AnyKey: A Key-Value SSD for All Workload Types

Of course. Here is a peer review of the paper "AnyKey: A Key-Value SSD for All Workload Types" from the perspective of 'The Guardian'.

ASPLOS 2025 Program Committee Review Form

Paper Title: AnyKey: A Key-Value SSD for All Workload Types
Reviewer: The Guardian (Adversarial Skeptic)

Summary

This paper identifies a performance vulnerability in state-of-the-art LSM-tree-based Key-Value SSDs, such as PinK, when subjected to workloads with low value-to-key (low-v/k) ratios. The authors argue that as the relative key size increases, the metadata required to index KV pairs bloats, exceeding the capacity of the device's internal DRAM and forcing metadata to be stored on flash. This results in additional, high-latency flash accesses for read operations, severely degrading performance.

To address this, the authors propose AnyKey, a novel KV-SSD design. AnyKey's core idea is to manage KV pairs in "data segment groups" and reduce metadata by storing only a sin

Of course. Here is a peer review of the paper "AnyKey: A Key-Value SSD for All Workload Types" from the perspective of 'The Synthesizer.'

Review Form: AnyKey: A Key-Value SSD for All Workload Types

Summary

This paper identifies and addresses a critical performance limitation in current state-of-the-art Key-Value SSD (KV-SSD) designs. The authors observe that existing LSM-tree-based KV-SSDs, such as PinK, are implicitly optimized for workloads with a high value-to-key (high-v/k) ratio, where values are significantly larger than keys. They demonstrate that for an important and previously under-explored class of "low-v/k" workloads, the metadata required to index the KV pairs grows too large to fit in the device's limited internal DRAM. This overflow leads to excessive flash reads for metadata, causing a severe degradation in latency and IOPS.

The authors propose AnyKey, a novel KV-SSD architecture designed to be robust across all workload types. The core contributio

Review Form: The Innovator (Novelty Specialist)

Summary

This paper identifies a performance bottleneck in existing LSM-tree-based Key-Value SSDs (KV-SSDs), exemplified by PinK, when subjected to workloads with low value-to-key (low-v/k) ratios. The authors correctly diagnose the problem as metadata bloat: when keys are large, the metadata required to index them consumes excessive device-internal DRAM, forcing metadata to be paged out to flash and incurring significant read amplification.

To address this, the authors propose "AnyKey," a novel KV-SSD design. The core contribution is a new metadata and data layout scheme. Instead of indexing individual key-value pairs, AnyKey groups KV pairs into "data segment groups" (spanning multiple physical pages) and indexes the group. Crucially, within these groups, KV pairs are sorted by a fixed-size hash of the key, not the key itself. This allows the metadata to remain compact regardless of key size. The design also incorporates a