Smart Build Targets Batching Service at Google

TL;DR

This paper presents a technique at Google that predicts resource usage for build targets and batches them to prevent memory and deadline issues, enhancing developer productivity.

Contribution

It introduces a novel prediction-based batching method for build targets to optimize resource usage and prevent build failures due to memory or time constraints.

Findings

Reduces build failures caused by memory overflows.

Improves build success rate and developer productivity.

Significantly decreases build timeouts and resource wastage.

Abstract

Google has a monolithic codebase with tens of millions build targets. Each build target specifies the information that is needed to build a software artifact or run tests. It is common to execute a subset of build targets at each revision and make sure that the change does not break the codebase. Google's build service system uses Bazel to build targets. Bazel takes as input a build that specifies the execution context, flags and build targets to run. The outputs are the build libraries, binaries or test results. To be able to support developer's daily activities, the build service system runs millions of builds per day. It is a known issue that a build with many targets could run out of the allocated memory or exceed its execution deadline. This is problematic because it reduces the developer's productivity, e.g. code submissions or binary releases. In this paper, we propose a technique that predicts the memory usage and executor occupancy of a build. The technique batches a set of targets such that the build created with those targets does not run out of memory or exceed its deadline. This approach significantly reduces the number of builds that run out of memory or exceed the deadlines, hence improving developer's productivity.