DPDK usage discussions
 help / color / mirror / Atom feed
* [E810 XXVDA4] timesync_read_tx_timestamp and timesync_read_rx_timestamp
@ 2024-10-11 17:32 Carlos de Souza Moraes Neto
  0 siblings, 0 replies; only message in thread
From: Carlos de Souza Moraes Neto @ 2024-10-11 17:32 UTC (permalink / raw)
  To: users

Hi,
We have implemented a PTP peer-to-peer client running on the main core, with Lcores handling packet transmission and reception. However, we are encountering issues using the card's clock:
1. timesync_read_rx_timestamp: What should be the correct index value to use in this function?
2. timesync_read_tx_timestamp: This function consistently returns incorrect timestamps. Could it be registering the timestamp of a packet from another core if they are sending packets on a different port or queue of the same card?
3. rte_eth_timesync_read_time and rte_eth_timesync_adjust_time: Is there any inherent delay between calling read_time after adjust_time or write_time? Should we set a initial time when initializing dpdk?

Thank you for your help.

Best regards,
Carlos


^ permalink raw reply	[flat|nested] only message in thread

only message in thread, other threads:[~2024-10-11 17:51 UTC | newest]

Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2024-10-11 17:32 [E810 XXVDA4] timesync_read_tx_timestamp and timesync_read_rx_timestamp Carlos de Souza Moraes Neto

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).