mirror of
https://github.com/followmsi/android_kernel_google_msm.git
synced 2024-11-06 23:17:41 +00:00
e7e3467ab1
This introduce TSQ (TCP Small Queues) TSQ goal is to reduce number of TCP packets in xmit queues (qdisc & device queues), to reduce RTT and cwnd bias, part of the bufferbloat problem. sk->sk_wmem_alloc not allowed to grow above a given limit, allowing no more than ~128KB [1] per tcp socket in qdisc/dev layers at a given time. TSO packets are sized/capped to half the limit, so that we have two TSO packets in flight, allowing better bandwidth use. As a side effect, setting the limit to 40000 automatically reduces the standard gso max limit (65536) to 40000/2 : It can help to reduce latencies of high prio packets, having smaller TSO packets. This means we divert sock_wfree() to a tcp_wfree() handler, to queue/send following frames when skb_orphan() [2] is called for the already queued skbs. Results on my dev machines (tg3/ixgbe nics) are really impressive, using standard pfifo_fast, and with or without TSO/GSO. Without reduction of nominal bandwidth, we have reduction of buffering per bulk sender : < 1ms on Gbit (instead of 50ms with TSO) < 8ms on 100Mbit (instead of 132 ms) I no longer have 4 MBytes backlogged in qdisc by a single netperf session, and both side socket autotuning no longer use 4 Mbytes. As skb destructor cannot restart xmit itself ( as qdisc lock might be taken at this point ), we delegate the work to a tasklet. We use one tasklest per cpu for performance reasons. If tasklet finds a socket owned by the user, it sets TSQ_OWNED flag. This flag is tested in a new protocol method called from release_sock(), to eventually send new segments. [1] New /proc/sys/net/ipv4/tcp_limit_output_bytes tunable [2] skb_orphan() is usually called at TX completion time, but some drivers call it in their start_xmit() handler. These drivers should at least use BQL, or else a single TCP session can still fill the whole NIC TX ring, since TSQ will have no effect. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Dave Taht <dave.taht@bufferbloat.net> Cc: Tom Herbert <therbert@google.com> Cc: Matt Mathis <mattmathis@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Nandita Dukkipati <nanditad@google.com> Signed-off-by: David S. Miller <davem@davemloft.net> Change-Id: I37d5e4d7c9ced1846385b6a04ae3ad134763a949 |
||
|---|---|---|
| .. | ||
| 9p | ||
| bluetooth | ||
| caif | ||
| irda | ||
| iucv | ||
| netfilter | ||
| netns | ||
| nfc | ||
| phonet | ||
| sctp | ||
| tc_act | ||
| act_api.h | ||
| activity_stats.h | ||
| addrconf.h | ||
| af_ieee802154.h | ||
| af_rxrpc.h | ||
| af_unix.h | ||
| ah.h | ||
| arp.h | ||
| atmclip.h | ||
| ax25.h | ||
| ax88796.h | ||
| cfg80211-wext.h | ||
| cfg80211.h | ||
| checksum.h | ||
| cipso_ipv4.h | ||
| cls_cgroup.h | ||
| compat.h | ||
| datalink.h | ||
| dcbevent.h | ||
| dcbnl.h | ||
| dn.h | ||
| dn_dev.h | ||
| dn_fib.h | ||
| dn_neigh.h | ||
| dn_nsp.h | ||
| dn_route.h | ||
| dsa.h | ||
| dsfield.h | ||
| dst.h | ||
| dst_ops.h | ||
| esp.h | ||
| ethoc.h | ||
| fib_rules.h | ||
| flow.h | ||
| flow_keys.h | ||
| garp.h | ||
| gen_stats.h | ||
| genetlink.h | ||
| gre.h | ||
| icmp.h | ||
| ieee80211_radiotap.h | ||
| ieee802154.h | ||
| ieee802154_netdev.h | ||
| if_inet6.h | ||
| inet6_connection_sock.h | ||
| inet6_hashtables.h | ||
| inet_common.h | ||
| inet_connection_sock.h | ||
| inet_ecn.h | ||
| inet_frag.h | ||
| inet_hashtables.h | ||
| inet_sock.h | ||
| inet_timewait_sock.h | ||
| inetpeer.h | ||
| ip.h | ||
| ip6_checksum.h | ||
| ip6_fib.h | ||
| ip6_route.h | ||
| ip6_tunnel.h | ||
| ip_fib.h | ||
| ip_vs.h | ||
| ipcomp.h | ||
| ipconfig.h | ||
| ipip.h | ||
| ipv6.h | ||
| ipx.h | ||
| iw_handler.h | ||
| lapb.h | ||
| lib80211.h | ||
| llc.h | ||
| llc_c_ac.h | ||
| llc_c_ev.h | ||
| llc_c_st.h | ||
| llc_conn.h | ||
| llc_if.h | ||
| llc_pdu.h | ||
| llc_s_ac.h | ||
| llc_s_ev.h | ||
| llc_s_st.h | ||
| llc_sap.h | ||
| mac80211.h | ||
| mip6.h | ||
| mld.h | ||
| ndisc.h | ||
| neighbour.h | ||
| net_namespace.h | ||
| net_ratelimit.h | ||
| netdma.h | ||
| netevent.h | ||
| netlabel.h | ||
| netlink.h | ||
| netprio_cgroup.h | ||
| netrom.h | ||
| nexthop.h | ||
| nl802154.h | ||
| p8022.h | ||
| ping.h | ||
| pkt_cls.h | ||
| pkt_sched.h | ||
| protocol.h | ||
| psnap.h | ||
| raw.h | ||
| rawv6.h | ||
| red.h | ||
| regulatory.h | ||
| request_sock.h | ||
| rose.h | ||
| route.h | ||
| rtnetlink.h | ||
| sch_generic.h | ||
| scm.h | ||
| secure_seq.h | ||
| slhc_vj.h | ||
| snmp.h | ||
| sock.h | ||
| stp.h | ||
| tcp.h | ||
| tcp_memcontrol.h | ||
| tcp_states.h | ||
| timewait_sock.h | ||
| transp_v6.h | ||
| udp.h | ||
| udplite.h | ||
| wext.h | ||
| wimax.h | ||
| wpan-phy.h | ||
| x25.h | ||
| x25device.h | ||
| xfrm.h | ||