Upload
memsql
View
595
Download
3
Embed Size (px)
Citation preview
The real-time database for transactions and analytics
MemSQL Product Introduction
2
Why MemSQL? Telecoms Must Operate in Real Time
Streaming Transactions Analytics
Detect and respond to business changes the moment they happen
Deliver real-time analytics to applications with growing user bases
Simultaneously ingest and serve data
• Streaming workloads
• Transactional workloads (OLTP)
• Analytical workloads (OLAP)
3
The Real-Time Database for Transactions and Analytics
In-Memory DistributedRelational Datacenter or Cloud
Multi-model RDBMS SQL Key-value pairs Documents (JSON) Geospatial
In-Memory rowstore Memory-optimized
on-disk columnstore
Distributed query optimizer and execution
Scale out on commodity hardware
Simple Real-Time Affordable Flexible
Deploy on-premises Deploy on AWS or
Azure Marketplaces
4
MemSQL Ecosystem and Architecture
Orchestration / Containers
Cloud / On-Premises Platform
MessagingInputs Business Intelligence Dashboards
Real-Time Applications
In-Memory Database
Columnstore
RAM, SSD, Disk / Fast appends
RelationalFull
transactional SQL
Key-ValueTwo column
table
DocumentJSON
Geospatial
Rowstore
RAM / Fast updates
StreamingReal-time
transformation
Streamliner
With Integrated Apache Spark
Wire-protocol
MemSQL Loader
Hadoop Amazon S3
5
MemSQL Streamliner Provides Immediate Access to Real-Time Analytics
ApplicationApache Spark
STREAMLINER
Extract Transform Load
STREAMLINER
Real-Time Inputs
One click deployment of integrated Apache Spark Create real-time data pipelines through a graphical UI Eliminate batch ETL Open sourced on GitHub at memsql.github.io/spark-streamliner
6
MemSQL Community and Enterprise Editions
Community EditionFree Forever
Enterprise EditionFree 30-day Trial
• Unlimited capacity and scale
• Comprehensive SQL features
• 24/7 support• Enterprise functionality
• High availability• Cluster replication• Granular access controls• Security features
7
Results Proactively diagnose issues Form real-time intelligence Deliver better viewer experience
Comcast: Real-Time Operational Intelligence and Monitoring
Log Collection Real-Time Analytics
• Analysts query live data• Alerts on complex
objects• Optimize CDN efficiency
~ 1 second
~ 30 minutes
ApplicationReal-time monitoring and analytics on streaming video
ProblemCollect streaming data at scale and make available to query in real-time
Akamai CDN Billing
ApplicationCDN customer billing
ProblemOracle Exadata solution could only handle 57k upserts/second, could not keep up with new billing model
ResultsMemSQL cluster performs at 1.9 million upserts/second, moving from monthly to daily billing
CDN resource usage statistics
INSERT... ON DUPLICATE KEY UPDATE... (1.9 million/sec)
Billing Application
• Compute customer charges daily
• Roll up infrastructure usage by cloud provider
• More sophisticated platform offers customers better service, partners new business opportunities
Thank Youwww.memsql.com