aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2008-07-23 19:38:45 -0400
committerDavid S. Miller <davem@davemloft.net>2008-07-23 19:38:45 -0400
commit4b53fb67e385b856a991d402096379dab462170a (patch)
tree333dada17059f4c67c48123974059206c2e676d9
parente8ebe3b893792887317bc24cc4608753f81b81d3 (diff)
tcp: Clear probes_out more aggressively in tcp_ack().
This is based upon an excellent bug report from Eric Dumazet. tcp_ack() should clear ->icsk_probes_out even if there are packets outstanding. Otherwise if we get a sequence of ACKs while we do have packets outstanding over and over again, we'll never clear the probes_out value and eventually think the connection is too sick and we'll reset it. This appears to be some "optimization" added to tcp_ack() in the 2.4.x timeframe. In 2.2.x, probes_out is pretty much always cleared by tcp_ack(). Here is Eric's original report: ---------------------------------------- Apparently, we can in some situations reset TCP connections in a couple of seconds when some frames are lost. In order to reproduce the problem, please try the following program on linux-2.6.25.* Setup some iptables rules to allow two frames per second sent on loopback interface to tcp destination port 12000 iptables -N SLOWLO iptables -A SLOWLO -m hashlimit --hashlimit 2 --hashlimit-burst 1 --hashlimit-mode dstip --hashlimit-name slow2 -j ACCEPT iptables -A SLOWLO -j DROP iptables -A OUTPUT -o lo -p tcp --dport 12000 -j SLOWLO Then run the attached program and see the output : # ./loop State Recv-Q Send-Q Local Address:Port Peer Address:Port ESTAB 0 40 127.0.0.1:54455 127.0.0.1:12000 timer:(persist,200ms,1) State Recv-Q Send-Q Local Address:Port Peer Address:Port ESTAB 0 40 127.0.0.1:54455 127.0.0.1:12000 timer:(persist,200ms,3) State Recv-Q Send-Q Local Address:Port Peer Address:Port ESTAB 0 40 127.0.0.1:54455 127.0.0.1:12000 timer:(persist,200ms,5) State Recv-Q Send-Q Local Address:Port Peer Address:Port ESTAB 0 40 127.0.0.1:54455 127.0.0.1:12000 timer:(persist,200ms,7) State Recv-Q Send-Q Local Address:Port Peer Address:Port ESTAB 0 40 127.0.0.1:54455 127.0.0.1:12000 timer:(persist,200ms,9) State Recv-Q Send-Q Local Address:Port Peer Address:Port ESTAB 0 40 127.0.0.1:54455 127.0.0.1:12000 timer:(persist,200ms,11) State Recv-Q Send-Q Local Address:Port Peer Address:Port ESTAB 0 40 127.0.0.1:54455 127.0.0.1:12000 timer:(persist,201ms,13) State Recv-Q Send-Q Local Address:Port Peer Address:Port ESTAB 0 40 127.0.0.1:54455 127.0.0.1:12000 timer:(persist,188ms,15) write(): Connection timed out wrote 890 bytes but was interrupted after 9 seconds ESTAB 0 0 127.0.0.1:12000 127.0.0.1:54455 Exiting read() because no data available (4000 ms timeout). read 860 bytes While this tcp session makes progress (sending frames with 50 bytes of payload, every 500ms), linux tcp stack decides to reset it, when tcp_retries 2 is reached (default value : 15) tcpdump : 15:30:28.856695 IP 127.0.0.1.56554 > 127.0.0.1.12000: S 33788768:33788768(0) win 32792 <mss 16396,nop,nop,sackOK,nop,wscale 7> 15:30:28.856711 IP 127.0.0.1.12000 > 127.0.0.1.56554: S 33899253:33899253(0) ack 33788769 win 32792 <mss 16396,nop,nop,sackOK,nop,wscale 7> 15:30:29.356947 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 1:61(60) ack 1 win 257 15:30:29.356966 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 61 win 257 15:30:29.866415 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 61:111(50) ack 1 win 257 15:30:29.866427 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 111 win 257 15:30:30.366516 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 111:161(50) ack 1 win 257 15:30:30.366527 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 161 win 257 15:30:30.876196 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 161:211(50) ack 1 win 257 15:30:30.876207 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 211 win 257 15:30:31.376282 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 211:261(50) ack 1 win 257 15:30:31.376290 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 261 win 257 15:30:31.885619 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 261:311(50) ack 1 win 257 15:30:31.885631 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 311 win 257 15:30:32.385705 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 311:361(50) ack 1 win 257 15:30:32.385715 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 361 win 257 15:30:32.895249 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 361:411(50) ack 1 win 257 15:30:32.895266 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 411 win 257 15:30:33.395341 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 411:461(50) ack 1 win 257 15:30:33.395351 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 461 win 257 15:30:33.918085 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 461:511(50) ack 1 win 257 15:30:33.918096 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 511 win 257 15:30:34.418163 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 511:561(50) ack 1 win 257 15:30:34.418172 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 561 win 257 15:30:34.927685 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 561:611(50) ack 1 win 257 15:30:34.927698 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 611 win 257 15:30:35.427757 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 611:661(50) ack 1 win 257 15:30:35.427766 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 661 win 257 15:30:35.937359 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 661:711(50) ack 1 win 257 15:30:35.937376 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 711 win 257 15:30:36.437451 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 711:761(50) ack 1 win 257 15:30:36.437464 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 761 win 257 15:30:36.947022 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 761:811(50) ack 1 win 257 15:30:36.947039 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 811 win 257 15:30:37.447135 IP 127.0.0.1.56554 > 127.0.0.1.12000: P 811:861(50) ack 1 win 257 15:30:37.447203 IP 127.0.0.1.12000 > 127.0.0.1.56554: . ack 861 win 257 15:30:41.448171 IP 127.0.0.1.12000 > 127.0.0.1.56554: F 1:1(0) ack 861 win 257 15:30:41.448189 IP 127.0.0.1.56554 > 127.0.0.1.12000: R 33789629:33789629(0) win 0 Source of program : /* * small producer/consumer program. * setup a listener on 127.0.0.1:12000 * Forks a child * child connect to 127.0.0.1, and sends 10 bytes on this tcp socket every 100 ms * Father accepts connection, and read all data */ #include <sys/types.h> #include <sys/socket.h> #include <netinet/in.h> #include <unistd.h> #include <stdio.h> #include <time.h> #include <sys/poll.h> int port = 12000; char buffer[4096]; int main(int argc, char *argv[]) { int lfd = socket(AF_INET, SOCK_STREAM, 0); struct sockaddr_in socket_address; time_t t0, t1; int on = 1, sfd, res; unsigned long total = 0; socklen_t alen = sizeof(socket_address); pid_t pid; time(&t0); socket_address.sin_family = AF_INET; socket_address.sin_port = htons(port); socket_address.sin_addr.s_addr = htonl(INADDR_LOOPBACK); if (lfd == -1) { perror("socket()"); return 1; } setsockopt(lfd, SOL_SOCKET, SO_REUSEADDR, &on, sizeof(int)); if (bind(lfd, (struct sockaddr *)&socket_address, sizeof(socket_address)) == -1) { perror("bind"); close(lfd); return 1; } if (listen(lfd, 1) == -1) { perror("listen()"); close(lfd); return 1; } pid = fork(); if (pid == 0) { int i, cfd = socket(AF_INET, SOCK_STREAM, 0); close(lfd); if (connect(cfd, (struct sockaddr *)&socket_address, sizeof(socket_address)) == -1) { perror("connect()"); return 1; } for (i = 0 ; ;) { res = write(cfd, "blablabla\n", 10); if (res > 0) total += res; else if (res == -1) { perror("write()"); break; } else break; usleep(100000); if (++i == 10) { system("ss -on dst 127.0.0.1:12000"); i = 0; } } time(&t1); fprintf(stderr, "wrote %lu bytes but was interrupted after %g seconds\n", total, difftime(t1, t0)); system("ss -on | grep 127.0.0.1:12000"); close(cfd); return 0; } sfd = accept(lfd, (struct sockaddr *)&socket_address, &alen); if (sfd == -1) { perror("accept"); return 1; } close(lfd); while (1) { struct pollfd pfd[1]; pfd[0].fd = sfd; pfd[0].events = POLLIN; if (poll(pfd, 1, 4000) == 0) { fprintf(stderr, "Exiting read() because no data available (4000 ms timeout).\n"); break; } res = read(sfd, buffer, sizeof(buffer)); if (res > 0) total += res; else if (res == 0) break; else perror("read()"); } fprintf(stderr, "read %lu bytes\n", total); close(sfd); return 0; } ---------------------------------------- Signed-off-by: David S. Miller <davem@davemloft.net>
-rw-r--r--net/ipv4/tcp_input.c3
1 files changed, 1 insertions, 2 deletions
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 1f5e6049883e..75efd244f2af 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3292,6 +3292,7 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag)
3292 * log. Something worked... 3292 * log. Something worked...
3293 */ 3293 */
3294 sk->sk_err_soft = 0; 3294 sk->sk_err_soft = 0;
3295 icsk->icsk_probes_out = 0;
3295 tp->rcv_tstamp = tcp_time_stamp; 3296 tp->rcv_tstamp = tcp_time_stamp;
3296 prior_packets = tp->packets_out; 3297 prior_packets = tp->packets_out;
3297 if (!prior_packets) 3298 if (!prior_packets)
@@ -3324,8 +3325,6 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag)
3324 return 1; 3325 return 1;
3325 3326
3326no_queue: 3327no_queue:
3327 icsk->icsk_probes_out = 0;
3328
3329 /* If this ack opens up a zero window, clear backoff. It was 3328 /* If this ack opens up a zero window, clear backoff. It was
3330 * being used to time the probes, and is probably far higher than 3329 * being used to time the probes, and is probably far higher than
3331 * it needs to be for normal retransmission. 3330 * it needs to be for normal retransmission.