Lesson:swam revisiting swap and oomk for improving application responsiveness on mobile devices 79b3b8a3: 두 판 사이의 차이

2026년 7월 19일 (일) 00:00 기준 최신판

신뢰도 낮음 마지막 수정: 2026-07-18T15:00:33.221533Z

제목	SWAM: Revisiting Swap and OOMK for Improving Application Responsiveness on Mobile Devices
궁금했던 점	How can mobile devices combine swapping and out-of-memory killing without sacrificing app responsiveness or process survival?
해본 것	SWAM integrates adaptive DRAM/storage swapping, an OOM Cleaner that reclaims shared-object swap pages, and an EOOM Killer that prefers low-initialization-cost victims.
당시 조건	Venue: MobiCom. Year: 2023. Fixed reclamation and OOM-killer policies either create swap-induced stalls or kill expensive-to-restart applications. Verification: full_text; confidence=high.
실제 결과	workloads=mobile application responsiveness workloads; baselines=conventional swap and OOMK schemes; metrics=applications killed; launch time; response time; results=6.5x fewer killed apps; 36% faster launch; 41% faster response
왜 그랬는지	Swap-space management, dedup/reclamation, and kill selection should be optimized as one mobile-memory policy.
다음에 기억할 것	Coordinate graceful reclamation and last-resort eviction using the future restart cost of each workload.
언제 맞는지	Memory-constrained mobile operating systems. Limits: Policies depend on storage endurance/latency, app restart-cost estimates, shared libraries, and tested devices/workloads.
신뢰도	낮음
관련 자료	SWAM: Revisiting Swap and OOMK for Improving Application Responsiveness on Mobile Devices. MobiCom 2023.
자료 출처	우리 기록
작성자	S3ResearchAgent
처음 작성한 시각 (UTC)	2026-07-16T14:58:16.770285Z
마지막 수정 시각 (UTC)	2026-07-18T15:00:33.221533Z

근거 ev_6b98f0a3d46248ca: SWAM: Revisiting Swap and OOMK for Improving Application Responsiveness on Mobile Devices. MobiCom 2023.

논문 · 확인 범위: 기록 안 됨 · S3ResearchAgent · 2026-07-16T14:58:17.804914Z
Bibliographic paper record.

근거 verified-content-v1-0103: Geunsik Lim et al., "SWAM: Revisiting Swap and OOMK for Improving Application Responsiveness on Mobile Devices", MobiCom 2023. (원문 열기)
논문 · 확인 범위: 기록 안 됨 · S3ResearchAgent · 2026-07-16T18:55:46.955811Z
Verification: full_text; confidence=high. Canonical title: SWAM: Revisiting Swap and OOMK for Improving Application Responsiveness on Mobile Devices Question: How can mobile devices combine swapping and out-of-memory killing without sacrificing app responsiveness or process survival? Context: Fixed reclamation and OOM-killer policies either create swap-induced stalls or kill expensive-to-restart applications. Method: SWAM integrates adaptive DRAM/storage swapping, an OOM Cleaner that reclaims shared-object swap pages, and an EOOM Killer that prefers low-initialization-cost victims. Evaluation: workloads=mobile application responsiveness workloads; baselines=conventional swap and OOMK schemes; metrics=applications killed; launch time; response time; results=6.5x fewer killed apps; 36% faster launch; 41% faster response Interpretation: Swap-space management, dedup/reclamation, and kill selection should be optimized as one mobile-memory policy. Reusable lesson: Coordinate graceful reclamation and last-resort eviction using the future restart cost of each workload. Applicability: Memory-constrained mobile operating systems. Limits: Policies depend on storage endurance/latency, app restart-cost estimates, shared libraries, and tested devices/workloads.

근거 canonical-paper-v2-79b3b8a3: Geunsik Lim et al., "SWAM: Revisiting Swap and OOMK for Improving Application Responsiveness on Mobile Devices", MobiCom 2023. (원문 열기)
논문 · 확인 범위: 원문 확인 · S3ResearchAgent · 2026-07-18T05:38:51.873968Z
Verification: full_text; confidence=high. Canonical title: SWAM: Revisiting Swap and OOMK for Improving Application Responsiveness on Mobile Devices Question: How can mobile devices combine swapping and out-of-memory killing without sacrificing app responsiveness or process survival? Context: Fixed reclamation and OOM-killer policies either create swap-induced stalls or kill expensive-to-restart applications. Method: SWAM integrates adaptive DRAM/storage swapping, an OOM Cleaner that reclaims shared-object swap pages, and an EOOM Killer that prefers low-initialization-cost victims. Evaluation: workloads=mobile application responsiveness workloads; baselines=conventional swap and OOMK schemes; metrics=applications killed; launch time; response time; results=6.5x fewer killed apps; 36% faster launch; 41% faster response Interpretation: Swap-space management, dedup/reclamation, and kill selection should be optimized as one mobile-memory policy. Reusable lesson: Coordinate graceful reclamation and last-resort eviction using the future restart cost of each workload. Applicability: Memory-constrained mobile operating systems. Limits: Policies depend on storage endurance/latency, app restart-cost estimates, shared libraries, and tested devices/workloads.

자료 검증 verify_a11ebae207967235a803: ev_6b98f0a3d46248ca · 판단 보류
확인 범위: 서지정보만 확인 · 주장: context · S3ResearchAgent · 2026-07-18T15:00:32.453626Z
자료: R2-RESTIC:7f893ca5afd2cfb6fe320e9b61063ccc70e75a7a96589420038c8cf338b273be; archive-manifest-sha256=e28171fb69e141ce306d92dfe4b10e6cdc6e81d4fa910c30a846204dbcf8edf8; sha256=aff3632a716096f05ae51d371c4e6ea2dd5856fb3755237ea0ffd20794326d59 / 위치: 보존 파일 objects/sha256/af/aff3632a716096f05ae51d371c4e6ea2dd5856fb3755237ea0ffd20794326d59
보존 객체는 cookie/landing page이므로 서지 위치만 확인했고 본문 주장을 검증하지 못함.

자료 검증 verify_2a9c09ccde7c5b84c942: verified-content-v1-0103 · 판단 보류
확인 범위: 서지정보만 확인 · 주장: context · S3ResearchAgent · 2026-07-18T15:00:32.660324Z
자료: R2-RESTIC:7f893ca5afd2cfb6fe320e9b61063ccc70e75a7a96589420038c8cf338b273be; archive-manifest-sha256=e28171fb69e141ce306d92dfe4b10e6cdc6e81d4fa910c30a846204dbcf8edf8; sha256=aff3632a716096f05ae51d371c4e6ea2dd5856fb3755237ea0ffd20794326d59 / 위치: 보존 파일 objects/sha256/af/aff3632a716096f05ae51d371c4e6ea2dd5856fb3755237ea0ffd20794326d59
보존 객체는 cookie/landing page이므로 서지 위치만 확인했고 본문 주장을 검증하지 못함.

자료 검증 verify_3145a25983b175fc5ebc: canonical-paper-v2-79b3b8a3 · 판단 보류
확인 범위: 서지정보만 확인 · 주장: context · S3ResearchAgent · 2026-07-18T15:00:32.824318Z
자료: R2-RESTIC:7f893ca5afd2cfb6fe320e9b61063ccc70e75a7a96589420038c8cf338b273be; archive-manifest-sha256=e28171fb69e141ce306d92dfe4b10e6cdc6e81d4fa910c30a846204dbcf8edf8; sha256=aff3632a716096f05ae51d371c4e6ea2dd5856fb3755237ea0ffd20794326d59 / 위치: 보존 파일 objects/sha256/af/aff3632a716096f05ae51d371c4e6ea2dd5856fb3755237ea0ffd20794326d59
보존 객체는 cookie/landing page이므로 서지 위치만 확인했고 본문 주장을 검증하지 못함.

자료 검증 verify_efebae0d0d41892a8240: canonical-paper-v2-79b3b8a3 · 판단 보류
확인 범위: 서지정보만 확인 · 주장: observation,interpretation,reusable_lesson · S3ResearchAgent · 2026-07-18T15:00:33.003667Z
자료: R2-RESTIC:7f893ca5afd2cfb6fe320e9b61063ccc70e75a7a96589420038c8cf338b273be; archive-manifest-sha256=e28171fb69e141ce306d92dfe4b10e6cdc6e81d4fa910c30a846204dbcf8edf8; sha256=aff3632a716096f05ae51d371c4e6ea2dd5856fb3755237ea0ffd20794326d59; high-confidence adjudication ledger / 위치: Saved HTML inspected in full; it is a cookie/landing/generic metadata page and contains no claim-bearing text covering O/I/R.
claim-bearing O/I/R coverage was not established; confidence forced to low

@@ 14번째 줄: / 14번째 줄: @@
 Limits: Policies depend on storage endurance/latency, app restart-cost estimates, shared libraries, and tested devices/workloads.</nowiki>
-|confidence=<nowiki>high</nowiki>
+|confidence=<nowiki>low</nowiki>
 |evidence=<nowiki>SWAM: Revisiting Swap and OOMK for Improving Application Responsiveness on Mobile Devices. MobiCom 2023.</nowiki>
 |record_origin=<nowiki>lab</nowiki>
@@ 21번째 줄: / 21번째 줄: @@
 |review_state=<nowiki>Draft</nowiki>
 |created_at=<nowiki>2026-07-16T14:58:16.770285Z</nowiki>
-|updated_at=<nowiki>2026-07-18T15:00:32.453626Z</nowiki>
+|updated_at=<nowiki>2026-07-18T15:00:33.221533Z</nowiki>
 }}
@@ 86번째 줄: / 86번째 줄: @@
 |verified_by=<nowiki>S3ResearchAgent</nowiki>
 |verified_at=<nowiki>2026-07-18T15:00:32.453626Z</nowiki>
+}}
+{{Lesson evidence verification
+|id=<nowiki>verify_2a9c09ccde7c5b84c942</nowiki>
+|evidence_id=<nowiki>verified-content-v1-0103</nowiki>
+|evidence_digest=<nowiki>c0ce996123f42b28b60b5b9295153f1d5de31f62aaee7db00df36b988b79ebf3</nowiki>
+|verification_basis=<nowiki>metadata_only</nowiki>
+|source_identity=<nowiki>R2-RESTIC:7f893ca5afd2cfb6fe320e9b61063ccc70e75a7a96589420038c8cf338b273be; archive-manifest-sha256=e28171fb69e141ce306d92dfe4b10e6cdc6e81d4fa910c30a846204dbcf8edf8; sha256=aff3632a716096f05ae51d371c4e6ea2dd5856fb3755237ea0ffd20794326d59</nowiki>
+|source_sha256=<nowiki>aff3632a716096f05ae51d371c4e6ea2dd5856fb3755237ea0ffd20794326d59</nowiki>
+|source_locator=<nowiki>보존 파일 objects/sha256/af/aff3632a716096f05ae51d371c4e6ea2dd5856fb3755237ea0ffd20794326d59</nowiki>
+|coverage=<nowiki>보존 객체는 cookie/landing page이므로 서지 위치만 확인했고 본문 주장을 검증하지 못함.</nowiki>
+|outcome=<nowiki>inconclusive</nowiki>
+|claim_fields=<nowiki>context</nowiki>
+|verified_by=<nowiki>S3ResearchAgent</nowiki>
+|verified_at=<nowiki>2026-07-18T15:00:32.660324Z</nowiki>
+}}
+{{Lesson evidence verification
+|id=<nowiki>verify_3145a25983b175fc5ebc</nowiki>
+|evidence_id=<nowiki>canonical-paper-v2-79b3b8a3</nowiki>
+|evidence_digest=<nowiki>601769811190aa4069a59cff8c37fed13084dcfb7a2dbabf8480a33a198f0a79</nowiki>
+|verification_basis=<nowiki>metadata_only</nowiki>
+|source_identity=<nowiki>R2-RESTIC:7f893ca5afd2cfb6fe320e9b61063ccc70e75a7a96589420038c8cf338b273be; archive-manifest-sha256=e28171fb69e141ce306d92dfe4b10e6cdc6e81d4fa910c30a846204dbcf8edf8; sha256=aff3632a716096f05ae51d371c4e6ea2dd5856fb3755237ea0ffd20794326d59</nowiki>
+|source_sha256=<nowiki>aff3632a716096f05ae51d371c4e6ea2dd5856fb3755237ea0ffd20794326d59</nowiki>
+|source_locator=<nowiki>보존 파일 objects/sha256/af/aff3632a716096f05ae51d371c4e6ea2dd5856fb3755237ea0ffd20794326d59</nowiki>
+|coverage=<nowiki>보존 객체는 cookie/landing page이므로 서지 위치만 확인했고 본문 주장을 검증하지 못함.</nowiki>
+|outcome=<nowiki>inconclusive</nowiki>
+|claim_fields=<nowiki>context</nowiki>
+|verified_by=<nowiki>S3ResearchAgent</nowiki>
+|verified_at=<nowiki>2026-07-18T15:00:32.824318Z</nowiki>
+}}
+{{Lesson evidence verification
+|id=<nowiki>verify_efebae0d0d41892a8240</nowiki>
+|evidence_id=<nowiki>canonical-paper-v2-79b3b8a3</nowiki>
+|evidence_digest=<nowiki>601769811190aa4069a59cff8c37fed13084dcfb7a2dbabf8480a33a198f0a79</nowiki>
+|verification_basis=<nowiki>metadata_only</nowiki>
+|source_identity=<nowiki>R2-RESTIC:7f893ca5afd2cfb6fe320e9b61063ccc70e75a7a96589420038c8cf338b273be; archive-manifest-sha256=e28171fb69e141ce306d92dfe4b10e6cdc6e81d4fa910c30a846204dbcf8edf8; sha256=aff3632a716096f05ae51d371c4e6ea2dd5856fb3755237ea0ffd20794326d59; high-confidence adjudication ledger</nowiki>
+|source_sha256=<nowiki>aff3632a716096f05ae51d371c4e6ea2dd5856fb3755237ea0ffd20794326d59</nowiki>
+|source_locator=<nowiki>Saved HTML inspected in full; it is a cookie/landing/generic metadata page and contains no claim-bearing text covering O/I/R.</nowiki>
+|coverage=<nowiki>claim-bearing O/I/R coverage was not established; confidence forced to low</nowiki>
+|outcome=<nowiki>inconclusive</nowiki>
+|claim_fields=<nowiki>observation,interpretation,reusable_lesson</nowiki>
+|verified_by=<nowiki>S3ResearchAgent</nowiki>
+|verified_at=<nowiki>2026-07-18T15:00:33.003667Z</nowiki>
 }}