Institute of Computer Science AGH Performance Monitoring of Java Web Service-based Applications Włodzimierz Funika, Piotr Handzlik Lechosław Trębacz Institute.

Slides:



Advertisements
Similar presentations
A Lightweight Platform for Integration of Mobile Devices into Pervasive Grids Stavros Isaiadis, Vladimir Getov University of Westminster, London {s.isaiadis,
Advertisements

Operating Systems Components of OS
GridPP7 – June 30 – July 2, 2003 – Fabric monitoring– n° 1 Fabric monitoring for LCG-1 in the CERN Computer Center Jan van Eldik CERN-IT/FIO/SM 7 th GridPP.
26/05/2004HEPIX, Edinburgh, May Lemon Web Monitoring Miroslav Šiket CERN IT/FIO
Operating-System Structures
BiodiversityWorld GRID Workshop NeSC, Edinburgh – 30 June and 1 July 2005 Resource wrappers, web services, grid services Jaspreet Singh School of Computer.
I.1 Distributed Systems Prof. Dr. Alexander Schill Dresden Technical University Computer Networks Dept.
DataGrid is a project funded by the European Union 22 September 2003 – n° 1 EDG WP4 Fabric Management: Fabric Monitoring and Fault Tolerance
Distributed Heterogeneous Data Warehouse For Grid Analysis
Technical Architectures
Camilo Lara KIP HLT Production Readiness Review 1 HLT Cluster Management.
Managing Agent Platforms with the Simple Network Management Protocol Brian Remick Thesis Defense June 26, 2015.
Common System Components
Network Management with JMX Thu Nguyen Oliver Argente CS158B.
Os31 Chapter 3 Operating-System Structures. os32 Outlines System Components Operating System Services System Calls System Programs System Structure Virtual.
© DSRG 2001www.cs.agh.edu.pl Cross Grid Workshop - Kraków Krzysztof Zieliński, Sławomir Zieliński University of Mining and Metallurgy {kz,
Chapter 3: Operating-System Structures System Components Operating System Services System Calls System Programs System Structure Virtual Machines System.
Understanding and Managing WebSphere V5
Abhinav Kamra Computer Science, Columbia University 3.1 Operating System Concepts Silberschatz, Galvin and Gagne  2002 Chapter 3: Operating-System Structures.
CERN IT Department CH-1211 Genève 23 Switzerland t Integrating Lemon Monitoring and Alarming System with the new CERN Agile Infrastructure.
31 January 2007Craig E. Ward1 Large-Scale Simulation Experimentation and Analysis Database Programming Using Java.
The SAM-Grid Fabric Services Gabriele Garzoglio (for the SAM-Grid team) Computing Division Fermilab.
Chapter 9 Elements of Systems Design
Cracow Grid Workshop 2003 Institute of Computer Science AGH A Concept of a Monitoring Infrastructure for Workflow-Based Grid Applications Bartosz Baliś,
Performance and Exception Monitoring Project Tim Smith CERN/IT.
 Cloud computing  Workflow  Workflow lifecycle  Workflow design  Workflow tools : xcp, eucalyptus, open nebula.
Advanced Grid-Enabled System for Online Application Monitoring Main Service Manager is a central component, one per each.
CGW 2003 Institute of Computer Science AGH Proposal of Adaptation of Legacy C/C++ Software to Grid Services Bartosz Baliś, Marian Bubak, Michał Węgiel,
Oracle10g RAC Service Architecture Overview of Real Application Cluster Ready Services, Nodeapps, and User Defined Services.
Computer and Automation Research Institute Hungarian Academy of Sciences Presentation and Analysis of Grid Performance Data Norbert Podhorszki and Peter.
Overview of MSS System Human Actors Non-Human Actors In-house developed components Third party products.
J-OCM is a system for monitoring distributed Java applications conforming to OMIS specification with J-OMIS extensions. It is used to: gather information.
PARMON A Comprehensive Cluster Monitoring System A Single System Image Case Study Developer: PARMON Team Centre for Development of Advanced Computing,
Ramiro Voicu December Design Considerations  Act as a true dynamic service and provide the necessary functionally to be used by any other services.
Lechoslaw Trębacz 1, Włodzimierz Funika 2, Piotr Handzlik 3, Marcin Smętek 2 1 Department of Computer Methods in Metallurgy, AGH, Kraków, Poland 2 Institute.
COMP3019 Coursework: Introduction to GridSAM Steve Crouch School of Electronics and Computer Science.
Information Grid Services in the Polish Optical Internet PIONIER Cezary Mazurek, Maciej Stroiński, Jan Węglarz.
May PEM status report. O.Bärring 1 PEM status report Large-Scale Cluster Computing Workshop FNAL, May Olof Bärring, CERN.
Event-Based Hybrid Consistency Framework (EBHCF) for Distributed Annotation Records Ahmet Fatih Mustacoglu Advisor: Prof. Geoffrey.
1 4/23/2007 Introduction to Grid computing Sunil Avutu Graduate Student Dept.of Computer Science.
OMIS Approach to Grid Application Monitoring Bartosz Baliś Marian Bubak Włodzimierz Funika Roland Wismueller.
Resource Brokering in the PROGRESS Project Juliusz Pukacki Grid Resource Management Workshop, October 2003.
And Tier 3 monitoring Tier 3 Ivan Kadochnikov LIT JINR
Issues Autonomic operation (fault tolerance) Minimize interference to applications Hardware support for new operating systems Resource management (global.
Silberschatz, Galvin and Gagne  Operating System Concepts Chapter 3: Operating-System Structures System Components Operating System Services.
Management of the LHCb DAQ Network Guoming Liu * †, Niko Neufeld * * CERN, Switzerland † University of Ferrara, Italy.
Lemon Monitoring Miroslav Siket, German Cancio, David Front, Maciej Stepniewski CERN-IT/FIO-FS LCG Operations Workshop Bologna, May 2005.
1 Putchong Uthayopas, Thara Angsakul, Jullawadee Maneesilp Parallel Research Group, Computer and Network System Research Laboratory Department of Computer.
Silberschatz, Galvin and Gagne  Operating System Concepts UNIT II Operating System Services.
Recording Actor Provenance in Scientific Workflows Ian Wootten, Shrija Rajbhandari, Omer Rana Cardiff University, UK.
© FPT SOFTWARE – TRAINING MATERIAL – Internal use 04e-BM/NS/HDCV/FSOFT v2/3 JSP Application Models.
CSI 3125, Preliminaries, page 1 SERVLET. CSI 3125, Preliminaries, page 2 SERVLET A servlet is a server-side software program, written in Java code, that.
Włodzimierz Funika 1, Marian Bubak 1,2, Marcin Smętek 1 and Roland Wismüller 3 1 Institute of Computer Science, AGH, Kraków, Poland 2 Academic Computer.
April 2003 Iosif Legrand MONitoring Agents using a Large Integrated Services Architecture Iosif Legrand California Institute of Technology.
PPDG February 2002 Iosif Legrand Monitoring systems requirements, Prototype tools and integration with other services Iosif Legrand California Institute.
ECHO A System Monitoring and Management Tool Yitao Duan and Dawey Huang.
CERN IT Department CH-1211 Genève 23 Switzerland t CERN IT Monitoring and Data Analytics Pedro Andrade (IT-GT) Openlab Workshop on Data Analytics.
Marian Bubak 1,2, Włodzimierz Funika 1,2, Roland Wismüller 3, Tomasz Arodź 1,2, Marcin Kurdziel 1,2 1 Institute of Computer Science, AGH, Kraków, Poland.
PROGRESS: GEW'2003 Using Resources of Multiple Grids with the Grid Service Provider Michał Kosiedowski.
Interoperability Architecture for Grid Networks Monitoring Systems Need for interoperability in grid networks monitoring systems: Monitored.
A System for Monitoring and Management of Computational Grids Warren Smith Computer Sciences Corporation NASA Ames Research Center.
9 Systems Analysis and Design in a Changing World, Fifth Edition.
Lemon Computer Monitoring at CERN Miroslav Siket, German Cancio, David Front, Maciej Stepniewski Presented by Harry Renshall CERN-IT/FIO-FS.
System Monitoring with Lemon
Chapter 2: System Structures
University of Technology
Chapter 3: Operating-System Structures
Chapter 2: Operating-System Structures
Outline Chapter 2 (cont) OS Design OS structure
Chapter 2: Operating-System Structures
Presentation transcript:

Institute of Computer Science AGH Performance Monitoring of Java Web Service-based Applications Włodzimierz Funika, Piotr Handzlik Lechosław Trębacz Institute of Computer Science, AGH, Krakow, Poland

Institute of Computer Science AGH Agenda  Review of existing monitoring systems JIMS (JMX) Lemon (CERN) Mercury  Concept of a system monitoring WebServices idea (J-OMIS, OCM-G) metrics feasibility study architecture

Institute of Computer Science AGH Monitoring System Funcionality Monitoring of application is observing, analyzing and manipulating the execution of the application, which gives information about threads, CPU usage, memory usage, informations about methods and classes. A particular case is monitoring of distributed applications where an additional issue is the performance analysis of nodes.

Institute of Computer Science AGH Functional requirements  Goals monitoring Web Services distinguishing which objects are interface of WS accessing information about Web Services on a node  Communication related performance data size of SOAP message time of communication time of parsing a SOAP message  Events receive request start/end of creating/parsing SOAP message  Basis use the J-OMIS interface hold the existing functionality of J-OCM make use of experience with extending OMIS/OCM for parallel applications, grid computing and Java distributed programming.

Institute of Computer Science AGH JMX Infrastructure Monitoring System JIMS is a monitoring service for GRID’s, exposing the following parameters to the outside world:  CPU load,  Number of processes,  Memory usage,  Network interface utilization. It uses Java Native Interface, Java Management Extension, Dynamic Discovery Service and Web Services

Institute of Computer Science AGH JIMS Architecture JIMS Node JIMS Node JIMS Node Cluster User SOAP Gateway SOAP RMI

Institute of Computer Science AGH LEMON (CERN) Lemon is a scalable and flexible fabric monitoring system. Distributed clients launch and control local sensors, schedule measurements, collect data and send them to one or several repositories. The system provides sensors for common performance and exception monitoring. Main parts of Lemon are:  Monitoring Sensor measures data  Monitoring Sensor Agent exists on all nodes and provides transport to MR  Monitoring Repository (MR) with backend to Oracle, MySQL, flat file,…  Alarm Broker – daemon for handling exceptions and communication between alarm GUI and MR  Round Robin Database – is used to store and to manipulate data

Institute of Computer Science AGH Lemon architecture Alarm GUI Alarm Broker Monitoring repository backend Monitoring repository RRD Tool Framework USERS Monitoring Sensor Agent Monitoring Sensor Node

Institute of Computer Science AGH Lemon - Performance Monitoring  In Lemon there are several types of data: Performance metrics: CPU usage, load averages, memory us age, disk us age /performance, sockets, network, … Exceptions: High load, swap us age over 90%, service down,… Status information: Uptime, boot time, kernel version,… Heartbeat  Data is gathered with different frequencies from 60s to 1 day/on boot

Institute of Computer Science AGH Mercury ( GridLab ) The architecture of Mercury Monitor is based on the Grid Monitoring Architecture proposed by Global Grid Forum (GGF), and implemented in a modular way. The Mercury Monitor provides:  monitoring data as metrics,  pull and push model,  performance monitoring and steering,  monitoring of grid entities such as resources and applications,  emphasis on simplicity, efficiency, portability and low intrusiveness.

Institute of Computer Science AGH Mercury ( GridLab ) The input of the monitoring system consists of measurements generated by sensors. Sensors are implemented as shared objects that are dynamically loaded at run-time depending on configuration and incoming requests for different measurements. Local monitor employs a set of sensors, implemented as loadable modules, to collect information about the local node, including host status, applications, etc., and sends it to the main monitor. The monitoring service sends requests to local monitors.

Institute of Computer Science AGH Mercury architecture Tool MM LM Sensor node 2 Sensor LM Sensor node 1 Sensor

Institute of Computer Science AGH Idea Our monitoring system will be based on J-OMIS interface and its implementation, J-OCM. The work dates back to 1995 when OMIS, a monitor/tool interface specification was released. Java-bound OMIS is a monitor extension to OMIS for Java applications intended to support the development of Java distributed applications with on-line tools. J-OMIS specifies three types of services:  information (providing information about an object)  manipulation (allowing to change the state of an object)  event (trigger arbitrary actions whenever a matching event takes place)

Institute of Computer Science AGH J-OCM architecture Tool 1Tool 2 Node Distribution Unit Local Monitor (RMI Ext, JVM Ext) agent JVM agent JVM Node Local Monitor (RMI Ext, JVM Ext) agent JVM agent JVM Node

Institute of Computer Science AGH J-OCM Node Distribution Unit is part, which is still responsible for distributing requests and assembling replies. Local Monitor is a monitor process. LM’s extension provides new services defined by J-OMIS, which control Java Virtual Machine via agent. LM stores information about the target Java application’s object, such as JVMs, threads, classes, interfaces, objects, methods, etc., referred to by tokens. Agent uses JVM native interfaces such as JVM Profiler Interface, JVM Debugging Interface, Java Native Interface to access low-level mechanism for interactive monitoring of JVM.

Institute of Computer Science AGH Grid-enabled OMIS-based Monitor The OCM-G is a decentralized, distributed system, consists of two types of components:  Service Managers (SM)  Local Monitors (LM) SMs reside permanently, one on each site of the Grid, where are application processes to be monitored. LMs execute OMIS request accepted from SMs and send the results back. LMs handle only objects which are on the same host. The LMs use OS mechanisms to control the application processes.

Institute of Computer Science AGH OCM-G Monitoring Services The OCM-G provides:  Debugging services (services for suspending/continuing process, reading/writing processes’ memory, etc.)  Performance analysis services, for example: services for detecting the beginnings and ends of function calls, services for handling probes, which are used by the user to define and detect arbitrary events in an application, services for the creation and management of counters and integrators - efficient data structures which allow to buffer and preprocess monitoring information in the context of the application.

Institute of Computer Science AGH Components of our system It contains three kinds of components:  application monitor (AM),  node's local monitor (LM),  service monitor (SM). AM is embedded into the application (in our case Web Service or application, which use Web Services). It is used to perform monitoring activities in the context of the application. It uses JVM Tool Interface, starting with JDK 1.5, for monitoring JVM. Node's local monitor is created on each node, where there are Web Services to be monitored. LM receives requests from Service monitor and transfers this request to AM. LM sends a reply from AM to SM. Service Monitor resides permanently and exposes the monitoring services to tools.

Institute of Computer Science AGH Metrics Our monitoring system have t w o types of metric s :  static – for WebServices, intended for o bservation and analysis of SOAP messages sended to and from a Web Service (requests and responses) : number of WebServices on a node request time, transport time, cache access time, response time, SOAP create/parsing time, computing time size of SOAP message (sent, received) u sage ( node resources )  dynamic – oriented towards application s which use WebServices : function call, service invocation number of exceptions (errors)

Institute of Computer Science AGH Feasibility study To build the Web Service we use Jakarta Tomcat and Apache Axis. Jakarta Tomcat is the servlet container:  open source,  reference platform,  simplicity of use,  universal tool for deploying web applications. Apache Axis is an implementation of the SOAP protocol and enables creation of web services on Tomcat. J-OCM will be a low-level layer of the architecture extended by a special extension for web services.

Institute of Computer Science AGH Architecture Tools Service monitor node's local monitor Node node's local monitor AM Node WebService WebService Tomcat+Axis AM WebService Tomcat+Axis AM WebService Tomcat+Axis AM WebService Tomcat+Axis Service monitor

Institute of Computer Science AGH Thank You !