On Wed, Jul 20, 2016 at 11:16 PM, Mattias Barthel <mbart...@accedian.com> wrote: > Hello, > > I am using the HW timestamp all RX packets option in the I350 for my > special application. > There is a requirement to keep the HW timestamping clock intact if the link > goes down. > Now, if the link goes down, the IGB watchdog checks the TX ring and of > there are some used descriptors in it, the entire adapter is reset.
The problem is that there is no other way to flush out the Tx FIFOs on the device other than resetting it. That is the reason for resetting the interface if there are Tx frames still on the ring. > I am suggesting to just clean the TX ring in question of this occurs. Do > you have any strong recommendations against this? If you don't reset the ring what you run the risk of is a data corruption and/or Tx hang when the link comes back up. - Alex ------------------------------------------------------------------------------ What NetFlow Analyzer can do for you? Monitors network bandwidth and traffic patterns at an interface-level. Reveals which users, apps, and protocols are consuming the most bandwidth. Provides multi-vendor support for NetFlow, J-Flow, sFlow and other flows. Make informed decisions using capacity planning reports.http://sdm.link/zohodev2dev _______________________________________________ E1000-devel mailing list E1000-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/e1000-devel To learn more about Intel® Ethernet, visit http://communities.intel.com/community/wired