Test Result : TaskSetManagerSuite

0 failures (±0)
50 tests (±0)
Took 31 sec.

All Tests

Test nameDurationStatus
Ensure TaskSetManager is usable after addition of levels0.25 secPassed
Executors exit for reason unrelated to currently running tasks0.33 secPassed
Kill other task attempts when one attempt belonging to the same task succeeds0.23 secPassed
Killing speculative tasks does not count towards aborting the taskset0.53 secPassed
Not serializable exception thrown if the task cannot be serialized0.72 secPassed
SPARK-13343 speculative tasks that didn't commit shouldn't be marked as success0.14 secPassed
SPARK-13704 Rack Resolution is done with a batch of de-duped hosts0.2 secPassed
SPARK-17894: Verify TaskSetManagers for different stage attempts have unique names0.76 secPassed
SPARK-19868: DagScheduler only notified of taskEnd when state is ready1.1 secPassed
SPARK-21563 context's added jars shouldn't change mid-TaskSet0.85 secPassed
SPARK-24677: Avoid NoSuchElementException from MedianHeap0.31 secPassed
SPARK-24755 Executor loss can cause task to not be resubmitted0.22 secPassed
SPARK-26755 Ensure that a speculative task is submitted only once for execution0.13 secPassed
SPARK-26755 Ensure that a speculative task obeys original locality preferences0.18 secPassed
SPARK-29976 Regular speculation configs should still take effect even when a threshold is provided0.17 secPassed
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 provided0.13 secPassed
SPARK-29976 when a speculation time threshold is provided, should speculative run the task even if there are not enough successful runs, total tasks: 10.16 secPassed
SPARK-29976 when a speculation time threshold is provided, should speculative run the task even if there are not enough successful runs, total tasks: 20.17 secPassed
SPARK-29976: when the speculation time threshold is not provided,don't speculative run if there are not enough successful runs, total tasks: 10.11 secPassed
SPARK-29976: when the speculation time threshold is not provided,don't speculative run if there are not enough successful runs, total tasks: 20.13 secPassed
SPARK-4939: no-pref tasks should be scheduled after process-local tasks finished0.55 secPassed
SPARK-4939: node-local tasks should be scheduled right after process-local tasks finished1.3 secPassed
TaskOutputFileAlreadyExistException lead to task set abortion0.16 secPassed
TaskSet with no preferences0.45 secPassed
TaskSetManager allocate resource addresses from available resources0.14 secPassed
Test TaskLocation for different host type1 msPassed
Test that locations with HDFSCacheTaskLocation are treated as PROCESS_LOCAL0.16 secPassed
[SPARK-13931] taskSetManager should not send Resubmitted tasks after being a zombie0.75 secPassed
[SPARK-22074] Task killed by other attempt task should not be resubmitted0.67 secPassed
abort the job if total size of results is too large2.9 secPassed
basic delay scheduling0.22 secPassed
cores due to standalone settings, speculate if there is only one task in the stage0.19 secPassed
delay scheduling with failed hosts0.18 secPassed
delay scheduling with fallback0.58 secPassed
do not emit warning when serialized task is small0.6 secPassed
don't update blacklist for shuffle-fetch failures, preemption, denied commits, or killed tasks0.81 secPassed
emit warning when serialized task is large0.56 secPassed
executors should be blacklisted after task failure, in spite of locality preferences0.33 secPassed
multiple offers with no preferences0.3 secPassed
new executors get added and lost0.32 secPassed
node-local tasks should be scheduled right away when there are only node-local and no-preference tasks0.87 secPassed
repeated failures lead to task set abortion0.46 secPassed
reset9.3 secPassed
skip unsatisfiable locality levels0.41 secPassed
speculative and noPref task should be scheduled after node-local0.32 secPassed
task result lost0.2 secPassed
test RACK_LOCAL tasks0.19 secPassed
update application blacklist for shuffle-fetch0.3 secPassed
update blacklist before adding pending task to avoid race condition0.75 secPassed
we do not need to delay scheduling when we only have noPref tasks in the queue0.11 secPassed