All Things Performance

P99 CONF is for developers who care about P99 percentiles and high-performance, low-latency applications.

P99 CONF 2023 Call for Speakers is Now Open

Filter Videos

Browse our library of talks on low-latency engineering strategies.

Misery Metrics & Consequences

Gil Tene

CTO and Co-Founder of Azul Systems
Join Azul System’s Gil Tene as he defines “misery metrics,” which describe what happens when our production systems are operating…

Sharpening the Axe: The Primacy of Toolmaking

Bryan Cantrill

CTO of Oxide Computer Company
Oxide’s Bryan Cantrill weighs in on allowing engineers to make their own tools, resulting in better systems delivered faster and…

P99 Pursuit: 8 Years of Battling P99 Latency

Dor Laor

CEO of ScyllaDB
ScyllaDB CEO Dor Laor covers principles for successful OSS projects like ScyllaDB, KVM, the Linux kernel and why they spurred…

From SLO to GOTY

Charity Majors

CTO of Honeycomb
Charity Majors shares the performance lessons we can all learn from game developers, who were among the first to run…

Linux Kernel vs DPDK: HTTP Performance Showdown

Marc Richards

Performance Engineer at Amazon Web Services
AWS’ Marc Richards uses an HTTP benchmark to compare performance of the Linux kernel networking stack with userspace networking doing…

Overcoming Variable Payloads to Optimize for Performance

Armin Ronacher

Creator of Flask and Principal Architect at Sentry
Hear from Sentry’s Armin Ronacher, creator of the Flask framework for Python, on how to optimize for performance when you…

Using eBPF for High-Performance Networking in Cilium

Liz Rice

Chief Open Source Officer at Isovalent
Isovalent’s Liz Rice shows how and why Cilium bypasses the kernel using eBPF for Kubernetes and container orchestration networking, observability…

High-speed Database Throughput Using Apache Arrow Flight SQL

Kyle Porter

Architect at Dremio

James Duong

Architect at Dremio
Kyle Porter and James Duong of Bit Quill Technologies share how Flight SQL can push SQL query throughput beyond existing…

Square Engineering’s “Fail Fast, Retry Soon” Performance Optimization Technique

Omar Elgabry

Software Engineer at Square
Learn how to build resilient systems, reduce failure rates, and improve application latency by employing one of the techniques in…

Clouds are Not Free: Guide to Observability-Driven Efficiency Optimizations

Bartłomiej Płotka

Principal Software Engineer at Red Hat
Red Hat’s Bartłomiej Płotka explains how to find and uncover efficiency problems effectively using the power of modern cloud-native observability…

How a Database Looks from a Disk’s Perspective

Avi Kivity

CTO and Co-Founder at ScyllaDB
ScyllaDB’s CTO Avi Kivity dives into how high performance distributed systems such as modern databases can make best, most efficient…

Measuring the CPU Performance of Android Apps at Lyft

Pavlo Stavytskyi

Senior Software Engineer at Lyft
Hear from Pavlo Stavytskyi on how Lyft measures CPU load to improve app performance. What metrics they collect, plus how…

Speedup Your Code Through Asynchronous Programing

Sabina Smajlaj

Operations Developer at Hudson River Trading
Hudson River Trading’s Sabina Smajlaj demonstrates how to take advantage of programming languages’ asynchronous libraries with a few minor tweaks…

Analyze Virtual Machine Overhead Compared to Bare Metal with Tracing

Steven Rostedt

Software Engineer at Google
Google’s Steve Rostedt discusses using tracing to analyze when the overhead from a Linux host running KVM is higher than…

A New IO Scheduler Algorithm for Mixed Workloads

Pavel Emelyanov

Principal Software Engineer, ScyllaDB
Discover how ScyllaDB, built on the highly asynchronous Seastar library, implemented an IO scheduler optimized for peak performance on modern…

Large-Scale, Semi-Automated Go Garbage Collection Tuning at Uber

Cristian Velazquez

Staff Site Reliability Engineer at Uber
Uber’s Cristian Velazquez talks about tuning garbage collection for Go to scale applications across 70,00 cores to maintain 30 mission-critical…

Why User-Mode Threads Are Good for Performance

Ron Pressler

Project Loom Technical Lead, Java Platform Group at Oracle
Hear from Oracle’s Ron Pressler how Java added virtual threads, an implementation of user-mode threads, to help write high-throughput servers.

Hardware Assisted Latency Investigations

Kshitij Doshi

Senior Principal Engineer, Intel Corportation

Harshad S Sane

Principal Engineer, Intel Corporation
Intel’s Harshad S Sane & Kshitij Doshi share new ways to use eBPF to better examine latency excursions.

Continuous Performance from Load Testing to SRE and Beyond

Leandro Melendez

DevRel at Grafana k6, Presenter, and Podcaster
Grafana k6’s Leandro Melendez explores how to use continuous methodologies, service structures, microservice tiers, cloud, and elasticity.

The Observant Developer — Continuous Feedback with OpenTelemetry

Roni Dover

CTO of Digma
Roni Dover shares practical ways that OpenTelemetry combined with open-source tools can be integrated into the modern development stack.

End-To-End Performance Testing, Profiling, and Analysis at Redis

Filipe Oliveira

Senior Performance Engineer at Redis
Learn how Redis developed an automated framework for performance regression testing, telemetry gathering, profiling, and data visualization upon code commit.

Keeping Latency Low for User-Defined Functions with WebAssembly

Piotr Sarna

Principal Software Engineer at ScyllaDB
Piotr Sarna describes how to integrate WebAssembly and Wasmtime into a C++ project in a latency-friendly manner by implementing UDFs…

Evaluating Performance In Go

William Kennedy

Managing Partner at Ardan Labs
William Kennedy provides a deep dive training on how to optimize Go’s concurrency and garbage collection.

How We Reduced Performance Tuning Time by Orders of Magnitude with Database Observability

Yuying Song

Database Performance Engineer at PingCAP
PingCap’s Database Performance Engineer Yuying will share how to measure latency in a distributed system using a top-down (holistic) approach,…

Implementing Highly Performant Distributed Aggregates

Michal Jadwiszczak

Software Engineer at ScyllaDB
ScyllaDB’s Michał Jadwiszczak explains how can you implement aggregate functions without hammering real-time availability and performance for other read/write operations.

Ultra-Low-Latency Web Rendering on the Edge

Malte Ubl

Chief Architect at Vercel
Vercel’s Malte Ubl will discuss the trade-offs of the new paradigm of rendering web pages in the edge, and look…

A Deep Dive into Query Performance

Peter Zaitsev

CEO and Co-Founder of Percona
Percona’s Peter Zaitsev explores overlooked and underappreciated ways to successfully establish a connection and get results to the queries promptly…

How Dashtable Helps Dragonfly Maintain Low Latency

Roman Gershman

Co-Founder of DragonflyDB
Roman Gershman explains how Dragonfly’s hastable implementation helps to keep its tail latency in check — including a look at…

Fast and Fault Tolerant

Michael Barker

Independent Consultant at Ephemeris Consulting
Michael Barker draws on knowledge from working on financial exchanges, messaging and clustering systems to describe a model that can…

Taming Go’s Memory Usage — and Avoiding a Rust Rewrite

Mark Gritter

Founding Engineer at Akita Software
Akita’s Mark Gritter goes against the current trends and describes why he and his team stuck with Golang and chose…

Tracking Syscall and Function Latency in Your k8s Cluster with eBPF

Matthew Lenhard

CTO of ContainIQ
ContainIQ’s Matthew Lenhard walks the audience through a real life performance tuning exercise, where we hunt down slow system calls…

Outrageous Performance: RageDB’s Experience with the Seastar Framework

Max De Marzi Jr.

Developer at RageDB
Learn how RageDB leveraged the Seastar framework to build an outrageously fast graph database in this talk by Max De…

Pitfalls in Writing High-Performance Systems in Rust

Marek Galovic

Staff Software Engineer at Pinecone
Pinecone’s Marek Galovic looks at common and maybe not so common pitfalls in writing high-performance distributed systems in Rust.

Why Kubernetes Freedom Requires Chaos Engineering to Shine in Production

Henrik Rexed

Cloud Native Advocate at Dynatrace
Dynatrace’s Henrik Rexed uses production methods and Kubernetes settings useful to avoid outages, from chaos engineering, to observability and load…

Testing Persistent Storage Performance in Kubernetes with Sherlock

Sagy Volkov

Distinguished Performance Architect at Lightbits Labs
Lightbits Labs’ Sagy Volkov demonstrates how to use Sherlock, an open source platform written to test persistent NVMe/TCP storage in…

Aggregator Leaf Tailer: Bringing Data to Your Users with Ultra Low Latency

Jeffery Utter

Staff Software Developer at theScore
Discover how and why theScore built Datadex, an aggregator leaf tailer system built for geographically distributed, low-latency queries and real-time…

Properly Understanding Latency is Hard — What We Learned When We Did it Correctly

Brian Taylor

Principle Software Engineer at Optimizely
Optimizely’s Brian Taylor applies lessons of Gil Tene’s coordinated omission talk to understand the surprising sources of latency found in…

Measuring P99 Latency in Event-Driven Architectures with OpenTelemetry

Antón Rodríguez

Principal Software Engineer at New Relic
New Relic’s Antón Rodríguez shows how Event-Driven Architectures can instrument apps using vendor-neutral APIs, libraries, and tools via OpenTelemetry.

C# as a System Language

Oren Eini

Founder & CEO of RavenDB
RavenDB’s Oren Eini discusses the features that make C# a viable system language for building high-end systems.

Retaining Goodput with Query Rate Limiting

Piotr Dulikowski

Senior Software Engineer, ScyllaDB
ScyllaDB’s Piotr Dulikowski walks through how they tackled a “hot partition” problem: a single partition accessed with disproportionate frequency that…

Improving Performance of Micro-Frontend Applications through Error Monitoring

Garrett Hamelin

Developer Advocate at Airbrake, a LogicMonitor Company
Airbrake’s Garret Hamelin walks you through some of the dos and don’ts for trying to reduce errors and improve performance…

It’s Time to Debloat the Cloud with Unikraft

Felipe Huici

CEO and Co-Founder of Unikraft UG
Felipe Huici introduces Unikraft, a cloud operating system that allows for easily building fully-tailored cloud-ready images that boot in a…

Building Efficient Multi-Threaded Filters for Faster SQL Queries

Vlad Ilyushchenko

Co-Founder and CTO at QuestDB
QuestDB’s Vlad Ilyushchenko will describe how they optimized their database performance using efficient zero garbage collection multithreaded query processing.

Performance Insights Into eBPF, Step by Step

Dmitrii Dolgov

Senior Software Engineer at Red Hat
Red Hat’s Dmitri Dolgov sheds light on using eBPF. How to collect execution metrics, profile programs and common pitfalls to…

cachegrand: A Take on High Performance Caching

Daniele Salvatore Albano

Senior Software Engineer II at Microsoft
Microsoft’s Daniele Salvatore Albano presents cachegrand, a SIMD-accelerated hashtable without locks or busy-wait loops using fibers, io_uring, and much more.

Throw Away Your Nines

Alex Hidalgo

Principal Reliability Advocate at Nobl9
You may encounter problems if you only think about “nines” setting service reliability targets. Throw away your nines. Let’s find…

The Role of Machine Learning In Cloud Native Performance Optimization

Brian Likosar

Global Director of Solutions Architecture at StormForge
StormForge’s Brian Likosar shows how machine learning can be used to optimally configure apps deployed in Kubernetes to ensure performance…

Capturing NIC and Kernel TX and RX Timestamps for Packets in Go

Blain Smith

Staff Software Engineer at Rocket Science
Rocket Science’s Blain Smith shows how to get better timestamp granularity from the NIC by directly sending and capturing data…

Cutting Through the Fog of Virtualization

Bernd Bandemer

Head of Data Science at Clockwork Systems Inc.
Clockwork Systems’ Bernd Bandemer details causes of cloud network latency, from its underlying infrastructure, to its physical topology and network…

Optimizing Servers for High-Throughput and Low-Latency at Dropbox

Alexey Ivanov

Software Engineer at Dapper Labs
Dapper Labs’ Alexey Ivanov explores layers of efficiency/performance optimizations from hardware, drivers, Linux kernel, library and application-level tunings.

Removing Implicit Deadlocks on a Thread-per-core Architecture with 2-phase Processing

Alex Gallego

CEO and Founder of Redpanda
Redpanda’s Alex Gallego will show how implicit limitations in asynchronous programming can be addressed by a 2-phase technique for resolving…

Apache Iceberg: An Architectural Look Under the Covers

Alex Merced

Developer Advocate at Dremio
Alex Merced, Developer Advocate at Dremio, describes the open data lakehouse architecture and performance-oriented capabilities of Apache Iceberg.

Three Perspectives on Measuring Latency

Geoffrey Beausire

Senior Site Reliability Engineer at Criteo
Discover from Criteo’s Geoffrey Beausire how to measures latency in key-value infrastructure from both server and client sides, as well…