computational storage acceleration through intelligence agility · computational storage:...
TRANSCRIPT
![Page 1: Computational Storage Acceleration Through Intelligence Agility · Computational Storage: Acceleration Through Intelligence & Agility Thad Omura EVP Marketing December, 2018. What’s](https://reader030.vdocuments.mx/reader030/viewer/2022040609/5ec9ad2c7968300dc8156e77/html5/thumbnails/1.jpg)
Presented By
Computational Storage:
Acceleration Through Intelligence & Agility
Thad Omura
EVP Marketing
December, 2018
![Page 3: Computational Storage Acceleration Through Intelligence Agility · Computational Storage: Acceleration Through Intelligence & Agility Thad Omura EVP Marketing December, 2018. What’s](https://reader030.vdocuments.mx/reader030/viewer/2022040609/5ec9ad2c7968300dc8156e77/html5/thumbnails/3.jpg)
What’s the Big Deal?
![Page 4: Computational Storage Acceleration Through Intelligence Agility · Computational Storage: Acceleration Through Intelligence & Agility Thad Omura EVP Marketing December, 2018. What’s](https://reader030.vdocuments.mx/reader030/viewer/2022040609/5ec9ad2c7968300dc8156e77/html5/thumbnails/4.jpg)
![Page 5: Computational Storage Acceleration Through Intelligence Agility · Computational Storage: Acceleration Through Intelligence & Agility Thad Omura EVP Marketing December, 2018. What’s](https://reader030.vdocuments.mx/reader030/viewer/2022040609/5ec9ad2c7968300dc8156e77/html5/thumbnails/5.jpg)
- Sheer volume of data taxing to process
Data Explosion
- Can’t store tons of data in the same place- Difficult for different applications to share
Data Islanding
- Exorbitant licensing fees- Expensive migrations
High Costof Alibaba Cloud’s clients encounter:
70%
![Page 6: Computational Storage Acceleration Through Intelligence Agility · Computational Storage: Acceleration Through Intelligence & Agility Thad Omura EVP Marketing December, 2018. What’s](https://reader030.vdocuments.mx/reader030/viewer/2022040609/5ec9ad2c7968300dc8156e77/html5/thumbnails/6.jpg)
Data ExplosionData IslandingHigh Cost
MARKET PROBLEM
Cloud Scale Economics
Unified Storage
Real-time Analytics
OPPORTUNITY SOLUTION
Computational Storage
![Page 7: Computational Storage Acceleration Through Intelligence Agility · Computational Storage: Acceleration Through Intelligence & Agility Thad Omura EVP Marketing December, 2018. What’s](https://reader030.vdocuments.mx/reader030/viewer/2022040609/5ec9ad2c7968300dc8156e77/html5/thumbnails/7.jpg)
Computational Storage Provides the Solution
Real-time analytical processing from transactional data
- Intelligent data management
- Hardware accelerated, parallelized database compute at data
- Programmable FPGA hardware to evolve functions with customer demands
POLARDBHTAP: Hybrid Transactional-
Analytical Database
![Page 8: Computational Storage Acceleration Through Intelligence Agility · Computational Storage: Acceleration Through Intelligence & Agility Thad Omura EVP Marketing December, 2018. What’s](https://reader030.vdocuments.mx/reader030/viewer/2022040609/5ec9ad2c7968300dc8156e77/html5/thumbnails/8.jpg)
By bringing compute to the data, ScaleFlux is transforming the way we are
architecting our Flash storage infrastructure.
We’re looking to fully utilize the values of Computational Storage in order to cost-
effectively scale real-time analytics across exploding transactional data sets, all the
while delivering the most responsive, cloud-native user experience.
“
”
10X Transactional-Analytical Processing, Half the Flash Capacity
GM at Database
![Page 9: Computational Storage Acceleration Through Intelligence Agility · Computational Storage: Acceleration Through Intelligence & Agility Thad Omura EVP Marketing December, 2018. What’s](https://reader030.vdocuments.mx/reader030/viewer/2022040609/5ec9ad2c7968300dc8156e77/html5/thumbnails/9.jpg)
How?
![Page 10: Computational Storage Acceleration Through Intelligence Agility · Computational Storage: Acceleration Through Intelligence & Agility Thad Omura EVP Marketing December, 2018. What’s](https://reader030.vdocuments.mx/reader030/viewer/2022040609/5ec9ad2c7968300dc8156e77/html5/thumbnails/10.jpg)
Open ChannelFlash Management
ComputationAcceleration
SolutionAgility
Cohesive Application to Storage Acceleration
![Page 11: Computational Storage Acceleration Through Intelligence Agility · Computational Storage: Acceleration Through Intelligence & Agility Thad Omura EVP Marketing December, 2018. What’s](https://reader030.vdocuments.mx/reader030/viewer/2022040609/5ec9ad2c7968300dc8156e77/html5/thumbnails/11.jpg)
Multi-Tenant
✓ Isolation✓ Consistent
Global View
✓ Reduce Overprovision✓ Minimize Write Amplification
Open Channel (Host) Flash Management
Data Placement
✓Controllable✓ Application Awareness
![Page 12: Computational Storage Acceleration Through Intelligence Agility · Computational Storage: Acceleration Through Intelligence & Agility Thad Omura EVP Marketing December, 2018. What’s](https://reader030.vdocuments.mx/reader030/viewer/2022040609/5ec9ad2c7968300dc8156e77/html5/thumbnails/12.jpg)
12
DRAM
CPU
DRAM
Page A
Page B
Page C
Single-Stream Multi-Stream
In-System FPGA (HW) & SW Update for NEW Features
ATOMIC WRITES
Database Logs FilesAnalytic DataSmall
Random
Re-written Often
Medium
Sequential & Random
Temporary Storage
Large
Sequential
Long Term Storage
MULTI-STREAMS
SSD
Page A
Page B
Page C
Double
Write
Buffer
1
Page A
Page B
Page C
2
Database Table
1
Page A
Page B
Page C
Database Table
Single Atomic Write
Guarantee larger write units are persisted to memory
2X Flash Endurance!Efficient management of different data types
Performance & Endurance
Typical Large Write Guarantee
![Page 13: Computational Storage Acceleration Through Intelligence Agility · Computational Storage: Acceleration Through Intelligence & Agility Thad Omura EVP Marketing December, 2018. What’s](https://reader030.vdocuments.mx/reader030/viewer/2022040609/5ec9ad2c7968300dc8156e77/html5/thumbnails/13.jpg)
13
Production Workload Optimization: Customer Case Study
Orange is ScaleFlux
4 Week Turnaround to tune and test optimized Flash I/O
Minimize both 1ms and 8ms (tail latencies)
Flexible hardware and software platform for application tuning
Significant impact on latency sensitive applications
Customer now using ScaleFlux for lowest latency Flash NoSQL database solution
![Page 14: Computational Storage Acceleration Through Intelligence Agility · Computational Storage: Acceleration Through Intelligence & Agility Thad Omura EVP Marketing December, 2018. What’s](https://reader030.vdocuments.mx/reader030/viewer/2022040609/5ec9ad2c7968300dc8156e77/html5/thumbnails/14.jpg)
Fast Transition to Latest 3D NAND TLC to QLC+
Simple Storage Class Memory Integration
Next: Industry standardization
14
More Values from Open Channel Model
![Page 15: Computational Storage Acceleration Through Intelligence Agility · Computational Storage: Acceleration Through Intelligence & Agility Thad Omura EVP Marketing December, 2018. What’s](https://reader030.vdocuments.mx/reader030/viewer/2022040609/5ec9ad2c7968300dc8156e77/html5/thumbnails/15.jpg)
Open ChannelFlash Management
ComputationAcceleration
SolutionAgility
Cohesive Application to Storage Acceleration
![Page 16: Computational Storage Acceleration Through Intelligence Agility · Computational Storage: Acceleration Through Intelligence & Agility Thad Omura EVP Marketing December, 2018. What’s](https://reader030.vdocuments.mx/reader030/viewer/2022040609/5ec9ad2c7968300dc8156e77/html5/thumbnails/16.jpg)
SLOWSLOW
Acceleration
…
Intense Compute(compression, fuzzy search)
Limited I/O and
Memory Capacity
Performance & Scalability
SLOW
We solve both simultaneously
Reduce Data Movement
Accelerate Computation
Parallelize Processing
Computational Storage Subsystem (CSS)
![Page 17: Computational Storage Acceleration Through Intelligence Agility · Computational Storage: Acceleration Through Intelligence & Agility Thad Omura EVP Marketing December, 2018. What’s](https://reader030.vdocuments.mx/reader030/viewer/2022040609/5ec9ad2c7968300dc8156e77/html5/thumbnails/17.jpg)
Compute Functions
- Data intensive, fixed function
- 5-100x speed up vs. CPU
Tradeoffs and Design Considerations
![Page 18: Computational Storage Acceleration Through Intelligence Agility · Computational Storage: Acceleration Through Intelligence & Agility Thad Omura EVP Marketing December, 2018. What’s](https://reader030.vdocuments.mx/reader030/viewer/2022040609/5ec9ad2c7968300dc8156e77/html5/thumbnails/18.jpg)
18
Parallelizing Computational Storage
GZIP Compression(CPU zlib vs. ScaleFlux css_zlib, corpus.cantebury E5-2667v4)
Me
ga
byte
s p
er
Se
co
nd
1000
2000
3000
4000
5000
6000
7000
8000
CPU Bound!
482MB/s
1 2 3 4# SSDs 1 2 3 4# CSSs
Fuzzy Search (POC Unindexed Text Data, Edit Distance = 8, E5-2637v3)
CPU Bound!
~700MB/s
1 8 16 24# SSDs 1 8 16 24# CSSs
3X
100X
Me
ga
byte
s p
er
Se
co
nd
10000
20000
30000
40000
50000
60000
70000
6X
17X
![Page 19: Computational Storage Acceleration Through Intelligence Agility · Computational Storage: Acceleration Through Intelligence & Agility Thad Omura EVP Marketing December, 2018. What’s](https://reader030.vdocuments.mx/reader030/viewer/2022040609/5ec9ad2c7968300dc8156e77/html5/thumbnails/19.jpg)
INFRASTRUCTURE
STORAGECompression (GZIP)Erasure Coding (RS)
Security (AES)Authentication (SHA)Error Checking (CRC)
PLATFORM
DATABASE, ANALYTICSKV-Store
Transactional-AnalyticalSQL Processing
Big Data Analytics
APPLICATION
AI, Genomics, CDN, SearchMedia Scaling & Transcoding
Neural NetworksFuzzy Search
Filtering, Matching
Identifying the Right Workloads
![Page 20: Computational Storage Acceleration Through Intelligence Agility · Computational Storage: Acceleration Through Intelligence & Agility Thad Omura EVP Marketing December, 2018. What’s](https://reader030.vdocuments.mx/reader030/viewer/2022040609/5ec9ad2c7968300dc8156e77/html5/thumbnails/20.jpg)
Open ChannelFlash Management
ComputationAcceleration
SolutionAgility
Cohesive Application to Storage Acceleration
![Page 21: Computational Storage Acceleration Through Intelligence Agility · Computational Storage: Acceleration Through Intelligence & Agility Thad Omura EVP Marketing December, 2018. What’s](https://reader030.vdocuments.mx/reader030/viewer/2022040609/5ec9ad2c7968300dc8156e77/html5/thumbnails/21.jpg)
Agility is Important
ENGAGEMENT
Demand to POC < 6 months
HW AGILITY
Update after deployment
FLASH LIFECYCLES
Reducing to 12 months
![Page 22: Computational Storage Acceleration Through Intelligence Agility · Computational Storage: Acceleration Through Intelligence & Agility Thad Omura EVP Marketing December, 2018. What’s](https://reader030.vdocuments.mx/reader030/viewer/2022040609/5ec9ad2c7968300dc8156e77/html5/thumbnails/22.jpg)
Solution Agility Across Whole Stack
Compute Libraries / APIs
Distributed File Systems(HDFS, Ceph, …)
Virtual File System (VFS)File System (Ext4, XFS, ZFS …)
Open Channel Flash ManagementComputational Storage Driver
Applications
Database Big Data ContentDelivery
AI/ML
AIC or U.2
PCIe
FPGARe-programmable Compute Engines
Simple Interface
Easy Integration
Programmable HW engines
Controllable Data Placement
Performance/QoS (latency)
![Page 23: Computational Storage Acceleration Through Intelligence Agility · Computational Storage: Acceleration Through Intelligence & Agility Thad Omura EVP Marketing December, 2018. What’s](https://reader030.vdocuments.mx/reader030/viewer/2022040609/5ec9ad2c7968300dc8156e77/html5/thumbnails/23.jpg)
Fast TTM for Turnkey Apps
Available Through:
![Page 24: Computational Storage Acceleration Through Intelligence Agility · Computational Storage: Acceleration Through Intelligence & Agility Thad Omura EVP Marketing December, 2018. What’s](https://reader030.vdocuments.mx/reader030/viewer/2022040609/5ec9ad2c7968300dc8156e77/html5/thumbnails/24.jpg)
Turnkey Compute & Storage Acceleration
24
24 Mapper/Reducers per Datanode *9 = 216 total
Better performance on CSS reported with lower Mapper/Reducers possible
Tim
e (
seco
nd
s)
Lo
wer
is B
ett
er
500
1000
1500
2000
2500
3000
3500
Teragen405 seconds
Terasort2787 seconds
Snappy HDD Temp
CPU GZIP HDD Storage
CPU/ISA-L EC
Baseline
Terasort2582 seconds
Teragen155 seconds
Snappy HDD Temp
CSS GZIP HDD Storage
CSS EC
14% ↓ vs. baseline
116% Job Throughput
Compute
Only
Terasort2040 seconds
Snappy CSS Flash Temp
CPU GZIP HDD Storage
CPU/ISA-L EC
Teragen405 seconds
Flash Temp
Only
23% ↓ vs. baseline
131% Job Throughput
Snappy CSS Flash Temp
CSS GZIP HDD Storage
CSS EC
Terasort1842 seconds
Teragen155 seconds
Compute & Flash Acceleration
37% ↓ vs. baseline
160% Job Throughput
3.1 w/ EC (6+3)
Datanode Config:
Dual E5-2640v3, 128GB DRAM, 12*6TB SAS HDD
…
…
![Page 25: Computational Storage Acceleration Through Intelligence Agility · Computational Storage: Acceleration Through Intelligence & Agility Thad Omura EVP Marketing December, 2018. What’s](https://reader030.vdocuments.mx/reader030/viewer/2022040609/5ec9ad2c7968300dc8156e77/html5/thumbnails/25.jpg)
Delighted Customers
![Page 26: Computational Storage Acceleration Through Intelligence Agility · Computational Storage: Acceleration Through Intelligence & Agility Thad Omura EVP Marketing December, 2018. What’s](https://reader030.vdocuments.mx/reader030/viewer/2022040609/5ec9ad2c7968300dc8156e77/html5/thumbnails/26.jpg)
26
“…delivering fantastic
OPERATIONS PER SECOND for
our latest NoSQL database…”
“…INSTANTLY saw how this can
help us COST-EFFECTIVELY
scale our infrastructure …”
FAST
“…accelerating MULTIPLE,
BUSINESS-CRITICAL
APPLICATIONS for us…”
PhonePe
AGILEEASY
![Page 27: Computational Storage Acceleration Through Intelligence Agility · Computational Storage: Acceleration Through Intelligence & Agility Thad Omura EVP Marketing December, 2018. What’s](https://reader030.vdocuments.mx/reader030/viewer/2022040609/5ec9ad2c7968300dc8156e77/html5/thumbnails/27.jpg)
- HQ in San Jose, Offices in China
- Shipping Computational Storage worldwide
The pioneer in deploying Computational Storage at scale
Thank You!Come visit us in the Exhibits!
www.scaleflux.com
![Page 28: Computational Storage Acceleration Through Intelligence Agility · Computational Storage: Acceleration Through Intelligence & Agility Thad Omura EVP Marketing December, 2018. What’s](https://reader030.vdocuments.mx/reader030/viewer/2022040609/5ec9ad2c7968300dc8156e77/html5/thumbnails/28.jpg)