• Corpus ID: 246607913

Direct Telemetry Access

@article{Langlet2022DirectTA,
  title={Direct Telemetry Access},
  author={Jonatan Langlet and Ran Ben Basat and Sivaramakrishnan Ramanathan and G. Oliaro and Michael Mitzenmacher and Minlan Yu and Gianni Antichi},
  journal={ArXiv},
  year={2022},
  volume={abs/2202.02270}
}
The emergence of programmable switches allows operators to collect a vast amount of fine-grained telemetry data in real time. However, consolidating the telemetry reports at centralized collectors to gain a network-wide view poses an im-mense challenge. The received data has to be transported from the switches, parsed, manipulated, and inserted in queryable data structures. As the network scales, this requires excessive CPU processing. RDMA is a transport protocol that bypasses the CPU and… 

References

SHOWING 1-10 OF 81 REFERENCES

Network telemetry: towards a top-down approach

TLDR
This paper argues for a top-down approach to network telemetry, which should provide a high-level declarative abstraction for operators to specify measurement queries, programmable measurement primitives at switches and hosts, and a runtime that translates the high- level queries into low-level API calls.

Sonata: query-driven streaming network telemetry

TLDR
Sonata provides a declarative interface to express queries for a wide range of common telemetry tasks and reduces the workload for the stream processor by as much as seven orders of magnitude compared to existing telemetry systems.

StRoM: smart remote memory

TLDR
StRoM is presented, a programmable, FPGA-based RoCE v2 NIC supporting the offloading of application level kernels that bypasses the CPU entirely and extends the semantics of RDMA to enable multi-step data access operations and in-network processing ofRDMA streams.

BTrDB: Optimizing Storage System Design for Timeseries Processing

TLDR
A novel abstraction for telemetry timeseries data and a data structure for providing this abstraction: a time-partitioning version-annotated copy-on-write tree that is shown to outperform existing solutions and represent a significant advance in the development of technology for the Internet of Things.

Programmable Event Detection for In-Band Network Telemetry

TLDR
This paper develops a programmable INT event detection mechanism in P4 that allows customization of which events to report to the monitoring system, on a per-flow basis, from the control plane, and significantly reduces the network overhead and stream processor load due to effective event pre-filtering inside the switch data plane.

Flow Event Telemetry on Programmable Data Plane

TLDR
This paper presents NetSeer, a flow event telemetry (FET) monitor which aims to discover and record all performance-critical data plane events, e.g. packet drops, congestion, path change, and packet pause, and can reduce NPA mitigation time by 61%-99% with only 0.01% overhead of monitoring traffic.

Stroboscope: Declarative Network Monitoring on a Budget

TLDR
Stroboscope is presented, a system that enables finegrained monitoring of any traffic flow by instructing routers to mirror millisecond-long traffic slices in a programmatic way and scales well: it computes schedules for large networks and query sizes in few seconds, and produces a number of mirroring rules well within the limits of current routers.

PacketScope: Monitoring the Packet Lifecycle Inside a Switch

TLDR
PacketScope is a network telemetry system that lets network operators peek inside network switches to ask a suite of useful queries about how switches modify, drop, delay, and forward packets, and gives network operators an intuitive and powerful Spark-like dataflow language to express these queries.

Turboflow: information rich flow record generation on commodity switches

TLDR
The design, implementation, and evaluation of TurboFlow are presented, a flow record generator for programmable switches that does not compromise on either cost or information richness and can support multi-terabit workloads on readily available commodity switches to enable information rich monitoring with high coverage.

Language-Directed Hardware Design for Network Performance Monitoring

TLDR
A performance query language, Marple, modeled on familiar functional constructs like map, filter, groupby, and zip is presented, backed by a new programmable key-value store primitive on switch hardware.
...