performance engineering

Bitu Technology

Mar 14, 2025 · Backend Development

Designing Argos: A Next‑Generation Load‑Testing Tool for Super‑Bowl Scale and the Path to a 10x Engineer in the AI Era

The article recounts a Tubi meetup where senior engineers presented Argos, a cloud‑native load‑testing platform built with curl, Lambda, and ClickHouse to handle Super Bowl‑level traffic, while also discussing engineering mindset, cross‑team processes, and how AI tools empower developers to become 10x engineers.

10x engineerAI toolsCloud Functions

0 likes · 13 min read

Designing Argos: A Next‑Generation Load‑Testing Tool for Super‑Bowl Scale and the Path to a 10x Engineer in the AI Era

Python Programming Learning Circle

Jan 6, 2025 · Fundamentals

Beyond Moore's Law: Software, Algorithms, and Architecture as New Performance Drivers

The article examines how, as Moore's Law ends, performance gains will increasingly rely on software optimization, algorithmic advances, and hardware architecture innovations, illustrated by matrix multiplication benchmarks and discussions of Dennard scaling, parallelism, and emerging technologies.

AlgorithmsHardware ArchitectureMoore's law

0 likes · 10 min read

Beyond Moore's Law: Software, Algorithms, and Architecture as New Performance Drivers

Airbnb Technology Team

Jul 2, 2024 · Frontend Development

Airbnb Page Performance Score (PPS): Multi‑Platform Metrics, Weighting, and Evolution

Airbnb created the Page Performance Score (PPS), a unified 0‑100 metric that aggregates platform‑specific initial‑load and post‑load user‑centric measurements for Web, iOS, and Android, using weighted curves to enable cross‑page, cross‑team comparisons, track organizational weighted averages, and evolve with new metrics while preserving a stable scale.

AirbnbMetricsPage Performance Score

0 likes · 10 min read

Airbnb Page Performance Score (PPS): Multi‑Platform Metrics, Weighting, and Evolution

DevOps

Jun 16, 2024 · Operations

Performance Engineering Challenges and Practices for Software‑Defined Vehicles

The article examines how the shift to Software‑Defined Vehicles introduces complex performance engineering challenges across software, hardware, and organizational domains, and proposes an engineering‑driven, continuous‑observability approach—including modeling, monitoring, iterative optimization, and specialized team structures—to sustainably improve automotive software performance.

ObservabilitySDVautomotive software

0 likes · 17 min read

Performance Engineering Challenges and Practices for Software‑Defined Vehicles

Python Programming Learning Circle

May 28, 2024 · Fundamentals

Beyond Moore's Law: Leveraging Software, Algorithms, and Architecture for Future Performance Gains

With Moore's Law reaching its limits, a recent Science paper by MIT, Nvidia, and Microsoft researchers argues that future computing performance will rely on improvements in the software stack, algorithmic innovations, and hardware architecture, as demonstrated by performance engineering benchmarks and evolving hardware trends.

AlgorithmsHardware ArchitectureMoore's law

0 likes · 9 min read

Beyond Moore's Law: Leveraging Software, Algorithms, and Architecture for Future Performance Gains

iQIYI Technical Product Team

May 10, 2024 · Operations

Full‑Link Load Testing of iQIYI Playback Service: Process, Tools, and Outcomes

iQIYI implemented full‑link load testing of its playback service using LoadMaker for traffic generation and Rover for link control, mapping the topology, creating weighted user scenarios, and safely pressurizing production‑like environments, which validated multi‑times historical peak capacity, uncovered bottlenecks, and enabled several performance and disaster‑recovery improvements without impacting real users.

capacity planningiQIYIload testing

0 likes · 10 min read

Full‑Link Load Testing of iQIYI Playback Service: Process, Tools, and Outcomes

JD Retail Technology

Feb 5, 2024 · Mobile Development

Efficient Optimization of JD App Review API: Reducing Peak Requests by 85% without Impacting User Experience

By analyzing user behavior and decoupling the review layer from the product detail flow, the JD app team introduced a scroll‑triggered, configurable request mechanism and fallback handling, achieving up to an 85% reduction in peak review API QPS during major sales events without degrading user experience.

API throttlingAsynchronous LoadingUser experience

0 likes · 7 min read

Efficient Optimization of JD App Review API: Reducing Peak Requests by 85% without Impacting User Experience

Tencent Cloud Developer

Sep 21, 2023 · Frontend Development

Memory Optimization of Desktop QQ: A Stage Summary

To curb Desktop QQ’s excessive Electron memory consumption, the team applied comprehensive profiling, code and resource slimming, thumbnail image generation, visible‑only DOM rendering, layer merging, Lottie animation tuning, API caching, and leak removal, achieving average usage around 228 MB and keeping all six processes below 300 MB with ongoing monitoring.

Desktop ApplicationElectronMemory Optimization

0 likes · 24 min read

Memory Optimization of Desktop QQ: A Stage Summary

Didi Tech

Aug 17, 2023 · Operations

Construction of a Full-Link Load Testing Simulation Measurement System for Didi Ride-Hailing

The article details how Didi’s ride‑hailing team built a full‑link load‑testing simulation‑degree measurement system that quantifies test coverage across five dimensions—interface, scenario, category, link, and module—using normalized metrics, traffic prediction, and scoring formulas to identify gaps, improve stability, and guide future capacity‑planning enhancements.

DidiRide-hailingload testing

0 likes · 16 min read

Construction of a Full-Link Load Testing Simulation Measurement System for Didi Ride-Hailing

DaTaobao Tech

Jun 14, 2023 · Artificial Intelligence

Optimizing NeRF for Real-Time Mobile 3D Rendering in Alibaba's Object Drawer

Alibaba’s Taobao engineers detail how they transformed slow, high‑quality NeRF reconstruction into a real‑time mobile solution by combining an Octree‑Tiny‑MLP architecture, SNeRG optimizations, and a high‑frequency voxel reduction that shrank models to ~5 MB and achieved ~6 FPS on low‑end Android phones, targeting sub‑1 MB models and 50 FPS.

3D reconstructioncomputer visionmobile optimization

0 likes · 10 min read

Optimizing NeRF for Real-Time Mobile 3D Rendering in Alibaba's Object Drawer

NetEase Yanxuan Technology Product Team

Feb 20, 2023 · Big Data

Data Task Optimization Techniques and Practices

The article surveys unconventional offline data‑task optimizations—such as distribution‑by, seeded random shuffling, explode‑based skew mitigation, hash bucketing, task‑parallelism tuning, and multi‑insert materialization—organized by point, line, and surface perspectives, and stresses that effective performance gains require both technical tricks and business‑driven pipeline adjustments.

Big DataData OptimizationHive

0 likes · 16 min read

Data Task Optimization Techniques and Practices

Tencent Cloud Developer

Feb 3, 2023 · Cloud Computing

Cloud Load Testing: Strategies, Scenarios, and Practice Cases for High‑Traffic Events

Tencent’s cloud load‑testing platform simulates massive Chinese‑New‑Year traffic by offering concurrency and RPS modes, multi‑language test authoring, realistic data generation, and unified OpenTelemetry reporting, enabling early bottleneck detection, proactive scaling, and successful high‑load drills such as Mobile QQ and video services.

GoJavaScriptObservability

0 likes · 23 min read

Cloud Load Testing: Strategies, Scenarios, and Practice Cases for High‑Traffic Events

Weimob Technology Center

Feb 3, 2023 · Operations

How Full‑Link Load Testing Became the Secret Weapon for E‑Commerce Mega‑Sales

This article explains how micro‑enterprise SaaS leader Weimeng built a full‑link load‑testing platform to simulate real‑world traffic for major shopping festivals, detailing the challenges, architecture, capabilities, results, and future plans for ensuring system stability and performance at scale.

JMetercapacity planninge-commerce

0 likes · 16 min read

How Full‑Link Load Testing Became the Secret Weapon for E‑Commerce Mega‑Sales

ByteDance SYS Tech

Jan 6, 2023 · Fundamentals

How ByteDance Scaled Profile‑Guided Optimization to Boost CPU Efficiency

This article explains ByteDance's large‑scale adoption of profile‑guided optimization (PGO), covering its principles, instrumentation and sampling methods, the automated platform built for data collection and compilation, and the resulting performance gains across dozens of critical services.

ByteDanceCompiler OptimizationInstrumentation

0 likes · 12 min read

Bilibili Tech

Dec 27, 2022 · Operations

Optimizing QUIC Gateway Performance with AF_XDP

Bilibili’s video CDN replaced its traditional TCP‑based gateway with a QUIC/HTTP‑3 gateway and, to curb the extra CPU load caused by complex UDP handling, adopted AF_XDP kernel‑bypass sockets that redirect packets via XDP, cutting CPU usage by about half, raising peak bandwidth to roughly 9 Gbps and improving per‑bandwidth efficiency by up to 30 %.

AF_XDPLinux KernelQUIC

0 likes · 14 min read

Optimizing QUIC Gateway Performance with AF_XDP

iQIYI Technical Product Team

Jul 8, 2022 · Mobile Development

Performance Optimization Practices for iQIYI International Mobile App

To prevent massive user loss from slow loads, iQIYI International overhauled its mobile app’s network stack—switching to HTTPDNS, enabling TCP Fast Open, upgrading to HTTP/2 and TLS 1.3, compressing payloads with Brotli and WebP, using protobuf, caching, and fallback protocols—cut latency, reduced failures, and boosted video playback across Southeast Asian markets.

Edge ComputingHTTP/2TLS

0 likes · 10 min read

Performance Optimization Practices for iQIYI International Mobile App

Bilibili Tech

Jun 24, 2022 · Cloud Native

Evolution and Design of Bilibili's Load‑Testing Platform (Platform 2.0)

Bilibili’s load‑testing platform evolved from ad‑hoc JMeter scripts to a fully automated, self‑service system (Platform 2.0) that uses a custom load client, adaptive scheduling, and flexible scenario modes—including traffic replay and data‑isolated testing—to efficiently stress‑test over a hundred microservices for large‑scale events, with further integration and circuit‑breaker enhancements planned.

cloud-nativedistributed systemsload testing

0 likes · 27 min read

Evolution and Design of Bilibili's Load‑Testing Platform (Platform 2.0)

Baidu Geek Talk

May 25, 2022 · Backend Development

Large-Scale C/C++ Service Compilation Performance Optimization and Platformization (OMAX)

The article details OMAX’s end‑to‑end platform for large‑scale C/C++ service compilation, covering optimization flags, profile‑guided and link‑time techniques, Facebook BOLT post‑link tuning, and real‑world results that cut CPU use, latency and deployment time while shrinking binary size.

BOLTC++Cloud Services

0 likes · 24 min read

Large-Scale C/C++ Service Compilation Performance Optimization and Platformization (OMAX)

Tencent Cloud Developer

Nov 30, 2021 · Cloud Native

Tencent sTGW TQUIC: Reducing Login Latency by 30% and Boosting 500 ms Success Rate to 90%

Tencent’s sTGW team introduced the TQUIC protocol stack, a lightweight QUIC/HTTP‑3 implementation with 0‑RTT handshakes, connection migration, and real‑time frames, cutting user login latency by 30 % and raising 500 ms download success from 60 % to 90 % in weak‑network conditions while shrinking the Android library to roughly 3 MB.

HTTP3QUICReal-time Transmission

0 likes · 14 min read

Tencent sTGW TQUIC: Reducing Login Latency by 30% and Boosting 500 ms Success Rate to 90%

High Availability Architecture

Jun 2, 2021 · Operations

Design and Implementation of Full‑Link Load Testing at Dada Group

This article describes Dada Group’s evolution from a simple 1:1 test environment to a sophisticated machine‑labeling load‑testing solution, detailing core design, isolation techniques, custom testing platform, model construction, pre‑heat strategies, and post‑test analysis that ensure system stability during high‑traffic events.

distributed systemsload testingmicroservices

0 likes · 16 min read

Design and Implementation of Full‑Link Load Testing at Dada Group