📂 Production Storage Workloads and Research Papers

A curated collection of research papers and publicly available datasets for storage workload analysis and performance research.

---

📅 2024

📍 Venue	📄 Paper	📊 Dataset / Trace
SYSTOR	Space-efficient FTL for Mobile Storage via Tiny Neural Nets	Mobile Application I/O Traces
ASPLOS	Thesios: Synthesizing Accurate Counterfactual I/O Traces from I/O Samples	Google Synthesized I/O Traces Thesios
FAST	Baleen: ML Admission & Prefetching for Flash Caches	Baleen

---

📅 2023

📍 Venue	📄 Paper	📊 Dataset / Trace
FAST	Perseus: A Fail-Slow Detection Framework for Cloud Storage Systems	Alibaba NVME Fail-Slow
SOSP	FIFO Queues are All You Need for Cache Eviction	MetaKV key-value traces
SOSP	FIFO Queues are All You Need for Cache Eviction	MetaCDN object traces

---

📅 2021

📍 Venue	📄 Paper	📊 Dataset / Trace
TOS	SSD-based Workload Characteristics and Their Performance Implications	YCSB RocksDB SSD

---

📅 2020

📍 Venue	📄 Paper	📊 Dataset / Trace
OSDI	The CacheLib Caching Engine: Design and Experiences at Scale	-
OSDI	A Large-Scale Analysis of Hundreds of In-Memory Cache Clusters at Twitter	Twitter Memcached
IISWC	An In-Depth Analysis of Cloud Block Storage Workloads in Large-Scale Production	Alibaba Block Traces
IPDPSW	Recorder 2.0: Efficient Parallel I/O Tracing and Analysis	HPC Application I/O Traces
ATC	OSCA: An Online-Model Based Cache Allocation Scheme in Cloud Block Storage Systems	Tencent Block
Hotstorage	It’s Time to Revisit LRU vs. FIFO	IBM Object Store

---

📅 2018

📍 Venue	📄 Paper	📊 Dataset / Trace
ICS	Demystifying Cache Policies for Photo Stores at Scale: A Tencent Case Study	Tencent Photo Cache

---

📅 2017

📍 Venue	📄 Paper	📊 Dataset / Trace
SYSTOR	Understanding storage traffic characteristics on enterprise virtual desktop infrastructure	Systor '17 Traces

---

📅 2015

📍 Venue	📄 Paper	📊 Dataset / Trace
FAST	Analysis of the ECMWF Storage Landscape	ECMWF Traces

---

📅 2016

📍 Venue	📄 Paper	📊 Dataset / Trace
FAST	Slacker: Fast Distribution with Lazy Docker Containers	Slacker Traces

---

📅 2010

📍 Venue	📄 Paper	📊 Dataset / Trace
TOS	I/O Deduplication: Utilizing content similarity to improve I/O performance	FIU

---

📅 2009

📍 Venue	📄 Paper	📊 Dataset / Trace
Computer Networks	Wikipedia Workload Analysis for Decentralized Hosting	Wikipedia Dumps

---

📅 2008

📍 Venue	📄 Paper	📊 Dataset / Trace
FAST	Write Off-Loading: Practical Power Management for Enterprise Storage	MSR Cambridge
IWQoS	Statistics and Social Network of YouTube Videos	YouTube Dataset

---

📌 Contributing

If you have additional papers or datasets to include, feel free to submit a pull request or open an issue!

📜 License

This repository is maintained for academic and research purposes. Please check individual papers and datasets for their respective licenses and terms of use.