Hitachi Data
Storage analytics challenges
Introducing Hitachi Data Center Analytics
Storage analytics use cases and solutions
Q&A
Agenda
Storage Analytics
Challenges
Storage Pain Points
Driven by rapid capacity growth,
storage analytics is required to
address key storage pain points
of delivering storage performance,
forecasting and reporting
Leading Performance Management Challenges
% of respondents 2.6 23.8 26.4 28.0 28.3 30.9 42.0 .0 5.0 10.0 15.0 20.0 25.0 30.0 35.0 40.0 45.0 Other Complexity in managing too many storage productarchitectures
Quickly fulfilling storage provisioning requests Time in planning/doing storage migrations/technology
refreshes
Time and/or budget to implement advanced storage features
Successfully troubleshooting potentially storage-related problems
Meeting SLAs on performance, availability or recovery
Most Pressing Storage Challenges
Source: IDC General Storage Quick Poll #243511
Hitachi Command Suite
Across all storage platforms
Across management functions
Across file, block, and object
Across global storage virtualization
Unified Management Framework
Control
Analyze
Optimize
Protect
Unified
HDI
Compute
Hitachi Blade
Server VSP G1000, VSP, VSP Midrange, HUS VM, HUS, HNAS
Appliance
Content
HCP
Automate
Key Storage Management Capabilities: Analyze
INTEGRATION
INTEGRATION
INTELLIGENCE
INTELLIGENCE
AUTOMATION
CONTROL
UNIFY ALL DATA TYPES AGILE DEPLOYMENT
MAXIMIZE, SIMPLIFY ANALYZE GAIN INSIGHT IMPROVE PERFORMANCE AVOID PROBLEMS OPTIMIZE INCREASE ROI GAIN EFFICIENCY ALIGN RESOURCES PROTECT REDUCE RISK BUSINESS CONTINUITY HIGH AVAILABILITY
STORAGE
ANALYTICS
APPROACH
HITACHI STORAGE PERFORMANCE ANALYTICS
BIG DATA ALIGNED
SERVICES ATTACHED SINGLE DATA COLLECTOR
SINGLE DATA REPOSITORY NEW STORAGE
ANALYTICS APPROACH SAAS MODEL
KEY Points
KEY Customer Value
CLOUD DEPLOYED
Introducing
Hitachi Data
Hitachi Data Center Analytics (HDCA)
provides data center managers with useful
insights about their Hitachi storage
infrastructure using sophisticated analytics
On-demand analytics
Tree view of the environment
Correlation capabilities
Near real-time reporting
Advanced interactive UI using HTML5 and Javascript
Customizable reports through report builder
External business intelligence integration
Scalable solution
Powered by proven NoSQL technology
Ability to store highly granular data for years
Easy and lightweight deployment
What Is Hitachi Data Center Analytics (HDCA)?
Hitachi Data Center Analytics Tree View Advanced Analytics Interactive UI Custom Reporting No SQL Near Real Time Baselines BI Integration REST API
Hitachi Data Center Analytics
Select an object to be analyzed
Tree
Shows hierarchical representation of the storage system objects
Interactive Reporting
Select a time duration Compare different time durations
“Zoom In” on a specified time
Select or deselect metrics to be displayed
Hitachi Data Center Analytics
Select First time duration Select Second time duration Compare TimelinesBoth values are plotted (primary in bold and
secondary in dash) View the
‘Zoom-In’ report
Zoom-in Reports
“Apply Zoom” to other reports
“Reset Zoom” to go back to original time interval
Zoom-In/Zoom-out bar : Apply zoom and reset
Hitachi Data Center Analytics:
Lightweight Deployment Model
RIAT Probe VM Data Center Analytics Server
Custom Reports User Interface Interactive Reports TMEA Collector Hitachi Storage Hitachi Storage End Users RMLIB RMLIB TMEA Collector
Data Center Analytics has just 2 software components; both are installed as virtual machines
Probes: gather performance and configuration data from targets (extract, transform and load) Server: receives data from probes for processing, analysis and reporting
Hitachi Data Center Analytics:
Scalability
Input Data Database Java, C#, SQL AnalysisTraditional performance analysis
Input
Data Database
Procedural Language (e.g.,
Swazall, Hive)
New approach
(i.e. Google Tools)Dehydrate data Rehydrate data Input Data MARS Query Language
Hitachi Data Center Analytics (HDCA)
Proprietary No-SQL DB
Dehydrate data
Hitachi Data Center Analytics
EFFICIENT AND SCALABLE ANALYTICS FOR TODAY’S DATA CENTER
Trend analysis
Historical trend reports spanning multiple years
Scalability and granularity
Highly scalable, granular enterprise class performance data collection
Performance data warehouse
Storage Analytics
Use Case and
Storage Analytics
Business scenario
‒ Collecting storage performance data doesn’t properly scale across the data center ‒ Inadequate performance statistics doesn’t facilitate historical trend analysis for
proper planning
Customer requirements
‒ Historical performance data collection that properly scale as the storage infrastructure grows
‒ Granular performance statistics for deep performance analysis
Scalable analytics with Hitachi Data Center Analytics
‒ Highly scalable and granular performance data warehouse solution for storage analytics reporting, to properly plan future storage infrastructure growth
Storage Analytics
How We Do It
Measure and store configuration and
performance data from storage, hypervisors, and operating systems
Correlate and analyze data center
performance issues from virtual machines to storage down to 1-second intervals [Currently only 1 second intervals on Linux platforms]
Trend and scale performance data long term across the data center infrastructure Report and solve the most difficult
Hitachi Data Center Analytics (HDCA)
Scalability − large-scale enterprise-class data
collection for historical reporting and analysis
‒ Complementary extension for Tuning Manager when longer range data collection is required
Granularity
−
near real time, fine-granularity data collection Data warehouse − performance data
warehouse for Hitachi storage environments Flexible reporting – includes both standard,
out-of-the-box reports and custom reporting capabilities
Hitachi Storage Analytics Solutions
Hitachi Tuning Manager (HTnM)
End-to-end performance monitoring and reporting – From applications (Oracle,
Microsoft® SQL Server®, Micrsoft Exchange) to logical storage devices
Troubleshooting – Excellent for deep dive analysis of data path problem areas for all Hitachi storage environments
Alarms – Provides granular monitoring and SNMP alarms for all Hitachi storage platforms Third-party management integrations –
REST-based API and CLI for 3rd-party integration
‒ Used for custom reporting
‒ Data interchange for custom-built applications or other familiar reporting tools