In this section
This section describes a number of time stamp features supported by the SmartNICs.
The time stamp clock
A SmartNIC maintains a time stamp clock, which is used for precise time-stamping of frames
received on the Ethernet ports of the SmartNIC. Received frames are time-stamped either when the first byte is received or
when the last
byte is received depending on the setting of the
configuration parameter in the
ntservice.ini file (see Specifying the Time Stamp Method). This setting also determines if the first
or the last byte of a frame is transmitted according to the time stamp in the packet
Note: Start-of-frame time-stamping does not apply to NT40E3-4-PTP
SmartNICs running on the capture/replay
image, to NT40A01-4×10/1-SLB SmartNICs nor to the Intel® Programmable Acceleration Card with Intel® Arria®
10 GX FPGA.
Note: Using different settings of
TimestampMethod for capturing data and later for transmitting the
same data, will result in inaccuracies.
The time stamp clock is also used for time-stamping statistics data blocks transferred to
the host memory. This enables the host application to correlate received frame data with
The time stamp clock is driven by a local clock oscillator, and the internal
resolution is 1 ns. The time stamp clock can either be free-running or be
adjusted according to another reference clock.
Time stamps in packet descriptors
The standard packet descriptor, the dynamic packet descriptors and the PCAP packet
descriptor contain the time stamp (see DN-1128). The time stamp in the standard packet descriptor can be retrieved using the
NT_NET_GET_PKT_TIMESTAMP macro (see DN-0449).