Merge branch 'master' of https://github.com/0xdata/h2o

riccitensor · Sep 18, 2014 · b3d1836 · b3d1836
2 parents fdc38aa + d48d6b5
commit b3d1836
Show file tree

Hide file tree

Showing 4 changed files with 28 additions and 16 deletions.
diff --git a/py/h2o_import.py b/py/h2o_import.py
@@ -250,7 +250,6 @@ def import_only(node=None, schema='local', bucket=None, path=None,
         else:
             folderOffset = head
 
-        print "\nimport_only:", h2o.python_test_name, schema, "uses", schema + "://" + folderOffset + "/" + pattern
         if h2o.abort_after_import:
             raise Exception("Aborting due to abort_after_import (-aai) argument's effect in import_only()")
 
@@ -267,9 +266,10 @@ def import_only(node=None, schema='local', bucket=None, path=None,
                 print "ERROR: Something was missing for s3 on the java -jar cmd line when the cloud was built"
 
             if importParentDir:
-                importResult = node.import_files(folderURI, timeoutSecs=timeoutSecs)
+                finalImportString = folderURI
             else:
-                importResult = node.import_files(folderURI + "/" + pattern, timeoutSecs=timeoutSecs)
+                finalImportString = folderURI + "/" + pattern
+            importResult = node.import_files(finalImportString, timeoutSecs=timeoutSecs)
 
         elif schema=='s3n' or node.redirect_import_folder_to_s3n_path:
             # FIX! hack for now...when we change import folder to import s3, point to unique bucket name for h2o
@@ -284,9 +284,10 @@ def import_only(node=None, schema='local', bucket=None, path=None,
                 print "ERROR: Something was missing for s3n on the java -jar cmd line when the cloud was built"
             folderURI = "s3n://" + folderOffset
             if importParentDir:
-                importResult = node.import_files(folderURI, timeoutSecs=timeoutSecs)
+                finalImportString = folderURI
             else:
-                importResult = node.import_files(folderURI + "/" + pattern, timeoutSecs=timeoutSecs)
+                finalImportString = folderURI + "/" + pattern
+            importResult = node.import_files(finalImportString, timeoutSecs=timeoutSecs)
 
         elif schema=='maprfs':
             if not n.use_maprfs:
@@ -302,9 +303,10 @@ def import_only(node=None, schema='local', bucket=None, path=None,
                 # folderURI = "maprfs:///" + folderOffset
                 folderURI = "maprfs:/" + folderOffset
             if importParentDir:
-                importResult = node.import_files(folderURI, timeoutSecs=timeoutSecs)
+                finalImportString = folderURI
             else:
-                importResult = node.import_files(folderURI + "/" + pattern, timeoutSecs=timeoutSecs)
+                finalImportString = folderURI + "/" + pattern
+            importResult = node.import_files(finalImportString, timeoutSecs=timeoutSecs)
 
         elif schema=='hdfs':
             # check that some state from the cloud building time was right
@@ -322,13 +324,17 @@ def import_only(node=None, schema='local', bucket=None, path=None,
                 # this is different than maprfs? normally we specify the name though
                 folderURI = "hdfs://" + folderOffset
             if importParentDir:
-                importResult = node.import_files(folderURI, timeoutSecs=timeoutSecs)
+                finalImportString = folderURI
             else:
-                importResult = node.import_files(folderURI + "/" + pattern, timeoutSecs=timeoutSecs)
+                finalImportString = folderURI + "/" + pattern
+            importResult = node.import_files(finalImportString, timeoutSecs=timeoutSecs)
 
         else: 
             raise Exception("schema not understood: %s" % schema)
 
+    print "\nimport_only:", h2o.python_test_name, schema, "uses", finalImportString
+    # FIX! why are we returning importPattern here..it's different than finalImportString if we import a folder?
+    # is it used for key matching by others?
     importPattern = folderURI + "/" + pattern
     return (importResult, importPattern)
 

diff --git a/py/testdir_release/c9/test_c9_GBM_airlines_hdfs_fvec.py b/py/testdir_release/c9/test_c9_GBM_airlines_hdfs_fvec.py
@@ -9,6 +9,7 @@ class releaseTest(h2o_common.ReleaseCommon, unittest.TestCase):
 
     def test_c9_GBM_airlines_hdfs_fvec(self):
         h2o.beta_features = True
+        # h2o.verbose = True
 
         files = [
                  ('datasets', 'airlines_all.csv', 'airlines_all.hex', 1800, 'IsDepDelayed')

diff --git a/py/testdir_release/pytest_config-jenkins-175-180.json b/py/testdir_release/pytest_config-jenkins-175-180.json
@@ -7,8 +7,8 @@
     "use_home_for_ice": true,
 
     "key_filename": "~/.0xcustomer/0xcustomer_id_rsa",
-    "h2o_per_host": 1, 
-    "java_heap_GB": 24, 
+    "h2o_per_host": 2, 
+    "java_heap_GB": 12, 
 
     "hdfs_name_node": "172.16.2.176",
     "hdfs_version": "cdh4",

diff --git a/py/testdir_release/runner.sh b/py/testdir_release/runner.sh
@@ -45,7 +45,8 @@ else
     else
         if [[ $USER == "kevin" ]]
         then
-            python ../four_hour_cloud.py -cj pytest_config-kevin.json &
+            # python ../four_hour_cloud.py -cj pytest_config-kevin.json &
+            python ../four_hour_cloud.py -cj pytest_config-jenkins-175-180.json &
         else
             python ../four_hour_cloud.py &
         fi
@@ -108,12 +109,16 @@ then
 
     #    myPy c6 test_c6_hdfs_fvec.py
     #    myPy c8 test_c8_rf_airlines_hdfs_fvec.py
-    #    myPy c9 test_c9_GBM_airlines_hdfs.py
     #    myPy c9 test_c9_GLM_airlines_hdfs_fvec.py
-    #    myPy c10  test_c10_rel_gbm.py
+    # myPy c10 test_c10_glm_fvec.py
+    # myPy c10 test_c10_gbm_fvec.py
+
+
+    # myPy c9 test_c9_GBM_airlines_hdfs_fvec.py
+    # myPy c8 test_c8_rf_airlines_hdfs_fvec.py
     myPy c5 test_c5_KMeans_sphere_26GB_fvec.py
-    myPy c8 test_c8_rf_airlines_hdfs_fvec.py
-    # myPy c9 test_c9_GLM_rc_fvec.py
+    myPy c9 test_c9_GLM_rc_fvec.py
+
 
     # put known failure last
     # doesn't work. key gets locked. forget about it