[SPARK-13408] [CORE] Ignore errors when it's already reported in JobWaiter

## What changes were proposed in this pull request?

`JobWaiter.taskSucceeded` will be called for each task. When `resultHandler` throws an exception, `taskSucceeded` will also throw it for each task. DAGScheduler just catches it and reports it like this:
```Scala
                  try {
                    job.listener.taskSucceeded(rt.outputId, event.result)
                  } catch {
                    case e: Exception =>
                      // TODO: Perhaps we want to mark the resultStage as failed?
                      job.listener.jobFailed(new SparkDriverExecutionException(e))
                  }
```
Therefore `JobWaiter.jobFailed` may be called multiple times.

So `JobWaiter.jobFailed` should use `Promise.tryFailure` instead of `Promise.failure` because the latter one doesn't support calling multiple times.

## How was the this patch tested?

Jenkins tests.

Author: Shixiong Zhu <shixiong@databricks.com>

Closes #11280 from zsxwing/SPARK-13408.

0 files changed, 0 insertions, 0 deletions