If restart fails it is usually due to an error for a restoring task,
which is place in ctx->errno. Then the coordinator wakes up and sees
an -EINTR.
This patch changes the coordinator's behavior to report the error
value placed in ctx->errno (if an error occurred) rather than report
a confusing -EINTR.
Signed-off-by: Oren Laadan <orenl@xxxxxxxxxxxxxxx>
---
checkpoint/restart.c | 15 +++++++++++++--
1 files changed, 13 insertions(+), 2 deletions(-)
diff --git a/checkpoint/restart.c b/checkpoint/restart.c
index 5daadc4..9b75de8 100644
--- a/checkpoint/restart.c
+++ b/checkpoint/restart.c
@@ -711,7 +711,7 @@ static inline int is_task_active(struct ckpt_ctx *ctx, pid_t pid)
}
/* should not be called under write_lock_irq(&tasklist_lock) */
-static inline void _restore_notify_error(struct ckpt_ctx *ctx, int errno)
+static void _restore_notify_error(struct ckpt_ctx *ctx, int errno)
{
/* first to fail: notify everyone (racy but harmless) */
if (!ckpt_test_ctx_error(ctx)) {
@@ -1263,9 +1263,20 @@ static int do_restore_coord(struct ckpt_ctx *ctx, pid_t pid)
post_restore_task();
restore_debug_error(ctx, ret);
- if (ret < 0) {
+
+ if (ret < 0)
ckpt_set_ctx_error(ctx, ret);
+
+ if (ckpt_test_ctx_error(ctx)) {
destroy_descendants(ctx);
+ /*
+ * If a restaring task (or we) reported an error, that set
+ * out return value to that error. (Need the unlikely loop
+ * because the error is recorded after the flag is set).
+ */
+ while (!ctx->errno)
+ yield();
+ ret = ctx->errno;
} else {
ckpt_set_ctx_success(ctx);
wake_up_all(&ctx->waitq);
--
1.6.0.4
_______________________________________________
Containers mailing list
Containers@xxxxxxxxxxxxxxxxxxxxxxxxxx
https://lists.linux-foundation.org/mailman/listinfo/containers
