]> 2026-09-08T16:38:29+09:00 Lesson:shiftlock mitigate one sided rdma lock contention via handover a5d67e63 3000 ko RDMA-based distributed storage and transaction systems. Limits: Requires client coordination and recovery for failures; gains depend on contention, network, and lock workload. ShiftLock uses nonblocking direct client-to-client handover inspired by MCS queues, with reader-writer semantics, starvation freedom, CPU efficiency, and fault handling. S3ResearchAgent medium Venue: FAST. Year: 2025. Clients repeatedly fail atomic acquisition of a held lock, inflating tail latency and consuming lock-server inbound IOPS. Verification: official_abstract; confidence=high. 2026-07-16T14:58:03Z 2461238.1236458 ShiftLock: Mitigate One-sided RDMA Lock Contention via Handover. FAST 2025. Explicit ownership transfer replaces remote contention with local waiting and bounded coordination. ShiftLock: Mitigate One-sided RDMA Lock Contention via Handover workloads=RDMA lock microbenchmarks; transaction workloads; baselines=existing one-sided RDMA locks; metrics=goodput; tail latency; transaction goodput; results=up to 3.62x microbenchmark goodput; up to 76.6% lower tail latency; up to 2.85x transaction goodput Can one-sided RDMA locks avoid retry storms and server-NIC IOPS collapse under contention? lab Under high contention, hand work directly to a known successor instead of reopening global competition. Draft 2026-07-18T14:59:05Z 2461240.1243634 2026-07-18T14:59:05Z 2461240.1243634 shiftlock mitigate one sided rdma lock contention via handover a5d67e63 3000 ev_339907610cde434d 2026-07-16T14:58:04Z 2461238.1236574 S3ResearchAgent ShiftLock: Mitigate One-sided RDMA Lock Contention via Handover. FAST 2025. paper Bibliographic paper record. not_recorded shiftlock mitigate one sided rdma lock contention via handover a5d67e63# d9e10139e5fdc6ce3112bc52d94f3efb 3000 verified-content-v1-0098 2026-07-16T18:55:12Z 2461238.2883333 S3ResearchAgent Jian Gao et al., "ShiftLock: Mitigate One-sided RDMA Lock Contention via Handover", FAST 2025. paper Verification: official_abstract; confidence=high. Canonical title: ShiftLock: Mitigate One-sided RDMA Lock Contention via Handover Question: Can one-sided RDMA locks avoid retry storms and server-NIC IOPS collapse under contention? Context: Clients repeatedly fail atomic acquisition of a held lock, inflating tail latency and consuming lock-server inbound IOPS. Method: ShiftLock uses nonblocking direct client-to-client handover inspired by MCS queues, with reader-writer semantics, starvation freedom, CPU efficiency, and fault handling. Evaluation: workloads=RDMA lock microbenchmarks; transaction workloads; baselines=existing one-sided RDMA locks; metrics=goodput; tail latency; transaction goodput; results=up to 3.62x microbenchmark goodput; up to 76.6% lower tail latency; up to 2.85x transaction goodput Interpretation: Explicit ownership transfer replaces remote contention with local waiting and bounded coordination. Reusable lesson: Under high contention, hand work directly to a known successor instead of reopening global competition. Applicability: RDMA-based distributed storage and transaction systems. Limits: Requires client coordination and recovery for failures; gains depend on contention, network, and lock workload. not_recorded shiftlock mitigate one sided rdma lock contention via handover a5d67e63# 1f7c8afcdb6dce0a396d367c06ffb49b 3000 canonical-paper-v2-a5d67e63 2026-07-18T05:37:26Z 2461239.7343287 S3ResearchAgent Jian Gao et al., "ShiftLock: Mitigate One-sided RDMA Lock Contention via Handover", FAST 2025. paper Verification: official_abstract; confidence=medium. Canonical title: ShiftLock: Mitigate One-sided RDMA Lock Contention via Handover Question: Can one-sided RDMA locks avoid retry storms and server-NIC IOPS collapse under contention? Context: Clients repeatedly fail atomic acquisition of a held lock, inflating tail latency and consuming lock-server inbound IOPS. Method: ShiftLock uses nonblocking direct client-to-client handover inspired by MCS queues, with reader-writer semantics, starvation freedom, CPU efficiency, and fault handling. Evaluation: workloads=RDMA lock microbenchmarks; transaction workloads; baselines=existing one-sided RDMA locks; metrics=goodput; tail latency; transaction goodput; results=up to 3.62x microbenchmark goodput; up to 76.6% lower tail latency; up to 2.85x transaction goodput Interpretation: Explicit ownership transfer replaces remote contention with local waiting and bounded coordination. Reusable lesson: Under high contention, hand work directly to a known successor instead of reopening global competition. Applicability: RDMA-based distributed storage and transaction systems. Limits: Requires client coordination and recovery for failures; gains depend on contention, network, and lock workload. official_abstract shiftlock mitigate one sided rdma lock contention via handover a5d67e63# 746b3cd5adf40c1efb5bde9b1cd65628 3000 2026-07-18T14:59:04Z 2461240.1243519 S3ResearchAgent verify_5dfff09e9b1fc1fe9224 partial_source context 보존 원문 객체를 확보했으나 이 일괄 검증에서는 claim-bearing 범위를 재판정하지 않아 결론을 보류함. inconclusive 2d1f69b136a36d6297a7345be75c5656bdc9ca5b43b2363c09108e9942960763 R2-RESTIC:7f893ca5afd2cfb6fe320e9b61063ccc70e75a7a96589420038c8cf338b273be; archive-manifest-sha256=e28171fb69e141ce306d92dfe4b10e6cdc6e81d4fa910c30a846204dbcf8edf8; sha256=2d1f69b136a36d6297a7345be75c5656bdc9ca5b43b2363c09108e9942960763 보존 파일 objects/sha256/2d/2d1f69b136a36d6297a7345be75c5656bdc9ca5b43b2363c09108e9942960763 ev_339907610cde434d dc43c9fa2b845d7168d77c0ad02d8516ebbc30506614ceb5f12a0de663e273ed shiftlock mitigate one sided rdma lock contention via handover a5d67e63# 50b4aaede1132bf33490a2c8d00e1ba5 3000 2026-07-18T14:59:05Z 2461240.1243634 S3ResearchAgent verify_0da1ddf969fbd87123d0 partial_source context 보존 원문 객체를 확보했으나 이 일괄 검증에서는 claim-bearing 범위를 재판정하지 않아 결론을 보류함. inconclusive 2d1f69b136a36d6297a7345be75c5656bdc9ca5b43b2363c09108e9942960763 R2-RESTIC:7f893ca5afd2cfb6fe320e9b61063ccc70e75a7a96589420038c8cf338b273be; archive-manifest-sha256=e28171fb69e141ce306d92dfe4b10e6cdc6e81d4fa910c30a846204dbcf8edf8; sha256=2d1f69b136a36d6297a7345be75c5656bdc9ca5b43b2363c09108e9942960763 보존 파일 objects/sha256/2d/2d1f69b136a36d6297a7345be75c5656bdc9ca5b43b2363c09108e9942960763 verified-content-v1-0098 cfaa4ad7aadf2656be42854cea00c2b41e1c4b8026ab747873d1f0b22a084bf0 shiftlock mitigate one sided rdma lock contention via handover a5d67e63# 3380eadc3eef394f2d5770445c634c38 3000 2026-07-18T14:59:05Z 2461240.1243634 S3ResearchAgent verify_3cddfe10167ddb8aa9b0 partial_source context 보존 원문 객체를 확보했으나 이 일괄 검증에서는 claim-bearing 범위를 재판정하지 않아 결론을 보류함. inconclusive 2d1f69b136a36d6297a7345be75c5656bdc9ca5b43b2363c09108e9942960763 R2-RESTIC:7f893ca5afd2cfb6fe320e9b61063ccc70e75a7a96589420038c8cf338b273be; archive-manifest-sha256=e28171fb69e141ce306d92dfe4b10e6cdc6e81d4fa910c30a846204dbcf8edf8; sha256=2d1f69b136a36d6297a7345be75c5656bdc9ca5b43b2363c09108e9942960763 보존 파일 objects/sha256/2d/2d1f69b136a36d6297a7345be75c5656bdc9ca5b43b2363c09108e9942960763 canonical-paper-v2-a5d67e63 0ed3206b2b3ed38c944e679672b0d4a21f2bfe29eed421389138d16600cd5e3c shiftlock mitigate one sided rdma lock contention via handover a5d67e63# 4b2b5c632f15b91c048af5d1adabedeb