fdm.c 25 May 2009 21:47:23 -0000 1.183
+++ fdm.c 26 May 2009 06:08:03 -0000
@@ -44,9 +44,11 @@ const char *malloc_options = "AFGJPRX";
void sighandler(int);
struct child *check_children(struct children *, u_int *);
+int wait_children(struct children *, struct children *);
struct conf conf;
+volatile sig_atomic_t sigchld;
volatile sig_atomic_t sigusr1;
volatile sig_atomic_t sigint;
volatile sig_atomic_t sigterm;
@@ -67,6 +69,9 @@ sighandler(int sig)
case SIGTERM:
sigterm = 1;
break;
+ case SIGCHLD:
+ sigchld = 1;
+ break;
}
}
@@ -181,6 +186,79 @@ check_children(struct children *children
return (NULL);
}
+/* Wait for a child and deal with its exit. */
+int
+wait_children(struct children *children, struct children *dead_children)
+{
+ struct child *child, *child2;
+ pid_t pid;
+ int status, retcode = 0;
+ u_int i, j;
+
+ for (;;) {
+ log_debug3("parent: waiting for children");
+ /* Wait for a child. */
+ switch (pid = waitpid(WAIT_ANY, &status, WNOHANG)) {
+ case 0:
+ return (0);
+ case -1:
+ if (errno == ECHILD)
+ return (0);
+ fatal("waitpid failed");
+ }
+
+ /* Handle the exit status. */
+ if (WIFSIGNALED(status)) {
+ retcode = 1;
+ log_debug2("parent: child %ld got signal %d",
+ (long) pid, WTERMSIG(status));
+ } else if (!WIFEXITED(status)) {
+ retcode = 1;
+ log_debug2("parent: child %ld exited badly",
+ (long) pid);
+ } else {
+ if (WEXITSTATUS(status) != 0)
+ retcode = 1;
+ log_debug2("parent: child %ld returned %d",
+ (long) pid, WEXITSTATUS(status));
+ }
+
+ /* Find this child. */
+ child = NULL;
+ for (i = 0; i < ARRAY_LENGTH(children); i++) {
+ child = ARRAY_ITEM(children, i);
+ if (pid == child->pid)
+ break;
+ }
+ if (i == ARRAY_LENGTH(children)) {
+ log_debug2("parent: unidentified child %ld",
+ (long) pid);
+ continue;
+ }
+
+ if (child->io != NULL) {
+ io_close(child->io);
+ io_free(child->io);
+ child->io = NULL;
+ }
+ ARRAY_REMOVE(children, i);
+ ARRAY_ADD(dead_children, child);
+
+ /* If this child was the parent of any others, kill them too. */
+ for (j = 0; j < ARRAY_LENGTH(children); j++) {
+ child2 = ARRAY_ITEM(children, j);
+ if (child2->parent != child)
+ continue;
+
+ log_debug2("parent: child %ld died: killing %ld",
+ (long) child->pid, (long) child2->pid);
+ kill(child2->pid, SIGTERM);
+ }
+ }
+
+ return (retcode);
+}
+
__dead void
usage(void)
{
@@ -198,7 +276,6 @@ main(int argc, char **argv)
enum fdmop op = FDMOP_NONE;
const char *proxy = NULL, *s;
char tmp[BUFSIZ], *ptr, *lock = NULL, *user, *home = NULL;
- long n;
struct utsname un;
struct passwd *pw;
struct stat sb;
@@ -207,8 +284,8 @@ main(int argc, char **argv)
TAILQ_HEAD(, account) actaq; /* active accounts */
pid_t pid;
struct children children, dead_children;
- struct child *child, *child2;
- struct io *rio;
+ struct child *child;
+ struct io *dead_io;
struct iolist iol;
double tim;
struct sigaction act;
@@ -218,6 +295,7 @@ main(int argc, char **argv)
struct strings macros;
struct child_fetch_data *cfd;
struct userdata *ud;
+ sigset_t sigset;
#ifdef DEBUG
struct rule *r;
struct action *t;
@@ -676,21 +754,29 @@ main(int argc, char **argv)
(long) child->pid, a->name);
}
- /* Fill the io list. */
+ /* Check children and fill the io list. */
ARRAY_CLEAR(&iol);
for (i = 0; i < ARRAY_LENGTH(&children); i++) {
child = ARRAY_ITEM(&children, i);
- ARRAY_ADD(&iol, child->io);
+ if (child->io != NULL)
+ ARRAY_ADD(&iol, child->io);
}
/* Poll the io list. */
- n = io_polln(
- ARRAY_DATA(&iol), ARRAY_LENGTH(&iol), &rio, INFTIM, NULL);
- switch (n) {
- case -1:
- fatalx("child socket error");
- case 0:
- fatalx("child socket closed");
+ if (ARRAY_LENGTH(&iol) != 0) {
+ switch (io_polln(ARRAY_DATA(&iol), ARRAY_LENGTH(&iol),
+ &dead_io, INFTIM, NULL)) {
+ case -1:
+ case 0:
+ break;
+ default:
+ dead_io = NULL;
+ break;
+ }
+ } else {
+ /* break? */
+ sigemptyset(&sigset);
+ sigsuspend(&sigset);
}
/* Check all children for pending privsep messages. */
@@ -704,48 +790,32 @@ main(int argc, char **argv)
continue;
/* Child has said it is ready to exit, tell it to. */
+ log_debug2("parent: sending exit message to child %ld",
+ (long) child->pid);
memset(&msg, 0, sizeof msg);
msg.type = MSG_EXIT;
if (privsep_send(child->io, &msg, NULL) != 0)
fatalx("privsep_send error");
+ }
- /* Wait for the child. */
- if (waitpid(child->pid, &status, 0) == -1)
- fatal("waitpid failed");
- if (WIFSIGNALED(status)) {
- res = 1;
- log_debug2("parent: child %ld got signal %d",
- (long) child->pid, WTERMSIG(status));
- } else if (!WIFEXITED(status)) {
- res = 1;
- log_debug2("parent: child %ld exited badly",
- (long) child->pid);
- } else {
- if (WEXITSTATUS(status) != 0)
- res = 1;
- log_debug2("parent: child %ld returned %d",
- (long) child->pid, WEXITSTATUS(status));
- }
-
- io_close(child->io);
- io_free(child->io);
- child->io = NULL;
-
- ARRAY_REMOVE(&children, i);
- ARRAY_ADD(&dead_children, child);
+ /* Collect any dead children. */
+ if (sigchld && wait_children(&children, &dead_children) != 0)
+ res = 1;
+ sigchld = 0;
- /*
- * If this child was the parent of any others, kill
- * them too.
- */
+ /* Close dead buffers (no more data coming now). */
+ if (dead_io != NULL) {
for (i = 0; i < ARRAY_LENGTH(&children); i++) {
- child2 = ARRAY_ITEM(&children, i);
- if (child2->parent != child)
+ child = ARRAY_ITEM(&children, i);
+ if (dead_io != child->io)
continue;
-
- log_debug("parent: child %ld died: killing %ld",
- (long) child->pid, (long) child2->pid);
- kill(child2->pid, SIGTERM);
+ log_debug2("parent: child %ld socket error",
+ (long) child->pid);
+ kill(child->pid, SIGTERM);
+
+ io_close(child->io);
+ io_free(child->io);
+ child->io = NULL;
}
}
}
Index: child.c
===================================================================
RCS file: /cvsroot/fdm/fdm/child.c,v
retrieving revision 1.149
diff -u -p -r1.149 child.c
--- child.c 26 May 2009 06:05:00 -0000 1.149
+++ child.c 26 May 2009 06:08:03 -0000
@@ -118,8 +118,10 @@ child_start(struct children *children, u
if ((child->pid = child_fork()) == 0) {
for (i = 0; i < ARRAY_LENGTH(children); i++) {
childp = ARRAY_ITEM(children, i);
- io_close(childp->io);
- io_free(childp->io);
+ if (childp->io != NULL) {
+ io_close(childp->io);
+ io_free(childp->io);
+ }
}
io_close(child->io);
io_free(child->io);
--
To UNSUBSCRIBE, email to debian-bugs-dist-requ...@lists.debian.org
with a subject of "unsubscribe". Trouble? Contact listmas...@lists.debian.org
