Proceedings of the 26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems 2021
DOI: 10.1145/3445814.3446719
|View full text |Cite
|
Sign up to set email alerts
|

Reducing solid-state drive read latency by optimizing read-retry

Abstract: 3D NAND flash memory with advanced multi-level cell techniques provides high storage density, but suffers from significant performance degradation due to a large number of read-retry operations. Although the read-retry mechanism is essential to ensuring the reliability of modern NAND flash memory, it can significantly increase the read latency of an SSD by introducing multiple retry steps that read the target page again with adjusted read-reference voltage values. Through a detailed analysis of the read mechan… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
5
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
6
1

Relationship

2
5

Authors

Journals

citations
Cited by 28 publications
(5 citation statements)
references
References 87 publications
0
5
0
Order By: Relevance
“…As explained, Step 1 only streams the data structures in batches from the underlying NAND flash chips to the internal DRAM, leveraging the SSD's full internal bandwidth. Therefore, the performance of GenStore-ER can be easily scaled up by increasing the SSD's internal parallelism (e.g., by deploying more channels or using low-latency NAND flash memory [122,151,152]).…”
Section: Genstore-em For Exactly-matching Readsmentioning
confidence: 99%
See 2 more Smart Citations
“…As explained, Step 1 only streams the data structures in batches from the underlying NAND flash chips to the internal DRAM, leveraging the SSD's full internal bandwidth. Therefore, the performance of GenStore-ER can be easily scaled up by increasing the SSD's internal parallelism (e.g., by deploying more channels or using low-latency NAND flash memory [122,151,152]).…”
Section: Genstore-em For Exactly-matching Readsmentioning
confidence: 99%
“…Similar to GenStore-EM, the steps of GenStore-NM are pipelined. The performance of GenStore-NM can be easily scaled up by increasing the SSD's internal parallelism (e.g., by deploying more channels or using low-latency NAND flash memory) [122,151,152].…”
Section: Inputmentioning
confidence: 99%
See 1 more Smart Citation
“…Realworld storage devices could have dynamic latency variations due to their complex hardware and software components (e.g., internal caching, garbage collection, error handling, multi-level cell reading, etc.) [80][81][82][83][84][85][86][87]. Second, if the fast storage is running out of free space, there might be evictions in the background from the fast storage to the slow storage.…”
Section: Introductionmentioning
confidence: 99%
“…In [23], [24], nonuniform soft sensing read reference voltage has been demonstrated to decrease latency by achieving high error correcting capability with low precision decoding mode. The authors in [25] have introduced read-retry mechanism with consecutive retry steps in a pipelined manner to reduce the read latency. Moreover, they reduced page-sensing latency with an adaptive reference voltage precharging timing based on offline profiling.…”
Section: Introductionmentioning
confidence: 99%