Conveyor: One-Tool-Fits-All Continuous Software Deployment at Meta
Boris Grubic, Yang Wang, Tyler Petrochko, Ran Yaniv, Brad Jones, David Callies, Matt Clarke-Lauer, Dan Kelley, Soteris Demetriou, Kenny Yu, Chunqiang Tang
摘要
We present Conveyor, Meta's software deployment tool, along with the valuable data obtained from managing over 30,000 deployment pipelines that deploy all kinds of services at Meta across millions of machines. We describe a wide range of deployment scenarios that Conveyor supports to achieve universal coverage. At Meta, out of all the deployment pipelines for services deployed via containers, 97% of them employ fully automated deployments without manual intervention: 55% utilize continuous deployment, instantly deploying every code change to production after passing automated tests, and the remaining 42% are automatically deployed on a fixed schedule (mostly daily or weekly) without manual validation. We highlight several distinguishing features of Conveyor, including safe in-place updates to reduce hardware costs, analysis of code dependencies to prevent faulty releases, and the capability to deploy complex ML models at scale.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了最后一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper6
- Rajomon: Decentralized and Coordinated Overload Control for Latency-Sensitive MicroservicesJiali Xing, Akis Giannoukos, Paul Loh, Shuyue Wang 等NSDI 2025 · 被引用 12 次
- ServiceLab: Preventing Tiny Performance Regressions at Hyperscale through Pre-Production TestingMike Chow, Yang Wang, William Wang, Ayichew Hailu 等OSDI 2024 · 被引用 11 次
- FBDetect: Catching Tiny Performance Regressions at Hyperscale through In-Production MonitoringDong Young Yoon, Yang Wang, Miao Yu, Elvis Huang 等SOSP 2024 · 被引用 5 次
- Observability Is Eating Your Cores: Fine-Grained Analysis of Microservice Metrics with IPU-Hosted SketchesAlessandro Cornacchia, Theophilus A. Benson, Muhammad Bilal, Marco CaniniNSDI 2026 · 被引用 3 次
- ServiceRouter: Hyperscale and Minimal Cost Service Mesh at MetaHarshit Saokar, Soteris Demetriou, Nick Magerko, Max Kontorovich 等OSDI 2023
它引用的顶会 Paper7
- Autopilot: workload autoscaling at GoogleKrzysztof Rzadca, Pawel Findeisen, Jacek Swiderski, Przemyslaw Zych 等EuroSys 2020 · 被引用 299 次
- Protean: VM Allocation Service at ScaleOri Hadary, Luke Marshall, Ishai Menache, Abhisek Pan 等OSDI 2020 · 被引用 189 次
- Twine: A Unified Cluster Management System for Shared InfrastructureChunqiang Tang, Kenny Yu, Kaushik Veeraraghavan, Jonathan Kaldor 等OSDI 2020 · 被引用 107 次
- Lifting the veil on Meta's microservice architecture: Analyses of topology and request workflowsDarby Huye, Yuri Shkuro, Raja R. SambasivanUSENIX ATC 2023 · 被引用 65 次
- Shard Manager: A Generic Shard Management Framework for Geo-distributed ApplicationsSangmin Lee, Zhenhua Guo, Omer Sunercan, Jun Ying 等SOSP 2021 · 被引用 18 次
相关 Paper
- AI-Assisted Code Authoring at Scale: Fine-Tuning, Deploying, and Mixed Methods EvaluationVijayaraghavan Murali, Chandra Shekhar Maddila, Imad Ahmad, Michael Bolin 等FSE 2024 · 被引用 17 次
- Metis: learning to schedule long-running applications in shared container clusters at scaleLuping Wang, Qizhen Weng, Wei Wang, Chen Chen 等SC 2020 · 被引用 46 次
- Scalable build service system with smart scheduling serviceKaiyuan Wang, Greg Tener, Vijay Gullapalli, Xin Huang 等ISSTA 2020 · 被引用 8 次
- Deep Pipeline Embeddings for AutoMLSebastian Pineda-Arango, Josif GrabockaKDD 2023 · 被引用 6 次
- Repo2Run: Automated Building Executable Environment for Code Repository at ScaleRuida Hu, Chao Peng, Xinchen Wang, Junjielong Xu 等NeurIPS 2025 · 被引用 49 次
