Serverless for High Performance Computing

Serverless is great for web applications and APIs, but this does not mean it cannot be used successfully for other use cases. In this talk, we will discuss a successful application of serverless in the field of High Performance Computing. Specifically we will discuss how Lambda, Fargate, Kinesis and other serverless technologies are being used to run sophisticated financial models at one of the major reinsurance companies in the World. We we learn about the architecture, the tradeoffs, some challenges and some unresolved pain points. Most importantly, we'll find out if serverless can be a great fit for HPC and if we can finally stop managing those boring EC2 instances!

Transcript

1. Serverless for HPC Luciano Mammino fourTheorem @loige
2. Diamond Sponsor Partner Platinum Sponsor Gold Sponsor
3. 👋 Hello, I am Luciano Senior architect nodejsdesignpatterns.com Let’s connect: 🌎 loige.co 🐦 @loige 🎥 loige 🧳 lucianomammino
4. Middy Framework SLIC Starter - Serverless Accelerator SLIC Watch - Observability Plugin Business focused technologists. Accelerated Serverless | AI as a Service | Platform Modernisation
5. We host a podcast about AWS and Cloud computing 🔗 awsbites.com 🎬 YouTube Channel 🎙 Podcast 📅 Episodes every week @loige #CLOUDDAY2022
6. Get the slides: fth.link/cd22 @loige #CLOUDDAY2022
7. Agenda • The 6 Rs of Cloud Migration • A serverless case study ◦ The problem space and types of workflows ◦ Original on premise implementation ◦ The PoC ◦ The final production version ◦ The components of a serverless job scheduler ◦ Challenges & Limits fth.link/cd22 @loige #CLOUDDAY2022
8. The 6 Rs of Cloud Migrations 🗑 🕸 🚚 Retire Retain Rehost 🏗 📐 💰 Replatform Refactor Repurchase @loige #CLOUDDAY2022 fth.link/cd22
9. A case study Case study on AWS blog: fth.link/awshpc @loige #CLOUDDAY2022
10. The workloads - Risk Rollup 🏦 Financial modeling to understand the portfolio of risk 🧠 Internal, custom-built risk model on all reinsurance deals ⚙ HPC (High-Performance Computing) workload 🗄 ~45TB data processed ⏱ 2/3 rollups per day (6-8 hours each!) @loige #CLOUDDAY2022
11. The workloads - Deal Analytics ⚡ Near real-time deal pricing using the same risk model 🗃 Lower data volumes 🔁 High frequency of execution – up to 1.000 per day @loige #CLOUDDAY2022
12. Original on-prem implementation @loige #CLOUDDAY2022
13. Challenges 🐢 Long execution times, constraining business agility 🥊 Competing workloads 📈 Limits our ability to support portfolio growth 😩 Can’t deliver new features 🧾 Very high total cost of ownership @loige #CLOUDDAY2022
14. Thinking Big 💭 Imagine a solution that would … 1. Offer a dramatic increase in performance 2. Provide consistent run times 3. Support more executions, more often 4. Support future portfolio growth and new capabilities – 15x data volumes @loige #CLOUDDAY2022
15. The Goal ⚽ Run a Risk Rollup in 1 hour! @loige #CLOUDDAY2022
16. Architecture Options for Compute/Orchestration AWS Lambda Amazon SQS AWS Step Functions AWS Fargate Com t om : Red he b to si l , s a l , ev -d i n co n s @loige #CLOUDDAY2022
17. POC Architecture AWS Batch S3 Step Functions Lambda SQS @loige #CLOUDDAY2022
18. Measure Everything! 📏 ⏱ Built metrics in from the start 󰤈 AWS metrics we wish existed out of the box: - Number of running containers - Success/failure counts 🎨 Custom metrics: - Scheduler overhead - Detailed timings (job duration, I/O time, algorithm steps) 🛠 Using CloudWatch, EMF @loige #CLOUDDAY2022
19. Measure Everything! 📏 👍 Rollup in 1 hour ☁ Running on AWS Batch 👎 Cluster utilisation was <50% ✅ Goal success 🤔 Understanding of what needs to be addressed next! @loige #CLOUDDAY2022
20. Beyond the PoC Production: optimise for unique workload characteristics @loige #CLOUDDAY2022
21. Job Plan @loige #CLOUDDAY2022
22. In reality, not all jobs are alike! @loige #CLOUDDAY2022
23. Horizontal scaling 🚀 1000’s of jobs Duration: 1 second – 45 minutes Scaling horizontally = splitting jobs Jobs split according to their complexity/duration Resulting in >1 million jobs @loige #CLOUDDAY2022
24. Moving to production 🚢 @loige #CLOUDDAY2022
25. Scope @loige #CLOUDDAY2022
26. Actual End to End overview @loige #CLOUDDAY2022
27. Modelling Worker @loige #CLOUDDAY2022
28. Compute Services Scales to 1000’s of tasks (containers) Little management overhead Up to 4 vCPUs and 30GB Memory Up to 200GB ephemeral storage Scales to 1000’s of function containers (in seconds!) Very little management overhead Up to 6 vCPUs and 10GB Memory Up to 10GB ephemeral storage It wasn’t always this way! @loige #CLOUDDAY2022
29. Store all the things in S3! The source of truth for: • Input Data (JSON, Parquet) • Intermediate Data (Parquet) • Results (Parquet) • Aggregates (Parquet) Input data: 20GB Output data: ~1 TB Reads and writes: 10,000s of objects per second. @loige #CLOUDDAY2022
30. Scheduling and Orchestration ✅ We have our cluster (Fargate or Lambda) ✅ We have a plan! (list of jobs, parameters and dependencies) 🤔 How do we feed this plan to the cluster?! 🤨 Existing schedulers use traditional clusters – there is no serverless job scheduler for workloads like this! @loige #CLOUDDAY2022
31. Lifecycle of a Job A new job get queued here 👇 A worker picks up the job and executes it The worker emits the job state (success or failure) @loige #CLOUDDAY2022
32. Event-Driven Scheduler Job states are pulled from a Kinesis Data Stream Redis stores: - Job states - Dependencies This scheduler checks new job states against the state in Redis and figures out if there are new jobs that can be scheduled next @loige #CLOUDDAY2022
33. Dynamic Runtime Handling We also need to handle system failures! @loige #CLOUDDAY2022
34. Outcomes 🙌 Business • Rollup in 1 hour • Removed limits on number of runs • Faster, more consistent deal analytics • Business spending more time on revenue-generating activities • Support portfolio growth and deliver new capabilities Technology • Brought serverless to HPC financial modeling • Reduced codebase by ~70% • Lowered total cost of ownership • Increased dev team agility • Reduced carbon footprint @loige #CLOUDDAY2022
35. Hitting the limits 😰 @loige #CLOUDDAY2022
36. S3 Throughput @loige #CLOUDDAY2022
37. S3 Partitioning S3 cleverly detects high-throughput prefixes and creates partitions ….normally If this does not happen… 🚨Please reduce your request rate; Status Code: 503; Error Code: SlowDown @loige #CLOUDDAY2022
38. The Solution Explicit Partitioning: ◦Figure out how many partitions you need ◦Update code to create keys uniformly distributed over all partitions /part/0… /part/1… /part/2… /part/3… … /part/f… 1. Talk (a lot) to AWS SAs, Support, Account Manager for special requirements like this! 2. Think ahead if you have multiple accounts for different environments! @loige #CLOUDDAY2022
39. Fargate Scaling •We want to run 3000 containers ASAP •This took > 1 hour! •We built a custom Fargate scaler ◦Using the RunTask API (no ECS Service) ◦Hidden quota increases ◦Step Function + Lambda •3000 containers in ~20 minutes The AWS ECS team since made lots of improvements, making it possible to scale to 3,000 containers in under 5 minutes @loige #CLOUDDAY2022
40. How high can we go today? 🚀 10,000 concurrent Lambda functions in seconds 🎢 10,000 Fargate containers in 10 minutes 💸 No additional cost vladionescu.me/posts/scaling-containers-on-aws-in-2022 @loige #CLOUDDAY2022
41. Wrapping up 🎁 • "Serverless supercomputer" lets you do HPC with commodity AWS compute • Plenty of challenges, but it's doable! • Agility and innovation benefits are massive • Customer is now serverless-first and expert in AWS Other interesting case studies: ☁ AWS HTC Grid - 🧬 COVID genome research @loige #CLOUDDAY2022
42. Special thanks to @eoins and @cmthorne10 fth.link/cd22 @loige #CLOUDDAY2022