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]>
