According to David, proper accounting and queueing (at all levels, not just TCP sockets) is more important than trying to skim a bunch of cycles by avoiding TX interrupts. Having an event to free the SKB is absolutely essential for the stack to operate correctly. This series tries to enable tx interrupt for virtio-net. The idea is simple: enable tx interrupt and schedule a tx napi to free old xmit skbs. Several notes: - Tx interrupt storm avoidance when queue is about to be full is kept. Since we may enable callbacks in both ndo_start_xmit() and tx napi, patch 1 adds a check to make sure used event never go back. This will let the napi not enable the callbacks wrongly after delayed callbacks was used. - For bulk dequeuing, there's no need to enable tx interrupt for each packet. The last patch only enable tx interrupt for the final skb in the chain through xmit_more and a new helper to publish current avail idx as used event. This series fixes several issues of original rfc pointed out by Michael. Smoking test is done, and will do complete netperf test. Send the seires for early review. Thanks Jason Wang (6): virtio: make sure used event never go backwards virtio: introduce virtio_enable_cb_avail() virtio-net: small optimization on free_old_xmit_skbs() virtio-net: return the number of packets sent in free_old_xmit_skbs() virtio-net: enable tx interrupt virtio-net: enable tx interrupt only for the final skb in the chain drivers/net/virtio_net.c | 125 ++++++++++++++++++++++++++++++------------ drivers/virtio/virtio_ring.c | 25 ++++++++- include/linux/virtio.h | 2 + 3 files changed, 115 insertions(+), 37 deletions(-) _______________________________________________ Virtualization mailing list Virtualization@xxxxxxxxxxxxxxxxxxxxxxxxxx https://lists.linuxfoundation.org/mailman/listinfo/virtualization
