diff options
| author | David S. Miller <davem@davemloft.net> | 2017-10-05 21:24:48 -0700 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2017-10-05 21:24:48 -0700 |
| commit | cec451ce60e50dba6d4136b7d1e62a5900cd264f (patch) | |
| tree | cb70c1552a2c58cc5b8f63bd8e85b7fdc3b33497 /include/linux | |
| parent | b1fb67fa501c4787035317f84db6caf013385581 (diff) | |
| parent | bef06223083b81d2064824afe2bc85be416ab73a (diff) | |
| download | cachepc-linux-cec451ce60e50dba6d4136b7d1e62a5900cd264f.tar.gz cachepc-linux-cec451ce60e50dba6d4136b7d1e62a5900cd264f.zip | |
Merge branch 'tcp-improving-RACK-cpu-performance'
Yuchung Cheng says:
====================
tcp: improving RACK cpu performance
This patch set improves the CPU consumption of the RACK TCP loss
recovery algorithm, in particular for high-speed networks. Currently,
for every ACK in recovery RACK can potentially iterate over all sent
packets in the write queue. On large BDP networks with non-trivial
losses the RACK write queue walk CPU usage becomes unreasonably high.
This patch introduces a new queue in TCP that keeps only skbs sent and
not yet (s)acked or marked lost, in time order instead of sequence
order. With that, RACK can examine this time-sorted list and only
check packets that were sent recently, within the reordering window,
per ACK. This is the fastest way without any write queue walks. The
number of skbs examined per ACK is reduced by orders of magnitude.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'include/linux')
| -rw-r--r-- | include/linux/skbuff.h | 11 | ||||
| -rw-r--r-- | include/linux/tcp.h | 1 |
2 files changed, 10 insertions, 2 deletions
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ada821466e88..01a985937867 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -617,6 +617,7 @@ typedef unsigned char *sk_buff_data_t; * @nf_trace: netfilter packet trace flag * @protocol: Packet protocol from driver * @destructor: Destruct function + * @tcp_tsorted_anchor: list structure for TCP (tp->tsorted_sent_queue) * @_nfct: Associated connection, if any (with nfctinfo bits) * @nf_bridge: Saved data about a bridged frame - see br_netfilter.c * @skb_iif: ifindex of device we arrived on @@ -686,8 +687,14 @@ struct sk_buff { */ char cb[48] __aligned(8); - unsigned long _skb_refdst; - void (*destructor)(struct sk_buff *skb); + union { + struct { + unsigned long _skb_refdst; + void (*destructor)(struct sk_buff *skb); + }; + struct list_head tcp_tsorted_anchor; + }; + #ifdef CONFIG_XFRM struct sec_path *sp; #endif diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 4aa40ef02d32..1d2c44e09e31 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -191,6 +191,7 @@ struct tcp_sock { u32 tsoffset; /* timestamp offset */ struct list_head tsq_node; /* anchor in tsq_tasklet.head list */ + struct list_head tsorted_sent_queue; /* time-sorted sent but un-SACKed skbs */ u32 snd_wl1; /* Sequence for window update */ u32 snd_wnd; /* The window we expect to receive */ |