IX: A Protected Dataplane Operating System for High Throughput and Low Latency

By A. Belay, George Prekas, A. Klimovic, Samuel Grossman, Christos Kozyrakis, Edouard Bugnion. USENIX Symposium on Operating Systems Design and Implementation, 2014

485 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/567f633bc74ac40364a1961fad1b7fe80605b815

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Datacenter RPCs can be General and Fast (2018, background): “Full- edged TCP/IP stacks such as IX and mTCP achieve much lower bandwidth—less than 10 Gbps with one core [16].”
The RAMCloud Storage System (2015, background): “Other examples include IX [Belay et al. 2014], a new operating system designed for high throughput and low latency; Arrakis [Peter et al. 2014], an operating system that supports kernel bypass for many I/O operations; and Herd [Kalia et al. 2014], a key-value cache that uses RDMA to improve latency…”
Accelerometer: Understanding Acceleration Opportunities for Data Center Overheads at Hyperscale (2020, background): “Software/hardware optimizations [28, 29, 32, 41, 44, 60, 73, 75, 116] that reduce scheduler latency (e.”
SoftSKU: Optimizing Server Architectures for Microservice Diversity @Scale (2019, background): “Software/hardware optimizations [54–62] that reduce context switch latency or counts might considerably improve Cache performance.”
Heracles: Improving resource efficiency at scale (2015, background): “optimizing various aspects of latency-critical workloads, including energy proportionality [53, 54, 47, 46, 34], networking performance [35, 8], and hardware-acceleration [41, 63, 72].”
Arrakis (2014, methodology): “Similarly, IX [Belay et al. 2014] implements a custom, per-application network stack in a protected domain accessed with batched system calls.”