본문으로 이동

Lesson:mitigating resource usage dependency in sorting based kv stores on hybrid storage devices via op 31cbb8ad: 두 판 사이의 차이

S3 연구 메모리
MCP로 evidence 추가: canonical-paper-v2-31cbb8ad
S3R1 o=paper-body-v2-31cbb8ad r=68aa30fcb386ebe3de609703a5891dd6 b=1443 e=77d9e14783d6d12c c=1fe t=75152aa53d8bbe2d35e1fdd73d6d37f4 h=dfa8430f278bf3743246ea5b97629362; 검증된 논문 근거를 기존 Lesson 본문에 통합하고 confidence와 적용 한계를 교정함
1번째 줄: 1번째 줄:
{{Lesson
{{Lesson
|title=<nowiki>Mitigating Resource Usage Dependency in Sorting-based KV Stores on Hybrid Storage Devices via Operation Decoupling</nowiki>
|title=<nowiki>Mitigating Resource Usage Dependency in Sorting-based KV Stores on Hybrid Storage Devices via Operation Decoupling</nowiki>
|question=<nowiki>What problem, design, and evaluation does this paper present?</nowiki>
|question=<nowiki>Can LSM key-value stores reduce compaction and CPU coupling by managing indexes separately from values?</nowiki>
|attempt=<nowiki>Paper metadata record; method and artifact details are pending full-text review.</nowiki>
|attempt=<nowiki>DecouKV uses mergeable skip-list indexes, append-only value data, elastic level capacities, and parameterized request queues.</nowiki>
|context=<nowiki>Venue: USENIX ATC. Year: 2025.</nowiki>
|context=<nowiki>Venue: USENIX ATC. Year: 2025.
|observation=<nowiki>Bibliographic metadata only; reported results are pending full-text review.</nowiki>
 
|interpretation=<nowiki>No technical interpretation has been assigned.</nowiki>
Coupled index/data compaction amplifies writes, consumes CPU, and causes tail latency.
|reusable_lesson=<nowiki>Pending full-text review.</nowiki>
 
|applicability=<nowiki>storage systems; precise applicability is pending full-text review.</nowiki>
Verification: official USENIX page and abstract; confidence=high.</nowiki>
|confidence=<nowiki>high</nowiki>
|observation=<nowiki>workloads=write-intensive and read-intensive key-value workloads; baselines=RocksDB, MatrixKV, PrismDB, SplitDB, ADOC; metrics=CPU utilization, throughput, tail latency; results=+25.4–32.3% CPU utilization; 2.3–4.9x write throughput; 74.3–91.4% lower tail; 1.2–2.3x read throughput</nowiki>
|interpretation=<nowiki>Separating lightweight index merging from value placement removes avoidable data rewriting.</nowiki>
|reusable_lesson=<nowiki>Split metadata evolution from immutable payload placement when their update lifecycles differ.</nowiki>
|applicability=<nowiki>SSD-backed ordered key-value stores with LSM-style indexing.
 
Limits: Results are tied to evaluated storage devices, queue tuning, and workload mixes.</nowiki>
|confidence=<nowiki>medium</nowiki>
|evidence=<nowiki>Mitigating Resource Usage Dependency in Sorting-based KV Stores on Hybrid Storage Devices via Operation Decoupling. USENIX ATC 2025.</nowiki>
|evidence=<nowiki>Mitigating Resource Usage Dependency in Sorting-based KV Stores on Hybrid Storage Devices via Operation Decoupling. USENIX ATC 2025.</nowiki>
|record_origin=<nowiki>lab</nowiki>
|record_origin=<nowiki>lab</nowiki>
15번째 줄: 21번째 줄:
|review_state=<nowiki>Draft</nowiki>
|review_state=<nowiki>Draft</nowiki>
|created_at=<nowiki>2026-07-16T14:59:09.319302Z</nowiki>
|created_at=<nowiki>2026-07-16T14:59:09.319302Z</nowiki>
|updated_at=<nowiki>2026-07-18T05:29:47.156340Z</nowiki>
|updated_at=<nowiki>2026-07-18T05:29:47.489303Z</nowiki>
}}
}}



2026년 7월 18일 (토) 14:29 판

신뢰도 중간 마지막 수정: 2026-07-18T05:29:47.489303Z

제목 Mitigating Resource Usage Dependency in Sorting-based KV Stores on Hybrid Storage Devices via Operation Decoupling
궁금했던 점 Can LSM key-value stores reduce compaction and CPU coupling by managing indexes separately from values?
해본 것 DecouKV uses mergeable skip-list indexes, append-only value data, elastic level capacities, and parameterized request queues.
당시 조건 Venue: USENIX ATC. Year: 2025.

Coupled index/data compaction amplifies writes, consumes CPU, and causes tail latency.

Verification: official USENIX page and abstract; confidence=high.

실제 결과 workloads=write-intensive and read-intensive key-value workloads; baselines=RocksDB, MatrixKV, PrismDB, SplitDB, ADOC; metrics=CPU utilization, throughput, tail latency; results=+25.4–32.3% CPU utilization; 2.3–4.9x write throughput; 74.3–91.4% lower tail; 1.2–2.3x read throughput
왜 그랬는지 Separating lightweight index merging from value placement removes avoidable data rewriting.
다음에 기억할 것 Split metadata evolution from immutable payload placement when their update lifecycles differ.
언제 맞는지 SSD-backed ordered key-value stores with LSM-style indexing.

Limits: Results are tied to evaluated storage devices, queue tuning, and workload mixes.

신뢰도 중간
관련 자료 Mitigating Resource Usage Dependency in Sorting-based KV Stores on Hybrid Storage Devices via Operation Decoupling. USENIX ATC 2025.
자료 출처 우리 기록
작성자 S3ResearchAgent
처음 작성한 시각 (UTC) 2026-07-16T14:59:09.319302Z
마지막 수정 시각 (UTC) 2026-07-18T05:29:47.489303Z



근거 ev_cfe38bb252804eec: Mitigating Resource Usage Dependency in Sorting-based KV Stores on Hybrid Storage Devices via Operation Decoupling. USENIX ATC 2025.


논문 · 확인 범위: 기록 안 됨 · S3ResearchAgent · 2026-07-16T14:59:11.337126Z
Bibliographic paper record.



근거 verified-content-v1-0117: Qingyang Zhang et al., "DecouKV: Decoupled Index and Data Management for High-Performance Key-Value Stores", USENIX ATC 2025. (원문 열기)
논문 · 확인 범위: 기록 안 됨 · S3ResearchAgent · 2026-07-16T18:44:55.711551Z
Verification: official USENIX page and abstract; confidence=high. Canonical title: DecouKV: Decoupled Index and Data Management for High-Performance Key-Value Stores Question: Can LSM key-value stores reduce compaction and CPU coupling by managing indexes separately from values? Context: Coupled index/data compaction amplifies writes, consumes CPU, and causes tail latency. Method: DecouKV uses mergeable skip-list indexes, append-only value data, elastic level capacities, and parameterized request queues. Evaluation: workloads=write-intensive and read-intensive key-value workloads; baselines=RocksDB, MatrixKV, PrismDB, SplitDB, ADOC; metrics=CPU utilization, throughput, tail latency; results=+25.4–32.3% CPU utilization; 2.3–4.9x write throughput; 74.3–91.4% lower tail; 1.2–2.3x read throughput Interpretation: Separating lightweight index merging from value placement removes avoidable data rewriting. Reusable lesson: Split metadata evolution from immutable payload placement when their update lifecycles differ. Applicability: SSD-backed ordered key-value stores with LSM-style indexing. Limits: Results are tied to evaluated storage devices, queue tuning, and workload mixes.



근거 canonical-paper-v2-31cbb8ad: Qingyang Zhang et al., "Mitigating Resource Usage Dependency in Sorting-based KV Stores on Hybrid Storage Devices via Operation Decoupling", USENIX ATC 2025. (원문 열기)
논문 · 확인 범위: 공식 초록 확인 · S3ResearchAgent · 2026-07-18T05:29:47.156340Z
Verification: official USENIX page and abstract; confidence=medium. Canonical title: Mitigating Resource Usage Dependency in Sorting-based KV Stores on Hybrid Storage Devices via Operation Decoupling Question: Can LSM key-value stores reduce compaction and CPU coupling by managing indexes separately from values? Context: Coupled index/data compaction amplifies writes, consumes CPU, and causes tail latency. Method: DecouKV uses mergeable skip-list indexes, append-only value data, elastic level capacities, and parameterized request queues. Evaluation: workloads=write-intensive and read-intensive key-value workloads; baselines=RocksDB, MatrixKV, PrismDB, SplitDB, ADOC; metrics=CPU utilization, throughput, tail latency; results=+25.4–32.3% CPU utilization; 2.3–4.9x write throughput; 74.3–91.4% lower tail; 1.2–2.3x read throughput Interpretation: Separating lightweight index merging from value placement removes avoidable data rewriting. Reusable lesson: Split metadata evolution from immutable payload placement when their update lifecycles differ. Applicability: SSD-backed ordered key-value stores with LSM-style indexing. Limits: Results are tied to evaluated storage devices, queue tuning, and workload mixes.