-
TraceUpscaler: Upscaling Traces to Evaluate Systems at High Load
-
Kerveros: Efficient and Scalable Cloud Admission Control
-
SplitRPC: A {Control + Data} Path Splitting RPC Stack for ML Inference Serving
-
Metastable Failures in the Wild
-
Overflowing Emerging Neural Network Inference Tasks from the GPU to the CPU on Heterogeneous Servers
-
tprof: Performance profiling via structural aggregation and automated analysis of distributed systems traces
-
Metastable failures in distributed systems
-
TraceSplitter: A New Paradigm for Downscaling Traces
-
Peafowl: In-application CPU scheduling to reduce power consumption of in-memory key-value stores
-
The Fast and The Frugal: Tail Latency Aware Provisioning for Coping with Load Variations
-
BurScale: Using Burstable Instances for Cost-Effective Autoscaling in the Public Cloud
-
RobinHood: Tail Latency Aware Caching — Dynamic Reallocation from Cache-Rich to Cache-Poor
-
WorkloadCompactor: Reducing Datacenter Cost While Providing Tail Latency SLO Guarantees
-
Thesis: Meeting tail latency SLOs in shared networked storage
-
SNC-Meister: Admitting More Tenants with Tail Latency SLOs
-
TetriSched: Global Rescheduling with Adaptive Plan-ahead in Dynamic Heterogeneous ClustersBest student paper award at EuroSys 2016 [pdf]
-
PriorityMeister: Tail Latency QoS for Shared Networked Storage
-
TetriSched: Space-Time Scheduling for Heterogeneous Datacenters
-
IOFlow: A Software-Defined Storage Architecture
-
SOFTScale: Stealing Opportunistically For Transient Scaling
-
Saving Cash by Using Less Cache