cherrypicking trunk revs 514-516

tmm1 · Aug 11, 2011 · fbe737e · fbe737e
2 parents 825d199 + 2e80669
commit fbe737e
Show file tree

Hide file tree

Showing 3 changed files with 35 additions and 9 deletions.
diff --git a/docs/config-carbon.rst b/docs/config-carbon.rst
@@ -45,7 +45,7 @@ Here's a more complicated example with multiple retention rates:
 
  [apache_busyWorkers]
  pattern = servers\.www.*\.workers\.busyWorkers$
- retentions = 15s:7d,1min:21d,15min:5y
+ retentions = 15s:7d,1m:21d,15m:5y
 
 The pattern matches server names that start with 'www', followed by anything, that end in '.workers.busyWorkers'.  This way not all metrics associated with your webservers need this type of retention.  
 

diff --git a/docs/tools.rst b/docs/tools.rst
@@ -37,6 +37,7 @@ mechanisms to store the values in a variety of ways, including RRD. To send coll
 - Jordan Sissel's node collectd-to-graphite_ proxy
 - Joe Miller's perl collectd-graphite_ plugin
 - Gregory Szorc's python collectd-carbon_ plugin
+- Scott Sanders's C collectd-write_graphite_ plugin
 
 Graphite can also read directly from `collectd`_'s RRD files. RRD files can
 simply be added to ``STORAGE_DIR/rrd`` (as long as directory names and files do not
@@ -69,6 +70,7 @@ Learn more here, http://code.google.com/p/rocksteady/
 .. _collectd-to-graphite: https://github.com/loggly/collectd-to-graphite
 .. _collectd-carbon: https://github.com/indygreg/collectd-carbon
 .. _collectd-graphite: https://github.com/joemiller/collectd-graphite
+.. _collectd-write_graphite: https://github.com/jssjr/collectd-write_graphite
 .. _Logster: https://github.com/etsy/logster
 .. _RabbitMQ: http://www.rabbitmq.com/
 .. _Esper: http://esper.codehaus.org/
diff --git a/webapp/graphite/render/functions.py b/webapp/graphite/render/functions.py
@@ -1201,7 +1201,7 @@ def exclude(requestContext, seriesList, pattern):
   return [s for s in seriesList if not regex.search(s.name)]
 
 
-def summarize(requestContext, seriesList, intervalString, func='sum'):
+def summarize(requestContext, seriesList, intervalString, func='sum', alignToFrom=False):
   """
   Summarize the data into interval buckets of a certain size.
 
@@ -1214,6 +1214,14 @@ def summarize(requestContext, seriesList, intervalString, func='sum'):
 
   'max', 'min' or 'last' can also be specified.
 
+  By default, buckets are caculated by rounding to the nearest interval. This
+  works well for intervals smaller than a day. For example, 22:32 will end up
+  in the bucket 22:00-23:00 when the interval=1hour.
+
+  Passing alignToFrom=true will instead create buckets starting at the from
+  time. In this case, the bucket for 22:32 depends on the from time. If
+  from=6:30 then the 1hour bucket for 22:32 is 22:30-23:30.
+
   Example:
 
   .. code-block:: none
@@ -1222,6 +1230,7 @@ def summarize(requestContext, seriesList, intervalString, func='sum'):
     &target=summarize(nonNegativeDerivative(gauge.num_users), "1week") # new users per week
     &target=summarize(queue.size, "1hour", "avg") # average queue size per hour
     &target=summarize(queue.size, "1hour", "max") # maximum queue size during each hour
+    &target=summarize(metric, "13week", "avg", true)&from=midnight+20100101 # 2010 Q1-4
   """
   results = []
   delta = parseTimeOffset(intervalString)
@@ -1234,20 +1243,32 @@ def summarize(requestContext, seriesList, intervalString, func='sum'):
     datapoints = zip(timestamps, series)
 
     for (timestamp, value) in datapoints:
-      bucketInterval = int((timestamp - series.start) / interval)
+      if alignToFrom:
+        bucketInterval = int((timestamp - series.start) / interval)
+      else:
+        bucketInterval = timestamp - (timestamp % interval)
 
       if bucketInterval not in buckets:
         buckets[bucketInterval] = []
 
       if value is not None:
         buckets[bucketInterval].append(value)
 
-    newStart = series.start
-    newEnd = series.end
+    if alignToFrom:
+      newStart = series.start
+      newEnd = series.end
+    else:
+      newStart = series.start - (series.start % interval)
+      newEnd = series.end - (series.end % interval) + interval
+
     newValues = []
-    for timestamp in range( int(series.start), int(series.end), interval ):
-      newEnd = timestamp
-      bucketInterval = int((timestamp - series.start) / interval)
+    for timestamp in range(newStart, newEnd, interval):
+      if alignToFrom:
+        newEnd = timestamp
+        bucketInterval = int((timestamp - series.start) / interval)
+      else:
+        bucketInterval = timestamp - (timestamp % interval)
+
       bucket = buckets.get(bucketInterval, [])
 
       if bucket:
@@ -1264,8 +1285,11 @@ def summarize(requestContext, seriesList, intervalString, func='sum'):
       else:
         newValues.append( None )
 
+    if alignToFrom:
+      newEnd += interval
+
     newName = "summarize(%s, \"%s\")" % (series.name, intervalString)
-    newSeries = TimeSeries(newName, newStart, newEnd + interval, interval, newValues)
+    newSeries = TimeSeries(newName, newStart, newEnd, interval, newValues)
     newSeries.pathExpression = newName
     results.append(newSeries)