Matthias Loibl, Polar Signals
For years Google has consistently been able to cut down multiple percentage points in their fleet-wide resource usage every quarter, using techniques described in their “Google-Wide Profiling” paper. Ad-hoc profiling has long been part of the developer’s toolbox to analyze CPU and memory usage of a running process, however, through continuous profiling, the systematic collection of profiles, and entirely new workflows suddenly become possible.
The speaker will start this talk with an introduction to profiling with Go and demonstrate via Parca - an open-source continuous profiling project - how continuous profiling allows for an unprecedented fleet-wide understanding of code at production runtime.
Attendees will learn how to continuously profile code to help guide building robust, reliable, and performant software and reduce cloud spend systematically in various languages.
Matthias Loibl, Polar Signals
Matthias Loibl is a Senior Software Engineer who works on cloud-native observability at Polar Signals, previously at Red Hat and Kubermatic, and is a maintainer of many projects like Prometheus, Thanos, Prometheus Operator and Parca. He enjoys working on Distributed Systems with Go and gRPC.
author = {Matthias Loibl},
title = {Continuous Profiling in the {Cloud-Native} era},
year = {2023},
address = {Dublin},
publisher = {USENIX Association},
month = oct
}
