Network Traffic Analysis using HADOOP Architecture Shan Zeng

Network Traffic Analysis using HADOOP Architecture Shan Zeng HEPi. X, Beijing 17 Oct 2012

Outline • Introduction to Hadoop • Traffic Information Capture • Traffic Information Resolution • Traffic Information Storage • Traffic Information Analysis • Traffic Information Display • Conclusion ZENG SHAN/CC/IHEP

Introduction to Hadoop ZENG SHAN/CC/IHEP

What can Hadoop do? • Hadoop is an open-source software framework. • It was originally developed to support distribution for the Nutch search engine project. • Supports data-intensive distributed applications. • Licensed under the Apache v 2 license. • It enables applications to work with thousands of computation-independent computers and petabytes of data ZENG SHAN/CC/IHEP

Traffic Information Capture ZENG SHAN/CC/IHEP

What is a flow? • Network flow is a sequence of packets • From a source computer to a destination, which may be another host, a multicast group, or a broadcast domain. • A network flow measures sequences of IP packets sharing a common feature as they pass between devices. • Flow format: • • Net. Flow(Cisco) J-Flow(Juniper) Sflow(HP) …. ZENG SHAN/CC/IHEP

What is n. Probe? • n. Probe is an open source tools • Capture packets flowing on a Ethernet segment, computes flows and export them to the specified collectors. • Features: • Ability to keep up with Gbit speeds on Ethernet networks handling thousand of packets per second without packet sampling on commodity hardware. • Support for major OS including Unix, Windows and Mac OS X • it is designed for environments with limited resources ZENG SHAN/CC/IHEP

Traffic Information Resolution ZENG SHAN/CC/IHEP

nfcapd • nfcapd is the netflow capture daemon, it reads netflow data from the network and stores it into files. • The output file is automatically rotated and renamed every n minutes - typically 5 min e. g. nfcapd. 201205030900 contains the data from May 3 rd 2012 09: 00 onward • Usage: /usr/local/bin/nfcapd -p 2055 -t 300 -l /home/zengshan/netflow/nfcapd_file/IHEP & -p portnum Specifies the port number to listen. Default port is 9995 -t interval Specifies the time interval in seconds to rotate files. -l base_directory Specifies the base directory to store the output files. ZENG SHAN/CC/IHEP

nfdump • nfdump Reads the netflow data from the files stored by nfcapd • And then dump them to text • ZENG SHAN/CC/IHEP

nfdump output text format • Tag Description Tag %ts Start Time - first seen %in %te End Time - last seen %out Output Interface num %td Duration %pkt Packets counts in this flow %pr Protocol %byt Bytes count in this flow %sa Source Address %fl Number of flows. %da Destination Address %flg TCP Flags %sap Source Address: Port %tos Type of Service %dap Destination Address: Port %bps bits per second Source Port %pps packets per second %dp Destination Port %bpp %sas Source AS %das Destination AS %sp Description Input Interface num Bytes per package ZENG SHAN/CC/IHEP

• ZENG SHAN/CC/IHEP

Traffic Information Storage ZENG SHAN/CC/IHEP

HDFS • HDFS is short for Hadoop Distributed File System • HDFS can provide high throughput access to application data • Differences from other distributed file systems: • • highly fault-tolerant designed to be deployed on low-cost hardware. Portability across heterogeneous hardware and software platforms Applications run on HDFS need streaming access to their data sets provides high throughput access to application data suitable for applications that have large data sets Moving computation is cheaper than moving data ZENG SHAN/CC/IHEP

HDFS master/slave architecture • Name. Node • Manages name space of the file system • Regulates access to files by clients • Determine the mapping of blocks to Data. Nodes • Data. Nodes • Responsible for serving read and write requests from the clients • Perform block creation, deletion and replication upon the instructions from Name. Node ZENG SHAN/CC/IHEP

Data Replication in HDFS • To ensure the fault tolerance in HDFS, the blocks of a file are replicated, the replicas of a block can be specified by the application ZENG SHAN/CC/IHEP

Traffic Information Analysis ZENG SHAN/CC/IHEP

Map/Reduce • Map. Reduce is a programming model for processing large data sets • Map. Reduce is typically used to do distributed computing on clusters of computers • Map. Reduce can take advantage of locality of data, processing data on or near the storage assets to decrease transmission of data. • The model is inspired by the map and reduce functions • "Map" step: The master node takes the input, divides it into smaller sub-problems, and distributes them to slave nodes. The slave node processes the smaller problem, and passes the answer back to its master node. • "Reduce" step: The master node then collects the answers to all the sub-problems and combines them in some way to form the final output ZENG SHAN/CC/IHEP

Traffic Information Display ZENG SHAN/CC/IHEP

Drawing tools • RRDtool • • acronym for round-robin database tool The data are stored in a round-robin database(circular buffer) It also includes tools to extract RRD data in a graphical format drawing flow trend graph in three dimensionality: Flow count, Packet count, Traffic count • Highstock lets you create stock or general timeline charts in pure Java. Script including sophisticated navigation options like a small navigator series, preset date ranges, date picker, scrolling and panning. • We just need to write API between HDFS and Highstock ZENG SHAN/CC/IHEP

Architecture ZENG SHAN/CC/IHEP

ZENG SHAN/CC/IHEP

ZENG SHAN/CC/IHEP

ZENG SHAN/CC/IHEP

ZENG SHAN/CC/IHEP

Conclusion • Network flow trend chart from IHEP every 5 minutes in three dimension: Flow count/Packet count/Traffic count • Detailed traffic information chart • select a single timeslot and get the detailed traffic information • select a time window and get the detailed traffic information • on hovering the chart, a tooltip text with traffic information on each point and series can be displayed. • the tooltip follows as the user moves the mouse over the graph • Traffic information related to the HEP experiments • Once the IP addresses of the machines related to the data transferring of the HEP experiment is specified • we already have DYB/YBJ/CMS/ALTAS ZENG SHAN/CC/IHEP

Thank You Questions? ZENG SHAN/CC/IHEP