On Wed, Oct 30, 2019 at 11:30:48AM +0800, txfh2007 wrote: > I have been testing OVS-DPDK Rate limit using meter table these days, but > I have found the rate deviation is larger than kernel meter. My test result > is as below:
You didn't mention an OVS version number or commit number. It might be important to make sure that the following commit is part of whatever you're testing. commit 42697ca7757b594cc841d944e43ffc17905e3188 Author: William Tu <u9012...@gmail.com> Date: Fri Apr 19 15:26:41 2019 -0700 dpif-netdev: fix meter at high packet rate. When testing packet rate around 1Mpps with meter enabled, the frequency of hitting meter action becomes much higher, around 30us each time. As a result, the meter's calculation of 'uint32_t delta_t' becomes always 0 and meter action has no effect. This is due to the previous commit 05f9e707e194 divides the delta by 1000, in order to convert to msec granularity. The patch fixes it updating the time when across millisecond boundary. Fixes: 05f9e707e194 ("dpif-netdev: Use microsecond granularity.") Acked-by: Yi-Hung Wei <yihung....@gmail.com> Acked-by: Ilya Maximets <i.maxim...@samsung.com> Signed-off-by: William Tu <u9012...@gmail.com> Signed-off-by: Ben Pfaff <b...@ovn.org> _______________________________________________ dev mailing list d...@openvswitch.org https://mail.openvswitch.org/mailman/listinfo/ovs-dev