Hi Oren,

commit 464ff47b6a1241410f432a55ce4bf93c8bd10861 isn't right.  I guess
the problem is that ckpt_coordinator_status(), doesn't do a waitpid
on the global_child_pid?  So if I do a 'restart -w --pids', then the
restarted task proceeds just fine, but restart immediately returns.

Maybe the right answer is to modify ckpt_coordinator_status() to
do a waitpid if ctx->args->wait, but just reverting this commit
doesn't seem to have any ill effects - all my default tests pass.

This reverts commit 464ff47b6a1241410f432a55ce4bf93c8bd10861.
---
 restart.c |   25 +++++++++++++------------
 1 files changed, 13 insertions(+), 12 deletions(-)

diff --git a/restart.c b/restart.c
index d5d069a..cfc359b 100644
--- a/restart.c
+++ b/restart.c
@@ -994,12 +994,10 @@ static int ckpt_coordinator_pidns(struct ckpt_ctx *ctx)
        ckpt_dbg("forking coordinator in new pidns\n");
 
        /*
-        * The coordinator report restart susccess/failure via pipe.
-        * (It cannot use return value, because the in the default
-        * --wait --copy-status case it is already used to report the
-        * root-task's return value).
+        * We won't wait for (collect) the coordinator, so we use a
+        * pipe instead for the coordinator to report success/failure.
         */
-       if (pipe(ctx->pipe_coord) < 0) {
+       if (!ctx->args->wait && pipe(ctx->pipe_coord)) {
                perror("pipe");
                return -1;
        }
@@ -1035,7 +1033,10 @@ static int ckpt_coordinator_pidns(struct ckpt_ctx *ctx)
                return -1;
 
        ctx->args->copy_status = copy;
-       return ckpt_coordinator_status(ctx);
+       if (ctx->args->wait)
+               return ckpt_collect_child(ctx);
+       else
+               return ckpt_coordinator_status(ctx);
 }
 #else
 static int ckpt_coordinator_pidns(struct ckpt_ctx *ctx)
@@ -1093,13 +1094,13 @@ static int ckpt_coordinator(struct ckpt_ctx *ctx)
                 * around and be reaper until all tasks are gone.
                 * Otherwise, container will die as soon as we exit.
                 */
-
-               /* Report success/failure to the parent */
-               if (write(ctx->pipe_coord[1], &ret, sizeof(ret)) < 0) {
-                       perror("failed to report status");
-                       exit(1);
+               if (!ctx->args->wait) {
+                       /* report status because parent won't wait for us */
+                       if (write(ctx->pipe_coord[1], &ret, sizeof(ret)) < 0) {
+                               perror("failed to report status");
+                               exit(1);
+                       }
                }
-
                ret = ckpt_pretend_reaper(ctx);
        } else if (ctx->args->wait) {
                ret = ckpt_collect_child(ctx);
-- 
1.6.1.1

_______________________________________________
Containers mailing list
[email protected]
https://lists.linux-foundation.org/mailman/listinfo/containers

_______________________________________________
Devel mailing list
[email protected]
https://openvz.org/mailman/listinfo/devel

Reply via email to