Hello! > Which should cause more shortages than our method, since X number of > buffers may be queued erroneously. No doubts. > Then why does inserting a "mark_bh" after a kfree_skb alleviate the problem > somewhat? Apparently, it is placebo effect. 8)8) > 1) packet arrives > 2) dest unknown, buffer is freed instead of passing it to netif_rx() > 3) rx ring buff is replenished > > there should never be a buffer failure. Of course. Alexey - : send the line "unsubscribe linux-net" in the body of a message to majordomo@vger.kernel.org
