TraceTracker: Hardware/Software Co-Evaluation for Large-Scale I/O Workload Reconstruction

TL;DR

TraceTracker is a novel co-evaluation method that enhances block trace analysis by accurately reconstructing execution contexts, including user idle periods and system delays, for large-scale I/O workload reconstruction.

Contribution

It introduces a software/hardware co-evaluation approach that reuses existing block traces with adjusted execution contexts for accurate system behavior simulation.

Findings

Achieved 99% accuracy in idle operation frequency reconstruction.

Achieved 96% accuracy in total idle period estimation.

Successfully revived 577 historical traces on modern flash storage.

Abstract

Block traces are widely used for system studies, model verifications, and design analyses in both industry and academia. While such traces include detailed block access patterns, existing trace-driven research unfortunately often fails to find true-north due to a lack of runtime contexts such as user idle periods and system delays, which are fundamentally linked to the characteristics of target storage hardware. In this work, we propose TraceTracker, a novel hardware/software co-evaluation method that allows users to reuse a broad range of the existing block traces by keeping most their execution contexts and user scenarios while adjusting them with new system information. Specifically, our TraceTracker's software evaluation model can infer CPU burst times and user idle periods from old storage traces, whereas its hardware evaluation method remasters the storage traces by interoperating the inferred time information, and updates all inter-arrival times by making them aware of the target storage system. We apply the proposed co-evaluation model to 577 traces, which were collected by servers from different institutions and locations a decade ago, and revive the traces on a high-performance flash-based storage array. The evaluation results reveal that the accuracy of the execution contexts reconstructed by TraceTracker is on average 99% and 96% with regard to the frequency of idle operations and the total idle periods, respectively.