Hi Pieter, > One question: 46956 removes the clib_max() ratchet in > clib_time_verify_frequency(), but the worker offset clamp in > vlib_worker_thread_barrier_check() stays. Baldur flagged both. Is the slewing > expected to keep each thread close enough to main that the barrier clamp > never engages, or does that need changing too?
I think we still need the barrier clamp to ensure time monotonicity because each worker slews toward wall clock time independently, however they should eventually converge and the barrier clamp should not cause error accumulation. At least it is the intent :) Best ben
-=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#27228): https://lists.fd.io/g/vpp-dev/message/27228 Mute This Topic: https://lists.fd.io/mt/121360743/21656 Group Owner: [email protected] Unsubscribe: https://lists.fd.io/g/vpp-dev/leave/14379924/21656/631435203/xyzzy [[email protected]] -=-=-=-=-=-=-=-=-=-=-=-
