Merge pull request #44 from draios/better-paging-coverage

Document paging parameter in get_data() and improve corresponding examples

Author: ldegio

examples/get_data_advanced.py

@@ -1,14 +1,15 @@
 #!/usr/bin/env python
 #
-# This script shows an advanced Sysdig Cloud data request that leverages
+# This script shows an advanced Sysdig Monitor data request that leverages
 # filtering and segmentation.
 #
-# The request returns the last 10 minutes of CPU utilization for all of the
-# containers inside the given host, with 1 minute data granularity
+# The request returns the last 10 minutes of CPU utilization for the 5
+# busiest containers inside the given host, with 1 minute data granularity
 #
 
 import os
 import sys
+import json
 sys.path.insert(0, os.path.join(os.path.dirname(os.path.realpath(sys.argv[0])), '..'))
 from sdcclient import SdcClient
 
@@ -34,10 +35,10 @@
 metrics = [
     # The first metric we request is the container name. This is a segmentation
     # metric, and you can tell by the fact that we don't specify any aggregation
-    # criteria. This entry tells Sysdig Cloud that we want to see the CPU
+    # criteria. This entry tells Sysdig Monitor that we want to see the CPU
     # utilization for each container separately.
     {"id": "container.name"},
-    # The second metric we reuest is the CPU. We aggregate it as an average.
+    # The second metric we request is the CPU. We aggregate it as an average.
     {"id": "cpu.used.percent",
      "aggregations": {
          "time": "avg",
@@ -51,19 +52,26 @@
 #
 filter = "host.hostName = '%s'" % hostname
 
+#
+# Paging (from and to included; by default you get from=0 to=9)
+# Here we'll get the top 5.
+#
+paging = { "from": 0, "to": 4 }
+
 #
 # Fire the query.
 #
-res = sdclient.get_data(metrics, # metrics list
-                        -600,   # start_ts = 600 seconds ago
-                        0,      # end_ts = now
-                        60,     # 1 data point per minute
-                        filter, # The filter
-                        'container') # The source for our metrics is the container
+res = sdclient.get_data(metrics=metrics,               # List of metrics to query
+                        start_ts=-600,                 # Start of query span is 600 seconds ago
+                        end_ts=0,                      # End the query span now
+                        sampling_s=60,                 # 1 data point per minute
+                        filter=filter,                 # The filter specifying the target host
+                        paging=paging,                 # Paging to limit to just the 5 most busy
+                        datasource_type='container')   # The source for our metrics is the container
 
 #
 # Show the result!
 #
-print res[1]
+print json.dumps(res[1], sort_keys=True, indent=4)
 if not res[0]:
     sys.exit(1)

examples/get_data_simple.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 #
-# This script shows the basics of getting data out of Sysdig Cloud by creating a
-# very simple request that has no filter an no segmentation.
+# This script shows the basics of getting data out of Sysdig Monitor by creating a
+# very simple request that has no filter and no segmentation.
 #
 # The request queries for the average CPU across all of the instrumented hosts for
 # the last 10 minutes, with 1 minute data granularity
@@ -54,15 +54,10 @@
 #
 sampling =  60
 
-#
-# Paging (from and to included; by default you get from=0 to=9)
-#
-paging = { "from": 0, "to": 9 }
-
 #
 # Load data
 #
-res = sdclient.get_data(metrics, start, end, sampling, filter = filter, paging = paging)
+res = sdclient.get_data(metrics, start, end, sampling, filter = filter)
 
 #
 # Show the result

sdcclient/_client.py

@@ -412,7 +412,7 @@ def get_data(self, metrics, start_ts, end_ts=0, sampling_s=0,
             - **sampling_s**: the duration of the samples that will be returned. 0 means that the whole data will be returned as a single sample.
             - **filter**: a boolean expression combining Sysdig Monitor segmentation criteria that defines what the query will be applied to. For example: *kubernetes.namespace.name='production' and container.image='nginx'*.
             - **datasource_type**: specify the metric source for the request, can be ``container`` or ``host``. Most metrics, for example ``cpu.used.percent`` or ``memory.bytes.used``, are reported by both hosts and containers. By default, host metrics are used, but if the request contains a container-specific grouping key in the metric list/filter (e.g. ``container.name``), then the container source is used. In cases where grouping keys are missing or apply to both hosts and containers (e.g. ``tag.Name``), *datasource_type* can be explicitly set to avoid any ambiguity and allow the user to select precisely what kind of data should be used for the request. `examples/get_data_datasource.py <https://github.com/draios/python-sdc-client/blob/master/examples/get_data_datasource.py>`_ contains a few examples that should clarify the use of this argument.
-            - **paging**:
+            - **paging**: if segmentation of the query generates values for several different entities (e.g. containers/hosts), this parameter specifies which to include in the returned result. It's specified as a dictionary of inclusive values for ``from`` and ``to`` with the default being ``{ "from": 0, "to": 9 }``, which will return values for the "top 10" entities. The meaning of "top" is query-dependent, based on points having been sorted via the specified group aggregation, with the results sorted in ascending order if the group aggregation is ``min`` or ``none``, and descending order otherwise.
 
         **Success Return Value**
             A dictionary with the requested data. Data is organized in a list of time samples, each of which includes a UTC timestamp and a list of values, whose content and order reflect what was specified in the *metrics* argument.