2. Enterprise workload examples
Optimizing Amazon EC2 cost and capacity
• High performance computing (HPC)
• Machine learning infrastructure
• Windows on AWS
• SAP on AWS
• VMware Cloud on AWS
Amazon EC2 foundations
Broadest and deepest platform for enterprise workloads
6. Broadest and deepest platform choice
Workloads Capabilities Options
(AWS, Intel, AMD)
(up to 4.0 GHz)
(up to 24 TiB)
(HDD and NVMe)
(up to 100 Gbps)
(GPUs and FPGA)
(Nano to 32xlarge)
+ + =
275+instance types
7. Machine learning/AI
Accelerated computing workloads
Applications that benefit from hardware acceleration
High-performance
computing
Graphics
Image and video
recognition
Natural language
processing
Autonomous
vehicle systems
Personalization &
recommendation
Computational
fluid dynamics
Financial and
data analytics
Genomics
Computational
chemistry
Virtual graphic
workstation
3D modeling &
rendering
Video encoding AR/VR
8. Gartner, Magic Quadrant for Cloud Infrastructure as a Service, Worldwide,
Raj Bala, Bob Gill, Dennis Smith, David Wright, July 2019. ID G00365830.
AWS recognized as
a cloud leader for the
9th consecutive year
10. Compute platform optimized for enterprise apps
HPC Windows
workloads
Machine
learning
SAP VMware Cloud on
AWS
11. HPC impacts your life every day
Your morning coffee The car you drive The fuel you use
Your retirement
portfolio
Knowing the weather
The movies you
watch
The medicines
you take
12. Addressing HPC technical requirements
Run HPC in the cloud easily and securely, without compromising on price performance
14. Scale tightly coupled HPC applications on AWS
SRD protocol Proving myths about latency constraints wrong
CFD Seismic
Weather
modeling
Application
MPI implementation
Userspace
Kernel
TCP/IP stack
ENA network driver
Without EFA
Application
MPI implementation
EFA kernel driver
Libfabric
EFA device
With EFA
ENA device
Elastic Fabric Adapter (EFA)
15. Frameworks Interfaces Infrastructure
AI services
Vision Speech Language Chatbots Forecasting Recommendations
ML services
ML frameworks + infrastructure
Amazon
Polly
Amazon
Transcribe
Amazon
Translate
Amazon Comprehend /
Amazon
Comprehend Medical
Amazon Lex Amazon
Forecast
Amazon
Rekognition
Image
Amazon
Rekognition
Video
Amazon
Textract
Amazon Personalize
EC2 C5EC2 P3
& P3DN
EC2 G4 AWS
Inferentia
AWS IoT
Greengrass
Amazon
Elastic
Inference
Amazon SageMaker Ground Truth Notebooks Algorithms + AWS Marketplace Reinforcement learning Training Optimization Deployment Hosting
FPGAs
The AWS ML stack
Broadest and deepest set of capabilities
16. Machine learning use cases
Applications that benefit from accelerated compute
Natural
language processing
Image/Video
analysis
Autonomous
vehicle systems
Recommendation
systems
Financial services
Retail
Healthcare &
life sciences
Travel & hospitality
Manufacturing
Energy
Machine learning/AI
17. Accelerated compute portfolio for machine learning
ML training
P3/P3dn GPU compute instance
• Up to 1 petaflop of compute with 8x
NVIDIA V100 GPUs
• Up to 256 GB of GPU memory
• Up to 100 Gbps of networking
• Designed to handle large distributed
training jobs for fastest time to train
G4: GPU compute instance
• Up to 520 teraflops of compute
with 8x NVIDIA T4 GPUs
• Cost-effective small-scale
training jobs
ML inference
AWS Inf1 instance
• Up to 2,000 TOPS with 16x AWS
Inferentia accelerators
• Lowest cost per inference in the cloud
• Designed for high throughput and
low latency
G4: GPU compute instance
• Up to 1,030 TOPS of compute with 8x
NVIDIA T4 GPUs
• Increased performance, lower latency,
and reduced cost per inference compared
to previous GPU-based instances
P2: GPU compute instance
• Up to 160 teraflops of compute with
16x NVIDIA K80 GPUs
• General-purpose GPU compute
G4
G4
18. As a managed service using
Amazon RDS
Self-managed using
Amazon EC2
BYOL Windows & SQL Server
Purchase EC2 Windows + BYOL SQL
Purchase EC2 Windows + SQL Server
Running Microsoft applications on AWS
RDS for SQL Server
20. 1. Flexible pay-as-you-go
licensing choices
2. Bring your license mobility
benefits to AWS
3. Bring licenses to AWS without
paying for software assurance
Dedicated options for
licenses not eligible for
license mobility
Default tenancy
for license mobility–
eligible products with
software assurance
AWS licensing
Buy license-included
instances from AWS
(Windows Server, SQL
Server)
Bring licenses to AWS
Flexible options for Microsoft licenses on the
AWS Cloud
21. .NET to Serverless
Our experiences with customers point to 4 dominant
modernization pathways
22. SAP on AWS: Unmatched pace of innovation
Engineering milestones SAP on AWS
SAP
SuccessFactors
SAP NS2 SAP Customer
Experience
SAP
Cloud Platform
SAP HANA
EnterpriseCloud
SAP
Concur
QualtricsXM
Customeradoption
2008 Today
SAP as a
customer
SAP S/4HANA
SAP Business Suite
SAP HANA One
SAP HANA Developer Edition
A1 / B1BOBJ
SAP HANA for B1
SAP Business Warehouse (BW) on SAP HANA
X1 (2TB) SAP BW/4 HANA X1 (14 TB)
X1e (4TB)
SAP HANA Enterprise Cloud on AWS
SAP Cloud Platform on AWS
SAP BW/4HANA (50 TB)
FAST Migrate
SAP NS2’s Secure SAP HANA Cloud
SAP HANA
as a ServiceEC2 Bare Metal for SAP HANA (6, 9 & 12TB)
2016
2017
2018
SAP Analytics Cloud
on AWS
2019
SAP S/4HANA 48TB scale-out
SAP BW/4HANA (100 TB)
IoT cloud-to-cloud and edge-to-edge
SAP solution spaces (31)
SAP S/4HANA QuickStart
SAP in 7 Regions, 44 services
AppStream
23. .244 .384 .488 .768 1
2
4
6
9
12
18
24
R4 R5 R4 R5 X1 X1 X1e High-memory instances
MemoryinTBAmazon EC2 instances for SAP HANA
Scale-up options Scale-out options
48 TB
50 TB
100 TB
12 TB
OLTP scale-out
(S/4HANA)
OLAP
scale-out*
OLAP
scale-out*
OLAP
scale-out*
* BWoH, BW/4HANA, and data mart
24. VMware Cloud on AWS
Rich VMware SDDC
delivered as a cloud
service on AWS
Consistency and
familiarity of VMware
technologies
Easy workload
portability and
hybrid capabilities
Direct access to the
power of native
AWS services
Existing and new
apps with containers
and VMs
VMware software-designed data center (SDDC) technologies you know and trust, delivered as a
service on the world’s most popular public cloud
27. Optimizing Amazon EC2 cost and capacity
We continue to innovate for our customers
Pricing Capacity Guidance
28. the second
Amazon EC2 purchasing options
savings of up to 90%a significant discount
more flexibility
29. To optimize Amazon EC2, combine purchase options
RIs or a Savings Plan
Spot for fault-tolerant,
flexible, stateless workloads
On-Demand
30. Types of Savings Plans
Provide the lowest prices, up to 72% off (same
as Standard RIs) on the selected instance family
(e.g., C5 or M5), in a specific AWS Region
Offer the greatest flexibility, up to 66% off
(same prices as Convertible RIs)
Flexible
across
Instance family: e.g., Move from C5 to M5
Region: e.g., Change from EU (Ireland) to EU
(London)
OS: e.g., Windows to Linux
Tenancy: e.g., Switch Dedicated tenancy to
Default tenancy
Compute options: e.g., Move from EC2 to
Fargate
Flexible
across
Size: e.g., Move from m5.xl to m5.4xl
OS: e.g., Change from m5.xl Windows
to m5.xl Linux
Tenancy: e.g., Modify m5.xl Dedicated
to m5.xl Default tenancy
Compute
Savings Plans
EC2 Instance
Savings Plans
31. Spot, On-Demand capacity reservations, and
Savings Plan together
On-Demand capacity
reservations
Savings Plan
Spot Instances
Cost-effective,
scalable compute
32. Capacity
Interruptions only
happen if OD
needs capacity
Pricing
Smooth, infrequent
changes, more predictable
Instances
Same infrastructure as
On-Demand and RIs
Usage
Choose different instance
types, sizes, and AZs in
a single fleet or EC2 Auto
Scaling group
Pricing is based on long-term supply and demand trends; no bidding!
Save up to 90% using EC2 Spot Instances
33. m4.xlarge Spot
Weight of 1
m4.2xlarge Spot
Weight of 2
m4.4xlarge On-Demand
Weight of 4
Availability
Zone 1
Availability
Zone 2
Availability
Zone 3
Different
instance types
contribute
differently to
total capacity
Now: Spot, On-Demand, and RIs in a single ASG with weights
34. Simplifying compute optimization
AWS Compute
Optimizer
Identify optimal
AWS compute resources
for your workloads
Mettle scans your AWS
infrastructure and uses
machine learning to
automatically identify
optimal AWS resources
for your workloads
Identifies workload
characteristics and
profile based on the
data gathered
Matches the resource
requirements of your
workloads to optimal
AWS resources with
recommendations
Amazon
CloudWatch
metrics
EC2 instance
EC2 Auto
Scaling groups
Helps you visualize
what-if scenarios
based on the
recommended
resources
AWS resources
metadata
35. Easy to choose with AWS Compute Optimizer
New services that recommend optimal AWS compute resources to reduce costs up to 25%
Recommends optimal EC2 instances
Optimizes performance and reduces costs by
making recommendations to help you
right-size compute to your workloads
Analyzes Amazon CloudWatch metrics and
considers Auto Scaling group configuration for
intuitive and actionable recommendations
Up to three recommendations per workload
Available at no additional charge
36. Learn compute with AWS Training and Certification
20+ free digital courses cover topics related to cloud compute,
including introduction to the following services:
Resources created by the experts at AWS to help you build cloud compute skills
Compute is also covered in the classroom offering, Architecting
on AWS, which features AWS expert instructors and hands-on
activities
• Amazon EC2
• Amazon EC2 Auto Scaling
• AWS Systems Manager
• AWS Inferentia and Amazon EC2
Inf1 instances
Visit the learning library at https://aws.training
So how are we going to do this?
Overview of what drives us to innovate at AWS
Automate cost and capacity management – Savings Plan, Compute Optimizer, EC2 Auto Scaling and Spot Instances
Workload examples – CI/CD, Containerized Web Apps, and Big Data, analytics and AI/ML.
Wrap up with next steps
We are break us the session in to 4 key categories. We’ll start be talking about EC2 resources, mainly the instances that we offers, as they are the core of EC2. We’ll then review how to take advantage of EC2 broad global footprint, how to manage your resources and finally how to optimize your spend on EC2.
We’ll use this slides as a reference for where we are in the presentation.
We’ll start with talking about EC2 Instances, will show you a quick demo on how easy it is to launch an instance and connect to it. Review the various instance type we offer and highlight the use-cases that they are designed for. This is the section where we’ll spend majority of our time.
Significant improvements optimizing underlying technology for performance and price.
Making improvements in CPU, SSD, Networking, and other components available to customer
We are providing you with new choice of processor and architecture.
What does all of this mean?
More choices enables better performance for specific workloads
Faster processors from Intel, processor choice with Graviton (ARM) and AMD, instances for accelerated computing with our partner Nvidia –
Network offerings up to 100GBps performance
Elastic Graphics or Elastic Inference and of course Elastic Block Store for greater performance and storage flexibility.
We will have nearly 300 instances by the end of the year to support virtually every workload and business need.
Our latest accelerated computing instance is our P3 instances which provides access to up to 8 NVIDIA V100 GPU in a single instances with support for NVLink for peer-to-peer GPU communications.
P3 is ideal for wide variety of use-cases including Deep Learning…HPC and batch graphics rendering
G3 is our other GPU accelerated instance featuring access to up to 4 NV M60 GPU with support for NVIDIA GRID.
Its designed for workloads for…
1/ Thanks to all of you, we continue to be the market leader in the cloud.
2/ As you know, Gartner’s Infrastructure as a Service Magic Quadrant is the longest running Magic Quadrant.
3/ And AWS is the longest running leader in the cloud with the 9th consecutive leader in the cloud.
1/EC2 offers the broadest and deepest choices for running diverse workloads ranging from HPC at extreme scale, to mission critical applications on VMware, to running machine learning training or inference for a new initiative.
Let us look at how we have tackled both categories of customer requests to make it easier to move HPC workloads to the cloud
First, technical requirements – Products that were announced in 2018 and have matured in 2019
1/ From weather modeling to genome mapping to the search for extraterrestrial intelligence, HPC has always been about solving the world’s most complex problems. The AWS HPC Solution combines the latest compute, networking, storage, security, and cloud orchestration, that you just saw to offer a highly customizable computing platform
2/By moving your HPC workloads to AWS you can get instant access to the infrastructure capacity you need to run your HPC applications.
3/The AWS HPC solution allows you to choose from a variety of compute instance types that can be configured to suit your needs, including CPU, GPU, and FPGA powered instances. EFA, a network interface for Amazon EC2, has a unique OS bypass networking mechanism that provides a low-latency, low-jitter channel for inter-instance communications.
4/ Instances such as C5n, EFA, and 100 Gbps come together to enable you to HPC in the cloud securely, with ease, performance and low-cost.
c5n as a memory bandwidth monster
100 G
other instances that are inspired by c5n (m5n, r5n, p3dn)
SRD as the secret behind the success of EFA
we’re watching HPC codes that we were told were 100% absolutely latency bound turn out to be 100% absolutely not latency bound (eg, esp weather codes) leverage NRL results, but with screenshots or argonne slides.
also radiant.
Add references as possible (logo)
Within AWS we see the stack as having three layers:
The bottom layer of the stack is for expert machine learning practitioners who work at the framework level and are comfortable building, training, tuning, and deploying machine learning models.
This is the foundation for all of the innovation we drive at every other layer of the stack.
We focus on performance, flexibility and reducing costs, so that anyone can experiment across frameworks and capabilities with the latest and greatest infrastructure.
We also focus on making it easy to connect more broadly to the AWS ecosystem, whether that’s about pulling in IoT data from Greengrass, or accessing our state-of-the art chips (P3), or leveraging elastic inference.
The vast majority of deep learning and machine learning in the cloud is being done on top of P3 instances in AWS. We recently announced P3dn instances, which are the most powerful GPU instances for machine learning that you'll find anywhere in the world. They have a hundred gigabits per second of networking, which changes how you can scale out and parallelize and lower costs on these models. They have networking throughput that’s three times as fast as anything else out there, twice as much GPU memory as anything out there, and a hundred plus gigabytes more of system memory than anything out there.
This is where you see customers starting to do machine learning at large scale. Of course, they use lots of different frameworks, and we support all the major frameworks that customers want to use. But the one with the most resonance right now in the community is TensorFlow.
If you look in the cloud, 85 percent of TensorFlow being run is run on top of AWS. You see this with lots of different types of customers, like Expedia, Siemens, Xendex, News Corp, and Snap. But for our customers who run TensorFlow, there are some challenges, particularly scaling. What they tell us is that it's really difficult to actually consume as much of the GPU with TensorFlow as they want to efficiently use the hardware and keep costs low. And that's because TensorFlow has a lot of processing overhead in distributing the weight of the neural network effectively across a large number of GPUs.
At AWS, we don't believe in one tool to rule the world. We want you to use the right tool for the right job. And it turns out if you're doing things like video analytics or natural language processing, MXNet is a great solution and scales the best. Or if you're doing computer vision, Caffe2 is great. There's all kinds of incredibly innovative research being done on top of PyTorch too.
More than half our customers who do machine learning at AWS are using more than two frameworks in their everyday machine learning work. And we will always make sure that all the frameworks you care about are supported equally well, so you have the right tool for the right job. The one constant in a very fluid world of machine learning is change. In the next couple of years, there will be other frameworks you care about, and we'll support them as well.
Additional info on infrastructure:
AWS offers a broad array of compute options for training and inference with powerful GPU-based instances, compute and memory optimized instances, and even FPGAs.
The new Amazon EC2 P3dn instance has four-times the networking bandwidth and twice the GPU memory of the largest P3 instance, P3dn is ideal for large scale distributed training. No one else has anything close.
P3dn.24xlarge instances offer 96vCPUs of Intel Skylake processors to reduce preprocessing time of data required for machine learning training.
The enhanced networking of the P3n instance allows GPUs to be used more efficiently in multi-node configurations so training jobs complete faster.
Finally, the extra GPU memory allows developers to easily handle more advanced machine learning models such as holding and processing multiple batches of 4k images for image classification and object detection systems
C5 instances offer higher memory to vCPU ratio and deliver 25% improvement in price/performance compared to C4 instances, and are ideal for demanding inference applications.
We also have Amazon EC2 F1, a compute instance with field programmable gate arrays (FPGAs) that you can program to create custom hardware accelerations for your machine learning applications. F1 instances are easy to program and come with everything you need to develop, simulate, debug, and compile your hardware acceleration code. You can reuse your designs as many times, and across as many F1 instances as you like.
Manufacturing:
Predictive maintenance or condition monitoring
Warranty reserve estimation
Propensity to buy
Demand forecasting
Process optimization
Retail
Predictive inventory planning
Upsell and cross channel marketing
Market segmentation and targeting
Customer ROI and lifetime value
Healthcare and life sciences
Alerts and diagnostics from realtime patient data
Disease identification and risk satisfaction
Patient triage optimization
Proactive health management
Healthcare provider sentiment analysis
Travel and hospitality
Aircraft scheduling
Dynamic pricing
Social media – customer feedback and interactions
Customer complaint resolution
Traffic patterns and congestion management
Financial services
Risk analytics and regulation
Customer segmentation
Cross selling and upselling
Sales and marketing campaign management
Credit worthiness evaluation
Energy
Power usage analytics
Seismic data processing
Carbon emissions and trading
Customer specific pricing
Smart grid management
Energy demand and supply optimization
Natural language processing
EC2 Windows
For Corporate or 3rd party legacy and custom applications including line-of-business applications, you can launch a database to support these apps using Amazon EC2 and Amazon EBS. Corp apps can include: MS SharePoint, Exchange, Skype for Business, or developed by an ISV that are used for collaboration and/or productivity.
AWS lets you run corporate applications more efficiently and flexibly, while maintaining the management and control of on-premises.
Most cost-effective option for hosting LoB apps on AWS
You manage software, compute, and storage resources with complete control
Relational database AMIs enable you to store database machine images for rapid provisioning
Amazon Web Services helps you build, deploy, scale, and manage Microsoft applications quickly, easily, more securely and more cost-effectively. For corporate IT applications, AWS gives you a cloud platform that helps run Microsoft applications like SharePoint, Dynamics and Exchange in a more secure, easily managed, high performance approach. For business owners, AWS gives you a fully managed database service to run Microsoft SQL Server, which helps you build web, mobile and custom business applications. For Microsoft developers, Amazon EC2 for Windows Server provides a flexible and agile development platform, deeply integrated with Visual Studio and .NET to help accelerate development cycles.
Amazon RDS
Amazon Relational Database Service (RDS) is a managed service that makes it easy to deploy a relational database to support LoB apps running on AWS
Automates database administration tasks such as provisioning, patching, backup, recovery, failure detection, and repair
Multi-AZ deployments provide automatic failover
Integrates with AWS Identity and Access Management for granular resource permission controls
1/As I mentioned before, customers have been running Microsoft workloads on AWS for over a decade. As customers migrate their on-premises Microsoft workloads to AWS, they get the flexibility to choose from a variety of available licensing options, including buying licenses from AWS with a pay-as-you-go model. But customers wanted to optimize their investment by bringing their own licenses.
2/They also want the elasticity, performance and reliability of AWS cloud as they bring their licenses onto Dedicated Hosts. But they also struggle with getting visibility into licenses across these different environments, and want a consolidated view across of their licenses on-premises and AWS cloud.
3/ In addition, they want an easy way to upgrade and manage these licenses
ReInvent 2018
.NET to Containers - ECS – Zocdoc
They broke the monolithic .NET application into containerized microservices that they migrated to the cloud.
They use the cloud, microservices and containers to increase the output and efficiency of engineers.
And with container based model they can deploy more containers as demand increase.
3x more delivery from Engineering Team.
Reduction of appointment booking time from 24 days to 24 hours
.NET to serverless For example, MindTouch is a technology company that designs SaaS computer software and online services. Mindtouch modernized their legacy C# applications to .NET Core. Before, they used VMs that needed to be patched, but now use Serverless to streamline their workloads.
They moved to Serverless in a big way and their applications now use dozens of Lambda functions to increase deployment speed.
1/ Moving on from Windows, SAP is another enterprise application where we are seeing customers accelerating their efforts to bring these applications to the cloud.
2/ SAP and AWS have been working together since 2008. This decade long partnership has been driven by working backwards to figure out what customers want and need for running SAP in the cloud.
3/ We’ve introduced many “Industry 1sts” for SAP including the first SAP certified cloud offerings with 2TB and 4TB instances.
4/ In September, we offer instances with as much as 24TB of memory for the largest SAP S/4 HANA workloads.
5/ SAP has become one of our more strategic customers providing us with great feedback as we partner together to support all the SAP offerings you see on the right side of this slide.
1/ Now you may ask what is driving this adoption.
2/ First, the breadth of SAP certified instances on AWS gives customers the best possible choice for their workloads. Starting from a few 100 GB of memory, we can scale all the way up to 48TB for S/4HANA and 100TB for HANA BW (Business Warehouse) environments.
3/ Second, the speed and ease of deployment on AWS brings agility to customer’s SAP workloads that they have not experienced elsewhere, allowing customers to experiment with new ideas. Finally, along with our innovation, we are constantly working to reduce costs and pass the savings onto customers, improving overall TCO.
4/ With SAP, we are enabling developers to innovate in ways we haven’t even yet imagined. For instance, today a SAP developer can build a full Alexa based interface to query sales orders in a few hours and have it tested and out to their customers in a matter days. It’s been fun to watch what people are doing with our combined offerings and we know we’re just getting started.
1/ Our first partner offering on Nitro was VMware Cloud on AWS, working together with VMware.
2/ Both companies are heaving invested in VMware Cloud on AWS and thus, we are looking at how we can bring these closer to together and return the tie for data processing.
3/ That innovation with AWS and VMware allows VMware customers to take advantage of a rich set of benefits with rapid time to value, including: Rich VMware SDDC delivered on AWS infrastructure, Consistency and familiarity of VMware technologies, Easy workload portability, Seamless access to native AWS services and Container and VM support.
4/ VMC is something you can get up and running today to deliver on the hybrid experiences customers want.
By focusing on customers we have evolved over time.
How we evolve our product strategy to enable you to innovate faster
Pricing and capacity optimizations, guidance (three pillars)
Four different ways to purchase compute
On-Demand: Pay-as-you-go, no commitments, best for fluctuating workloads
Reserved Instance: Long term commitments that offer big savings over On-Demand prices. Best for always on workloads
Introducing Savings Plan: Just like Reserved Instances, but monetary commitment based and compute can be used across Fargate and EC2
Spot Instances: Same as pay-as-you-go pricing as On-Demand, but at up to 90% off. EC2 can reclaim with a 2 minute warning. Best for stateless or fault tolerant workloads
All four purchasing options use the same underlying EC2 instances and AWS infrastructure across 22 Regions
[Poll] How many of you use Spot Instances?
Excited to announce
New Spot integrations
Updates to EC2 Auto Scaling that make it easier than ever to incorporate Spot
Customer initiated Start/Stop for EC2 Spot
So, when should you use Spot, On-Demand or RIs?
Picking just one option is the wrong solution.
Use all three to optimize cost and capacity
AWS offers two types of Savings Plans - EC2 Instance Savings Plans and Compute Savings Plans
Compute Savings Plans provide the most flexibility and help reduce usage costs by up to 66%, just like Convertible RIs. These plans automatically apply to EC2 instance usage regardless of instance family, size, AZ, region, OS or tenancy, as well as Fargate usage. For example, with Compute Savings Plans, you can switch from C4 to M5 instances, shift a workload from EU (Ireland) to EU (London), or move a workload from EC2 to Fargate at any time and automatically continue to receive discounts.
EC2 Instance Savings Plans provide the lowest prices, in exchange for a commitment to usage of individual instance families in a region (e.g. commit to a consistent level of M5 usage in N. Virginia). This automatically provides you with savings of up to 72% off the On-Demand price of the selected instance family in that region regardless of AZ, size, OS or tenancy. EC2 Instance Savings Plans allows you to change your usage between instances within a family in that region. For example, you can move from c5.xlarge running Windows to c5.2xlarge running Linux, and automatically benefit from the Savings Plans prices.
Combine savings plan and on-demand capacity reservations for steady state workloads and add Spot Instances to maximize savings and scalability.
Leverage the scale of AWS at a fraction of the cost
Simplified pricing model, no more bidding.
Spot is only interrupted when the EC2 needs to reclaim Spot for On-Demand capacity. No need to worry about your bidding strategy. Spot prices gradually adjust based on long-term supply and demand trends.
Spot is a reward for good architecture
Introducing instance type weights
Configure weight to scale in and out based on previous gen instances or vCPUs across multiple AZs
Distribute Capacity evenly between availability zones for On-Demand and Spot separately
1/ Mettle uses machine learning models trained on millions of workloads to help customers optimize their compute resources for cost and performance across all of workloads they run. You can take advantage of the recommendations in Mettle to reduce costs by up to 25%.
2/ Mettle delivers instance type and auto scaling groups recommendations, making it even easier for customers to choose the right compute resources for specific workloads.
3/ Mettle analyzes the configuration, resource utilization, and performance data of a workload to identify dozens of defining characteristics, such as whether the workload is CPU-intensive and whether it exhibits a daily pattern. Mettle then uses machine learning to process these characteristics to predict how the workload would perform on various hardware platforms, delivering resource recommendations.
4/ Mettle delivers up to 3 recommended options for each AWS resource analyzed to right size and improve workload performance. Mettle predicts the expected CPU and memory utilization of your workload on various EC2 instance types. This helps you understand how your workload would perform on the recommended options before implementing the recommendations.
How does this work? Predictive Scaling’s machine learning algorithms leverage data from billions of traffic patterns in1/ Mettle uses machine learning models trained on millions of workloads to help customers optimize their compute resources for cost and performance across all of workloads they run. You can take advantage of the recommendations in Mettle to reduce costs by up to 25%.
2/ Mettle delivers instance type and auto scaling groups recommendations, making it even easier for customers to choose the right compute resources for specific workloads.
3/ Mettle analyzes the configuration, resource utilization, and performance data of a workload to identify dozens of defining characteristics, such as whether the workload is CPU-intensive and whether it exhibits a daily pattern. Mettle then uses machine learning to process these characteristics to predict how the workload would perform on various hardware platforms, delivering resource recommendations.
4/ Mettle delivers up to 3 recommended options for each AWS resource analyzed to right size and improve workload performance. Mettle predicts the expected CPU and memory utilization of your workload on various EC2 instance types. This helps you understand how your workload would perform on the recommended options before implementing the recommendations Amazon.com to predict future changes.
The pre-trained model then processes last 2 weeks of load metrics to forecasts the load metric for the next two days
The model also performs regression analysis between load metric and scaling metric, schedules scaling actions for the next two days, hourly, and then repeats this process every day
If you’re ready to continue learning, check out our library of free digital courses, including introductory primers on a range of services
You can also take classroom training to get hands on practice and learn directly from an instructor.
Visit the learning library for the full list of courses