arXiv subjects

Jianshun Zhang

Publications and source records attributed to Jianshun Zhang.

3 recordsLinked to original sources

arXiv2025

Scavenger: Better Space-Time Trade-Offs for Key-Value Separated LSM-trees

Key-Value Stores (KVS) implemented with log-structured merge-tree (LSM-tree) have gained widespread acceptance in storage systems. Nonetheless, a significant challenge arises in the form of high write amplification due to the compaction process. While KV-separated LSM-trees successfully tackle this issue, they also bring about substantial space amplification problems, a concern that cannot be overlooked in cost-sensitive scenarios. Garbage collection (GC) holds significant promise for space amplification reduction, yet existing GC strategies often fall short in optimization performance, lacking thorough consideration of workload characteristics. Additionally, current KV-separated LSM-trees also ignore the adverse effect of the space amplification in the index LSM-tree. In this paper, we systematically analyze the sources of space amplification of KV-separated LSM-trees and introduce Scavenger, which achieves a better trade-off between performance and space amplification. Scavenger initially proposes an I/O-efficient garbage collection scheme to reduce I/O overhead and incorporates a space-aware compaction strategy based on compensated size to minimize the space amplification of index LSM-trees. Extensive experiments show that Scavenger significantly improves write performance and achieves lower space amplification than other KV-separated LSM-trees (including BlobDB, Titan, and TerarkDB).

cs.DB↗

arXiv2025

Scavenger+: Revisiting Space-Time Tradeoffs in Key-Value Separated LSM-trees

Key-Value Stores (KVS) based on log-structured merge-trees (LSM-trees) are widely used in storage systems but face significant challenges, such as high write amplification caused by compaction. KV-separated LSM-trees address write amplification but introduce significant space amplification, a critical concern in cost-sensitive scenarios. Garbage collection (GC) can reduce space amplification, but existing strategies are often inefficient and fail to account for workload characteristics. Moreover, current key-value (KV) separated LSM-trees overlook the space amplification caused by the index LSM-tree. In this paper, we systematically analyze the sources of space amplification in KV-separated LSM-trees and propose Scavenger+, which achieves a better performance-space trade-off. Scavenger+ introduces (1) an I/O-efficient garbage collection scheme to reduce I/O overhead, (2) a space-aware compaction strategy based on compensated size to mitigate index-induced space amplification, and (3) a dynamic GC scheduler that adapts to system load to make better use of CPU and storage resources. Extensive experiments demonstrate that Scavenger+ significantly improves write performance and reduces space amplification compared to state-of-the-art KV-separated LSM-trees, including BlobDB, Titan, and TerarkDB.

cs.DB↗

arXiv2023

WLFC: Write Less in Flash-based Cache

Flash-based disk caches, for example Bcache and Flashcache, has gained tremendous popularity in industry in the last decade because of its low energy consumption, non-volatile nature and high I/O speed. But these cache systems have a worse write performance than the read performance because of the asymmetric I/O costs and the the internal GC mechanism. In addition to the performance issues, since the NAND flash is a type of EEPROM device, the lifespan is also limited by the Program/Erase (P/E) cycles. So how to improve the performance and the lifespan of flash-based caches in write-intensive scenarios has always been a hot issue. Benefiting from Open-Channel SSDs (OCSSDs), we propose a write-friendly flash-based disk cache system, which is called WLFC (Write Less in the Flash-based Cache). In WLFC, a strictly sequential writing method is used to minimize the write amplification. A new replacement algorithm for the write buffer is designed to minimize the erase count caused by the evicting. And a new data layout strategy is designed to minimize the metadata size persisted in SSDs. As a result, the Over-Provisioned (OP) space is completely removed, the erase count of the flash is greatly reduced, and the metadata size is 1/10 or less than that in BCache. Even with a small amount of metadata, the data consistency after the crash is still guaranteed. Compared with the existing mechanism, WLFC brings a 7%-80% reduction in write latency, a 1.07*-4.5* increment in write throughput, and a 50%-88.9% reduction in erase count, with a moderate overhead in read performance.

cs.OS↗