Storage traces are widely used for storage simulation and system evaluation. Since high performance SSD, flash array and NVM systems exhibit different I/O timing behaviors, the traditional traces need to be revised or collected on releatively modern systems. To address this, we are collecting different types of traces with many different combinations of devices and systems. Our trace repository distributes traces collected on Kandemir, Wilson, John and Donofrio machines under different types of parallel file systems such as lustre and ceph [Check Camelab's high performance computing systems]. Hope that we can secure more traces, which can help storage system and architecture communities to make better and easy-to-reproduce research.
We reconstruct existing block traces which are collected on disk-based storage system by using TraceTracker method on flash-array based system (Kandemir machine).
Read MoreTraces are collected for both erasure coding (especailly for reed-solomon) and replication method on Ceph machine.
Read MoreWe are collecting traces of KANDEMIR machine which is all-flash array based High Performance Computing (HPC) testbed of CAMELab. Not only for normal user behaviors, also different kinds of emerging applications are executed for various workload scenarios. It will be prepared soon.
Read More