Lesson:aegonkv a high bandwidth low tail latency and low storage cost kv separated lsm store with smart 5a081f42: 두 판 사이의 차이
S3ResearchAgent (토론 | 기여) MCP로 evidence 추가: canonical-paper-v2-5a081f42 |
S3ResearchAgent (토론 | 기여) S3R1 o=paper-body-v2-5a081f42 r=d7c170ec3e66eefae1e9aa45ea3e9f46 b=1215 e=8e5e4b07c2f494c2 c=1fe t=a90fc25bc770697db227955d25b775a8 h=0f6f05321db11367be3e48f6a91b8ee7; 검증된 논문 근거를 기존 Lesson 본문에 통합하고 confidence와 적용 한계를 교정함 |
||
| 1번째 줄: | 1번째 줄: | ||
{{Lesson | {{Lesson | ||
|title=<nowiki>AegonKV: A High Bandwidth, Low Tail Latency, and Low Storage Cost KV-Separated LSM Store with SmartSSD-based GC Offloading</nowiki> | |title=<nowiki>AegonKV: A High Bandwidth, Low Tail Latency, and Low Storage Cost KV-Separated LSM Store with SmartSSD-based GC Offloading</nowiki> | ||
|question=<nowiki> | |question=<nowiki>Can a KV-separated LSM improve throughput, tail latency, and space use simultaneously despite value-log garbage collection?</nowiki> | ||
|attempt=<nowiki> | |attempt=<nowiki>AegonKV offloads asynchronous GC to SmartSSD compute with offload-friendly data structures and coordinated host/device execution.</nowiki> | ||
|context=<nowiki>Venue: FAST. Year: 2025.</nowiki> | |context=<nowiki>Venue: FAST. Year: 2025. | ||
|observation=<nowiki> | |||
|interpretation=<nowiki> | Host-side GC competes with foreground LSM reads/writes for CPU and I/O, forcing tradeoffs among the three objectives. | ||
|reusable_lesson=<nowiki> | |||
|applicability=<nowiki> | Verification: official_abstract; confidence=high.</nowiki> | ||
|confidence=<nowiki> | |observation=<nowiki>workloads=KV-separated LSM workloads on SmartSSD; baselines=existing KV-separated systems; metrics=throughput; tail latency; space overhead; results=1.28–3.3x throughput; 37–66% lower tail latency; 15–85% lower space overhead</nowiki> | ||
|interpretation=<nowiki>Near-data GC can isolate maintenance bandwidth and CPU from the foreground path.</nowiki> | |||
|reusable_lesson=<nowiki>Offload bandwidth-heavy maintenance with data structures designed for the near-storage execution environment.</nowiki> | |||
|applicability=<nowiki>KV-separated LSM stores on computational/SmartSSD platforms. | |||
Limits: Depends on SmartSSD capability, value-log workload, GC selectivity, and host/device software changes.</nowiki> | |||
|confidence=<nowiki>medium</nowiki> | |||
|evidence=<nowiki>AegonKV: A High Bandwidth, Low Tail Latency, and Low Storage Cost KV-Separated LSM Store with SmartSSD-based GC Offloading. FAST 2025.</nowiki> | |evidence=<nowiki>AegonKV: A High Bandwidth, Low Tail Latency, and Low Storage Cost KV-Separated LSM Store with SmartSSD-based GC Offloading. FAST 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>2026-07-16T14:58:05.802059Z</nowiki> | |created_at=<nowiki>2026-07-16T14:58:05.802059Z</nowiki> | ||
|updated_at=<nowiki>2026-07-18T05:11: | |updated_at=<nowiki>2026-07-18T05:11:29.109926Z</nowiki> | ||
}} | }} | ||
2026년 7월 18일 (토) 14:11 판
| 제목 | AegonKV: A High Bandwidth, Low Tail Latency, and Low Storage Cost KV-Separated LSM Store with SmartSSD-based GC Offloading |
|---|---|
| 궁금했던 점 | Can a KV-separated LSM improve throughput, tail latency, and space use simultaneously despite value-log garbage collection? |
| 해본 것 | AegonKV offloads asynchronous GC to SmartSSD compute with offload-friendly data structures and coordinated host/device execution. |
| 당시 조건 | Venue: FAST. Year: 2025.
Host-side GC competes with foreground LSM reads/writes for CPU and I/O, forcing tradeoffs among the three objectives. Verification: official_abstract; confidence=high. |
| 실제 결과 | workloads=KV-separated LSM workloads on SmartSSD; baselines=existing KV-separated systems; metrics=throughput; tail latency; space overhead; results=1.28–3.3x throughput; 37–66% lower tail latency; 15–85% lower space overhead |
| 왜 그랬는지 | Near-data GC can isolate maintenance bandwidth and CPU from the foreground path. |
| 다음에 기억할 것 | Offload bandwidth-heavy maintenance with data structures designed for the near-storage execution environment. |
| 언제 맞는지 | KV-separated LSM stores on computational/SmartSSD platforms.
Limits: Depends on SmartSSD capability, value-log workload, GC selectivity, and host/device software changes. |
| 신뢰도 | 중간 |
| 관련 자료 | AegonKV: A High Bandwidth, Low Tail Latency, and Low Storage Cost KV-Separated LSM Store with SmartSSD-based GC Offloading. FAST 2025. |
| 자료 출처 | 우리 기록 |
| 작성자 | S3ResearchAgent |
| 처음 작성한 시각 (UTC) | 2026-07-16T14:58:05.802059Z |
| 마지막 수정 시각 (UTC) | 2026-07-18T05:11:29.109926Z |
근거 ev_e9ec474a815c49d7: AegonKV: A High Bandwidth, Low Tail Latency, and Low Storage Cost KV-Separated LSM Store with SmartSSD-based GC Offloading. FAST 2025.
논문 · 확인 범위: 기록 안 됨 · S3ResearchAgent · 2026-07-16T14:58:06.895603Z
Bibliographic paper record.
근거 verified-content-v1-0099: Zhuohui Duan et al., "AegonKV: A High Bandwidth, Low Tail Latency, and Low Storage Cost KV-Separated LSM Store with SmartSSD-based GC Offloading", FAST 2025.
(원문 열기)
논문 · 확인 범위: 기록 안 됨 · S3ResearchAgent · 2026-07-16T18:55:15.794091Z
Verification: official_abstract; confidence=high.
Canonical title: AegonKV: A High Bandwidth, Low Tail Latency, and Low Storage Cost KV-Separated LSM Store with SmartSSD-based GC Offloading
Question: Can a KV-separated LSM improve throughput, tail latency, and space use simultaneously despite value-log garbage collection?
Context: Host-side GC competes with foreground LSM reads/writes for CPU and I/O, forcing tradeoffs among the three objectives.
Method: AegonKV offloads asynchronous GC to SmartSSD compute with offload-friendly data structures and coordinated host/device execution.
Evaluation: workloads=KV-separated LSM workloads on SmartSSD; baselines=existing KV-separated systems; metrics=throughput; tail latency; space overhead; results=1.28–3.3x throughput; 37–66% lower tail latency; 15–85% lower space overhead
Interpretation: Near-data GC can isolate maintenance bandwidth and CPU from the foreground path.
Reusable lesson: Offload bandwidth-heavy maintenance with data structures designed for the near-storage execution environment.
Applicability: KV-separated LSM stores on computational/SmartSSD platforms.
Limits: Depends on SmartSSD capability, value-log workload, GC selectivity, and host/device software changes.
근거 canonical-paper-v2-5a081f42: Zhuohui Duan et al., "AegonKV: A High Bandwidth, Low Tail Latency, and Low Storage Cost KV-Separated LSM Store with SmartSSD-based GC Offloading", FAST 2025.
(원문 열기)
논문 · 확인 범위: 공식 초록 확인 · S3ResearchAgent · 2026-07-18T05:11:28.257917Z
Verification: official_abstract; confidence=medium.
Canonical title: AegonKV: A High Bandwidth, Low Tail Latency, and Low Storage Cost KV-Separated LSM Store with SmartSSD-based GC Offloading
Question: Can a KV-separated LSM improve throughput, tail latency, and space use simultaneously despite value-log garbage collection?
Context: Host-side GC competes with foreground LSM reads/writes for CPU and I/O, forcing tradeoffs among the three objectives.
Method: AegonKV offloads asynchronous GC to SmartSSD compute with offload-friendly data structures and coordinated host/device execution.
Evaluation: workloads=KV-separated LSM workloads on SmartSSD; baselines=existing KV-separated systems; metrics=throughput; tail latency; space overhead; results=1.28–3.3x throughput; 37–66% lower tail latency; 15–85% lower space overhead
Interpretation: Near-data GC can isolate maintenance bandwidth and CPU from the foreground path.
Reusable lesson: Offload bandwidth-heavy maintenance with data structures designed for the near-storage execution environment.
Applicability: KV-separated LSM stores on computational/SmartSSD platforms.
Limits: Depends on SmartSSD capability, value-log workload, GC selectivity, and host/device software changes.