Develop Dask parallel execution for runner

docker-compose.yml

@@ -1,5 +1,3 @@
-version: "3.8"
-
 services:
   db:
     image: postgres:15-alpine
@@ -111,14 +109,15 @@ services:
       - .env
     ports:
       - "8500:8500"
+      - "8787:8787"
     depends_on:
       - api
       - s3
       - sqs
     volumes:
       - ./workers/current_evaluation:/root/worker/current_evaluation
       - ./workers/logs:/root/worker/logs
-      - ./workers/tmp:/tmp
+      # - ./workers/tmp:/tmp
       - ./workers/requirements.txt:/root/worker/requirements.txt
       - ./workers/src:/root/worker/src
     restart: unless-stopped

prod.docker-compose.yml

@@ -1,5 +1,3 @@
-version: "3.8"
-
 services:
   db:
     image: postgres:15-alpine

valhub/base/errorcodes.json

@@ -6,7 +6,9 @@
         "4": "No system metadata returned from API",
         "5": "Configuration file not found in current evaluation directory",
         "6": "Required function name not found within submission python file",
-        "7": "Failure cutoff met for submission evaluation and execution has been terminated"
+        "7": "Failure cutoff met for submission evaluation and execution has been terminated",
+        "8": "Submission result length does not match ground truth length",
+        "500": "Internal server error"
     },
     "wr": {
         "1": "Error uploading file to s3",
@@ -19,9 +21,13 @@
         "8": "No file metadata found in API for analysis ID",
         "9": "Not all ground truth data files found in s3 bucket for analysis",
         "10": "Not all analytical data files found in s3 bucket for analysis",
-        "11": "Runner module does not have a 'run' function"
+        "11": "Runner module does not have a 'run' function",
+        "12": "Error posting Error Report to API",
+        "13": "API did not return a valid response",
+        "500": "Internal server error"
     },
     "sb": {
-        "1": ""
+        "1": "Submission function exceeded maximum execution time",
+        "500": "Internal server error"
     }
 }

workers/requirements.txt

@@ -3,4 +3,7 @@ boto3
 pandas
 numpy
 seaborn
-matplotlib
+matplotlib
+dask
+distributed
+bokeh

workers/src/errorcodes.json

@@ -0,0 +1,33 @@
+{
+    "op": {
+        "1": "Submission file is not a valid zipped file",
+        "2": "Error installing Python submission dependencies",
+        "3": "Failed to get system metadata information",
+        "4": "No system metadata returned from API",
+        "5": "Configuration file not found in current evaluation directory",
+        "6": "Required function name not found within submission python file",
+        "7": "Failure cutoff met for submission evaluation and execution has been terminated",
+        "8": "Submission result length does not match ground truth length",
+        "500": "Internal server error"
+    },
+    "wr": {
+        "1": "Error uploading file to s3",
+        "2": "Error downloading file from s3",
+        "3": "No files found in s3 bucket for analysis",
+        "4": "Error updating submission result to API",
+        "5": "Error updating submission status to API",
+        "6": "Required evaluation files not found in s3 bucket",
+        "7": "File metadata for file ID not found in API",
+        "8": "No file metadata found in API for analysis ID",
+        "9": "Not all ground truth data files found in s3 bucket for analysis",
+        "10": "Not all analytical data files found in s3 bucket for analysis",
+        "11": "Runner module does not have a 'run' function",
+        "12": "Error posting Error Report to API",
+        "13": "API did not return a valid response",
+        "500": "Internal server error"
+    },
+    "sb": {
+        "1": "Submission function exceeded maximum execution time",
+        "500": "Internal server error"
+    }
+}

workers/src/logging_config.json

@@ -51,7 +51,8 @@
                 "stdout",
                 "file",
                 "json_file"
-            ]
+            ],
+            "propagate": false
         }
     }
 }