Reptail: Cutting Storage Tail Latency with Inherent Redundancy

Chen, Yun-Chih; Wu, Chun-Feng; Chang, Yuan-Hao; Kuo, Tei-Wei

doi:10.1109/dac18074.2021.9586218

Cited by 3 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SSD channel having hot updated data chunks may induce a large number of read and write requests, as well as more garbage collections. As a result, the problem of long-tail latency on such channels becomes even worse [14]. Chen et al [14] proposed a co-design of host OS and SSD, to assist scheduling on read requests in ultra-dense SSDs with host's data redundancy semantics.…”

Section: Related Work and Motivation 21 Background And Related Workmentioning

confidence: 99%

“…As a result, the problem of long-tail latency on such channels becomes even worse [14]. Chen et al [14] proposed a co-design of host OS and SSD, to assist scheduling on read requests in ultra-dense SSDs with host's data redundancy semantics. Moreover, they exempliied this idea with the journaling ile system and illustrated the tail latency of storage can be efectively cut down.…”

Section: Related Work and Motivation 21 Background And Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Degraded Mode-benefited I/O Scheduling to Ensure I/O Responsiveness in RAID-enabled SSDs

Sha

Cai

et al. 2022

ACM Trans. Des. Autom. Electron. Syst.

View full text Add to dashboard Cite

RAID-enabled SSDs commonly have unbalanced I/O workloads on their components (e.g. SSD channels), as the data/parity chunks in the same stripe may have varied access frequency, which greatly impacts I/O responsiveness. This paper proposes a I/O scheduling scheme by resorting to the degraded read mode and the read-modify-write mode, to reduce the long-tail latency of I/O requests in RAID-enabled SSDs. The basic idea is to avoid scheduling read or update requests to the heavily congested but targeted RAID components. Such requests are satisfied by accessing other relevant RAID components by certain XOR computations (we call the degraded modes ). Specially, we build a queuing overhead assessment model on the top of factors of data redundancy and the current blocked I/O traffics on SSD channels, to precisely dispatch incoming I/O requests to be fulfilled with the degraded mode or not. The trace-driven experiments illustrate that the proposed scheme can reduce the long-tail latency of read requests by 23.1% on average at the 99.99th percentile, in contrast to state-of-the-art scheduling methods.

show abstract

Section: Related Work and Motivation 21 Background And Related Workmentioning

confidence: 99%

Section: Related Work and Motivation 21 Background And Related Workmentioning

confidence: 99%