Question

在服务器停止运行后，TCP keepalive（小超时）是否阻止客户端挂起recv？

情景：

在不同的计算机上运行的服务器和客户端：

客户端通过TCP使用KEEPALIVE选项
客户端发送“Hello服务器”并等待响应
服务器收到“Hello server”并响应“Hello client”
客户收到回复，睡10秒，重复步骤2-4（现在跳过步骤1 - 保留连接）

在客户端休眠期间，服务器现已插上电源：

客户醒来
发送“Hello服务器”并等待回复
20分钟后recv放弃 - 我希望KEEPALIVE在 45秒之后打破recv功能：

设置KEEPALIVE选项：

void TCPclient::setkeepalive()
{
   int optval;
   socklen_t optlen = sizeof(optval);

   /* Check the status for the keepalive option */
   if(getsockopt(sock, SOL_SOCKET, SO_KEEPALIVE, &optval, &optlen) < 0) {
        throw std::string("getsockopt");
   }

   optval = 1;
   optlen = sizeof(optval);
   if(setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE, &optval, optlen) < 0) {
      close(s);
      exit(EXIT_FAILURE);
   }

    optval = 2;
    if (setsockopt(sock, SOL_TCP, TCP_KEEPCNT, &optval, optlen) < 0) {
        throw std::string("setsockopt");
    }

    optval = 15;
    if (setsockopt(sock, SOL_TCP, TCP_KEEPIDLE, &optval, optlen) < 0) {
        throw std::string("setsockopt");
    }

    optval = 15;
    if (setsockopt(sock, SOL_TCP, TCP_KEEPINTVL, &optval, optlen) < 0) {
        throw std::string("setsockopt");
    }   
}

linux 3.2.0-84-generic

Answer 1

当线路空闲15秒后，Keepalive变为活动状态。在你的情况下，Keepalive启动超时是15秒，睡眠是10秒，这意味着＆＃34;你好服务器＆＃34;将是服务器被杀死后发送的下一个命令。

您的Linux会尝试多次重新传输该消息。 Keepalive仍然不会被触发。在达到重试限制后连接将中断 - 这将需要10-30分钟。

Answer 2

@ MMA的回答是正确的。我在写作之前写了一个类似的客户等待20秒。一旦客户端唤醒并发送消息，则不再发送由keep alive发送的ACK消息（连接不再空闲）。

在15次重试（在/ proc / sys / net / ipv4中使用tcp_retries2配置）发送tcp段后，其中超时呈指数级增长，直到达到~2分钟（在我的情况下），连接被设置为错误并且挂起读取或恢复返回ETIMEDOUT（错误110）。在我的情况下，花了约15分钟。这个时间取决于RTO。看到TCPDUMP，三次握手后有两个ACK（我不知道为什么这两个ack的第一个）然后是15个带有数据和推送标志的消息。

tcpdump: verbose output suppressed, use -v or -vv for full protocol decode
listening on p2p1, link-type EN10MB (Ethernet), capture size 65535 bytes
01:16:45.296179 IP 192.168.2.100.60895 > ec2-52-7-150-140.compute-1.amazonaws.com.10221: Flags [S], seq 515423022, win 14600, options [mss 1460,sackOK,TS val 19212623 ecr 0,nop,wscale 7], length 0
E..<.a@.@......d4.....'...........9............
.%)O........
01:16:45.477983 IP ec2-52-7-150-140.compute-1.amazonaws.com.10221 > 192.168.2.100.60895: Flags [S.], seq 3672727778, ack 515423023, win 26847, options [mss 1436,sackOK,TS val 114765522 ecr 19212623,nop,wscale 7], length 0
E..<..@.-...4......d'.....`..../..h............
.....%)O....
01:16:45.478046 IP 192.168.2.100.60895 > ec2-52-7-150-140.compute-1.amazonaws.com.10221: Flags [.], ack 1, win 115, options [nop,nop,TS val 19212805 ecr 114765522], length 0
E..4.b@.@......d4.....'..../..`....s.......
.%*.....
01:17:00.512812 IP 192.168.2.100.60895 > ec2-52-7-150-140.compute-1.amazonaws.com.10221: Flags [.], ack 1, win 115, options [nop,nop,TS val 19227840 ecr 114765522], length 0
E..4.c@.@......d4.....'.......`....s.......
.%d.....
01:17:00.731160 IP ec2-52-7-150-140.compute-1.amazonaws.com.10221 > 192.168.2.100.60895: Flags [.], ack 1, win 210, options [nop,nop,TS val 114769336 ecr 19212805], length 0
E..4N.@.-.r.4......d'.....`..../....M......
..=..%*.
01:17:05.478933 IP 192.168.2.100.60895 > ec2-52-7-150-140.compute-1.amazonaws.com.10221: Flags [P.], seq 1:15, ack 1, win 115, options [nop,nop,TS val 19232806 ecr 114769336], length 14
E..B.d@.@......d4.....'..../..`....s.......
.%x&..=.Hello Word :).
01:17:06.027768 IP 192.168.2.100.60895 > ec2-52-7-150-140.compute-1.amazonaws.com.10221: Flags [P.], seq 1:15, ack 1, win 115, options [nop,nop,TS val 19233354 ecr 114769336], length 14
E..B.e@.@......d4.....'..../..`....s.......
.%zJ..=.Hello Word :).
01:17:07.120879 IP 192.168.2.100.60895 > ec2-52-7-150-140.compute-1.amazonaws.com.10221: Flags [P.], seq 1:15, ack 1, win 115, options [nop,nop,TS val 19234448 ecr 114769336], length 14
E..B.f@.@......d4.....'..../..`....s.......
.%~...=.Hello Word :).
01:17:09.312833 IP 192.168.2.100.60895 > ec2-52-7-150-140.compute-1.amazonaws.com.10221: Flags [P.], seq 1:15, ack 1, win 115, options [nop,nop,TS val 19236640 ecr 114769336], length 14
E..B.g@.@......d4.....'..../..`....s.......
.%. ..=.Hello Word :).
01:17:13.697663 IP 192.168.2.100.60895 > ec2-52-7-150-140.compute-1.amazonaws.com.10221: Flags [P.], seq 1:15, ack 1, win 115, options [nop,nop,TS val 19241024 ecr 114769336], length 14
E..B.h@.@......d4.....'..../..`....s.......
.%.@..=.Hello Word :).
01:17:22.466187 IP 192.168.2.100.60895 > ec2-52-7-150-140.compute-1.amazonaws.com.10221: Flags [P.], seq 1:15, ack 1, win 115, options [nop,nop,TS val 19249793 ecr 114769336], length 14
E..B.i@.@......d4.....'..../..`....s.......
.%....=.Hello Word :).
01:17:40.001653 IP 192.168.2.100.60895 > ec2-52-7-150-140.compute-1.amazonaws.com.10221: Flags [P.], seq 1:15, ack 1, win 115, options [nop,nop,TS val 19267328 ecr 114769336], length 14
E..B.j@.@......d4.....'..../..`....s.......
.%....=.Hello Word :).
01:18:15.074493 IP 192.168.2.100.60895 > ec2-52-7-150-140.compute-1.amazonaws.com.10221: Flags [P.], seq 1:15, ack 1, win 115, options [nop,nop,TS val 19302401 ecr 114769336], length 14
E..B.k@.@......d4.....'..../..`....s.......
.&....=.Hello Word :).
01:19:25.217799 IP 192.168.2.100.60895 > ec2-52-7-150-140.compute-1.amazonaws.com.10221: Flags [P.], seq 1:15, ack 1, win 115, options [nop,nop,TS val 19372545 ecr 114769336], length 14
E..B.l@.@......d4.....'..../..`....s.......
.'....=.Hello Word :).
01:21:25.537775 IP 192.168.2.100.60895 > ec2-52-7-150-140.compute-1.amazonaws.com.10221: Flags [P.], seq 1:15, ack 1, win 115, options [nop,nop,TS val 19492864 ecr 114769336], length 14
E..B.m@.@......d4.....'..../..`....s.......
.)p...=.Hello Word :).
01:23:25.856854 IP 192.168.2.100.60895 > ec2-52-7-150-140.compute-1.amazonaws.com.10221: Flags [P.], seq 1:15, 69336], length 14
E..B.n@.@......d4.....'..../..`....s.......
.+F...=.Hello Word :).
01:25:26.176894 IP 192.168.2.100.60895 > ec2-52-7-150-140.compute-1.amazonaws.com.10221: Flags [P.], seq 1:15, 69336], length 14
E..B.o@.@......d4.....'..../..`....s.......
.-....=.Hello Word :).
01:27:26.497691 IP 192.168.2.100.60895 > ec2-52-7-150-140.compute-1.amazonaws.com.10221: Flags [P.], seq 1:15, 69336], length 14
E..B.p@.@......d4.....'..../..`....s.......
......=.Hello Word :).
01:29:26.816905 IP 192.168.2.100.60895 > ec2-52-7-150-140.compute-1.amazonaws.com.10221: Flags [P.], seq 1:15, 69336], length 14
E..B.q@.@......d4.....'..../..`....s.......
.0....=.Hello Word :).
01:31:27.137013 IP 192.168.2.100.60895 > ec2-52-7-150-140.compute-1.amazonaws.com.10221: Flags [P.], seq 1:15, ack 1, win 115, options [nop,nop,TS val 20094464 ecr 114769336], length 14
E..B.r@.@......d4.....'..../..`....s.......
.2....=.Hello Word :).

我使用的客户端代码：

#include <sys/types.h>
#include <sys/socket.h>
#include <string.h>
#include <errno.h>
#include <unistd.h>
#include <netinet/in.h>
#include <net/if.h>
#include <arpa/inet.h>
#include <stdio.h>


#include <sys/socket.h>
#include <stdlib.h>
#include <netinet/tcp.h>


#define DEST_PORT 10221
#define ADDRLEN INET_ADDRSTRLEN


int main(int argc, char** argv)
{
    int sock;
    int bytesWritten;
    struct sockaddr_in their_addr;
    char buffer[] = "Hello Word :)";
    char addrstr[ADDRLEN + 1];

    if (argc != 2)
    {
       printf("ERROR - Number of args\n");
       return 10;
    }

    strncpy(addrstr, argv[1], ADDRLEN);

    bzero(&their_addr, sizeof(their_addr));
    their_addr.sin_family = AF_INET;
    their_addr.sin_port = htons(DEST_PORT);

    if (inet_pton(AF_INET, addrstr,(void *)&their_addr.sin_addr) != 1)
    {
        printf("ERROR - Converting Address: %d\n", errno);
        return 2;
    }

    if ((sock = socket(AF_INET, SOCK_STREAM, 0)) == -1)
    {
        printf("ERROR - Socket could not be open: %d\n", errno);
        return 1;
    }

//// Copied option setting
   int optval;
   socklen_t optlen = sizeof(optval);

   /* Check the status for the keepalive option */
   if(getsockopt(sock, SOL_SOCKET, SO_KEEPALIVE, &optval, &optlen) < 0) {
        printf("ERROR - SOL_SOCKET: %d\n", errno);
        return 19;
   }

   optval = 1;
   optlen = sizeof(optval);
   if(setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE, &optval, optlen) < 0) {
        printf("ERROR - SOL_SOCKET-2: %d\n", errno);
        return 20;
   }

    optval = 2;
    if (setsockopt(sock, SOL_TCP, TCP_KEEPCNT, &optval, optlen) < 0) {
        printf("ERROR - SOL_TCP: %d\n", errno);
        return 21;
    }

    optval = 15;
    if (setsockopt(sock, SOL_TCP, TCP_KEEPIDLE, &optval, optlen) < 0) {
        printf("ERROR - SOL_TCP-2: %d\n", errno);
        return 22;
    }

    optval = 15;
    if (setsockopt(sock, SOL_TCP, TCP_KEEPINTVL, &optval, optlen) < 0) {
        printf("ERROR - SOL_TCP-3: %d\n", errno);
        return 23;
    }   
/////
    if (connect(sock, (const struct sockaddr *)&their_addr, 
                (socklen_t)sizeof(their_addr)) == -1)
    {
        printf("ERROR - Could not connect to destination: %d\n", errno);
        return 3;
    }

/// Sleep 20 seconds    
    sleep(20);
    printf("About to write\n");

    if ((bytesWritten = write(sock, (const void *)buffer, sizeof(buffer))) == -1)
    {
        printf("ERROR - Sending message: %d\n", errno);
        return 4;
    }

    printf("Message Sent to Address %s, Port: %d\n\n", addrstr, DEST_PORT);

    int bytesRead;

    if ((bytesRead = read(sock, buffer, sizeof(buffer))) == -1)
    {
        printf("ERROR - Sending message: %d\n", errno);
        return 4;
    }

    close(sock);

    return 0;
}

我使用AWS托管的服务器运行此测试。在没有注意到客户端的情况下模拟删除服务器的方法是：我有一个与服务器关联的公共（弹性）IP，并且在三次握手后立即将Elastic IP与服务器解除关联。我无法粘贴服务器代码，但这里不相关。

请注意，在此示例中，由于发送消息，keepalive已停止。

TCP，recv功能挂起尽管KEEPALIVE

2 个答案: