속성:Observation
직접 확인한 결과를 적습니다. 원인에 대한 해석은 따로 적습니다.
e
PostgreSQL, MongoDB, Redis에서 기본 Linux 대비 request throughput 최대 53% 향상, 99th-percentile latency 3581ms에서 84ms로 42배 개선을 보고했다. 전문에서는 Redis throughput 7-49% 향상, 99.9th latency 78ms 및 기존 대비 2-20배 개선을 보였다. 구성요소 하나를 끄면 PostgreSQL 7-33%, MongoDB 6-45% 처리량이 감소했다. +
workloads=256 GB production analytics dataset; YCSB without locality; baselines=RocksDB; metrics=ingestion throughput; write amplification; results=4.4× ingest and nearly 4× lower WAF; parity on no-locality YCSB. +
workloads=ETL; stateful serverless workflows; baselines=specialized workflow systems; metrics=recovery correctness; performance; results=Abstract verifies broad support but provides no aggregate numeric result. +
exploiting asymmetric cpu performance for fast startup of subsystem in mobile smart devices c00616ec +
Image subsystem startup time을 최대 78% 줄였다. +
BlackScholes의 virtualization overhead는 0.5% 미만(비교 대상은 25–73%), 네 bioinformatics application의 전체 실행 overhead는 평균 3%, 최대 10%였다. hot plug-in/out은 각각 1.3±0.1초였다. 네 VM이 한 GPU를 공유할 때 idle/sleep 구간에 따라 총 실행시간이 20–53% 줄었다. 한 GPU일 때 평균 대기 25.05초, 두 GPU일 때 4.15초였다. +
workloads=high-latency memory filesystem evaluation summarized by the authors’ institution; baselines=traditional synchronous-memory-access filesystem; metrics=CPU consumption required to reach peak bandwidth and throughput at equal CPU resources; results=EasyIO reduces the CPU needed for peak bandwidth by up to 88% and improves throughput by 1.03–2.3× at the same CPU allocation. Detailed workload and per-configuration tables require the full paper. +
workloads=six application-extension use cases; baselines=native/in-process and isolated extension approaches; metrics=safety and efficiency; results=six use cases demonstrated; exact figures unavailable in abstract +
extmem enabling application aware virtual memory management for data intensive applications 8a6dc0e4 +
workloads=data-intensive applications; names not stated in abstract; baselines=Linux VM and application-specific managers; metrics=performance; framework overhead; deployability; results=no numeric headline stated in official abstract +
f
faasmem improving memory efficiency of serverless computing with memory pool architecture b6ab9eec +
workloads=serverless function workloads; baselines=local-memory serverless deployment; metrics=local memory use; deployment density; p95 latency; results=9.9–79.8% lower average local memory; 108–218% higher density; negligible p95 increase +
workloads=latency-critical and best-effort colocated workloads; baselines=kernel-based core scheduling; metrics=rescheduling latency; overall performance; tail latency; results=sub-microsecond rescheduling; no numeric speedup in accessible primary abstract +
workloads=diverse kernel extensions and end-to-end applications; baselines=eBPF and existing extension mechanisms; metrics=performance; expressiveness; safety overhead; results=qualitative significant benefit; no numeric headline verified +
workloads=multiple mobile-sized billion-parameter LLMs and one real application; baselines=mobile CPU/GPU execution; metrics=prefill speed, energy, end-to-end latency; results=22.4x average prefill speedup; 30.7x average energy saving; up to 32.8x end-to-end +
workloads=Linux kernel probe sites; baselines=standard Kprobe; prior optimized Kprobe; metrics=probe cost; kernel-code coverage; results=10x probe performance; 96% coverage vs about 80% +
workloads=prefetch policies reproduced from prior work; baselines=equivalent native-kernel policies; metrics=runtime overhead; prefetch effectiveness; results=negligible framework overhead +
workloads=6,594 traces; 14 datasets; baselines=optimized LRU; state-of-the-art eviction algorithms; metrics=miss ratio; throughput; results=Best mean miss ratio on 10/14 datasets; 6× throughput vs 16-thread LRU. +
공개된 공식 초록 범위에서는 정량 결과를 확인할 수 없다. +
workloads=diverse cloud applications; runtime I/O traces; real programmable SSD board; baselines=state-of-the-art storage sharing approaches; metrics=storage utilization; I/O tail latency; SLO impact; results=up to 1.4x utilization; 1.5x lower average tail latency +
workloads=common memory-intensive benchmarks; baselines=Tiering-0.8; TPP; MEMTIS; metrics=application performance; profiling overhead; migration efficiency; results=32% average over Tiering-0.8; 23% over TPP; 27% over MEMTIS +
following the data not the function rethinking function orchestration in serverless computing 5edeca75 +
workloads=complex serverless workflows; baselines=commercial serverless platforms; open-source platforms; metrics=function interaction latency; data-exchange latency; scalability; results=Orders-of-magnitude latency reduction; exact figure not abstract-verified. +
FIO random write에서 HPB 대비 GC 없을 때 최대 78%, GC 있을 때 최대 70% 향상.
SQLite transaction latency는 HPB 대비 GC 없을 때 최대 39%, GC 발생 시 최대 88% 감소.
모바일 trace workload에서 충분한 내부 DRAM을 가진 이상적 UFS와 평균 성능 차이가 4%에 불과. +