Merging upstream version 1.31.0.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

5 files changed, 102 insertions, 12 deletions

diff --git a/collectors/cgroups.plugin/README.md b/collectors/cgroups.plugin/README.md
index 21dbcae83..86776d6e0 100644
--- a/collectors/cgroups.plugin/README.md
+++ b/collectors/cgroups.plugin/README.md
@@ -147,6 +147,33 @@ Support per distribution:
 |AMI|NO|[here](http://pastebin.com/FrxmptjL)|not a systemd system|
 |CentOS 7.3.1611|NO|[here](http://pastebin.com/SpzgezAg)|can be enabled, see below|
 
+### Monitored systemd service metrics
+
+- CPU utilization
+- Used memory
+- RSS memory
+- Mapped memory
+- Cache memory
+- Writeback memory
+- Memory minor page faults
+- Memory major page faults
+- Memory charging activity
+- Memory uncharging activity
+- Memory limit failures
+- Swap memory used
+- Disk read bandwidth
+- Disk write bandwidth
+- Disk read operations
+- Disk write operations
+- Throttle disk read bandwidth
+- Throttle disk write bandwidth
+- Throttle disk read operations
+- Throttle disk write operations
+- Queued disk read operations
+- Queued disk write operations
+- Merged disk read operations
+- Merged disk write operations
+
 ### how to enable cgroup accounting on systemd systems that is by default disabled
 
 You can verify there is no accounting enabled, by running `systemd-cgtop`. The program will show only resources for cgroup `/`, but all services will show nothing.
@@ -230,4 +257,31 @@ So, when a network interface or container stops, Netdata might log a few errors
 6.  obsolete charts will be removed from memory, 1 hour after the last user viewed them (configurable with `[global].cleanup obsolete charts after seconds = 3600` (at `netdata.conf`).
 7.  when obsolete charts are removed from memory they are also deleted from disk (configurable with `[global].delete obsolete charts files = yes`)
 
+### Monitored container metrics
+
+- CPU usage
+- CPU usage within the limits
+- CPU usage per core
+- Memory usage
+- Writeback memory
+- Memory activity
+- Memory page faults
+- Used memory
+- Used RAM within the limits
+- Memory utilization
+- Memory limit failures
+- I/O bandwidth (all disks)
+- Serviced I/O operations (all disks)
+- Throttle I/O bandwidth (all disks)
+- Throttle serviced I/O operations (all disks)
+- Queued I/O operations (all disks)
+- Merged I/O operations (all disks)
+- CPU pressure
+- Memory pressure
+- Memory full pressure
+- I/O pressure
+- I/O full pressure
+  
+Network interfaces are monitored by means of the [proc plugin](/collectors/proc.plugin/README.md#monitored-network-interface-metrics).
+
 [![analytics](https://www.google-analytics.com/collect?v=1&aip=1&t=pageview&_s=1&ds=github&dr=https%3A%2F%2Fgithub.com%2Fnetdata%2Fnetdata&dl=https%3A%2F%2Fmy-netdata.io%2Fgithub%2Fcollectors%2Fcgroups.plugin%2FREADME&_u=MAC~&cid=5792dfd7-8dc4-476b-af31-da2fdb9f93d2&tid=UA-64295674-3)](<>)
diff --git a/collectors/cgroups.plugin/cgroup-name.sh.in b/collectors/cgroups.plugin/cgroup-name.sh.in
index 19fbf3989..8ef8ab58e 100755
--- a/collectors/cgroups.plugin/cgroup-name.sh.in
+++ b/collectors/cgroups.plugin/cgroup-name.sh.in
@@ -428,6 +428,14 @@ if [ -z "${NAME}" ]; then
     # systemd-nspawn
     NAME="$(echo "${CGROUP}" | sed 's/.*machine.slice[_\/]\(.*\)\.service/\1/g')"
 
+  elif [[ ${CGROUP} =~ machine.slice_machine.*-lxc ]]; then
+    # libvirtd / lxc containers
+	# examples:
+	# before: machine.slice machine-lxc/x2d969/x2dhubud0xians01.scope
+    # after:  lxc/hubud0xians01
+	# before: machine.slice_machine-lxc/x2d969/x2dhubud0xians01.scope/libvirt_init.scope
+	# after:  lxc/hubud0xians01/libvirt_init
+    NAME="lxc/$(echo "${CGROUP}" | sed 's/machine.slice_machine.*-lxc//; s/\/x2d[[:digit:]]*//; s/\/x2d//g; s/\.scope//g')"
   elif [[ ${CGROUP} =~ machine.slice_machine.*-qemu ]]; then
     # libvirtd / qemu virtual machines
     # NAME="$(echo ${CGROUP} | sed 's/machine.slice_machine.*-qemu//; s/\/x2d//; s/\/x2d/\-/g; s/\.scope//g')"
diff --git a/collectors/cgroups.plugin/cgroup-network-helper.sh b/collectors/cgroups.plugin/cgroup-network-helper.sh
index eb839ef57..1b60f452a 100755
--- a/collectors/cgroups.plugin/cgroup-network-helper.sh
+++ b/collectors/cgroups.plugin/cgroup-network-helper.sh
@@ -123,7 +123,7 @@ proc_pid_fdinfo_iff() {
 find_tun_tap_interfaces_for_cgroup() {
     local c="${1}" # the cgroup path
     [ -d "${c}/emulator" ] && c="${c}/emulator" # check for 'emulator' subdirectory
-    c="${c}/cgroup.procs" # make full path 
+    c="${c}/cgroup.procs" # make full path
 
     # for each pid of the cgroup
     # find any tun/tap devices linked to the pid
@@ -168,18 +168,26 @@ virsh_find_all_interfaces_for_cgroup() {
     then
         local d
         d="$(virsh_cgroup_to_domain_name "${c}")"
+        # convert hex to character
+        # e.g.: vm01\x2dweb => vm01-web (https://github.com/netdata/netdata/issues/11088#issuecomment-832618149)
+        d="$(printf '%b' "${d}")"
 
         if [ ! -z "${d}" ]
         then
             debug "running: virsh domiflist ${d}; to find the network interfaces"
 
-            # match only 'network' interfaces from virsh output
+            # 'virsh -r domiflist <domain>' example output
+            # Interface  Type       Source     Model       MAC
+            #--------------------------------------------------------------
+            # vnet3       bridge    br0        virtio   52:54:00:xx:xx:xx
+            # vnet4       network   default    virtio   52:54:00:yy:yy:yy
 
+            # match only 'network' interfaces from virsh output
             set_source "virsh"
             "${virsh}" -r domiflist "${d}" |\
                 sed -n \
-                    -e "s|^\([^[:space:]]\+\)[[:space:]]\+network[[:space:]]\+\([^[:space:]]\+\)[[:space:]]\+[^[:space:]]\+[[:space:]]\+[^[:space:]]\+$|\1 \1_\2|p" \
-                    -e "s|^\([^[:space:]]\+\)[[:space:]]\+bridge[[:space:]]\+\([^[:space:]]\+\)[[:space:]]\+[^[:space:]]\+[[:space:]]\+[^[:space:]]\+$|\1 \1_\2|p"
+                    -e "s|^[[:space:]]\?\([^[:space:]]\+\)[[:space:]]\+network[[:space:]]\+\([^[:space:]]\+\)[[:space:]]\+[^[:space:]]\+[[:space:]]\+[^[:space:]]\+$|\1 \1_\2|p" \
+                    -e "s|^[[:space:]]\?\([^[:space:]]\+\)[[:space:]]\+bridge[[:space:]]\+\([^[:space:]]\+\)[[:space:]]\+[^[:space:]]\+[[:space:]]\+[^[:space:]]\+$|\1 \1_\2|p"
         else
             debug "no virsh domain extracted from cgroup ${c}"
         fi
diff --git a/collectors/cgroups.plugin/cgroup-network.c b/collectors/cgroups.plugin/cgroup-network.c
index 921b14dfb..562d30663 100644
--- a/collectors/cgroups.plugin/cgroup-network.c
+++ b/collectors/cgroups.plugin/cgroup-network.c
@@ -453,7 +453,7 @@ void detect_veth_interfaces(pid_t pid) {
 
     if(!eligible_ifaces(host)) {
         errno = 0;
-        error("there are no double-linked host interfaces available.");
+        info("there are no double-linked host interfaces available.");
         goto cleanup;
     }
 
diff --git a/collectors/cgroups.plugin/sys_fs_cgroup.c b/collectors/cgroups.plugin/sys_fs_cgroup.c
index ceffffe92..eea4d9ae7 100644
--- a/collectors/cgroups.plugin/sys_fs_cgroup.c
+++ b/collectors/cgroups.plugin/sys_fs_cgroup.c
@@ -142,7 +142,7 @@ static enum cgroups_type cgroups_try_detect_version()
     enum cgroups_systemd_setting systemd_setting;
     int cgroups2_available = 0;
 
-    // 1. check if cgroups2 availible on system at all
+    // 1. check if cgroups2 available on system at all
     FILE *f = mypopen("grep cgroup /proc/filesystems", &command_pid);
     if (!f) {
         error("popen failed");
@@ -160,7 +160,20 @@ static enum cgroups_type cgroups_try_detect_version()
     if(!cgroups2_available)
         return CGROUPS_V1;
 
-    // 2. check systemd compiletime setting
+#if defined CGROUP2_SUPER_MAGIC
+    // 2. check filesystem type for the default mountpoint
+    char filename[FILENAME_MAX + 1];
+    snprintfz(filename, FILENAME_MAX, "%s%s", netdata_configured_host_prefix, "/sys/fs/cgroup");
+    struct statfs fsinfo;
+    if (!statfs(filename, &fsinfo)) {
+        if (fsinfo.f_type == CGROUP2_SUPER_MAGIC)
+            return CGROUPS_V2;
+        if (fsinfo.f_type == CGROUP_SUPER_MAGIC)
+            return CGROUPS_V1;
+    }
+#endif
+
+    // 3. check systemd compiletime setting
     if ((systemd_setting = cgroups_detect_systemd("systemd --version")) == SYSTEMD_CGROUP_ERR)
         systemd_setting = cgroups_detect_systemd(SYSTEMD_CMD_RHEL);
 
@@ -168,13 +181,13 @@ static enum cgroups_type cgroups_try_detect_version()
         return CGROUPS_AUTODETECT_FAIL;
 
     if(systemd_setting == SYSTEMD_CGROUP_LEGACY || systemd_setting == SYSTEMD_CGROUP_HYBRID) {
-        // curently we prefer V1 if HYBRID is set as it seems to be more feature complete
+        // currently we prefer V1 if HYBRID is set as it seems to be more feature complete
         // in the future we might want to continue here if SYSTEMD_CGROUP_HYBRID
         // and go ahead with V2
         return CGROUPS_V1;
     }
 
-    // 3. if we are unified as on Fedora (default cgroups2 only mode)
+    // 4. if we are unified as on Fedora (default cgroups2 only mode)
     //    check kernel command line flag that can override that setting
     f = fopen("/proc/cmdline", "r");
     if (!f) {
@@ -1300,6 +1313,12 @@ static inline char *cgroup_chart_id_strdupz(const char *s) {
     char *r = strdupz(s);
     netdata_fix_chart_id(r);
 
+    // dots are used to distinguish chart type and id in streaming, so we should replace them
+    for (char *d = r; *d; d++) {
+        if (*d == '.')
+            *d = '-';
+    }
+
     return r;
 }
 
@@ -1469,7 +1488,7 @@ static inline struct cgroup *cgroup_add(const char *id) {
     }
 
     if(user_configurable) {
-        // allow the user to enable/disable this individualy
+        // allow the user to enable/disable this individually
         char option[FILENAME_MAX + 1];
         snprintfz(option, FILENAME_MAX, "enable cgroup %s", cg->chart_title);
         cg->enabled = (char) config_get_boolean("plugin:cgroups", option, def);
@@ -3996,9 +4015,10 @@ static void cgroup_main_cleanup(void *ptr) {
         uv_mutex_unlock(&discovery_thread.mutex);
     }
 
+    info("waiting for discovery thread to finish...");
+    
     while (!discovery_thread.exited && max > 0) {
         max -= step;
-        info("waiting for discovery thread to finish...");
         sleep_usec(step);
     }
 
@@ -4077,7 +4097,7 @@ void *cgroups_main(void *ptr) {
                         , NULL
                         , "cgroups"
                         , NULL
-                        , "NetData CGroups Plugin CPU usage"
+                        , "Netdata CGroups Plugin CPU usage"
                         , "milliseconds/s"
                         , PLUGIN_CGROUPS_NAME
                         , "stats"