summaryrefslogtreecommitdiffstats
path: root/net/ipv4/tcp_output.c
Commit message (Collapse)AuthorAgeFilesLines
* tcp: make local functions staticstephen hemminger2013-12-291-1/+1
| | | | | | | | | The following are only used in one file: tcp_connect_init tcp_set_rto Signed-off-by: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: David S. Miller <davem@davemloft.net>
* tcp: refine TSO splitsEric Dumazet2013-12-171-39/+54
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | While investigating performance problems on small RPC workloads, I noticed linux TCP stack was always splitting the last TSO skb into two parts (skbs). One being a multiple of MSS, and a small one with the Push flag. This split is done even if TCP_NODELAY is set, or if no small packet is in flight. Example with request/response of 4K/4K IP A > B: . ack 68432 win 2783 <nop,nop,timestamp 6524593 6525001> IP A > B: . 65537:68433(2896) ack 69632 win 2783 <nop,nop,timestamp 6524593 6525001> IP A > B: P 68433:69633(1200) ack 69632 win 2783 <nop,nop,timestamp 6524593 6525001> IP B > A: . ack 68433 win 2768 <nop,nop,timestamp 6525001 6524593> IP B > A: . 69632:72528(2896) ack 69633 win 2768 <nop,nop,timestamp 6525001 6524593> IP B > A: P 72528:73728(1200) ack 69633 win 2768 <nop,nop,timestamp 6525001 6524593> IP A > B: . ack 72528 win 2783 <nop,nop,timestamp 6524593 6525001> IP A > B: . 69633:72529(2896) ack 73728 win 2783 <nop,nop,timestamp 6524593 6525001> IP A > B: P 72529:73729(1200) ack 73728 win 2783 <nop,nop,timestamp 6524593 6525001> We can avoid this split by including the Nagle tests at the right place. Note : If some NIC had trouble sending TSO packets with a partial last segment, we would have hit the problem in GRO/forwarding workload already. tcp_minshall_update() is moved to tcp_output.c and is updated as we might feed a TSO packet with a partial last segment. This patch tremendously improves performance, as the traffic now looks like : IP A > B: . ack 98304 win 2783 <nop,nop,timestamp 6834277 6834685> IP A > B: P 94209:98305(4096) ack 98304 win 2783 <nop,nop,timestamp 6834277 6834685> IP B > A: . ack 98305 win 2768 <nop,nop,timestamp 6834686 6834277> IP B > A: P 98304:102400(4096) ack 98305 win 2768 <nop,nop,timestamp 6834686 6834277> IP A > B: . ack 102400 win 2783 <nop,nop,timestamp 6834279 6834686> IP A > B: P 98305:102401(4096) ack 102400 win 2783 <nop,nop,timestamp 6834279 6834686> IP B > A: . ack 102401 win 2768 <nop,nop,timestamp 6834687 6834279> IP B > A: P 102400:106496(4096) ack 102401 win 2768 <nop,nop,timestamp 6834687 6834279> IP A > B: . ack 106496 win 2783 <nop,nop,timestamp 6834280 6834687> IP A > B: P 102401:106497(4096) ack 106496 win 2783 <nop,nop,timestamp 6834280 6834687> IP B > A: . ack 106497 win 2768 <nop,nop,timestamp 6834688 6834280> IP B > A: P 106496:110592(4096) ack 106497 win 2768 <nop,nop,timestamp 6834688 6834280> Before : lpq83:~# nstat >/dev/null;perf stat ./super_netperf 200 -t TCP_RR -H lpq84 -l 20 -- -r 4K,4K 280774 Performance counter stats for './super_netperf 200 -t TCP_RR -H lpq84 -l 20 -- -r 4K,4K': 205719.049006 task-clock # 9.278 CPUs utilized 8,449,968 context-switches # 0.041 M/sec 1,935,997 CPU-migrations # 0.009 M/sec 160,541 page-faults # 0.780 K/sec 548,478,722,290 cycles # 2.666 GHz [83.20%] 455,240,670,857 stalled-cycles-frontend # 83.00% frontend cycles idle [83.48%] 272,881,454,275 stalled-cycles-backend # 49.75% backend cycles idle [66.73%] 166,091,460,030 instructions # 0.30 insns per cycle # 2.74 stalled cycles per insn [83.39%] 29,150,229,399 branches # 141.699 M/sec [83.30%] 1,943,814,026 branch-misses # 6.67% of all branches [83.32%] 22.173517844 seconds time elapsed lpq83:~# nstat | egrep "IpOutRequests|IpExtOutOctets" IpOutRequests 16851063 0.0 IpExtOutOctets 23878580777 0.0 After patch : lpq83:~# nstat >/dev/null;perf stat ./super_netperf 200 -t TCP_RR -H lpq84 -l 20 -- -r 4K,4K 280877 Performance counter stats for './super_netperf 200 -t TCP_RR -H lpq84 -l 20 -- -r 4K,4K': 107496.071918 task-clock # 4.847 CPUs utilized 5,635,458 context-switches # 0.052 M/sec 1,374,707 CPU-migrations # 0.013 M/sec 160,920 page-faults # 0.001 M/sec 281,500,010,924 cycles # 2.619 GHz [83.28%] 228,865,069,307 stalled-cycles-frontend # 81.30% frontend cycles idle [83.38%] 142,462,742,658 stalled-cycles-backend # 50.61% backend cycles idle [66.81%] 95,227,712,566 instructions # 0.34 insns per cycle # 2.40 stalled cycles per insn [83.43%] 16,209,868,171 branches # 150.795 M/sec [83.20%] 874,252,952 branch-misses # 5.39% of all branches [83.37%] 22.175821286 seconds time elapsed lpq83:~# nstat | egrep "IpOutRequests|IpExtOutOctets" IpOutRequests 11239428 0.0 IpExtOutOctets 23595191035 0.0 Indeed, the occupancy of tx skbs (IpExtOutOctets/IpOutRequests) is higher : 2099 instead of 1417, thus helping GRO to be more efficient when using FQ packet scheduler. Many thanks to Neal for review and ideas. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Neal Cardwell <ncardwell@google.com> Cc: Nandita Dukkipati <nanditad@google.com> Cc: Van Jacobson <vanj@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Tested-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* net: more spelling fixesstephen hemminger2013-12-101-5/+5
| | | | | | | Various spelling fixes in networking stack Signed-off-by: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: David S. Miller <davem@davemloft.net>
* tcp: optimize some skb_shinfo(skb) usesEric Dumazet2013-12-061-15/+21
| | | | | | | | | | | Compiler doesn't know skb_shinfo(skb) pointer is usually constant. By using a temporary variable, we help generating smaller code. For example, tcp_init_nondata_skb() is inlined after this patch. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* tcp: don't update snd_nxt, when a socket is switched from repair modeAndrey Vagin2013-11-191-1/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | snd_nxt must be updated synchronously with sk_send_head. Otherwise tp->packets_out may be updated incorrectly, what may bring a kernel panic. Here is a kernel panic from my host. [ 103.043194] BUG: unable to handle kernel NULL pointer dereference at 0000000000000048 [ 103.044025] IP: [<ffffffff815aaaaf>] tcp_rearm_rto+0xcf/0x150 ... [ 146.301158] Call Trace: [ 146.301158] [<ffffffff815ab7f0>] tcp_ack+0xcc0/0x12c0 Before this panic a tcp socket was restored. This socket had sent and unsent data in the write queue. Sent data was restored in repair mode, then the socket was switched from reapair mode and unsent data was restored. After that the socket was switched back into repair mode. In that moment we had a socket where write queue looks like this: snd_una snd_nxt write_seq |_________|________| | sk_send_head After a second switching from repair mode the state of socket was changed: snd_una snd_nxt, write_seq |_________ ________| | sk_send_head This state is inconsistent, because snd_nxt and sk_send_head are not synchronized. Bellow you can find a call trace, how packets_out can be incremented twice for one skb, if snd_nxt and sk_send_head are not synchronized. In this case packets_out will be always positive, even when sk_write_queue is empty. tcp_write_wakeup skb = tcp_send_head(sk); tcp_fragment if (!before(tp->snd_nxt, TCP_SKB_CB(buff)->end_seq)) tcp_adjust_pcount(sk, skb, diff); tcp_event_new_data_sent tp->packets_out += tcp_skb_pcount(skb); I think update of snd_nxt isn't required, when a socket is switched from repair mode. Because it's initialized in tcp_connect_init. Then when a write queue is restored, snd_nxt is incremented in tcp_event_new_data_sent, so it's always is in consistent state. I have checked, that the bug is not reproduced with this patch and all tests about restoring tcp connections work fine. Cc: Pavel Emelyanov <xemul@parallels.com> Cc: Eric Dumazet <edumazet@google.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> Cc: James Morris <jmorris@namei.org> Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org> Cc: Patrick McHardy <kaber@trash.net> Signed-off-by: Andrey Vagin <avagin@openvz.org> Acked-by: Pavel Emelyanov <xemul@parallels.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* tcp: tsq: restore minimal amount of queueingEric Dumazet2013-11-141-1/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | After commit c9eeec26e32e ("tcp: TSQ can use a dynamic limit"), several users reported throughput regressions, notably on mvneta and wifi adapters. 802.11 AMPDU requires a fair amount of queueing to be effective. This patch partially reverts the change done in tcp_write_xmit() so that the minimal amount is sysctl_tcp_limit_output_bytes. It also remove the use of this sysctl while building skb stored in write queue, as TSO autosizing does the right thing anyway. Users with well behaving NICS and correct qdisc (like sch_fq), can then lower the default sysctl_tcp_limit_output_bytes value from 128KB to 8KB. This new usage of sysctl_tcp_limit_output_bytes permits each driver authors to check how their driver performs when/if the value is set to a minimum of 4KB. Normally, line rate for a single TCP flow should be possible, but some drivers rely on timers to perform TX completion and too long TX completion delays prevent reaching full throughput. Fixes: c9eeec26e32e ("tcp: TSQ can use a dynamic limit") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Sujith Manoharan <sujith@msujith.org> Reported-by: Arnaud Ebalard <arno@natisbad.org> Tested-by: Sujith Manoharan <sujith@msujith.org> Cc: Felix Fietkau <nbd@openwrt.org> Signed-off-by: David S. Miller <davem@davemloft.net>
* Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller2013-10-231-5/+7
|\ | | | | | | | | | | | | | | | | | | Conflicts: drivers/net/usb/qmi_wwan.c include/net/dst.h Trivial merge conflicts, both were overlapping changes. Signed-off-by: David S. Miller <davem@davemloft.net>
| * tcp: remove the sk_can_gso() check from tcp_set_skb_tso_segs()Eric Dumazet2013-10-171-2/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | sk_can_gso() should only be used as a hint in tcp_sendmsg() to build GSO packets in the first place. (As a performance hint) Once we have GSO packets in write queue, we can not decide they are no longer GSO only because flow now uses a route which doesn't handle TSO/GSO. Core networking stack handles the case very well for us, all we need is keeping track of packet counts in MSS terms, regardless of segmentation done later (in GSO or hardware) Right now, if tcp_fragment() splits a GSO packet in two parts, @left and @right, and route changed through a non GSO device, both @left and @right have pcount set to 1, which is wrong, and leads to incorrect packet_count tracking. This problem was added in commit d5ac99a648 ("[TCP]: skb pcount with MTU discovery") Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: Yuchung Cheng <ycheng@google.com> Reported-by: Maciej Żenczykowski <maze@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * tcp: must unclone packets before mangling themEric Dumazet2013-10-171-3/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | TCP stack should make sure it owns skbs before mangling them. We had various crashes using bnx2x, and it turned out gso_size was cleared right before bnx2x driver was populating TC descriptor of the _previous_ packet send. TCP stack can sometime retransmit packets that are still in Qdisc. Of course we could make bnx2x driver more robust (using ACCESS_ONCE(shinfo->gso_size) for example), but the bug is TCP stack. We have identified two points where skb_unclone() was needed. This patch adds a WARN_ON_ONCE() to warn us if we missed another fix of this kind. Kudos to Neal for finding the root cause of this bug. Its visible using small MSS. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Neal Cardwell <ncardwell@google.com> Cc: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | tcp: remove redundant code in __tcp_retransmit_skb()Neal Cardwell2013-10-181-15/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Remove the specialized code in __tcp_retransmit_skb() that tries to trim any ACKed payload preceding a FIN before we retransmit (this was added in 1999 in v2.2.3pre3). This trimming code was made unreachable by the more general code added above it that uses tcp_trim_head() to trim any ACKed payload, with or without a FIN (this was added in "[NET]: Add segmentation offload support to TCP." in 2002 circa v2.5.33). Signed-off-by: Neal Cardwell <ncardwell@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Yuchung Cheng <ycheng@google.com> Acked-by: Eric Dumazet <edumazet@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | tcp: tcp_transmit_skb() optimizationsEric Dumazet2013-10-111-7/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 1) We need to take a timestamp only for skb that should be cloned. Other skbs are not in write queue and no rtt estimation is done on them. 2) the unlikely() hint is wrong for receivers (they send pure ACK) Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: MF Nowlan <fitz@cs.yale.edu> Cc: Yuchung Cheng <ycheng@google.com> Cc: Neal Cardwell <ncardwell@google.com> Acked-By: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | inet: rename ir_loc_port to ir_numEric Dumazet2013-10-101-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In commit 634fb979e8f ("inet: includes a sock_common in request_sock") I forgot that the two ports in sock_common do not have same byte order : skc_dport is __be16 (network order), but skc_num is __u16 (host order) So sparse complains because ir_loc_port (mapped into skc_num) is considered as __u16 while it should be __be16 Let rename ir_loc_port to ireq->ir_num (analogy with inet->inet_num), and perform appropriate htons/ntohs conversions. Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | inet: includes a sock_common in request_sockEric Dumazet2013-10-101-2/+2
|/ | | | | | | | | | | | | | | | | | | | | | | | | | | TCP listener refactoring, part 5 : We want to be able to insert request sockets (SYN_RECV) into main ehash table instead of the per listener hash table to allow RCU lookups and remove listener lock contention. This patch includes the needed struct sock_common in front of struct request_sock This means there is no more inet6_request_sock IPv6 specific structure. Following inet_request_sock fields were renamed as they became macros to reference fields from struct sock_common. Prefix ir_ was chosen to avoid name collisions. loc_port -> ir_loc_port loc_addr -> ir_loc_addr rmt_addr -> ir_rmt_addr rmt_port -> ir_rmt_port iif -> ir_iif Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* tcp: Always set options to 0 before calling tcp_established_optionsAndi Kleen2013-10-021-0/+2
| | | | | | | | | | | | | | | | | tcp_established_options assumes opts->options is 0 before calling, as it read modify writes it. For the tcp_current_mss() case the opts structure is not zeroed, so this can be done with uninitialized values. This is ok, because ->options is not read in this path. But it's still better to avoid the operation on the uninitialized field. This shuts up a static code analyzer, and presumably may help the optimizer. Cc: netdev@vger.kernel.org Signed-off-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* tcp: TSQ can use a dynamic limitEric Dumazet2013-09-301-6/+11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When TCP Small Queues was added, we used a sysctl to limit amount of packets queues on Qdisc/device queues for a given TCP flow. Problem is this limit is either too big for low rates, or too small for high rates. Now TCP stack has rate estimation in sk->sk_pacing_rate, and TSO auto sizing, it can better control number of packets in Qdisc/device queues. New limit is two packets or at least 1 to 2 ms worth of packets. Low rates flows benefit from this patch by having even smaller number of packets in queues, allowing for faster recovery, better RTT estimations. High rates flows benefit from this patch by allowing more than 2 packets in flight as we had reports this was a limiting factor to reach line rate. [ In particular if TX completion is delayed because of coalescing parameters ] Example for a single flow on 10Gbp link controlled by FQ/pacing 14 packets in flight instead of 2 $ tc -s -d qd qdisc fq 8001: dev eth0 root refcnt 32 limit 10000p flow_limit 100p buckets 1024 quantum 3028 initial_quantum 15140 Sent 1168459366606 bytes 771822841 pkt (dropped 0, overlimits 0 requeues 6822476) rate 9346Mbit 771713pps backlog 953820b 14p requeues 6822476 2047 flow, 2046 inactive, 1 throttled, delay 15673 ns 2372 gc, 0 highprio, 0 retrans, 9739249 throttled, 0 flows_plimit Note that sk_pacing_rate is currently set to twice the actual rate, but this might be refined in the future when a flow is in congestion avoidance. Additional change : skb->destructor should be set to tcp_wfree(). A future patch (for linux 3.13+) might remove tcp_limit_output_bytes Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Wei Liu <wei.liu2@citrix.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Neal Cardwell <ncardwell@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller2013-09-051-1/+3
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Conflicts: drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c net/bridge/br_multicast.c net/ipv6/sit.c The conflicts were minor: 1) sit.c changes overlap with change to ip_tunnel_xmit() signature. 2) br_multicast.c had an overlap between computing max_delay using msecs_to_jiffies and turning MLDV2_MRC() into an inline function with a name using lowercase instead of uppercase letters. 3) stmmac had two overlapping changes, one which conditionally allocated and hooked up a dma_cfg based upon the presence of the pbl OF property, and another one handling store-and-forward DMA made. The latter of which should not go into the new of_find_property() basic block. Signed-off-by: David S. Miller <davem@davemloft.net>
| * tcp: tcp_make_synack() should use sock_wmallocPhil Oester2013-08-301-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | In commit 90ba9b19 (tcp: tcp_make_synack() can use alloc_skb()), Eric changed the call to sock_wmalloc in tcp_make_synack to alloc_skb. In doing so, the netfilter owner match lost its ability to block the SYNACK packet on outbound listening sockets. Revert the change, restoring the owner match functionality. This closes netfilter bugzilla #847. Signed-off-by: Phil Oester <kernel@linuxace.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * tcp: initialize rcv_tstamp for restored socketsAndrew Vagin2013-08-291-0/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | u32 rcv_tstamp; /* timestamp of last received ACK */ Its value used in tcp_retransmit_timer, which closes socket if the last ack was received more then TCP_RTO_MAX ago. Currently rcv_tstamp is initialized to zero and if tcp_retransmit_timer is called before receiving a first ack, the connection is closed. This patch initializes rcv_tstamp to a timestamp, when a socket was restored. Cc: Pavel Emelyanov <xemul@parallels.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> Cc: James Morris <jmorris@namei.org> Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org> Cc: Patrick McHardy <kaber@trash.net> Reported-by: Cyrill Gorcunov <gorcunov@openvz.org> Signed-off-by: Andrey Vagin <avagin@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
* | tcp: TSO packets automatic sizingEric Dumazet2013-08-291-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | After hearing many people over past years complaining against TSO being bursty or even buggy, we are proud to present automatic sizing of TSO packets. One part of the problem is that tcp_tso_should_defer() uses an heuristic relying on upcoming ACKS instead of a timer, but more generally, having big TSO packets makes little sense for low rates, as it tends to create micro bursts on the network, and general consensus is to reduce the buffering amount. This patch introduces a per socket sk_pacing_rate, that approximates the current sending rate, and allows us to size the TSO packets so that we try to send one packet every ms. This field could be set by other transports. Patch has no impact for high speed flows, where having large TSO packets makes sense to reach line rate. For other flows, this helps better packet scheduling and ACK clocking. This patch increases performance of TCP flows in lossy environments. A new sysctl (tcp_min_tso_segs) is added, to specify the minimal size of a TSO packet (default being 2). A follow-up patch will provide a new packet scheduler (FQ), using sk_pacing_rate as an input to perform optional per flow pacing. This explains why we chose to set sk_pacing_rate to twice the current rate, allowing 'slow start' ramp up. sk_pacing_rate = 2 * cwnd * mss / srtt v2: Neal Cardwell reported a suspect deferring of last two segments on initial write of 10 MSS, I had to change tcp_tso_should_defer() to take into account tp->xmit_size_goal_segs Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neal Cardwell <ncardwell@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Van Jacobson <vanj@google.com> Cc: Tom Herbert <therbert@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | tcp: TCP_NOTSENT_LOWAT socket optionEric Dumazet2013-07-241-0/+3
|/ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Idea of this patch is to add optional limitation of number of unsent bytes in TCP sockets, to reduce usage of kernel memory. TCP receiver might announce a big window, and TCP sender autotuning might allow a large amount of bytes in write queue, but this has little performance impact if a large part of this buffering is wasted : Write queue needs to be large only to deal with large BDP, not necessarily to cope with scheduling delays (incoming ACKS make room for the application to queue more bytes) For most workloads, using a value of 128 KB or less is OK to give applications enough time to react to POLLOUT events in time (or being awaken in a blocking sendmsg()) This patch adds two ways to set the limit : 1) Per socket option TCP_NOTSENT_LOWAT 2) A sysctl (/proc/sys/net/ipv4/tcp_notsent_lowat) for sockets not using TCP_NOTSENT_LOWAT socket option (or setting a zero value) Default value being UINT_MAX (0xFFFFFFFF), meaning this has no effect. This changes poll()/select()/epoll() to report POLLOUT only if number of unsent bytes is below tp->nosent_lowat Note this might increase number of sendmsg()/sendfile() calls when using non blocking sockets, and increase number of context switches for blocking sockets. Note this is not related to SO_SNDLOWAT (as SO_SNDLOWAT is defined as : Specify the minimum number of bytes in the buffer until the socket layer will pass the data to the protocol) Tested: netperf sessions, and watching /proc/net/protocols "memory" column for TCP With 200 concurrent netperf -t TCP_STREAM sessions, amount of kernel memory used by TCP buffers shrinks by ~55 % (20567 pages instead of 45458) lpq83:~# echo -1 >/proc/sys/net/ipv4/tcp_notsent_lowat lpq83:~# (super_netperf 200 -t TCP_STREAM -H remote -l 90 &); sleep 60 ; grep TCP /proc/net/protocols TCPv6 1880 2 45458 no 208 yes ipv6 y y y y y y y y y y y y y n y y y y y TCP 1696 508 45458 no 208 yes kernel y y y y y y y y y y y y y n y y y y y lpq83:~# echo 131072 >/proc/sys/net/ipv4/tcp_notsent_lowat lpq83:~# (super_netperf 200 -t TCP_STREAM -H remote -l 90 &); sleep 60 ; grep TCP /proc/net/protocols TCPv6 1880 2 20567 no 208 yes ipv6 y y y y y y y y y y y y y n y y y y y TCP 1696 508 20567 no 208 yes kernel y y y y y y y y y y y y y n y y y y y Using 128KB has no bad effect on the throughput or cpu usage of a single flow, although there is an increase of context switches. A bonus is that we hold socket lock for a shorter amount of time and should improve latencies of ACK processing. lpq83:~# echo -1 >/proc/sys/net/ipv4/tcp_notsent_lowat lpq83:~# perf stat -e context-switches ./netperf -H 7.7.7.84 -t omni -l 20 -c -i10,3 OMNI Send TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 7.7.7.84 () port 0 AF_INET : +/-2.500% @ 99% conf. Local Remote Local Elapsed Throughput Throughput Local Local Remote Remote Local Remote Service Send Socket Recv Socket Send Time Units CPU CPU CPU CPU Service Service Demand Size Size Size (sec) Util Util Util Util Demand Demand Units Final Final % Method % Method 1651584 6291456 16384 20.00 17447.90 10^6bits/s 3.13 S -1.00 U 0.353 -1.000 usec/KB Performance counter stats for './netperf -H 7.7.7.84 -t omni -l 20 -c -i10,3': 412,514 context-switches 200.034645535 seconds time elapsed lpq83:~# echo 131072 >/proc/sys/net/ipv4/tcp_notsent_lowat lpq83:~# perf stat -e context-switches ./netperf -H 7.7.7.84 -t omni -l 20 -c -i10,3 OMNI Send TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 7.7.7.84 () port 0 AF_INET : +/-2.500% @ 99% conf. Local Remote Local Elapsed Throughput Throughput Local Local Remote Remote Local Remote Service Send Socket Recv Socket Send Time Units CPU CPU CPU CPU Service Service Demand Size Size Size (sec) Util Util Util Util Demand Demand Units Final Final % Method % Method 1593240 6291456 16384 20.00 17321.16 10^6bits/s 3.35 S -1.00 U 0.381 -1.000 usec/KB Performance counter stats for './netperf -H 7.7.7.84 -t omni -l 20 -c -i10,3': 2,675,818 context-switches 200.029651391 seconds time elapsed Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Neal Cardwell <ncardwell@google.com> Cc: Yuchung Cheng <ycheng@google.com> Acked-By: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* tcp: account all retransmit failuresYuchung Cheng2013-07-121-3/+4
| | | | | | | | | | Change snmp RETRANSFAILS stat to include timeout retransmit failures in addition to other loss recoveries. Signed-off-by: Yuchung Cheng <ycheng@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* tcp: introduce a per-route knob for quick ackCong Wang2013-06-191-2/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In previous discussions, I tried to find some reasonable heuristics for delayed ACK, however this seems not possible, according to Eric: "ACKS might also be delayed because of bidirectional traffic, and is more controlled by the application response time. TCP stack can not easily estimate it." "ACK can be incredibly useful to recover from losses in a short time. The vast majority of TCP sessions are small lived, and we send one ACK per received segment anyway at beginning or retransmits to let the sender smoothly increase its cwnd, so an auto-tuning facility wont help them that much." and according to David: "ACKs are the only information we have to detect loss. And, for the same reasons that TCP VEGAS is fundamentally broken, we cannot measure the pipe or some other receiver-side-visible piece of information to determine when it's "safe" to stretch ACK. And even if it's "safe", we should not do it so that losses are accurately detected and we don't spuriously retransmit. The only way to know when the bandwidth increases is to "test" it, by sending more and more packets until drops happen. That's why all successful congestion control algorithms must operate on explicited tested pieces of information. Similarly, it's not really possible to universally know if it's safe to stretch ACK or not." It still makes sense to enable or disable quick ack mode like what TCP_QUICK_ACK does. Similar to TCP_QUICK_ACK option, but for people who can't modify the source code and still wants to control TCP delayed ACK behavior. As David suggested, this should belong to per-path scope, since different pathes may want different behaviors. Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Rick Jones <rick.jones2@hp.com> Cc: Stephen Hemminger <stephen@networkplumber.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Thomas Graf <tgraf@suug.ch> CC: David Laight <David.Laight@ACULAB.COM> Signed-off-by: Cong Wang <amwang@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* tcp:typo unset should be unsentWeiping Pan2013-06-191-1/+1
| | | | | Signed-off-by: Weiping Pan <wpan@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* tcp: properly send new data in fast recovery in first RTTYuchung Cheng2013-06-131-15/+18
| | | | | | | | | | | | | | | | | | | Linux sends new unset data during disorder and recovery state if all (suspected) lost packets have been retransmitted ( RFC5681, section 3.2 step 1 & 2, RFC3517 section 4, NexSeg() Rule 2). One requirement is to keep the receive window about twice the estimated sender's congestion window (tcp_rcv_space_adjust()), assuming the fast retransmits repair the losses in the next round trip. But currently it's not the case on the first round trip in either normal or Fast Open connection, beucase the initial receive window is identical to (expected) sender's initial congestion window. The fix is to double it. Signed-off-by: Yuchung Cheng <ycheng@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* tcp: xps: fix reordering issuesEric Dumazet2013-05-231-4/+6
| | | | | | | | | | | | | | | | commit 3853b5841c01a ("xps: Improvements in TX queue selection") introduced ooo_okay flag, but the condition to set it is slightly wrong. In our traces, we have seen ACK packets being received out of order, and RST packets sent in response. We should test if we have any packets still in host queue. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Tom Herbert <therbert@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* net: Add MIB counters for checksum errorsEric Dumazet2013-04-291-1/+2
| | | | | | | | | | | | | | | | Add MIB counters for checksum errors in IP layer, and TCP/UDP/ICMP layers, to help diagnose problems. $ nstat -a | grep Csum IcmpInCsumErrors 72 0.0 TcpInCsumErrors 382 0.0 UdpInCsumErrors 463221 0.0 Icmp6InCsumErrors 75 0.0 Udp6InCsumErrors 173442 0.0 IpExtInCsumErrors 10884 0.0 Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller2013-04-221-2/+7
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Conflicts: drivers/net/ethernet/emulex/benet/be_main.c drivers/net/ethernet/intel/igb/igb_main.c drivers/net/wireless/brcm80211/brcmsmac/mac80211_if.c include/net/scm.h net/batman-adv/routing.c net/ipv4/tcp_input.c The e{uid,gid} --> {uid,gid} credentials fix conflicted with the cleanup in net-next to now pass cred structs around. The be2net driver had a bug fix in 'net' that overlapped with the VLAN interface changes by Patrick McHardy in net-next. An IGB conflict existed because in 'net' the build_skb() support was reverted, and in 'net-next' there was a comment style fix within that code. Several batman-adv conflicts were resolved by making sure that all calls to batadv_is_my_mac() are changed to have a new bat_priv first argument. Eric Dumazet's TS ECR fix in TCP in 'net' conflicted with the F-RTO rewrite in 'net-next', mostly overlapping changes. Thanks to Stephen Rothwell and Antonio Quartulli for help with several of these merge resolutions. Signed-off-by: David S. Miller <davem@davemloft.net>
| * tcp: Reallocate headroom if it would overflow csum_startThomas Graf2013-04-111-2/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If a TCP retransmission gets partially ACKed and collapsed multiple times it is possible for the headroom to grow beyond 64K which will overflow the 16bit skb->csum_start which is based on the start of the headroom. It has been observed rarely in the wild with IPoIB due to the 64K MTU. Verify if the acking and collapsing resulted in a headroom exceeding what csum_start can cover and reallocate the headroom if so. A big thank you to Jim Foraker <foraker1@llnl.gov> and the team at LLNL for helping out with the investigation and testing. Reported-by: Jim Foraker <foraker1@llnl.gov> Signed-off-by: Thomas Graf <tgraf@suug.ch> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * selinux: add a skb_owned_by() hookEric Dumazet2013-04-091-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Commit 90ba9b1986b5ac (tcp: tcp_make_synack() can use alloc_skb()) broke certain SELinux/NetLabel configurations by no longer correctly assigning the sock to the outgoing SYNACK packet. Cost of atomic operations on the LISTEN socket is quite big, and we would like it to happen only if really needed. This patch introduces a new security_ops->skb_owned_by() method, that is a void operation unless selinux is active. Reported-by: Miroslav Vadkerti <mvadkert@redhat.com> Diagnosed-by: Paul Moore <pmoore@redhat.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: linux-security-module@vger.kernel.org Acked-by: James Morris <james.l.morris@oracle.com> Tested-by: Paul Moore <pmoore@redhat.com> Acked-by: Paul Moore <pmoore@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | tcp: introduce TCPSpuriousRtxHostQueues SNMP counterEric Dumazet2013-04-181-0/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Host queues (Qdisc + NIC) can hold packets so long that TCP can eventually retransmit a packet before the first transmit even left the host. Its not clear right now if we could avoid this in the first place : - We could arm RTO timer not at the time we enqueue packets, but at the time we TX complete them (tcp_wfree()) - Cancel the sending of the new copy of the packet if prior one is still in queue. This patch adds instrumentation so that we can at least see how often this problem happens. TCPSpuriousRtxHostQueues SNMP counter is incremented every time we detect the fast clone is not yet freed in tcp_transmit_skb() Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Neal Cardwell <ncardwell@google.com> Cc: Tom Herbert <therbert@google.com> Cc: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | tcp: GSO should be TSQ friendlyEric Dumazet2013-04-121-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | I noticed that TSQ (TCP Small queues) was less effective when TSO is turned off, and GSO is on. If BQL is not enabled, TSQ has then no effect. It turns out the GSO engine frees the original gso_skb at the time the fragments are generated and queued to the NIC. We should instead call the tcp_wfree() destructor for the last fragment, to keep the flow control as intended in TSQ. This effectively limits the number of queued packets on qdisc + NIC layers. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Tom Herbert <therbert@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Nandita Dukkipati <nanditad@google.com> Cc: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller2013-03-221-2/+5
|\| | | | | | | | | | | | | | | Pull to get the thermal netlink multicast group name fix, otherwise the assertion added in net-next to netlink to detect that kind of bug makes systems unbootable for some folks. Signed-off-by: David S. Miller <davem@davemloft.net>
| * tcp: preserve ACK clocking in TSOEric Dumazet2013-03-221-2/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | A long standing problem with TSO is the fact that tcp_tso_should_defer() rearms the deferred timer, while it should not. Current code leads to following bad bursty behavior : 20:11:24.484333 IP A > B: . 297161:316921(19760) ack 1 win 119 20:11:24.484337 IP B > A: . ack 263721 win 1117 20:11:24.485086 IP B > A: . ack 265241 win 1117 20:11:24.485925 IP B > A: . ack 266761 win 1117 20:11:24.486759 IP B > A: . ack 268281 win 1117 20:11:24.487594 IP B > A: . ack 269801 win 1117 20:11:24.488430 IP B > A: . ack 271321 win 1117 20:11:24.489267 IP B > A: . ack 272841 win 1117 20:11:24.490104 IP B > A: . ack 274361 win 1117 20:11:24.490939 IP B > A: . ack 275881 win 1117 20:11:24.491775 IP B > A: . ack 277401 win 1117 20:11:24.491784 IP A > B: . 316921:332881(15960) ack 1 win 119 20:11:24.492620 IP B > A: . ack 278921 win 1117 20:11:24.493448 IP B > A: . ack 280441 win 1117 20:11:24.494286 IP B > A: . ack 281961 win 1117 20:11:24.495122 IP B > A: . ack 283481 win 1117 20:11:24.495958 IP B > A: . ack 285001 win 1117 20:11:24.496791 IP B > A: . ack 286521 win 1117 20:11:24.497628 IP B > A: . ack 288041 win 1117 20:11:24.498459 IP B > A: . ack 289561 win 1117 20:11:24.499296 IP B > A: . ack 291081 win 1117 20:11:24.500133 IP B > A: . ack 292601 win 1117 20:11:24.500970 IP B > A: . ack 294121 win 1117 20:11:24.501388 IP B > A: . ack 295641 win 1117 20:11:24.501398 IP A > B: . 332881:351881(19000) ack 1 win 119 While the expected behavior is more like : 20:19:49.259620 IP A > B: . 197601:202161(4560) ack 1 win 119 20:19:49.260446 IP B > A: . ack 154281 win 1212 20:19:49.261282 IP B > A: . ack 155801 win 1212 20:19:49.262125 IP B > A: . ack 157321 win 1212 20:19:49.262136 IP A > B: . 202161:206721(4560) ack 1 win 119 20:19:49.262958 IP B > A: . ack 158841 win 1212 20:19:49.263795 IP B > A: . ack 160361 win 1212 20:19:49.264628 IP B > A: . ack 161881 win 1212 20:19:49.264637 IP A > B: . 206721:211281(4560) ack 1 win 119 20:19:49.265465 IP B > A: . ack 163401 win 1212 20:19:49.265886 IP B > A: . ack 164921 win 1212 20:19:49.266722 IP B > A: . ack 166441 win 1212 20:19:49.266732 IP A > B: . 211281:215841(4560) ack 1 win 119 20:19:49.267559 IP B > A: . ack 167961 win 1212 20:19:49.268394 IP B > A: . ack 169481 win 1212 20:19:49.269232 IP B > A: . ack 171001 win 1212 20:19:49.269241 IP A > B: . 215841:221161(5320) ack 1 win 119 Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Yuchung Cheng <ycheng@google.com> Cc: Van Jacobson <vanj@google.com> Cc: Neal Cardwell <ncardwell@google.com> Cc: Nandita Dukkipati <nanditad@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | tcp: refactor F-RTOYuchung Cheng2013-03-211-9/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The patch series refactor the F-RTO feature (RFC4138/5682). This is to simplify the loss recovery processing. Existing F-RTO was developed during the experimental stage (RFC4138) and has many experimental features. It takes a separate code path from the traditional timeout processing by overloading CA_Disorder instead of using CA_Loss state. This complicates CA_Disorder state handling because it's also used for handling dubious ACKs and undos. While the algorithm in the RFC does not change the congestion control, the implementation intercepts congestion control in various places (e.g., frto_cwnd in tcp_ack()). The new code implements newer F-RTO RFC5682 using CA_Loss processing path. F-RTO becomes a small extension in the timeout processing and interfaces with congestion control and Eifel undo modules. It lets congestion control (module) determines how many to send independently. F-RTO only chooses what to send in order to detect spurious retranmission. If timeout is found spurious it invokes existing Eifel undo algorithms like DSACK or TCP timestamp based detection. The first patch removes all F-RTO code except the sysctl_tcp_frto is left for the new implementation. Since CA_EVENT_FRTO is removed, TCP westwood now computes ssthresh on regular timeout CA_EVENT_LOSS event. Signed-off-by: Yuchung Cheng <ycheng@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller2013-03-201-1/+0
|\| | | | | | | | | | | | | Pull in the 'net' tree to get Daniel Borkmann's flow dissector infrastructure change. Signed-off-by: David S. Miller <davem@davemloft.net>
| * tcp: fix skb_availroom()Eric Dumazet2013-03-141-1/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Chrome OS team reported a crash on a Pixel ChromeBook in TCP stack : https://code.google.com/p/chromium/issues/detail?id=182056 commit a21d45726acac (tcp: avoid order-1 allocations on wifi and tx path) did a poor choice adding an 'avail_size' field to skb, while what we really needed was a 'reserved_tailroom' one. It would have avoided commit 22b4a4f22da (tcp: fix retransmit of partially acked frames) and this commit. Crash occurs because skb_split() is not aware of the 'avail_size' management (and should not be aware) Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Mukesh Agrawal <quiche@chromium.org> Signed-off-by: David S. Miller <davem@davemloft.net>
* | tcp: Remove TCPCTChristoph Paasch2013-03-171-213/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | TCPCT uses option-number 253, reserved for experimental use and should not be used in production environments. Further, TCPCT does not fully implement RFC 6013. As a nice side-effect, removing TCPCT increases TCP's performance for very short flows: Doing an apache-benchmark with -c 100 -n 100000, sending HTTP-requests for files of 1KB size. before this patch: average (among 7 runs) of 20845.5 Requests/Second after: average (among 7 runs) of 21403.6 Requests/Second Signed-off-by: Christoph Paasch <christoph.paasch@uclouvain.be> Signed-off-by: David S. Miller <davem@davemloft.net>
* | tcp: TLP loss detection.Nandita Dukkipati2013-03-121-0/+9
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This is the second of the TLP patch series; it augments the basic TLP algorithm with a loss detection scheme. This patch implements a mechanism for loss detection when a Tail loss probe retransmission plugs a hole thereby masking packet loss from the sender. The loss detection algorithm relies on counting TLP dupacks as outlined in Sec. 3 of: http://tools.ietf.org/html/draft-dukkipati-tcpm-tcp-loss-probe-01 The basic idea is: Sender keeps track of TLP "episode" upon retransmission of a TLP packet. An episode ends when the sender receives an ACK above the SND.NXT (tracked by tlp_high_seq) at the time of the episode. We want to make sure that before the episode ends the sender receives a "TLP dupack", indicating that the TLP retransmission was unnecessary, so there was no loss/hole that needed plugging. If the sender gets no TLP dupack before the end of the episode, then it reduces ssthresh and the congestion window, because the TLP packet arriving at the receiver probably plugged a hole. Signed-off-by: Nandita Dukkipati <nanditad@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | tcp: Tail loss probe (TLP)Nandita Dukkipati2013-03-121-4/+124
|/ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch series implement the Tail loss probe (TLP) algorithm described in http://tools.ietf.org/html/draft-dukkipati-tcpm-tcp-loss-probe-01. The first patch implements the basic algorithm. TLP's goal is to reduce tail latency of short transactions. It achieves this by converting retransmission timeouts (RTOs) occuring due to tail losses (losses at end of transactions) into fast recovery. TLP transmits one packet in two round-trips when a connection is in Open state and isn't receiving any ACKs. The transmitted packet, aka loss probe, can be either new or a retransmission. When there is tail loss, the ACK from a loss probe triggers FACK/early-retransmit based fast recovery, thus avoiding a costly RTO. In the absence of loss, there is no change in the connection state. PTO stands for probe timeout. It is a timer event indicating that an ACK is overdue and triggers a loss probe packet. The PTO value is set to max(2*SRTT, 10ms) and is adjusted to account for delayed ACK timer when there is only one oustanding packet. TLP Algorithm On transmission of new data in Open state: -> packets_out > 1: schedule PTO in max(2*SRTT, 10ms). -> packets_out == 1: schedule PTO in max(2*RTT, 1.5*RTT + 200ms) -> PTO = min(PTO, RTO) Conditions for scheduling PTO: -> Connection is in Open state. -> Connection is either cwnd limited or no new data to send. -> Number of probes per tail loss episode is limited to one. -> Connection is SACK enabled. When PTO fires: new_segment_exists: -> transmit new segment. -> packets_out++. cwnd remains same. no_new_packet: -> retransmit the last segment. Its ACK triggers FACK or early retransmit based recovery. ACK path: -> rearm RTO at start of ACK processing. -> reschedule PTO if need be. In addition, the patch includes a small variation to the Early Retransmit (ER) algorithm, such that ER and TLP together can in principle recover any N-degree of tail loss through fast recovery. TLP is controlled by the same sysctl as ER, tcp_early_retrans sysctl. tcp_early_retrans==0; disables TLP and ER. ==1; enables RFC5827 ER. ==2; delayed ER. ==3; TLP and delayed ER. [DEFAULT] ==4; TLP only. The TLP patch series have been extensively tested on Google Web servers. It is most effective for short Web trasactions, where it reduced RTOs by 15% and improved HTTP response time (average by 6%, 99th percentile by 10%). The transmitted probes account for <0.5% of the overall transmissions. Signed-off-by: Nandita Dukkipati <nanditad@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Acked-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* tcp: fix SYN-data space mis-accountingYuchung Cheng2013-02-221-7/+11
| | | | | | | | | | | | In fast open the sender unncessarily reduces the space available for data in SYN by 12 bytes. This is because in the sender incorrectly reserves space for TS option twice in tcp_send_syn_data(): tcp_mtu_to_mss() already accounts for TS option space. But it further reserves MAX_TCP_OPTION_SPACE when computing the payload space. Signed-off-by: Yuchung Cheng <ycheng@google.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* net: Add skb_unclone() helper function.Pravin B Shelar2013-02-151-1/+1
| | | | | | | | This function will be used in next GRE_GSO patch. This patch does not change any functionality. Signed-off-by: Pravin B Shelar <pshelar@nicira.com> Acked-by: Eric Dumazet <edumazet@google.com>
* net: Fix possible wrong checksum generation.Pravin B Shelar2013-02-131-2/+2
| | | | | | | | | | | | | | | | | | | | | Patch cef401de7be8c4e (net: fix possible wrong checksum generation) fixed wrong checksum calculation but it broke TSO by defining new GSO type but not a netdev feature for that type. net_gso_ok() would not allow hardware checksum/segmentation offload of such packets without the feature. Following patch fixes TSO and wrong checksum. This patch uses same logic that Eric Dumazet used. Patch introduces new flag SKBTX_SHARED_FRAG if at least one frag can be modified by the user. but SKBTX_SHARED_FRAG flag is kept in skb shared info tx_flags rather than gso_type. tx_flags is better compared to gso_type since we can have skb with shared frag without gso packet. It does not link SHARED_FRAG to GSO, So there is no need to define netdev feature for this. Signed-off-by: Pravin B Shelar <pshelar@nicira.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* tcp: send packets with a socket timestampAndrey Vagin2013-02-131-2/+2
| | | | | | | | | | | | | | | | | | | | | | | A socket timestamp is a sum of the global tcp_time_stamp and a per-socket offset. A socket offset is added in places where externally visible tcp timestamp option is parsed/initialized. Connections in the SYN_RECV state are not supported, global tcp_time_stamp is used for them, because repair mode doesn't support this state. In a future it can be implemented by the similar way as for TIME_WAIT sockets. Cc: "David S. Miller" <davem@davemloft.net> Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> Cc: James Morris <jmorris@namei.org> Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org> Cc: Patrick McHardy <kaber@trash.net> Cc: Eric Dumazet <edumazet@google.com> Cc: Pavel Emelyanov <xemul@parallels.com> Signed-off-by: Andrey Vagin <avagin@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
* net: fix possible wrong checksum generationEric Dumazet2013-01-281-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Pravin Shelar mentioned that GSO could potentially generate wrong TX checksum if skb has fragments that are overwritten by the user between the checksum computation and transmit. He suggested to linearize skbs but this extra copy can be avoided for normal tcp skbs cooked by tcp_sendmsg(). This patch introduces a new SKB_GSO_SHARED_FRAG flag, set in skb_shinfo(skb)->gso_type if at least one frag can be modified by the user. Typical sources of such possible overwrites are {vm}splice(), sendfile(), and macvtap/tun/virtio_net drivers. Tested: $ netperf -H 7.7.8.84 MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 7.7.8.84 () port 0 AF_INET Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 87380 16384 16384 10.00 3959.52 $ netperf -H 7.7.8.84 -t TCP_SENDFILE TCP SENDFILE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 7.7.8.84 () port 0 AF_INET Recv Send Send Socket Socket Message Elapsed Size Size Size Time Throughput bytes bytes bytes secs. 10^6bits/sec 87380 16384 16384 10.00 3216.80 Performance of the SENDFILE is impacted by the extra allocation and copy, and because we use order-0 pages, while the TCP_STREAM uses bigger pages. Reported-by: Pravin Shelar <pshelar@nicira.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* tcp: make sysctl_tcp_ecn namespace awareHannes Frederic Sowa2013-01-061-1/+1
| | | | | | | | | | | | | | As per suggestion from Eric Dumazet this patch makes tcp_ecn sysctl namespace aware. The reason behind this patch is to ease the testing of ecn problems on the internet and allows applications to tune their own use of ecn. Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: David Miller <davem@davemloft.net> Cc: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-nextLinus Torvalds2012-12-121-0/+5
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Pull networking changes from David Miller: 1) Allow to dump, monitor, and change the bridge multicast database using netlink. From Cong Wang. 2) RFC 5961 TCP blind data injection attack mitigation, from Eric Dumazet. 3) Networking user namespace support from Eric W. Biederman. 4) tuntap/virtio-net multiqueue support by Jason Wang. 5) Support for checksum offload of encapsulated packets (basically, tunneled traffic can still be checksummed by HW). From Joseph Gasparakis. 6) Allow BPF filter access to VLAN tags, from Eric Dumazet and Daniel Borkmann. 7) Bridge port parameters over netlink and BPDU blocking support from Stephen Hemminger. 8) Improve data access patterns during inet socket demux by rearranging socket layout, from Eric Dumazet. 9) TIPC protocol updates and cleanups from Ying Xue, Paul Gortmaker, and Jon Maloy. 10) Update TCP socket hash sizing to be more in line with current day realities. The existing heurstics were choosen a decade ago. From Eric Dumazet. 11) Fix races, queue bloat, and excessive wakeups in ATM and associated drivers, from Krzysztof Mazur and David Woodhouse. 12) Support DOVE (Distributed Overlay Virtual Ethernet) extensions in VXLAN driver, from David Stevens. 13) Add "oops_only" mode to netconsole, from Amerigo Wang. 14) Support set and query of VEB/VEPA bridge mode via PF_BRIDGE, also allow DCB netlink to work on namespaces other than the initial namespace. From John Fastabend. 15) Support PTP in the Tigon3 driver, from Matt Carlson. 16) tun/vhost zero copy fixes and improvements, plus turn it on by default, from Michael S. Tsirkin. 17) Support per-association statistics in SCTP, from Michele Baldessari. And many, many, driver updates, cleanups, and improvements. Too numerous to mention individually. * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1722 commits) net/mlx4_en: Add support for destination MAC in steering rules net/mlx4_en: Use generic etherdevice.h functions. net: ethtool: Add destination MAC address to flow steering API bridge: add support of adding and deleting mdb entries bridge: notify mdb changes via netlink ndisc: Unexport ndisc_{build,send}_skb(). uapi: add missing netconf.h to export list pkt_sched: avoid requeues if possible solos-pci: fix double-free of TX skb in DMA mode bnx2: Fix accidental reversions. bna: Driver Version Updated to 3.1.2.1 bna: Firmware update bna: Add RX State bna: Rx Page Based Allocation bna: TX Intr Coalescing Fix bna: Tx and Rx Optimizations bna: Code Cleanup and Enhancements ath9k: check pdata variable before dereferencing it ath5k: RX timestamp is reported at end of frame ath9k_htc: RX timestamp is reported at end of frame ...
| * ipv6: adapt connect for repair moveAndrey Vagin2012-11-221-0/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This is work the same as for ipv4. All other hacks about tcp repair are in common code for ipv4 and ipv6, so this patch is enough for repairing ipv6 connections. Cc: "David S. Miller" <davem@davemloft.net> Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> Cc: James Morris <jmorris@namei.org> Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org> Cc: Patrick McHardy <kaber@trash.net> Cc: Pavel Emelyanov <xemul@parallels.com> Signed-off-by: Andrey Vagin <avagin@openvz.org> Acked-by: Pavel Emelyanov <xemul@parallels.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* | tcp: bug fix Fast Open client retransmissionYuchung Cheng2012-12-071-5/+10
|/ | | | | | | | | | | | | | | | | | | | If SYN-ACK partially acks SYN-data, the client retransmits the remaining data by tcp_retransmit_skb(). This increments lost recovery state variables like tp->retrans_out in Open state. If loss recovery happens before the retransmission is acked, it triggers the WARN_ON check in tcp_fastretrans_alert(). For example: the client sends SYN-data, gets SYN-ACK acking only ISN, retransmits data, sends another 4 data packets and get 3 dupacks. Since the retransmission is not caused by network drop it should not update the recovery state variables. Further the server may return a smaller MSS than the cached MSS used for SYN-data, so the retranmission needs a loop. Otherwise some data will not be retransmitted until timeout or other loss recovery events. Signed-off-by: Yuchung Cheng <ycheng@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* tcp: fix retransmission in repair modeAndrew Vagin2012-11-151-0/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Currently if a socket was repaired with a few packet in a write queue, a kernel bug may be triggered: kernel BUG at net/ipv4/tcp_output.c:2330! RIP: 0010:[<ffffffff8155784f>] tcp_retransmit_skb+0x5ff/0x610 According to the initial realization v3.4-rc2-963-gc0e88ff, all skb-s should look like already posted. This patch fixes code according with this sentence. Here are three points, which were not done in the initial patch: 1. A tcp send head should not be changed 2. Initialize TSO state of a skb 3. Reset the retransmission time This patch moves logic from tcp_sendmsg to tcp_write_xmit. A packet passes the ussual way, but isn't sent to network. This patch solves all described problems and handles tcp_sendpages. Cc: Pavel Emelyanov <xemul@parallels.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> Cc: James Morris <jmorris@namei.org> Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org> Cc: Patrick McHardy <kaber@trash.net> Signed-off-by: Andrey Vagin <avagin@openvz.org> Acked-by: Pavel Emelyanov <xemul@parallels.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* tcp: use PRR to reduce cwin in CWR stateYuchung Cheng2012-09-031-3/+3
| | | | | | | | | | | | | | | | | | | | | Use proportional rate reduction (PRR) algorithm to reduce cwnd in CWR state, in addition to Recovery state. Retire the current rate-halving in CWR. When losses are detected via ACKs in CWR state, the sender enters Recovery state but the cwnd reduction continues and does not restart. Rename and refactor cwnd reduction functions since both CWR and Recovery use the same algorithm: tcp_init_cwnd_reduction() is new and initiates reduction state variables. tcp_cwnd_reduction() is previously tcp_update_cwnd_in_recovery(). tcp_ends_cwnd_reduction() is previously tcp_complete_cwr(). The rate halving functions and logic such as tcp_cwnd_down(), tcp_min_cwnd(), and the cwnd moderation inside tcp_enter_cwr() are removed. The unused parameter, flag, in tcp_cwnd_reduction() is also removed. Signed-off-by: Yuchung Cheng <ycheng@google.com> Acked-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
generated by cgit v1.2.3 (git 2.25.1) at 2024-12-27 01:04:44 +0000