From 600adc18eba823f9fd8ed5fec8b04f11dddf3884 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 9 Jan 2014 14:12:19 -0800 Subject: net: gro: change GRO overflow strategy GRO layer has a limit of 8 flows being held in GRO list, for performance reason. When a packet comes for a flow not yet in the list, and list is full, we immediately give it to upper stacks, lowering aggregation performance. With TSO auto sizing and FQ packet scheduler, this situation happens more often. This patch changes strategy to simply evict the oldest flow of the list. This works better because of the nature of packet trains for which GRO is efficient. This also has the effect of lowering the GRO latency if many flows are competing. Tested : Used a 40Gbps NIC, with 4 RX queues, and 200 concurrent TCP_STREAM netperf. Before patch, aggregate rate is 11Gbps (while a single flow can reach 30Gbps) After patch, line rate is reached. Signed-off-by: Eric Dumazet Cc: Jerry Chu Cc: Neal Cardwell Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- net/core/dev.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/net/core/dev.c b/net/core/dev.c index ce01847793c0..a8280154c42a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3882,10 +3882,23 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff if (same_flow) goto ok; - if (NAPI_GRO_CB(skb)->flush || napi->gro_count >= MAX_GRO_SKBS) + if (NAPI_GRO_CB(skb)->flush) goto normal; - napi->gro_count++; + if (unlikely(napi->gro_count >= MAX_GRO_SKBS)) { + struct sk_buff *nskb = napi->gro_list; + + /* locate the end of the list to select the 'oldest' flow */ + while (nskb->next) { + pp = &nskb->next; + nskb = *pp; + } + *pp = NULL; + nskb->next = NULL; + napi_gro_complete(nskb); + } else { + napi->gro_count++; + } NAPI_GRO_CB(skb)->count = 1; NAPI_GRO_CB(skb)->age = jiffies; skb_shinfo(skb)->gso_size = skb_gro_len(skb); -- cgit v1.2.3-59-g8ed1b