• No results found

Hitachi Data Center Analytics

N/A
N/A
Protected

Academic year: 2021

Share "Hitachi Data Center Analytics"

Copied!
22
0
0

Loading.... (view fulltext now)

Full text

(1)

Hitachi Data

(2)

Storage analytics challenges

Introducing Hitachi Data Center Analytics

Storage analytics use cases and solutions

Q&A

Agenda

(3)

Storage Analytics

Challenges

(4)

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

(5)

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 product

architectures

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

(6)

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

(7)

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

(8)

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

(9)

Introducing

Hitachi Data

(10)

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

(11)

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

(12)

Hitachi Data Center Analytics

Select First time duration Select Second time duration Compare Timelines

Both 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

(13)

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

(14)

Hitachi Data Center Analytics:

Scalability

Input Data Database Java, C#, SQL Analysis

Traditional 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

(15)

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

(16)

Storage Analytics

Use Case and

(17)

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

(18)

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

(19)

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

(20)

Hitachi Data Center Analytics

Advantages

Storage Analytics Simplified

 Scalable performance data

warehouse for large enterprise data

growth

 Utilize historical trend analysis for

future infrastructure requirement

planning

 Generate both standard and

customized reports

 Provide deep performance monitoring

for efficient problem identification and

management

(21)

Questions

(22)

References

Related documents

More specifically, there is a need to explore the concepts related to application-driven overlay networking (ADON) with novel cloud services such as “Network-as-a-Service” to

This book consists of nine main chapters namely, introduction, preliminary of rule based systems, generation of classi fi cation rules, simpli fi cation of classi fi cation

In borrow mode (sometimes called borrow-display mode), the program borrows the full screen and the keyboard from the Display Manager and uses the display driver

GPR _ $POSITION _ T format. This data type is 4 bytes long. See the GPR Data Types section for more information. Coordinate values must be within the limits of the current

AI might take information from not just one doctor but many doctors' experiences and it can pull out information from different patients that share similarities.” Scientists at

The case studies in Chapter 16 cover a wide range of real-world problems that were solved using Map- Reduce, and in each case, the data processing task is implemented using two

All DS3000 and DS4000 systems equipped with optional storage devices contain controllers to manage the Winchester disk drives and floppy disk or tape cartridge drives, and

Abstract. The objective of this study was to introduce the recommender system based on expert and item category to match the right items to users. In this study, the