An Experimental Evaluation of Accurate Scheduling and Hardware Timestamping on NVIDIA ConnectX NICs

Abstract

High-precision packet transmission is becoming increasingly important in deterministic networking applications, including 5G fronthaul and Time-Sensitive Networking (TSN). Recent NVIDIA ConnectX network interface cards (NICs) provide Accurate Scheduling, a hardware-assisted mechanism for transmitting Ethernet frames at designated times, as part of their 5T for 5G feature set. They also provide hardware timestamping for received and transmitted frames. Although these functions are expected to satisfy the stringent timing requirements of 5G fronthaul, little public information is available regarding their timing accuracy and performance characteristics. This paper presents an experimental characterization of the Accurate Scheduling and hardware timestamping capabilities of the NVIDIA ConnectX-7 NIC. Using an FPGA-based measurement platform with deterministic frame generation and nanosecond-resolution timestamping, we first evaluate the precision of the receive and transmit hardware timestamps and then evaluate the transmission timing accuracy of Accurate Scheduling. The experimental results show that the receive and transmit hardware timestamps exhibit a measured variation of approximately $\pm$7-8 ns when compared across independently clocked Ethernet entities. Furthermore, Accurate Scheduling transmits approximately 99% of frames within $\pm$900 ns of the specified transmission time, while occasional outliers of up to approximately 5 us are observed. These results indicate that Accurate Scheduling is well suited for applications with latency requirements on the order of several tens of microseconds, such as 5G fronthaul, whereas its timing accuracy is insufficient for highly deterministic TSN applications, which typically require transmission timing accuracy on the order of several to several tens of nanoseconds.