[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Protocol Action: Network performance measurement for periodic streams to Proposed Standard

The IESG has approved the Internet-Draft 'Network performance 
measurement for periodic streams' <draft-ietf-ippm-npmps-08.txt> 
as a Proposed Standard.  This document is the product of the IP 
Performance Metrics Working Group.  The IESG contact persons are 
Allison Mankin and Scott Bradner.
Technical Summary
The document specifies a metric that introduces packets
with repeating periods and length as a particular model.
It formalizes periodic stream measurement to achieve
comparable results between independent implementations.

As noted in the IPPM framework RFC 2330, this type of metric
has some limitations, such as probing only a limited part of
of the perfomrance spectrum, but it also has strengths, of
which just a few:

* It can be configured to match particular inelastic media flows.

* Measurement of many network impairments (e.g., delay variation,
    consecutive loss, reordering) are sensitive to the sampling
    frequency. When the impairments themselves are time-varying (and
    the variations are somewhat rare, yet important), a constant
    probing frequency may simplify analysis

The specification provides the definition of the metric, and its
analysis, a repeatable algorithm for it, and considerations for
its security. It also specifies how to avoidcongestion
and network synchronization effects that might arise with long
running tests:

  1. The performance sampled may be synchronized with some other
        periodic behavior, or the samples may be anticipated and the
        results manipulated. Unpredictable sampling is preferred.

  2. Active measurements of sufficient volume can cause congestion,
        and periodic sampling might drive congestion-aware senders
        into a synchronized state, producing atypical results.

  The total traffic generated by this or any metric should be
  limited to avoid adverse affects on non-test traffic (random start
  times, choice of packet size, and test duration should be carefully
  considered, for instance).

Working Group Summary
There was good working group consensus on this document and
careful review to ensure a correct specification.

Protocol Quality
The specification was reviewed for the IESG by Allison Mankin.