Merge "Update dib stats"

doc/source/operation.rst

@@ -407,23 +407,33 @@ Nodepool builder
 .. zuul:stat:: nodepool.dib_image_build.<diskimage_name>.<ext>.size
    :type: gauge
 
-   This stat reports the size of the built image in bytes.
+   This stat reports the size of the built image in bytes.  ``ext`` is
+   based on the formats of the images created for the build, for
+   example ``qcow2``, ``raw``, ``vhd``, etc.
 
-.. zuul:stat:: nodepool.image_update.<image name>.<provider name>
-   :type: counter, timer
+.. zuul:stat:: nodepool.dib_image_build.<diskimage_name>.status.rc
+   :type: gauge
 
-   Number of image uploads to a specific provider in the cloud plus the time in
-   seconds spent to upload the image.
+   Return code of the last DIB run.  Zero is successful, non-zero is
+   unsuccessful.
+
+.. zuul:stat:: nodepool.dib_image_build.<diskimage_name>.status.duration
+   :type: timer
 
-.. zuul:stat:: nodepool.dib_image_build.<diskimage_name>.<ext>.rc
+   Time the last DIB run for this image build took, in ms
+
+.. zuul:stat:: nodepool.dib_image_build.<diskimage_name>.status.last_build
    :type: gauge
 
-   Return code of the DIB.
+   The UNIX timestamp of the last time a build for this image
+   returned.  This can be useful for presenting a relative time ("X
+   hours ago") in a dashboard.
 
-.. zuul:stat:: nodepool.dib_image_build.<diskimage_name>.<ext>.duration
-   :type: timer
+.. zuul:stat:: nodepool.image_update.<image name>.<provider name>
+   :type: counter, timer
 
-   Time the DIB run took in ms
+   Number of image uploads to a specific provider in the cloud plus the time in
+   seconds spent to upload the image.
 
 Nodepool launcher
 ~~~~~~~~~~~~~~~~~

nodepool/builder.py

@@ -915,12 +915,13 @@ class BuildWorker(BaseWorker):
 
         if self._statsd:
             # report result to statsd
-            for ext in img_types.split(','):
-                key_base = 'nodepool.dib_image_build.%s.%s' % (
-                    diskimage.name, ext)
-                pipeline.gauge(key_base + '.rc', rc)
-                pipeline.timing(key_base + '.duration',
-                                int(build_time * 1000))
+            key_base = 'nodepool.dib_image_build.%s.status' % (
+                diskimage.name)
+            pipeline.timing(key_base + '.duration',
+                            int(build_time * 1000))
+            pipeline.gauge(key_base + '.rc', rc)
+            pipeline.gauge(key_base + '.last_build',
+                           int(time.time()))
             pipeline.send()
 
         return build_data

nodepool/tests/unit/test_builder.py

@@ -309,10 +309,11 @@ class TestNodePoolBuilder(tests.DBTestCase):
         self.waitForImage('fake-provider', 'fake-image')
         # Make sure our cleanup worker properly removes the first build.
         self.waitForBuildDeletion('fake-image', '0000000001')
-        self.assertReportedStat('nodepool.dib_image_build.fake-image.qcow2.rc',
+        self.assertReportedStat('nodepool.dib_image_build.'
+                                'fake-image.status.rc',
                                 '127', 'g')
         self.assertReportedStat('nodepool.dib_image_build.'
-                                'fake-image.qcow2.duration', None, 'ms')
+                                'fake-image.status.duration', None, 'ms')
 
     def test_diskimage_build_only(self):
         configfile = self.setup_config('node_diskimage_only.yaml')
@@ -323,12 +324,15 @@ class TestNodePoolBuilder(tests.DBTestCase):
 
         self.assertEqual(build_tar._formats, ['tar'])
         self.assertEqual(build_default._formats, ['qcow2'])
-        self.assertReportedStat('nodepool.dib_image_build.fake-image.tar.rc',
+        self.assertReportedStat('nodepool.dib_image_build.'
+                                'fake-image.status.rc',
                                 '0', 'g')
         self.assertReportedStat('nodepool.dib_image_build.'
-                                'fake-image.tar.duration', None, 'ms')
+                                'fake-image.status.duration', None, 'ms')
         self.assertReportedStat('nodepool.dib_image_build.'
                                 'fake-image.tar.size', '4096', 'g')
+        self.assertReportedStat('nodepool.dib_image_build.'
+                                'fake-image.status.last_build', None, 'g')
 
     def test_diskimage_build_formats(self):
         configfile = self.setup_config('node_diskimage_formats.yaml')

releasenotes/notes/dib-stats-update-c4efeab13753e090.yaml

@@ -0,0 +1,12 @@
+---
+upgrade:
+  - The diskimage-builder stats have been reworked to be more useful.
+    The return code and duration is now stored in
+    ``nodepool.dib_image-build.<diskimage_name>.status.<rc|duration>``;
+    previously this was split for each image format.  This is
+    unnecessary and confusing since the results will always be the
+    same, since all formats are generated from the same
+    diskimage-builder run.  An additional gauge
+    ``nodepool.dib_image_build.<diskimage_name>.status.last_build`` is
+    added to make it easy to show relative time of builds in
+    dashboards.