A curated collection of research papers and publicly available datasets for storage workload analysis and performance research.
| 📍 Venue | 📄 Paper | 📊 Dataset / Trace |
|---|---|---|
| FAST | Perseus: A Fail-Slow Detection Framework for Cloud Storage Systems | Alibaba NVME Fail-Slow |
| 📍 Venue | 📄 Paper | 📊 Dataset / Trace |
|---|---|---|
| TOS | SSD-based Workload Characteristics and Their Performance Implications | YCSB RocksDB SSD |
| 📍 Venue | 📄 Paper | 📊 Dataset / Trace |
|---|---|---|
| ICS | Demystifying Cache Policies for Photo Stores at Scale: A Tencent Case Study | Tencent Photo Cache |
| 📍 Venue | 📄 Paper | 📊 Dataset / Trace |
|---|---|---|
| SYSTOR | Understanding storage traffic characteristics on enterprise virtual desktop infrastructure | Systor '17 Traces |
| 📍 Venue | 📄 Paper | 📊 Dataset / Trace |
|---|---|---|
| FAST | Analysis of the ECMWF Storage Landscape | ECMWF Traces |
| 📍 Venue | 📄 Paper | 📊 Dataset / Trace |
|---|---|---|
| FAST | Slacker: Fast Distribution with Lazy Docker Containers | Slacker Traces |
| 📍 Venue | 📄 Paper | 📊 Dataset / Trace |
|---|---|---|
| TOS | I/O Deduplication: Utilizing content similarity to improve I/O performance | FIU |
| 📍 Venue | 📄 Paper | 📊 Dataset / Trace |
|---|---|---|
| Computer Networks | Wikipedia Workload Analysis for Decentralized Hosting | Wikipedia Dumps |
| 📍 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 |
If you have additional papers or datasets to include, feel free to submit a pull request or open an issue!
This repository is maintained for academic and research purposes. Please check individual papers and datasets for their respective licenses and terms of use.