This is part two of a two-part series about Amazon Web Services (AWS) re:Invent 2014 and other recent cloud updates, read part one here.
Announcements and enhancements made by AWS during re:Invent include:
In addition to announcing new higher performance Elastic Cloud Compute (EC2) compute instances along with container service, another new service is AWS Lambda. Lambda is a service that automatically and quickly runs your applications code in response to events, activities, or other triggers. In addition to running your code, Lambda service is billed in 100 millisecond increments along with corresponding memory use vs. standard EC2 per hour billing. What this means is that instead of paying for an hour of time for your code to run, you can choose to use the Lambda service with more fine-grained consumption billing.
Lambda service can be used to have your code functions staged ready to execute. AWS Lambda can run your code in response to S3 bucket content (e.g. objects) changes, messages arriving via Kinesis streams or table updates in databases. Some examples include responding to event such as a web-site click, response to data upload (photo, image, audio, file or other object), index, stream or analyze data, receive output from a connected device (think Internet of Things IoT or Internet of Device IoD), trigger from an in-app event among others. The basic idea with Lambda is to be able to pay for only the amount of time needed to do a particular function without having to have an AWS EC2 instance dedicated to your application. Initially Lambda supports Node.js (JavaScript) based code that runs in its own isolated environment.
Various application code deployment models
Lambda service is a pay for what you consume, charges are based on the number of requests for your code function (e.g. application), amount of memory and execution time. There is a free tier for Lambda that includes 1 million requests and 400,000 GByte seconds of time per month. A GByte second is the amount of memory (e.g. DRAM vs. storage) consumed during a second. An example is your application is run 100,000 times and runs for 1 second consuming 128MB of memory = 128,000,000MB = 128,000GB seconds. View various pricing models here on the AWS Lambda site that show examples for different memory sizes, times a function runs and run time.
How much memory you select for your application code determines how it can run in the AWS free tier, which is available to both existing and new customers. Lambda fees are based on the total across all of your functions starting with the code when it runs. Note that you could have from one to thousands or more different functions running in Lambda service. As of this time, AWS is showing Lambda pricing as free for the first 1 million requests, and beyond that, $0.20 per 1 million request ($0.0000002 per request) per duration. Duration is from when you code runs until it ends or otherwise terminates rounded up to the nearest 100ms. The Lambda price also depends on the amount of memory you allocated for your code. Once past the 400,000 GByte second per month free tier the fee is $0.00001667 for every GB second used.
Why would you use AWS Lambda vs. provisioning an Container, EC2 instance or running your application code function on a traditional or virtual machine?
If you need control and can leverage an entire physical server with its operating system (O.S.), application and support tools for your piece of code (e.g. JavaScript), that could be an option. If you simply need to have an isolated image instance (O.S., applications and tools) for your code on a shared virtual on-premises environment then that can be an option. Likewise if you have the need to move your application to an isolated cloud machine (CM) that hosts an O.S. along with your application paying for those resources such as on an hourly basis, that could be your option. Simply need a lighter-weight container to drop your application into that’s where Docker and containers comes into play to off-load some of the traditional application dependencies overhead.
However, if all you want to do is to add some code logic to support processing activity for example when an object, file or image is uploaded to AWS S3 without having to standup an EC2 instance along with associated server, O.S. and complete application activity, that’s where AWS Lambda comes into play. Simply create your code (initially JavaScript) and specify how much memory it needs, define what events or activities will trigger or invoke the event, and you have a solution.
View AWS Lambda pricing along with free tier information here.
AWS is increasing the performance and size of General Purpose SSD and Provisioned IOP’s SSD volumes. This means that you can create volumes up to 16TB and 10,000 IOP’s for AWS EBS general-purpose SSD volumes. For EBS Provisioned IOP’s SSD volumes you can create up to 16TB for 20,000 IOP’s. General-purpose SSD volumes deliver a maximum throughput (bandwidth) of 160 MBps and Provisioned IOP SSD volumes have been specified by AWS at 320MBps when attached to EBS optimized instances. Learn more about EBS capabilities here. Verify your IO size and verify AWS sizing information to avoid surprises as all IO sizes are not considered to be the same. Learn more about Provisioned IOP’s, optimized instances, EBS and EC2 fundamentals in this StorageIO AWS primer here.
In addition to compute and storage resource enhancements, AWS has also announced several tools to support application development, configuration along with deployment (life-cycle management). These include tools that AWS uses themselves as part of building and maintaining the AWS platform services.
Management, reporting and monitoring capabilities including Data center infrastructure management (DCIM) for monitoring your AWS resources, configuration (including history), governance, change management and notifications. AWS Config enables similar capabilities to support DCIM, Change Management Database (CMDB), trouble shooting and diagnostics, auditing, resource and configuration analysis among other activities. Learn more about AWS Config here.
AWS announced a new service catalog that will be available in early 2015. This new service capability will enable administrators to create and manage catalogs of approved resources for users to use via their personalized portal. Learn more about AWS service catalog here.
To support code rapid deployment automation for EC2 instances, AWS has released CodeDeploy. CodeDeploy masks complexity associated with deployment when adding new features to your applications while reducing human error-prone operations. As part of the announcement, AWS mentioned that they are using CodeDeploy as part of their own applications development, maintenance, and change-management and deployment operations. While suited for at scale deployments across many instances, CodeDeploy works with as small as a single EC2 instance. Learn more about AWS CodeDeploy here.
For application code management, AWS will be making available in early 2015 a new service called CodeCommit. CodeCommit is a highly scalable secure source control service that host private Git repositories. Supporting standard functionalities of Git, including collaboration, you can store things from source code to binaries while working with your existing tools. Learn more about AWS CodeCommit here.
To support application delivery and release automation along with associated management tools, AWS is making available CodePipeline. CodePipeline is a tool (service) that supports build, checking workflow’s, code staging, testing and release to production including support for 3rd party tool integration. CodePipeline will be available in early 2015, learn more here.
Learn more about the above and other AWS services by actually truing hands on using their free tier (AWS Free Tier). View AWS re:Invent produced breakout session videos here, audio podcasts here, and session slides here (all sessions may not yet be uploaded by AWS re:Invent)
AWS continues to invest as well as re-invest into its environment both adding new feature functionality, as well as expanding the extensibility of those features. This means that AWS like other vendors or service providers adds new check-box features, however they also like some increase the depth extensibility of those capabilities. Besides adding new features and increasing the extensibility of existing capabilities, AWS is addressing both the data and information infrastructure including compute (server), storage and database, networking along with associated management tools while also adding extra developer tools. Developer tools include life-cycle management supporting code creation, testing, tracking, testing, change management among other management activities.
Another observation is that while AWS continues to promote the public cloud such as those services they offer as the present and future, they are also talking hybrid cloud. Granted you have to listen carefully as you may not simply hear hybrid cloud used like some toss it around, however listen for and look into AWS Virtual Private Cloud (VPC), along with what you can do using various technologies via the AWS marketplace. AWS is also speaking the language of enterprise and traditional IT from an applications and development to data and information infrastructure perspective while also walking the cloud talk. What this means is that AWS realizes that they need to help existing environments evolve and make the transition to the cloud which means speaking their language vs. converting them to cloud conversations to then be able to migrate them to the cloud. These steps should make AWS practical for many enterprise environments looking to make the transition to public and hybrid cloud at their pace, some faster than others. More on these and some related themes in future posts.
The AWS re:Invent event continues to grow year over year, I heard a figure of over 12,000 people however it was not clear if that included exhibiting vendors, AWS people, attendees, analyst, bloggers and media among others. However a simple validation is that the keynotes were in the larger rooms used by events such as EMCworld and VMworld when they hosted in Las Vegas as was the expo space vs. what I saw last year while at re:Invent. Unlike some large events such as VMworld where at best there is a waiting queue or line to get into sessions or hands on lab (HOL), while becoming more crowded, AWS re:Invent is still easy to get in and spend some time using the HOL which is of course powered by AWS meaning you can resume what you started while at re:Invent later. Overall a good event and nice series of enhancements by AWS, looking forward to next years AWS re:Invent.
Ok, nuff said (for now)
Cheers gs
Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio
All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved
RTO Context Matters With RTO context matters similar to many things in and around Information…
What is Azure Elastic SAN Azure Elastic SAN (AES) is a new (now GA) Azure…
Yes, you read that correctly, Microsoft Hyper-V is alive and enhanced with Windows Server 2025,…
A theme I mention in the above two articles as well as elsewhere about server,…
March 31st is world backup day; when is world recovery day If March 31st is…
ToE NVMeoF TCP Performance Line Boost Performance Reduce Costs. Yes, you read that correct; leverage…