0

When the number of blocked processes grow indefinitely, how to identify exactly what are these processes.

enter image description here

Since I'm inside a system container (LXC/OpenVZ), I can't modify the hosts' kernel modules to use tools like perf-tools or bcc-tools/bpfcc-tools


The question How to track newly created processes in Linux? doesn't cover the scenario of system containers, and most of the answers rely on tools like perf-tools and bcc-tools.

0

1. Check CONFIG_PROC_EVENTS

First check if CONFIG_PROC_EVENTS is enable. Depending on your distro, you can run:

grep CONFIG_PROC_EVENTS= /boot/config-`uname -r`

If it's enabled, you will get the following result:

CONFIG_PROC_EVENTS=y

2. If it's enabled, create the monitor

Create a file proc_events.c with the content:

static volatile bool need_exit = false;

static int nl_connect()
{
    int rc;
    int nl_sock;
    struct sockaddr_nl sa_nl;

    nl_sock = socket(PF_NETLINK, SOCK_DGRAM, NETLINK_CONNECTOR);
    if (nl_sock == -1) {
        perror("socket");
        return -1;
    }
    sa_nl.nl_family = AF_NETLINK;
    sa_nl.nl_groups = CN_IDX_PROC;
    sa_nl.nl_pid = getpid();
    rc = bind(nl_sock, (struct sockaddr *)&sa_nl, sizeof(sa_nl));
    if (rc == -1) {
        perror("bind");
        close(nl_sock);
        return -1;
    }
    return nl_sock;
}

static int set_proc_ev_listen(int nl_sock, bool enable)
{
    int rc;
    struct __attribute__ ((aligned(NLMSG_ALIGNTO))) {
        struct nlmsghdr nl_hdr;
        struct __attribute__ ((__packed__)) {
            struct cn_msg cn_msg;
            enum proc_cn_mcast_op cn_mcast;
        };
    } nlcn_msg;

    memset(&nlcn_msg, 0, sizeof(nlcn_msg));
    nlcn_msg.nl_hdr.nlmsg_len = sizeof(nlcn_msg);
    nlcn_msg.nl_hdr.nlmsg_pid = getpid();
    nlcn_msg.nl_hdr.nlmsg_type = NLMSG_DONE;

    nlcn_msg.cn_msg.id.idx = CN_IDX_PROC;
    nlcn_msg.cn_msg.id.val = CN_VAL_PROC;
    nlcn_msg.cn_msg.len = sizeof(enum proc_cn_mcast_op);

    nlcn_msg.cn_mcast = enable ? PROC_CN_MCAST_LISTEN : PROC_CN_MCAST_IGNORE;

    rc = send(nl_sock, &nlcn_msg, sizeof(nlcn_msg), 0);
    if (rc == -1) {
        perror("netlink send");
        return -1;
    }

    return 0;
}

static int handle_proc_ev(int nl_sock)
{
    int rc;
    struct __attribute__ ((aligned(NLMSG_ALIGNTO))) {
        struct nlmsghdr nl_hdr;
        struct __attribute__ ((__packed__)) {
            struct cn_msg cn_msg;
            struct proc_event proc_ev;
        };
    } nlcn_msg;
    while (!need_exit) {
        rc = recv(nl_sock, &nlcn_msg, sizeof(nlcn_msg), 0);
        if (rc == 0) {
            /* shutdown? */
            return 0;
        } else if (rc == -1) {
            if (errno == EINTR) continue;
            perror("netlink recv");
            return -1;
        }
        switch (nlcn_msg.proc_ev.what) {
            case PROC_EVENT_NONE:
                printf("set mcast listen ok\n");
                break;
            case PROC_EVENT_FORK:
                printf("fork: parent tid=%d pid=%d -> child tid=%d pid=%d\n",
                        nlcn_msg.proc_ev.event_data.fork.parent_pid,
                        nlcn_msg.proc_ev.event_data.fork.parent_tgid,
                        nlcn_msg.proc_ev.event_data.fork.child_pid,
                        nlcn_msg.proc_ev.event_data.fork.child_tgid);
                break;
            case PROC_EVENT_EXEC:
                printf("exec: tid=%d pid=%d\n",
                        nlcn_msg.proc_ev.event_data.exec.process_pid,
                        nlcn_msg.proc_ev.event_data.exec.process_tgid);
                break;
            case PROC_EVENT_UID:
                printf("uid change: tid=%d pid=%d from %d to %d\n",
                        nlcn_msg.proc_ev.event_data.id.process_pid,
                        nlcn_msg.proc_ev.event_data.id.process_tgid,
                        nlcn_msg.proc_ev.event_data.id.r.ruid,
                        nlcn_msg.proc_ev.event_data.id.e.euid);
                break;
            case PROC_EVENT_GID:
                printf("gid change: tid=%d pid=%d from %d to %d\n",
                        nlcn_msg.proc_ev.event_data.id.process_pid,
                        nlcn_msg.proc_ev.event_data.id.process_tgid,
                        nlcn_msg.proc_ev.event_data.id.r.rgid,
                        nlcn_msg.proc_ev.event_data.id.e.egid);
                break;
            case PROC_EVENT_EXIT:
                printf("exit: tid=%d pid=%d exit_code=%d\n",
                        nlcn_msg.proc_ev.event_data.exit.process_pid,
                        nlcn_msg.proc_ev.event_data.exit.process_tgid,
                        nlcn_msg.proc_ev.event_data.exit.exit_code);
                break;
            default:
                printf("unhandled proc event\n");
                break;
        }
    }

    return 0;
}

static void on_sigint(__attribute__ ((unused)) int unused)
{
    need_exit = true;
}

int main()
{
    int nl_sock;
    int rc = EXIT_SUCCESS;

    signal(SIGINT, &on_sigint);
    siginterrupt(SIGINT, true);
    nl_sock = nl_connect();
    if (nl_sock == -1)
        exit(EXIT_FAILURE);
    rc = set_proc_ev_listen(nl_sock, true);
    if (rc == -1) {
        rc = EXIT_FAILURE;
        goto out;
    }
    rc = handle_proc_ev(nl_sock);
    if (rc == -1) {
        rc = EXIT_FAILURE;
        goto out;
    }
    set_proc_ev_listen(nl_sock, false);
out:
    close(nl_sock);
    exit(rc);
}

Ensure that you can compile C programs. On Debian or Debian-based distros, like Ubuntu, run:

sudo apt-get install build-essential

And compile it with:

gcc proc_events.c -o proc_events

3. Run it for a few seconds

Running it this way will output directly on terminal:

./proc_events

But you can also redirect it and run for a few seconds, in order to save its output on a file:

./proc_events > results_file

4. Analise the results

The output will be in the following format:

fork: parent tid=48 pid=48 -> child tid=56 pid=56
fork: parent tid=48 pid=48 -> child tid=57 pid=57
exec: tid=57 pid=57
exec: tid=56 pid=56
exit: tid=57 pid=57 exit_code=0
exit: tid=56 pid=56 exit_code=0

Credits to @cirosantilli

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.