use netnsid for detecting cgroup networks; fixes #5383 (#5413)

2 files changed, 67 insertions, 6 deletions

diff --git a/collectors/cgroups.plugin/cgroup-network-helper.sh b/collectors/cgroups.plugin/cgroup-network-helper.sh
index 666f02fc88..4ac25cec80 100755
--- a/collectors/cgroups.plugin/cgroup-network-helper.sh
+++ b/collectors/cgroups.plugin/cgroup-network-helper.sh
@@ -60,7 +60,7 @@ fatal() {
     exit 1
 }
 
-debug=0
+debug=${NETDATA_CGROUP_NETWORK_HELPER_DEBUG=0}
 debug() {
     [ "${debug}" = "1" ] && log DEBUG "${@}"
 }
@@ -132,6 +132,8 @@ find_tun_tap_interfaces_for_cgroup() {
         do
             proc_pid_fdinfo_iff "${p}"
         done
+    else
+        debug "Cannot find file '${c}/emulator/cgroup.procs', not searching for tun/tap interfaces."
     fi
 }
 
@@ -185,6 +187,39 @@ virsh_find_all_interfaces_for_cgroup() {
 }
 
 # -----------------------------------------------------------------------------
+# netnsid detected interfaces
+
+netnsid_find_all_interfaces_for_pid() {
+    local pid="${1}"
+    [ -z "${pid}" ] && return 1
+
+    local nsid=$(lsns -t net -p ${pid} -o NETNSID -nr)
+    [ -z "${nsid}" -o "${nsid}" = "unassigned" ] && return 1
+
+    set_source "netnsid"
+    ip link show |\
+        grep -B 1 -E " link-netnsid ${nsid}($| )" |\
+        ip link show | grep -B 1 -E " link-netnsid ${nsid}($| )" | sed -n -e "s|^[[:space:]]*[0-9]\+:[[:space:]]\+\([A-Za-z0-9_]\+\)\(@[A-Za-z0-9_]\+\)*:[[:space:]].*$|\1|p"
+}
+
+netnsid_find_all_interfaces_for_cgroup() {
+    local c="${1}" # the cgroup path
+
+    # for each pid of the cgroup
+    # find any tun/tap devices linked to the pid
+    if [ -f "${c}/cgroup.procs" ]
+    then
+        local p
+        for p in $(< "${c}/cgroup.procs" )
+        do
+            netnsid_find_all_interfaces_for_pid "${p}"
+        done
+    else
+        debug "Cannot find file '${c}/cgroup.procs', not searching for netnsid interfaces."
+    fi
+}
+
+# -----------------------------------------------------------------------------
 
 find_all_interfaces_of_pid_or_cgroup() {
     local p="${1}" c="${2}" # the pid and the cgroup path
@@ -194,6 +229,7 @@ find_all_interfaces_of_pid_or_cgroup() {
         # we have been called with a pid
 
         proc_pid_fdinfo_iff "${p}"
+        netnsid_find_all_interfaces_for_pid "${p}"
 
     elif [ ! -z "${c}" ]
     then
@@ -203,6 +239,7 @@ find_all_interfaces_of_pid_or_cgroup() {
 
         find_tun_tap_interfaces_for_cgroup "${c}"
         virsh_find_all_interfaces_for_cgroup "${c}"
+        netnsid_find_all_interfaces_for_cgroup "${c}"
 
     else
 
diff --git a/collectors/cgroups.plugin/cgroup-network.c b/collectors/cgroups.plugin/cgroup-network.c
index 385672295e..87cb5ef121 100644
--- a/collectors/cgroups.plugin/cgroup-network.c
+++ b/collectors/cgroups.plugin/cgroup-network.c
@@ -86,13 +86,18 @@ unsigned int read_iface_ifindex(const char *prefix, const char *iface) {
     return (unsigned int)ifindex;
 }
 
-struct iface *read_proc_net_dev(const char *prefix) {
+struct iface *read_proc_net_dev(const char *scope, const char *prefix) {
     if(!prefix) prefix = "";
 
     procfile *ff = NULL;
     char filename[FILENAME_MAX + 1];
 
     snprintfz(filename, FILENAME_MAX, "%s%s", prefix, (*prefix)?"/proc/1/net/dev":"/proc/net/dev");
+
+#ifdef NETDATA_INTERNAL_CHECKS
+    info("parsing '%s'", filename);
+#endif
+
     ff = procfile_open(filename, " \t,:|", PROCFILE_FLAG_DEFAULT);
     if(unlikely(!ff)) {
         error("Cannot open file '%s'", filename);
@@ -117,6 +122,10 @@ struct iface *read_proc_net_dev(const char *prefix) {
         t->iflink  = read_iface_iflink(prefix, t->device);
         t->next = root;
         root = t;
+
+#ifdef NETDATA_INTERNAL_CHECKS
+        info("added %s interface '%s', ifindex %u, iflink %u", scope, t->device, t->ifindex, t->iflink);
+#endif
     }
 
     procfile_close(ff);
@@ -323,6 +332,11 @@ pid_t read_pid_from_cgroup_file(const char *filename) {
     }
 
     fclose(fp);
+
+#ifdef NETDATA_INTERNAL_CHECKS
+    if(pid > 0) info("found pid %d on file '%s'", pid, filename);
+#endif
+
     return pid;
 }
 
@@ -380,6 +394,10 @@ struct found_device {
 } *detected_devices = NULL;
 
 void add_device(const char *host, const char *guest) {
+#ifdef NETDATA_INTERNAL_CHECKS
+    info("adding device with host '%s', guest '%s'", host, guest);
+#endif
+
     uint32_t hash = simple_hash(host);
 
     if(guest && (!*guest || strcmp(host, guest) == 0))
@@ -387,10 +405,12 @@ void add_device(const char *host, const char *guest) {
 
     struct found_device *f;
     for(f = detected_devices; f ; f = f->next) {
-        if(f->host_device_hash == hash && strcmp(host, f->host_device) == 0) {
+        if(f->host_device_hash == hash && !strcmp(host, f->host_device)) {
 
-            if(guest && !f->guest_device)
+            if(guest && (!f->guest_device || !strcmp(f->host_device, f->guest_device))) {
+                if(f->guest_device) freez((void *)f->guest_device);
                 f->guest_device = strdupz(guest);
+            }
 
             return;
         }
@@ -425,7 +445,7 @@ void detect_veth_interfaces(pid_t pid) {
     struct iface *cgroup = NULL;
     struct iface *host, *h, *c;
 
-    host = read_proc_net_dev(netdata_configured_host_prefix);
+    host = read_proc_net_dev("host", netdata_configured_host_prefix);
     if(!host) {
         errno = 0;
         error("cannot read host interface list.");
@@ -444,7 +464,11 @@ void detect_veth_interfaces(pid_t pid) {
         goto cleanup;
     }
 
-    cgroup = read_proc_net_dev(NULL);
+#ifdef NETDATA_INTERNAL_CHECKS
+    info("switched to namespaces of pid %d", pid);
+#endif
+
+    cgroup = read_proc_net_dev("cgroup", NULL);
     if(!cgroup) {
         errno = 0;
         error("cannot read cgroup interface list.");