At Opsani, we run into lots of people who think they are optimizing their apps to the max. But in fact, they are barely scratching the surface. The majority of cloud optimization tools focus on code and the app layer: UI, database schema, and so on. Application Performance Monitoring (APM) systems monitor basic app transactions, and track top-layer usage statistics. Typically, none of these approaches properly optimize Linux kernel parameters like page sizes or jumbo packet sizes.

The thousands of Linux kernel parameters, the multiple pieces of middleware, the cloud and container layers – most people don’t go near these. Even experienced application architecture people are frequently unable to identify more than a third of the application parameters available to them. They leave the settings at default, and over-spend and over-provision to ensure peace of mind. Some companies just buy all the resources they can afford. Which is great for Amazon, Microsoft, and Google. But what does it mean for the company? Millions of dollars spent needlessly, and performance potential left untapped due to unoptimized parameters. 

To properly optimize their infrastructure, users should be: 

  • Tweaking Linux kernel parameters like page sizes and jumbo packet sizes
  • Testing their latest instance types
  • Testing their high IOPs volumes
  • Checking whether the application is sensitive to stolen CPU
  • Testing different garbage collection settings when using a JVM 
  • Pinpointing the ideal setting thread count
  • Experimenting with disabling Linux’s noatime
  • Experimenting with different values for min_spare_servers and start_servers when using PHP
  • Employing an on-demand rather than a dynamic process manager when using PHP
  • Tweaking application parameters like thread pools, cache timeouts and write delays
  • Testing buffer sizes, API traffic limiters, file descriptor limits, and cache size

But most people are not optimizing these hundreds of important application parameters. Why?

Short answer: because it is too complicated. In the DevOps era, even a simple application with a handful of containers can have quite literally trillions of resource and basic parameter permutations. Not only are these permutations numerous; they are interdependent, and perpetually shifting. To effectively engage with them, you would need a flawless knowledge of the entire application infrastructure, and the workload itself. 

This is why so many users don’t optimize their apps properly. It’s incredibly, dauntingly complex. Tweaking blindly and fiddling with instance types, Linux kernel parameters, or garbage collection settings can be very risky. So the safe option is to not touch anything, and hope and pray that these application parameters and settings don’t end up contributing to your system running hot. 

Opsani’s Cloud Optimization

This is why we built Opsani. Opsani performs Cloud Optimization of apps at the deployment level. It slots into the CI/CD chain, and leverages deep reinforcement learning to continuously examine millions of configurations, and identify the optimal combination of resources and settings, including settings around Linux kernel parameters. Opsani reacts constantly to new traffic patterns, new code, new instance types, and all other relevant factors. It learns as it goes, so the improvements compound. This ensures that your system will achieve, and continuously achieve, optimal performance at the lowest cost.

To learn more about Cloud Optimization, read our “What Is Cloud Optimization?” page here. Or check out our whitepaper:

Read our Cloud Optimization Whitepaper

Opsani dives right into all those instance types, Linux kernel parameters, buffer sizes, and other application parameters that are routinely ignored, left to run at too high a cost and too low an impact. The end result is that infrastructure is tuned precisely to the workload and goals of the application – whether those goals relate to cost, performance, or some balance of the two. 

On average, when they implement Cloud Optimization, Opsani customers experience a 2x increase in performance or a 40-70% decrease in cost. Overnight.

Contact us today for a free demo.