Thank you for the clarification regarding hardware/NIC timestamp on i210 and ENA.
Does DPDK take a timestamp to facilitate my second measurement, from the packet ring buffer to my application? On Mon, 9 Sept 2024 at 00:07, Dmitry Kozlyuk <[email protected]> wrote: > > 2024-09-08 23:34 (UTC+0100), Dpdk Newbie: > > Hi. I am using Intel (i210) and AWS ENA network interface cards. > > > > I would like to measure the following RX latencies: > > > > 1) NIC to DPDK packet ring buffer > > 2) DPDK packet ring buffer to application via rte_eth_rx_burst. > > > > I don't mind measuring in nanoseconds or CPU cycles. > > > > Unfortunately I cannot find any mention of hardware timestamps. > > > > I found brief references to mbuf containing a timestamp in the dynamic > > fields, but nothing definitive. > > > > Could someone please clarify what the situation is? > > > > Thanks, > > DPDK only provides API to access Rx timestamp if it's available. > Example: https://elixir.bootlin.com/dpdk/v24.07/source/app/test-pmd/util.c#L37 > > Rx timestamp availability depends on the PMD and HW. > Support matrix: https://doc.dpdk.org/guides/nics/overview.html > It seems to be no support for i210 (igb?) or AWS ENA (ena). > >
