fix(trace/wtf): Disable Parquet strict typing

This change fixes an issue where some of the traces from the Workflow
Trace Archive would fail to load with the trace format in OpenDC. This
was caused by one of the fields being stored as a double, while the
formats expects it to be a long.

Parquet does not support unioning primitive types. Therefore, we have to
disable strict type checking when reading the file. Furthermore, we need
to support double entries for storing the workflow ids.

3 files changed, 1 insertions, 0 deletions

diff --git a/opendc-trace/opendc-trace-wtf/src/test/resources/shell/tasks/schema-1.0/part.0.parquet b/opendc-trace/opendc-trace-wtf/src/test/resources/shell/tasks/schema-1.0/part.0.parquet
new file mode 100755
index 00000000..31256990
--- /dev/null
+++ b/opendc-trace/opendc-trace-wtf/src/test/resources/shell/tasks/schema-1.0/part.0.parquet
diff --git a/opendc-trace/opendc-trace-wtf/src/test/resources/shell/workflows/schema-1.0/part.0.parquet b/opendc-trace/opendc-trace-wtf/src/test/resources/shell/workflows/schema-1.0/part.0.parquet
new file mode 100755
index 00000000..872469d5
--- /dev/null
+++ b/opendc-trace/opendc-trace-wtf/src/test/resources/shell/workflows/schema-1.0/part.0.parquet
diff --git a/opendc-trace/opendc-trace-wtf/src/test/resources/shell/workload/schema-1.0/generic_information.json b/opendc-trace/opendc-trace-wtf/src/test/resources/shell/workload/schema-1.0/generic_information.json
new file mode 100755
index 00000000..5949ab59
--- /dev/null
+++ b/opendc-trace/opendc-trace-wtf/src/test/resources/shell/workload/schema-1.0/generic_information.json
@@ -0,0 +1 @@
+{"total_workflows": 3403, "total_tasks": 10208, "domain": "Industrial", "date_start": null, "date_end": null, "num_sites": 3403, "num_resources": 10208.0, "num_users": 1, "num_groups": 1, "total_resource_seconds": 89229.863, "authors": ["Shenjun Ma", "Alexey Ilyushkin", "Alexander Stegehuis", "Alexandru Iosup"], "min_resource_task": 1.0, "max_resource_task": 1.0, "std_resource_task": 0.0, "mean_resource_task": 1.0, "median_resource_task": 1.0, "first_quartile_resource_task": 1.0, "third_quartile_resource_task": 1.0, "cov_resource_task": 0.0, "min_memory": -1, "max_memory": -1, "std_memory": 0.0, "mean_memory": -1.0, "median_memory": -1, "first_quartile_memory": -1, "third_quartile_memory": -1, "cov_memory": -0.0, "min_network_usage": -1, "max_network_usage": -1, "std_network_usage": 0.0, "mean_network_usage": -1.0, "median_network_usage": -1, "first_quartile_network_usage": -1, "third_quartile_network_usage": -1, "cov_network_usage": -0.0, "min_disk_space_usage": -1, "max_disk_space_usage": -1, "std_disk_space_usage": 0.0, "mean_disk_space_usage": -1.0, "median_disk_space_usage": -1, "first_quartile_disk_space_usage": -1, "third_quartile_disk_space_usage": -1, "cov_disk_space_usage": -0.0, "min_energy": -1, "max_energy": -1, "std_energy": 0.0, "mean_energy": -1.0, "median_energy": -1, "first_quartile_energy": -1, "third_quartile_energy": -1, "cov_energy": -0.0, "workload_description": "Chronos is a trace from Shell's Chronos IoT production system. It contains pipelines where sensor data is obtained, checked if values are within range (e.g. temperature, operational status, etc.), and the outcomes are written to persistent storage."}
\ No newline at end of file