Version 12 (modified by, 5 years ago) (diff)


Navigation: Up

BLiPP and NetLogger: Access active measurement probe data


The goal of this exercise is to configure BLiPP (Basic Lightweight Periscope Probes) and enable active measurements within your slice. An example NetLogger script will be used to generate data that will be collected with an active BLiPP probe. A final exercise will use a NetLogger wrapper library to instrument an existing application.

The role of BLiPP

BLiPP is a measurement agent that runs on every GEMINI experiment node within your slice. Through a web interface and/or command line, you can configure BLiPP to collect both passive and active measurements from the given node. BLiPP retrieves its configuration from a central information store known as UNIS, the contents of which we update through the configuration interfaces. BLiPP will then store measurement data to a measurement store (MS) running on the GEMINI global node within your slice. Each measurement is associated with one or more "event types" that identify what metric(s) are collected for a given measurement. These event types are displayed in a drop down box next to the configured measurements with an option for graphing the collected data.

Configure BLiPP measurements

From the GENI Desktop page, click on the and then select 'GEMINI GN' from . Select 'Open PS Config' from the new GN window:

You should then see a page similar to the below image. This page will provide an overview of your slice and show any recent active measurements.

Click the 'Services' tab from the navigation bar. Here you should see a BLiPP service running on each Measurement Points(MP).

Click the 'BLiPP Test' tab. Here you can configure a measurement probe to be run by BLiPP. We'll start with a Ping test. Select a node to configure from the source dropdown menu , then fill the rest of the form.

For example, above we configure a ping test. At the moment, only a single target may be configured per test. You can also add external hosts (i.e., outside of the slice) to ping by entering an IP or hostname in the Destination box.

Once configured, BLiPP will poll UNIS, update its configuration, and begin collecting the desired measurements. The scheduled measurement will be seen above in the table by clicking the 'Measurements' tab. On the 'Metadata' tab you can see event types generated for each measurement submitted. Once data is available (give it a few minutes to begin collecting!), you can select an event type, 'View Data', and display the associated graph.

NOTE: For throughput testing, no assumption is made about listening servers. For example, an iperf test will attempt to connect to the specified host at each interval, but if no iperf server is listening, no result will be collected. Future work will allow BLiPP to start a throughput listener on another node within the slice. By default, the iperf server listens on port 6002.

Using NetLogger

NetLogger is a set of software tools that can be used to log application events and perform analysis and debugging of the collected log data. The python netlogger tools and libraries are installed on your slice nodes by default with GEMINI. More details and software can be obtained from the NetLogger website

An application instrumented with NetLogger can output log messages to a file in a standardized format. BLiPP has a netlogger probe that can parse this log file and report the measurements to the measurement store on your global node. In this way, measurement data collected from experiments in your slice will be in the same format as the other GEMINI measurements. This also means they are accessible in a common location and will be archived to iRODS along with any other measurements collected through the GEMINI system.

To configure a NetLogger probe, you simply add another BLiPP test as shown below.

Specify the file on the given node where you are collecting NetLogger log messages. BLiPP will then check the file for new messages on the specified interval and report the collected values to the measurement store.

The event type(s) for NetLogger probes depend on what is found in the log messages. Since they are defined by the programmer, BLiPP does not know about them until it begins parsing the log file. Once data is available, BLiPP will update the measurement information and display the event types in the drop down next to the scheduled test. Give it a few minutes. Once the event types appear, you can select 'View Data' and display a graph of the collected measurements from the log file. The following exercise will ask you to use NetLogger on your experiment node and collect the measurement data with BLiPP.

Exercise Task 1 -- Python !NetLogger

For the following exercise, if you do not have your own source code that you want to try and instrument with NetLogger, you can simply use the following program.

import sys
import logging
import time
import random
from netlogger.nllog import get_logger
from netlogger import nlapi, nllog

log = nllog.get_logger(".mynamespace")
handler = logging.StreamHandler(sys.stdout)

while True:"random.number", VAL=random.random())
  1. Task 1: Upload the NetLogger application/script to one of your experiment nodes. For example: ssh USERNAME @ VM-3 -p PORT_NUMBER
  2. Task 2: Execute the application on the node. For example:
    sudo python ./ > /tmp/my_random
  3. Task 3: Configure a NetLogger probe to read the log file and graph the measurements.