Efficient Garbage Collection Algorithm for Low Latency SSD

Ae, Jin; Yuan, Hong

doi:10.3390/electronics11071084

Cited by 2 publications

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We implemented the conventional GC and proposed GC scheme and compared their performances. As a framework to test GC performance, we selected the plane-blocking GC (PBGC) scheme presented in [11] and block-blocking GC (BBGC) scheme from [13]. GC was enabled if 70% of the entire SSD storage was full for all schemes.…”

Section: Resultsmentioning

confidence: 99%

“…The existing approaches for reducing GC overhead include fine-grained blocking of operations and interrupting GC if a new RW operation is required; however, these approaches have limitations in terms of data hazards and pre-emptive schedule management [13]. Another approach is to distribute data over multiple flash memory chips in a way that reduces the frequency of GC, but this requires careful management of the hotness of data and proper placement of data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

On-Demand Garbage Collection Algorithm with Prioritized Victim Blocks for SSDs

2023

Self Cite

View full text Add to dashboard Cite

Because of their numerous benefits, solid-state drives (SSDs) are increasingly being used in a wide range of applications, including data centers, cloud computing, and high-performance computing. The growing demand for SSDs has led to a continuous improvement in their technology and a reduction in their cost, making them a more accessible storage solution for a wide range of users. Garbage collection (GC) is a process that reclaims wasted storage space in NAND flash memories, which are used as the memory devices for SSDs. However, the GC process can cause performance degradation and lifetime reduction. This paper proposes an efficient garbage collection (GC) scheme that minimizes overhead by invoking GC operations only when necessary. Each GC operation is executed in a specific order based on the expected storage gain and the execution cost, ensuring that the storage space requirement is met while minimizing the frequency of GC invocation. This approach not only reduces the overhead due to GC, but also improves the overall performance of SSDs, including the latency and write amplification factor (WAF) which is an important indicator of the longevity of SSDs.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

On-Demand Garbage Collection Algorithm with Prioritized Victim Blocks for SSDs

2023

Self Cite

View full text Add to dashboard Cite

show abstract

High-Performance Garbage Collection Scheme with Low Data Transfer Overhead for NoC-Based SSDC

Ahn,

Im,

You

et al. 2024

Electronics

View full text Add to dashboard Cite

Solid-state drives (SSDs) have become the preferred storage solution for performance-critical applications due to their high speed, durability, and energy efficiency. However, the inherent characteristics of NAND flash memory, such as block-level erasure and data fragmentation, necessitate frequent garbage collection (GC) operations to reclaim storage space. These operations, while essential, introduce significant performance overhead, particularly in modern SSD controllers (SSDCs) that utilize network-on-chip (NoC) architectures. In such architectures, GC requires substantial data transfer over interconnects for error correction, leading to increased latency and reduced throughput. This paper presents a novel GC scheme designed to minimize latency in NoC-based SSDCs. Unlike conventional methods that unconditionally transfer data for error correction, the proposed approach selectively determines the data transfer path based on the presence of errors. By leveraging the low error probability of NAND flash memory, this scheme avoids unnecessary data traversal across the interconnect, significantly reducing GC overhead. A hardware implementation using task queues ensures efficient parallelism without disrupting other operations. The experimental results demonstrate that the proposed scheme improves SSD performance across various real-world workloads, achieving up to a 26.9% reduction in average latency and a 50.0% reduction in peak latency compared to traditional GC methods. These findings highlight the potential of optimizing data traversal paths in NoC architectures, providing a scalable solution for enhancing SSD performance for diverse applications.

show abstract

Efficient Garbage Collection Algorithm for Low Latency SSD

Cited by 2 publications

References 27 publications

On-Demand Garbage Collection Algorithm with Prioritized Victim Blocks for SSDs

On-Demand Garbage Collection Algorithm with Prioritized Victim Blocks for SSDs

High-Performance Garbage Collection Scheme with Low Data Transfer Overhead for NoC-Based SSDC

Contact Info

Product

Resources

About