Advanced TCP Metrics
- Martin Moghadam
- Youssef Benarab
PerformanceGuard is able to collect counters regarding TCP/IP sockets. Data may be collected independently on either client sockets or server sockets.
Collection of advanced TCP/IP socket metrics is only supported on Windows operating systems from Windows Vista and onwards. This means that you can't view advanced TCP counters data from computers with earlier Windows versions.
Data Sampling
PerformanceGuard will collect the metrics on a regular basis. The sampling time is controlled by the parameter AdvancedTCPStatInterval. Data is consolidated into a report, one for each report interval (typically every minute). For each metric the minimum and maximum value is collected together with the average. Each of these values is calculated for the reporting interval. If the reporting interval is set to the default value of 1 minute, and the AdvancedTCPStatInterval is set to 10 seconds, the minimum, maximum and average values for each metric will be calculated over 6 samples.
Metrics
The additional metrics are described in the following:
Metric | Description |
---|---|
FastRetran | The number of invocations of the Fast Retransmit algorithm. |
Timeouts | The number of times the retransmit timeout has expired when the retransmission timer backoff multiplier is equal to one. |
BytesRetrans | The number of bytes retransmitted. |
DupAcksIn | The number of duplicate ACKs received. |
SacksRcvd | The number of Selective Acknowledgement (SACK) options received. |
CongSignals | The number of multiplicative downward congestion window adjustments due to all forms of congestion signals, including Fast Retransmit, Explicit Congestion Notification (ECN), and timeouts. This member summarizes all events that invoke the Multiplicative Decrease (MD) portion of Additive Increase Multiplicative Decrease (AIMD) congestion control, and as such is the best indicator of how a congestion windows is being affected by congestion. Note that retransmission timeouts multiplicatively reduce the window implicitly by setting the slow start threshold size, and are included in the value stored in the CongSignals member. In order to minimize spurious congestion indications due to out-of-order segments, the CongSignals member is incremented in association with the Fast Retransmit algorithm. |
PreCongSumCwnd | The sum of the values of the congestion window, in bytes, captured each time a congestion signal is received. |
SampleRtt | The most recent raw network round trip time measurement, in milliseconds, used in calculation of the retransmission timer (RTO). |
MaxRtt | The maximum sampled round trip time in milliseconds. |
MinRtt | The minimum sampled round trip time in milliseconds. |
CurRto | The current value, in milliseconds, of the retransmit timer. |
SpuriousRtoDetections | The number of acknowledgments reporting segments that have already been retransmitted due to a Retransmission Timeout. |
More information may be available from Microsoft: TCP_ESTATS_PATH_ROD_v0
Search this documentation
On this page
In this section