The theoretical and practical mix of the HPC System Administration program has the following learning objectives:
- Fundamental knowledge of High-Performance computing and applications.
- HPC Cluster architecture, Clustering, resource allocation and job scheduling tools, Parallel file systems, Designing Data Centers, Troubleshooting techniques and various other tools for administration and monitoring.
- Hadoop and Map reduce Concepts, designing Hadoop cluster for big data applications.
- Virtualization and Cloud computing technologies, accessing resources and services needed to perform functions with dynamically changing needs.
- Network and Cloud security concepts to create secure development environment, recognizing security loopholes and strengthening the solutions.
- DevOps and automation using container technology and scripting.
- Undertaking industrial research projects for the development of future solutions in the domain of HPC Administration to make an impact in the technological advancement.
The educational eligibility criteria for PG-DHPCSA course is
- Graduate in Engineering (10+2+4 or 10+3+3 years) in IT / Computer Science / Electronics / Telecommunications / Electrical / Instrumentation, OR
- MSc/MS (10+2+3+2 years) in Computer Science, IT, Electronics OR
- Post Graduate Degree in Mathematics / Statistics, OR
- The candidates must have secured a minimum of 55% marks in their qualifying examination.
PG-DHPCSA course will be delivered in fully PHYSICAL mode. The total course fee and payment details are as detailed herein below:
The total course fee is INR. 90,000/- plus Goods and Service Tax (GST) as applicable by Government of India (GOI).
The course fee for PG-DHPCSA has to be paid in two installments as per the schedule.
- First installment is INR. 10,000/- plus Goods and Service Tax (GST) as applicable by GOI.
- Second installment is INR. 80,000/- plus Goods and Service Tax (GST) as applicable by GOI.
The course fee includes expenses towards delivering classes, conducting examinations, final mark-list and certificate, and placement assistance provided.
The first installment course fee of Rs 10,000/- + GST on it as applicable at the time of payment is to be paid online as per the schedule. It can be paid using credit/debit cards through the payment gateway. The first installment of the course fees is to be paid after seat is allocated during counseling rounds.
The second installment of the course fees is to be paid before the course commencement through NEFT.
NOTE: Candidates may take note that no Demand Draft (DD) or cheque or cash will be accepted at any C-DAC training centre towards payment of any installment of course fees.
Cloud Computing: Definition, Characteristics, Components, Cloud provider, SAAS, PAAS, IAAS and other Organizational scenarios of clouds, Administering & Monitoring cloud services, benefits and limitations, Deploy application over cloud. Comparison among SAAS, PAAS, IAAS, Cloud computing platforms: Infrastructure as service: Amazon EC2, Platform as Service: Google App Engine.
Cloud Technologies: Virtualization, Virtual machine provisioning, virtualization applications in enterprises, Pitfalls of virtualization, Multitenant software: Multi-entity support, Multi-schema approach, Multi-tenancy using cloud data stores, Data access control for enterprise applications, OpenStack.
Container based technologies, Automation and administration: Introduction to DevOps, Version controlling, GIT, Branching and Merging, Workflow, Jenkins, Maven, Docker, Containers, Microservices platforms, Kubernetes.
Basic concepts of computer organization, Classes of computer architecture, Processor vs. System architecture, Elements of computer systems, CISC vs. RISC architectures, pipelining, Multi core Processor architecture, Memory Hierarchy, Cache memory, Cache coherency, Standard IO interfaces, GPU elements, Compute GPU Architecture, overview of the latest Intel, AMD, ARM, POWER processors.
Introduction to communication system, issues in Computer Networking, OSI Layers, TCP/IP Models, Networking Protocols, IP Addressing and Routing, Network Devices (Hub, Switch, Router), Interconnect networks, Types of Interconnect networks, Gigabit Ethernet, InfiniBand, Omni Path Architecture(OPA), types of protocol supported, Communication subnet, Interconnect networks subsystem: HCA, FC ports and other supported accessories, Network monitoring
Hadoop Framework: What is Hadoop, Why Hadoop, History of Hadoop, Use Cases of Hadoop, Hadoop eco system, HDFS, Hadoop Distributed File System, HDFS Architecture, Name Nodes, Data Nodes, Secondary Name Node, Command Line Interface, Reading and Writing Date, Hadoop on YARN
Map Reduce: Map Operation, Map Reduce Anatomy, Job Submissions, Job Initialization, Task Assignment, Job Completion, Job Scheduling, Job Failures, Shuffle and sort, Word Count Problem, Word Count Flow and Solution, Word Count Flow and Solution.
Hadoop Environment: Setting up a Hadoop Cluster, Cluster specification, Cluster Setup and Installation, Hadoop Configuration, Security in Hadoop (Security System Concepts used in Hadoop, Hadoop Cluster With LDAP), Administering Hadoop, HDFS – Monitoring & Maintenance (Data transfer Between Clusters, Adding and Removing Nodes, Cluster Rebalancing), Hadoop benchmarks.
Basics of Data Center Design Management
Data center overview, Real life issues on design, Cabinets, Power, cooling, Cable Management, Safety, efficient design and planning a strategy, Collecting the heat, Heat rejection or reuse, Liquid cooling, Energy use systems, Data Centre Metrics, Best Practices, Fire Protection and Security Systems
Design of HPC Cluster – Ecosystem
Requirement Analysis, building blocks of HPC, Hardware and software selection process, Design of HPC Cluster, Cluster Planning, Architecture and Cluster software, Cluster building tools, Multicore architecture, Accelerator cards, Configuring & setting environment for accelerator cards, Latest trends and technologies in HPC.
HPC System Management and Monitoring
IPMI, HMC, User management, LDAP, NIS, Node resources, processor usage, memory usage, network usage, statistics, network monitoring, monitoring tools (Ganglia, Nagios), System Benchmarking, theoretical peak performance, HPL bench mark, Tuning HPL
Case study of HPC solutions like Param Shavak
Linux: Introduction to Operating System and it’s Architecture, Process Management, Signals, Systems Concepts, Processes Scheduling & synchronization, Memory management, File System management, Introduction to Linux, Startup Files, Linux boot process, Installation of Linux, Disk partitioning, Controlling and managing Services, Basic Linux commands, User administration of Linux, Network Configuring, Network Monitoring and Troubleshooting (netstat/iproute2), System Configuration Files, Perform System Management, Maintenance and troubleshooting, Basic Service Security, Log Management, Network Authentication
Shell Scripting: Introduction to BASH Command Line Interface (CLI) Error Handling, Debugging & Redirection of scripts Control Structure, Loop, Variable & String, Conditional Statement Regular Expressions, Automate Task Using Bash Script, Security patches, Logging & Monitoring using script.
Perl: Control structure and loops, Useful/necessary functions to memorize, Array Functions, Hash Functions, Array and hash manipulation, Inbuilt special variables Regular Expressions basics, File Handling, Introduction to Modules and Packages, Database Connectivity.
Introduction to Python, Python basics, Data Types and variables Operators, Looping & Control Structure, List, Modules, Dictionaries, String, Regular Expressions, Functions and Functional Programming, Object Oriented Linux Scripting Environment, Classes, Objects and OOPS concepts, File and Directory Access Permissions, Libraries and Functionality Programming, Writing plugins in Python, Data analysis Automation Process, Debugging basics, Task Automation with Python.
Resource manager, Batch systems, Scheduler, various open source schedulers in HPC PBS Pro, Slurm, SGE, Components of resource manager, installation and configuration of Slurm and PBS Pro, submitting and managing jobs, Writing the batch script , Application level check pointing, Managing nodes, setting server scheduling policies, scheduler integration, Maui, Moab, MPI support, Accounting records, Gold
Security Fundamentals, Risk Management, Exposure and Countermeasure, DMZ, Firewalls, Types of Firewalls, Limitations of firewall, firewalld, Threat Management Gateway, Web Application Firewall, Packet capturing, Packet Signature and Analysis, Reverse proxy, Virtual Private Networks, IPSec, CA, SSL/TLS Certificate generation, Intrusion Detection And Prevention, Intrusion risks, Security policy, Monitoring and reporting of traffics, Traffic shaping, Investigating and verifying detected intrusions, reporting and documenting intrusions, Define the Types of intrusion Prevention Systems, Intrusion prevention system basics, Limitations of Intrusion Prevention System, Spoof Prevention, Dos, Ddos, QoS Policy, and Snort configuration.
Types of Storage, Protocols, Components of a disk drive, physical disk and factors affecting disk drive performance. RAID level performance and availability considerations, Components and benefits of an intelligent storage system, (DAS) architecture, (SAN) attributes, components, topologies, connectivity options and zoning, FC protocol stack, addressing, flow control, and classes of service, Network Attached Storage (NAS) components, protocols, IP Storage Area Network (IP SAN) iSCSI, FCIP and FCoE architecture, Logical Volume Manager (LVM)
Parallel File Systems
Introduction to Parallel File Systems, types of Parallel File Systems, PVFS2, Lustre, BeeGFS, GPSF, Components, Installation and configuration, benchmarking, comparison of Parallel File Systems, Optimization
Backup, Backup tools, Types of backup, backup policies, Archive, retrieve, backup optimization, restore, Backup media (LTO), Tape library.
- Manage the HPC infrastructure like (Network, Storage, Resource and Backup Management)
- Design an efficient data center.
- Maintain the HADOOP cluster and related technology
- Explore on HPC applications and solutions
- Understand the fundamentals of various cloud techniques and system security.
· Graduate in Engineering (10+2+4 or 10+3+3 years) in IT / Computer Science / Electronics / Telecommunications / Electrical / Instrumentation.
MSc/MS (10+2+3+2 years) in Computer Science, IT, Electronics.
· Mathematics in 10+2 (exempted for candidates with Diploma + Engineering).
- Post Graduate Degree in Mathematics or allied areas,
- The candidates must have secured a minimum of 55% marks in their qualifying examination.