On Wed, 23 Nov 2016 09:12:50 -0800 Alexander Duyck <[email protected]> wrote:
> On Wed, Nov 23, 2016 at 8:44 AM, Eric Dumazet <[email protected]> wrote: > > From: Eric Dumazet <[email protected]> > > > > Typical NAPI drivers use napi_consume_skb(skb) at TX completion time. > > This put skb in a percpu special queue, napi_alloc_cache, to get bulk > > frees. > > > > It turns out the queue is not flushed and hits the NAPI_SKB_CACHE_SIZE > > limit quite often, with skbs that were queued hundreds of usec earlier. > > I measured this can take ~6000 nsec to perform one flush. > > > > __kfree_skb_flush() can be called from two points right now : > > > > 1) From net_tx_action(), but only for skbs that were queued to > > sd->completion_queue. > > > > -> Irrelevant for NAPI drivers in normal operation. > > > > 2) From net_rx_action(), but only under high stress or if RPS/RFS has a > > pending action. > > > > This patch changes net_rx_action() to perform the flush in all cases and > > after more urgent operations happened (like kicking remote CPUS for > > RPS/RFS). > > > > Signed-off-by: Eric Dumazet <[email protected]> > > Cc: Jesper Dangaard Brouer <[email protected]> > > Cc: Alexander Duyck <[email protected]> > > --- > > Yeah, we didn't intent the data to be sitting around that long. The > change looks good to me. > > Acked-by: Alexander Duyck <[email protected]> Also looks good to me! Thanks for catching this. Acked-by: Jesper Dangaard Brouer <[email protected]> -- Best regards, Jesper Dangaard Brouer MSc.CS, Principal Kernel Engineer at Red Hat Author of http://www.iptv-analyzer.org LinkedIn: http://www.linkedin.com/in/brouer
