| Ensure TaskSetManager is usable after addition of levels | 0.25 sec | Passed |
| Executors exit for reason unrelated to currently running tasks | 0.33 sec | Passed |
| Kill other task attempts when one attempt belonging to the same task succeeds | 0.23 sec | Passed |
| Killing speculative tasks does not count towards aborting the taskset | 0.53 sec | Passed |
| Not serializable exception thrown if the task cannot be serialized | 0.72 sec | Passed |
| SPARK-13343 speculative tasks that didn't commit shouldn't be marked as success | 0.14 sec | Passed |
| SPARK-13704 Rack Resolution is done with a batch of de-duped hosts | 0.2 sec | Passed |
| SPARK-17894: Verify TaskSetManagers for different stage attempts have unique names | 0.76 sec | Passed |
| SPARK-19868: DagScheduler only notified of taskEnd when state is ready | 1.1 sec | Passed |
| SPARK-21563 context's added jars shouldn't change mid-TaskSet | 0.85 sec | Passed |
| SPARK-24677: Avoid NoSuchElementException from MedianHeap | 0.31 sec | Passed |
| SPARK-24755 Executor loss can cause task to not be resubmitted | 0.22 sec | Passed |
| SPARK-26755 Ensure that a speculative task is submitted only once for execution | 0.13 sec | Passed |
| SPARK-26755 Ensure that a speculative task obeys original locality preferences | 0.18 sec | Passed |
| SPARK-29976 Regular speculation configs should still take effect even when a threshold is provided | 0.17 sec | Passed |
| SPARK-29976 when a speculation time threshold is provided, should not speculative if there are too many tasks in the stage even though time threshold is provided | 0.13 sec | Passed |
| SPARK-29976 when a speculation time threshold is provided, should speculative run the task even if there are not enough successful runs, total tasks: 1 | 0.16 sec | Passed |
| SPARK-29976 when a speculation time threshold is provided, should speculative run the task even if there are not enough successful runs, total tasks: 2 | 0.17 sec | Passed |
| SPARK-29976: when the speculation time threshold is not provided,don't speculative run if there are not enough successful runs, total tasks: 1 | 0.11 sec | Passed |
| SPARK-29976: when the speculation time threshold is not provided,don't speculative run if there are not enough successful runs, total tasks: 2 | 0.13 sec | Passed |
| SPARK-4939: no-pref tasks should be scheduled after process-local tasks finished | 0.55 sec | Passed |
| SPARK-4939: node-local tasks should be scheduled right after process-local tasks finished | 1.3 sec | Passed |
| TaskOutputFileAlreadyExistException lead to task set abortion | 0.16 sec | Passed |
| TaskSet with no preferences | 0.45 sec | Passed |
| TaskSetManager allocate resource addresses from available resources | 0.14 sec | Passed |
| Test TaskLocation for different host type | 1 ms | Passed |
| Test that locations with HDFSCacheTaskLocation are treated as PROCESS_LOCAL | 0.16 sec | Passed |
| [SPARK-13931] taskSetManager should not send Resubmitted tasks after being a zombie | 0.75 sec | Passed |
| [SPARK-22074] Task killed by other attempt task should not be resubmitted | 0.67 sec | Passed |
| abort the job if total size of results is too large | 2.9 sec | Passed |
| basic delay scheduling | 0.22 sec | Passed |
| cores due to standalone settings, speculate if there is only one task in the stage | 0.19 sec | Passed |
| delay scheduling with failed hosts | 0.18 sec | Passed |
| delay scheduling with fallback | 0.58 sec | Passed |
| do not emit warning when serialized task is small | 0.6 sec | Passed |
| don't update blacklist for shuffle-fetch failures, preemption, denied commits, or killed tasks | 0.81 sec | Passed |
| emit warning when serialized task is large | 0.56 sec | Passed |
| executors should be blacklisted after task failure, in spite of locality preferences | 0.33 sec | Passed |
| multiple offers with no preferences | 0.3 sec | Passed |
| new executors get added and lost | 0.32 sec | Passed |
| node-local tasks should be scheduled right away when there are only node-local and no-preference tasks | 0.87 sec | Passed |
| repeated failures lead to task set abortion | 0.46 sec | Passed |
| reset | 9.3 sec | Passed |
| skip unsatisfiable locality levels | 0.41 sec | Passed |
| speculative and noPref task should be scheduled after node-local | 0.32 sec | Passed |
| task result lost | 0.2 sec | Passed |
| test RACK_LOCAL tasks | 0.19 sec | Passed |
| update application blacklist for shuffle-fetch | 0.3 sec | Passed |
| update blacklist before adding pending task to avoid race condition | 0.75 sec | Passed |
| we do not need to delay scheduling when we only have noPref tasks in the queue | 0.11 sec | Passed |
![[Jenkins]](/jenkins/static/239d5bf3/images/jenkins-header-logo-v2.svg){kind=logo}
