From 8b37126169f292a6d3e7e6e716e3d08192b8e20b Mon Sep 17 00:00:00 2001
From: msimonin <matthieu.simonin@inria.fr>
Date: Sun, 20 Mar 2022 21:59:32 +0100
Subject: [PATCH] Update metric endpoint
---
README.org | 79 ++++++++------------------------------
examples/job_timeseries.py | 36 -----------------
examples/timeseries.py | 37 ++++++++----------
grid5000/base.py | 4 ++
grid5000/objects.py | 9 +++++
5 files changed, 46 insertions(+), 119 deletions(-)
delete mode 100644 examples/job_timeseries.py
diff --git a/README.org b/README.org
index 6445c33..726ba72 100644
--- a/README.org
+++ b/README.org
@@ -594,47 +594,6 @@ In [2]: # gk is your entry point
#+END_SRC
** Metrics API
-*** Get the timeseries corresponding to a job
- Credits to ~lturpin~.
- #+BEGIN_SRC python :exports code :tangle examples/job_timeseries.py
-import logging
-import os
-
-from grid5000 import Grid5000
-
-
-logging.basicConfig(level=logging.DEBUG)
-
-
-def get_job_consumption(job_id, gk, site):
- metrics = gk.sites[site].metrics
- job = gk.sites[site].jobs[job_id]
- # nodes as list : "cluster-number.site.grid5000.fr"
- nodes_dom = job.assigned_nodes
- # nodes as list : "cluster-number"
- nodes = map(lambda node_dom: node_dom.split('.')[0], nodes_dom)
- # nodes as string : "cluster-number,cluster-number,..."
- nodes_str = ','.join(nodes)
-
- start = job.started_at
- end = job.stopped_at
- kwargs = {
- "only": nodes_str,
- "resolution": 1,
- "from": start,
- "to": end
- }
- timeseries = metrics["power"].timeseries.list(**kwargs)
- return timeseries
-
-
-conf_file = os.path.join(os.environ.get("HOME"), ".python-grid5000.yaml")
-gk = Grid5000.from_yaml(conf_file)
-
-timeseries = get_job_consumption("1092446", gk, "lyon")
-print(timeseries)
- #+END_SRC
-
*** Get some timeseries (and plot them)
For this example you'll need ~matplotlib~, ~seaborn~ and ~pandas~.
@@ -649,47 +608,43 @@ print(timeseries)
import seaborn as sns
import time
- logging.basicConfig(level=logging.DEBUG)
+ logging.basicConfig(level=logging.INFO)
conf_file = os.path.join(os.environ.get("HOME"), ".python-grid5000.yaml")
gk = Grid5000.from_yaml(conf_file)
- metrics = gk.sites["lyon"].metrics
+ metrics = gk.sites["lyon"].clusters["nova"].metrics
print("--- available metrics")
- print(metrics.list())
-
- print("---- power metric")
- print(metrics["power"])
+ print(metrics)
print("----- a timeserie")
now = time.time()
+ # NOTE that you can pass a job_id here
kwargs = {
- "only": "nova-1,nova-2,nova-3",
- "resolution": 1,
- "from": int(now - 600),
- "to": int(now)
+ "nodes": "nova-1,nova-2,nova-3",
+ "metrics": "wattmetre_power_watt",
+ "start_time": int(now - 600),
}
- timeseries = metrics["power"].timeseries.list(**kwargs)
+ metrics = gk.sites["lyon"].metrics.list(**kwargs)
# let's visualize this
df = pd.DataFrame()
- for timeserie in timeseries:
- print(timeserie)
- timestamp = timeserie.timestamps
- value = timeserie.values
- measurement = timeserie.uid
+ for metric in metrics:
+ timestamp = metric.timestamp
+ value = metric.value
+ device_id = metric.device_id
df = pd.concat([df, pd.DataFrame({
- "timestamp": timestamp,
- "value": value,
- "measurement": [measurement]*len(timestamp)
+ "timestamp": [timestamp],
+ "value": [value],
+ "device_id": [device_id]
})])
-
sns.relplot(data=df,
x="timestamp",
y="value",
- hue="measurement",
+ hue="device_id",
kind="line")
plt.show()
+
#+END_SRC
diff --git a/examples/job_timeseries.py b/examples/job_timeseries.py
deleted file mode 100644
index 492477a..0000000
--- a/examples/job_timeseries.py
+++ /dev/null
@@ -1,36 +0,0 @@
-import logging
-import os
-
-from grid5000 import Grid5000
-
-
-logging.basicConfig(level=logging.DEBUG)
-
-
-def get_job_consumption(job_id, gk, site):
- metrics = gk.sites[site].metrics
- job = gk.sites[site].jobs[job_id]
- # nodes as list : "cluster-number.site.grid5000.fr"
- nodes_dom = job.assigned_nodes
- # nodes as list : "cluster-number"
- nodes = map(lambda node_dom: node_dom.split('.')[0], nodes_dom)
- # nodes as string : "cluster-number,cluster-number,..."
- nodes_str = ','.join(nodes)
-
- start = job.started_at
- end = job.stopped_at
- kwargs = {
- "only": nodes_str,
- "resolution": 1,
- "from": start,
- "to": end
- }
- timeseries = metrics["power"].timeseries.list(**kwargs)
- return timeseries
-
-
-conf_file = os.path.join(os.environ.get("HOME"), ".python-grid5000.yaml")
-gk = Grid5000.from_yaml(conf_file)
-
-timeseries = get_job_consumption("1092446", gk, "lyon")
-print(timeseries)
diff --git a/examples/timeseries.py b/examples/timeseries.py
index 82a7ba0..af6ce84 100644
--- a/examples/timeseries.py
+++ b/examples/timeseries.py
@@ -8,44 +8,39 @@ import matplotlib.pyplot as plt
import seaborn as sns
import time
-logging.basicConfig(level=logging.DEBUG)
+logging.basicConfig(level=logging.INFO)
conf_file = os.path.join(os.environ.get("HOME"), ".python-grid5000.yaml")
gk = Grid5000.from_yaml(conf_file)
-metrics = gk.sites["lyon"].metrics
+metrics = gk.sites["lyon"].clusters["nova"].metrics
print("--- available metrics")
-print(metrics.list())
-
-print("---- power metric")
-print(metrics["power"])
+print(metrics)
print("----- a timeserie")
now = time.time()
+# NOTE that you can pass a job_id here
kwargs = {
- "only": "nova-1,nova-2,nova-3",
- "resolution": 1,
- "from": int(now - 600),
- "to": int(now)
+ "nodes": "nova-1,nova-2,nova-3",
+ "metrics": "wattmetre_power_watt",
+ "start_time": int(now - 600),
}
-timeseries = metrics["power"].timeseries.list(**kwargs)
+metrics = gk.sites["lyon"].metrics.list(**kwargs)
# let's visualize this
df = pd.DataFrame()
-for timeserie in timeseries:
- print(timeserie)
- timestamp = timeserie.timestamps
- value = timeserie.values
- measurement = timeserie.uid
+for metric in metrics:
+ timestamp = metric.timestamp
+ value = metric.value
+ device_id = metric.device_id
df = pd.concat([df, pd.DataFrame({
- "timestamp": timestamp,
- "value": value,
- "measurement": [measurement]*len(timestamp)
+ "timestamp": [timestamp],
+ "value": [value],
+ "device_id": [device_id]
})])
-
sns.relplot(data=df,
x="timestamp",
y="value",
- hue="measurement",
+ hue="device_id",
kind="line")
plt.show()
diff --git a/grid5000/base.py b/grid5000/base.py
index fe28466..74044ac 100644
--- a/grid5000/base.py
+++ b/grid5000/base.py
@@ -1,3 +1,4 @@
+import copy
import importlib
import json
@@ -164,3 +165,6 @@ class RESTObject(object):
def __eq__(self, value):
return self.get_id() == value.get_id()
+
+ def to_dict(self):
+ return copy.deepcopy(self._attrs)
\ No newline at end of file
diff --git a/grid5000/objects.py b/grid5000/objects.py
index d3ebca3..73d54e5 100644
--- a/grid5000/objects.py
+++ b/grid5000/objects.py
@@ -16,6 +16,15 @@ class Timeserie(RESTObject):
class Metric(RESTObject):
_managers = (("timeseries", "TimeserieManager"),)
+ _id_attr = None
+
+ def __repr__(self):
+ keys = ["timestamp", "value", "metric_id", "device_id"]
+ try:
+ _repr = ["%s:%s" % (k, getattr(self, k)) for k in keys]
+ return "<%s %s>" % (self.__class__.__name__, " ".join(_repr))
+ except Exception:
+ return super().__repr__()
class Server(RESTObject):
--
GitLab