summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
authorEric Dumazet <edumazet@google.com>2014-10-13 06:27:47 -0700
committerDavid S. Miller <davem@davemloft.net>2014-10-14 17:16:26 -0400
commit9b462d02d6dd671a9ebdc45caed6fe98a53c0ebe (patch)
tree4bf0fb418ff8aa3760e6fdc46342f77c7c64308d /net/ipv4
parent82b009f9b38e8285987b842f1f13015acf4439db (diff)
tcp: TCP Small Queues and strange attractors
TCP Small queues tries to keep number of packets in qdisc as small as possible, and depends on a tasklet to feed following packets at TX completion time. Choice of tasklet was driven by latencies requirements. Then, TCP stack tries to avoid reorders, by locking flows with outstanding packets in qdisc in a given TX queue. What can happen is that many flows get attracted by a low performing TX queue, and cpu servicing TX completion has to feed packets for all of them, making this cpu 100% busy in softirq mode. This became particularly visible with latest skb->xmit_more support Strategy adopted in this patch is to detect when tcp_wfree() is called from ksoftirqd and let the outstanding queue for this flow being drained before feeding additional packets, so that skb->ooo_okay can be set to allow select_queue() to select the optimal queue : Incoming ACKS are normally handled by different cpus, so this patch gives more chance for these cpus to take over the burden of feeding qdisc with future packets. Tested: lpaa23:~# ./super_netperf 1400 --google-pacing-rate 3028000 -H lpaa24 -l 3600 & lpaa23:~# sar -n DEV 1 10 | grep eth1 06:16:18 AM eth1 595448.00 1190564.00 38381.09 1760253.12 0.00 0.00 1.00 06:16:19 AM eth1 594858.00 1189686.00 38340.76 1758952.72 0.00 0.00 0.00 06:16:20 AM eth1 597017.00 1194019.00 38480.79 1765370.29 0.00 0.00 1.00 06:16:21 AM eth1 595450.00 1190936.00 38380.19 1760805.05 0.00 0.00 0.00 06:16:22 AM eth1 596385.00 1193096.00 38442.56 1763976.29 0.00 0.00 1.00 06:16:23 AM eth1 598155.00 1195978.00 38552.97 1768264.60 0.00 0.00 0.00 06:16:24 AM eth1 594405.00 1188643.00 38312.57 1757414.89 0.00 0.00 1.00 06:16:25 AM eth1 593366.00 1187154.00 38252.16 1755195.83 0.00 0.00 0.00 06:16:26 AM eth1 593188.00 1186118.00 38232.88 1753682.57 0.00 0.00 1.00 06:16:27 AM eth1 596301.00 1192241.00 38440.94 1762733.09 0.00 0.00 0.00 Average: eth1 595457.30 1190843.50 38381.69 1760664.84 0.00 0.00 0.50 lpaa23:~# ./tc -s -d qd sh dev eth1 | grep backlog backlog 7606336b 2513p requeues 167982 backlog 224072b 74p requeues 566 backlog 581376b 192p requeues 5598 backlog 181680b 60p requeues 1070 backlog 5305056b 1753p requeues 110166 // Here, this TX queue is attracting flows backlog 157456b 52p requeues 1758 backlog 672216b 222p requeues 3025 backlog 60560b 20p requeues 24541 backlog 448144b 148p requeues 21258 lpaa23:~# echo 1 >/proc/sys/net/ipv4/tcp_tsq_enable_tcp_wfree_ksoftirqd_detect Immediate jump to full bandwidth, and traffic is properly shard on all tx queues. lpaa23:~# sar -n DEV 1 10 | grep eth1 06:16:46 AM eth1 1397632.00 2795397.00 90081.87 4133031.26 0.00 0.00 1.00 06:16:47 AM eth1 1396874.00 2793614.00 90032.99 4130385.46 0.00 0.00 0.00 06:16:48 AM eth1 1395842.00 2791600.00 89966.46 4127409.67 0.00 0.00 1.00 06:16:49 AM eth1 1395528.00 2791017.00 89946.17 4126551.24 0.00 0.00 0.00 06:16:50 AM eth1 1397891.00 2795716.00 90098.74 4133497.39 0.00 0.00 1.00 06:16:51 AM eth1 1394951.00 2789984.00 89908.96 4125022.51 0.00 0.00 0.00 06:16:52 AM eth1 1394608.00 2789190.00 89886.90 4123851.36 0.00 0.00 1.00 06:16:53 AM eth1 1395314.00 2790653.00 89934.33 4125983.09 0.00 0.00 0.00 06:16:54 AM eth1 1396115.00 2792276.00 89984.25 4128411.21 0.00 0.00 1.00 06:16:55 AM eth1 1396829.00 2793523.00 90030.19 4130250.28 0.00 0.00 0.00 Average: eth1 1396158.40 2792297.00 89987.09 4128439.35 0.00 0.00 0.50 lpaa23:~# tc -s -d qd sh dev eth1 | grep backlog backlog 7900052b 2609p requeues 173287 backlog 878120b 290p requeues 589 backlog 1068884b 354p requeues 5621 backlog 996212b 329p requeues 1088 backlog 984100b 325p requeues 115316 backlog 956848b 316p requeues 1781 backlog 1080996b 357p requeues 3047 backlog 975016b 322p requeues 24571 backlog 990156b 327p requeues 21274 (All 8 TX queues get a fair share of the traffic) Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/tcp_output.c26
1 files changed, 19 insertions, 7 deletions
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 0a5d97c20aa9..e13d77857225 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -839,26 +839,38 @@ void tcp_wfree(struct sk_buff *skb)
{
struct sock *sk = skb->sk;
struct tcp_sock *tp = tcp_sk(sk);
+ int wmem;
+
+ /* Keep one reference on sk_wmem_alloc.
+ * Will be released by sk_free() from here or tcp_tasklet_func()
+ */
+ wmem = atomic_sub_return(skb->truesize - 1, &sk->sk_wmem_alloc);
+
+ /* If this softirq is serviced by ksoftirqd, we are likely under stress.
+ * Wait until our queues (qdisc + devices) are drained.
+ * This gives :
+ * - less callbacks to tcp_write_xmit(), reducing stress (batches)
+ * - chance for incoming ACK (processed by another cpu maybe)
+ * to migrate this flow (skb->ooo_okay will be eventually set)
+ */
+ if (wmem >= SKB_TRUESIZE(1) && this_cpu_ksoftirqd() == current)
+ goto out;
if (test_and_clear_bit(TSQ_THROTTLED, &tp->tsq_flags) &&
!test_and_set_bit(TSQ_QUEUED, &tp->tsq_flags)) {
unsigned long flags;
struct tsq_tasklet *tsq;
- /* Keep a ref on socket.
- * This last ref will be released in tcp_tasklet_func()
- */
- atomic_sub(skb->truesize - 1, &sk->sk_wmem_alloc);
-
/* queue this socket to tasklet queue */
local_irq_save(flags);
tsq = &__get_cpu_var(tsq_tasklet);
list_add(&tp->tsq_node, &tsq->head);
tasklet_schedule(&tsq->tasklet);
local_irq_restore(flags);
- } else {
- sock_wfree(skb);
+ return;
}
+out:
+ sk_free(sk);
}
/* This routine actually transmits TCP packets queued in by