diff options
author | David S. Miller <davem@davemloft.net> | 2017-05-16 15:41:31 -0400 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2017-05-16 15:41:31 -0400 |
commit | 8dfedc5343401512f80060628263ee0f52937c86 (patch) | |
tree | d69a117f59aeb3a96f42f6b452b471becfa9d803 /net/core/datagram.c | |
parent | Merge branch 'nfp-LSO-checksum-and-XDP-datapath-updates' (diff) | |
parent | udp: keep the sk_receive_queue held when splicing (diff) | |
download | linux-dev-8dfedc5343401512f80060628263ee0f52937c86.tar.xz linux-dev-8dfedc5343401512f80060628263ee0f52937c86.zip |
Merge branch 'udp-scalability-improvements'
Paolo Abeni says:
====================
udp: scalability improvements
This patch series implement an idea suggested by Eric Dumazet to
reduce the contention of the udp sk_receive_queue lock when the socket is
under flood.
An ancillary queue is added to the udp socket, and the socket always
tries first to read packets from such queue. If it's empty, we splice
the content from sk_receive_queue into the ancillary queue.
The first patch introduces some helpers to keep the udp code small, and the
following two implement the ancillary queue strategy. The code is split
to hopefully help the reviewing process.
The measured overall gain under udp flood is up to the 30% depending on
the numa layout and the number of ingress queue used by the relevant nic.
The performance numbers have been gathered using pktgen as sender, with 64
bytes packets, random src port on a host b2b connected via a 10Gbs link
with the dut.
The receiver used the udp_sink program by Jesper [1] and an h/w l4 rx hash on
the ingress nic, so that the number of ingress nic rx queues hit by the udp
traffic could be controlled via ethtool -L.
The udp_sink program was bound to the first idle cpu, to get more
stable numbers.
On a single numa node receiver:
nic rx queues vanilla patched kernel
1 1820 kpps 1900 kpps
2 1950 kpps 2500 kpps
16 1670 kpps 2120 kpps
When using a single nic rx queue, busy polling was also enabled,
elsewhere, in the above scenario, the bh processing becomes the bottle-neck
and this produces large artifacts in the measured performances (e.g.
improving the udp sink run time, decreases the overall tput, since more
action from the scheduler comes into play).
[1] https://github.com/netoptimizer/network-testing/blob/master/src/udp_sink.c
v1 -> v2:
Patches 1/3 and 2/3 are unchanged, in patch 3/3 the rx_queue_lock_held param
of udp_rmem_release() is now a bool.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/core/datagram.c')
-rw-r--r-- | net/core/datagram.c | 90 |
1 files changed, 51 insertions, 39 deletions
diff --git a/net/core/datagram.c b/net/core/datagram.c index db1866f2ffcf..a4592b43b40d 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -161,6 +161,43 @@ done: return skb; } +struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, + struct sk_buff_head *queue, + unsigned int flags, + void (*destructor)(struct sock *sk, + struct sk_buff *skb), + int *peeked, int *off, int *err, + struct sk_buff **last) +{ + struct sk_buff *skb; + + *last = queue->prev; + skb_queue_walk(queue, skb) { + if (flags & MSG_PEEK) { + if (*off >= skb->len && (skb->len || *off || + skb->peeked)) { + *off -= skb->len; + continue; + } + if (!skb->len) { + skb = skb_set_peeked(skb); + if (unlikely(IS_ERR(skb))) { + *err = PTR_ERR(skb); + return skb; + } + } + *peeked = 1; + atomic_inc(&skb->users); + } else { + __skb_unlink(skb, queue); + if (destructor) + destructor(sk, skb); + } + return skb; + } + return NULL; +} + /** * __skb_try_recv_datagram - Receive a datagram skbuff * @sk: socket @@ -216,46 +253,20 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags, *peeked = 0; do { + int _off = *off; + /* Again only user level code calls this function, so nothing * interrupt level will suddenly eat the receive_queue. * * Look at current nfs client by the way... * However, this function was correct in any case. 8) */ - int _off = *off; - - *last = (struct sk_buff *)queue; spin_lock_irqsave(&queue->lock, cpu_flags); - skb_queue_walk(queue, skb) { - *last = skb; - if (flags & MSG_PEEK) { - if (_off >= skb->len && (skb->len || _off || - skb->peeked)) { - _off -= skb->len; - continue; - } - if (!skb->len) { - skb = skb_set_peeked(skb); - if (IS_ERR(skb)) { - error = PTR_ERR(skb); - spin_unlock_irqrestore(&queue->lock, - cpu_flags); - goto no_packet; - } - } - *peeked = 1; - atomic_inc(&skb->users); - } else { - __skb_unlink(skb, queue); - if (destructor) - destructor(sk, skb); - } - spin_unlock_irqrestore(&queue->lock, cpu_flags); - *off = _off; - return skb; - } - + skb = __skb_try_recv_from_queue(sk, queue, flags, destructor, + peeked, &_off, err, last); spin_unlock_irqrestore(&queue->lock, cpu_flags); + if (skb) + return skb; if (!sk_can_busy_loop(sk)) break; @@ -335,8 +346,8 @@ void __skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb, int len) } EXPORT_SYMBOL(__skb_free_datagram_locked); -int __sk_queue_drop_skb(struct sock *sk, struct sk_buff *skb, - unsigned int flags, +int __sk_queue_drop_skb(struct sock *sk, struct sk_buff_head *sk_queue, + struct sk_buff *skb, unsigned int flags, void (*destructor)(struct sock *sk, struct sk_buff *skb)) { @@ -344,15 +355,15 @@ int __sk_queue_drop_skb(struct sock *sk, struct sk_buff *skb, if (flags & MSG_PEEK) { err = -ENOENT; - spin_lock_bh(&sk->sk_receive_queue.lock); - if (skb == skb_peek(&sk->sk_receive_queue)) { - __skb_unlink(skb, &sk->sk_receive_queue); + spin_lock_bh(&sk_queue->lock); + if (skb == skb_peek(sk_queue)) { + __skb_unlink(skb, sk_queue); atomic_dec(&skb->users); if (destructor) destructor(sk, skb); err = 0; } - spin_unlock_bh(&sk->sk_receive_queue.lock); + spin_unlock_bh(&sk_queue->lock); } atomic_inc(&sk->sk_drops); @@ -383,7 +394,8 @@ EXPORT_SYMBOL(__sk_queue_drop_skb); int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags) { - int err = __sk_queue_drop_skb(sk, skb, flags, NULL); + int err = __sk_queue_drop_skb(sk, &sk->sk_receive_queue, skb, flags, + NULL); kfree_skb(skb); sk_mem_reclaim_partial(sk); |