Adding upstream version 1.29.3.upstream/1.29.3upstream

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

4 files changed, 391 insertions, 0 deletions

diff --git a/collectors/python.d.plugin/adaptec_raid/Makefile.inc b/collectors/python.d.plugin/adaptec_raid/Makefile.inc
new file mode 100644
index 0000000..716cdb2
--- /dev/null
+++ b/collectors/python.d.plugin/adaptec_raid/Makefile.inc
@@ -0,0 +1,13 @@
+# SPDX-License-Identifier: GPL-3.0-or-later
+
+# THIS IS NOT A COMPLETE Makefile
+# IT IS INCLUDED BY ITS PARENT'S Makefile.am
+# IT IS REQUIRED TO REFERENCE ALL FILES RELATIVE TO THE PARENT
+
+# install these files
+dist_python_DATA       += adaptec_raid/adaptec_raid.chart.py
+dist_pythonconfig_DATA += adaptec_raid/adaptec_raid.conf
+
+# do not install these files, but include them in the distribution
+dist_noinst_DATA       += adaptec_raid/README.md adaptec_raid/Makefile.inc
+
diff --git a/collectors/python.d.plugin/adaptec_raid/README.md b/collectors/python.d.plugin/adaptec_raid/README.md
new file mode 100644
index 0000000..b14e8f9
--- /dev/null
+++ b/collectors/python.d.plugin/adaptec_raid/README.md
@@ -0,0 +1,80 @@
+<!--
+title: "Adaptec RAID controller monitoring with Netdata"
+custom_edit_url: https://github.com/netdata/netdata/edit/master/collectors/python.d.plugin/adaptec_raid/README.md
+sidebar_label: "Adaptec RAID"
+-->
+
+# Adaptec RAID controller monitoring with Netdata
+
+Collects logical and physical devices metrics using `arcconf` command-line utility.
+
+Executed commands:
+
+- `sudo -n arcconf GETCONFIG 1 LD`
+- `sudo -n arcconf GETCONFIG 1 PD`
+
+## Requirements
+
+The module uses `arcconf`, which can only be executed by `root`. It uses
+`sudo` and assumes that it is configured such that the `netdata` user can execute `arcconf` as root without a password.
+
+-  Add to your `/etc/sudoers` file:
+
+`which arcconf` shows the full path to the binary.
+
+```bash
+netdata ALL=(root)       NOPASSWD: /path/to/arcconf
+```
+
+- Reset Netdata's systemd
+  unit [CapabilityBoundingSet](https://www.freedesktop.org/software/systemd/man/systemd.exec.html#Capabilities) (Linux
+  distributions with systemd)
+
+The default CapabilityBoundingSet doesn't allow using `sudo`, and is quite strict in general. Resetting is not optimal, but a next-best solution given the inability to execute `arcconf` using `sudo`.
+
+
+As the `root` user, do the following:
+
+```cmd
+mkdir /etc/systemd/system/netdata.service.d
+echo -e '[Service]\nCapabilityBoundingSet=~' | tee /etc/systemd/system/netdata.service.d/unset-capability-bounding-set.conf
+systemctl daemon-reload
+systemctl restart netdata.service
+```
+
+## Charts
+
+- Logical Device Status
+- Physical Device State
+- Physical Device S.M.A.R.T warnings
+- Physical Device Temperature
+
+## Enable the collector
+
+The `adaptec_raid` collector is disabled by default. To enable it, use `edit-config` from the
+Netdata [config directory](/docs/configure/nodes.md), which is typically at `/etc/netdata`, to edit the `python.d.conf`
+file.
+
+```bash
+cd /etc/netdata   # Replace this path with your Netdata config directory, if different
+sudo ./edit-config python.d.conf
+```
+
+Change the value of the `adaptec_raid` setting to `yes`. Save the file and restart the Netdata Agent
+with `sudo systemctl restart netdata`, or the appropriate method for your system.
+
+## Configuration
+
+Edit the `python.d/adaptec_raid.conf` configuration file using `edit-config` from the
+Netdata [config directory](/docs/configure/nodes.md), which is typically at `/etc/netdata`.
+
+```bash
+cd /etc/netdata   # Replace this path with your Netdata config directory, if different
+sudo ./edit-config python.d/adaptec_raid.conf
+```
+
+![image](https://user-images.githubusercontent.com/22274335/47278133-6d306680-d601-11e8-87c2-cc9c0f42d686.png)
+
+---
+
+[![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%2Fpython.d.plugin%2Fadaptec_raid%2FREADME&_u=MAC~&cid=5792dfd7-8dc4-476b-af31-da2fdb9f93d2&tid=UA-64295674-3)](<>)
diff --git a/collectors/python.d.plugin/adaptec_raid/adaptec_raid.chart.py b/collectors/python.d.plugin/adaptec_raid/adaptec_raid.chart.py
new file mode 100644
index 0000000..564c2ce
--- /dev/null
+++ b/collectors/python.d.plugin/adaptec_raid/adaptec_raid.chart.py
@@ -0,0 +1,245 @@
+# -*- coding: utf-8 -*-
+# Description: adaptec_raid netdata python.d module
+# Author: Ilya Mashchenko (ilyam8)
+# SPDX-License-Identifier: GPL-3.0-or-later
+
+
+import re
+from copy import deepcopy
+
+from bases.FrameworkServices.ExecutableService import ExecutableService
+from bases.collection import find_binary
+
+disabled_by_default = True
+
+update_every = 5
+
+ORDER = [
+    'ld_status',
+    'pd_state',
+    'pd_smart_warnings',
+    'pd_temperature',
+]
+
+CHARTS = {
+    'ld_status': {
+        'options': [None, 'Status Is Not OK', 'bool', 'logical devices', 'adapter_raid.ld_status', 'line'],
+        'lines': []
+    },
+    'pd_state': {
+        'options': [None, 'State Is Not OK', 'bool', 'physical devices', 'adapter_raid.pd_state', 'line'],
+        'lines': []
+    },
+    'pd_smart_warnings': {
+        'options': [None, 'S.M.A.R.T warnings', 'count', 'physical devices',
+                    'adapter_raid.smart_warnings', 'line'],
+        'lines': []
+    },
+    'pd_temperature': {
+        'options': [None, 'Temperature', 'celsius', 'physical devices', 'adapter_raid.temperature', 'line'],
+        'lines': []
+    },
+}
+
+SUDO = 'sudo'
+ARCCONF = 'arcconf'
+
+BAD_LD_STATUS = (
+    'Degraded',
+    'Failed',
+)
+
+GOOD_PD_STATUS = (
+    'Online',
+)
+
+RE_LD = re.compile(
+    r'Logical [dD]evice number\s+([0-9]+).*?'
+    r'Status of [lL]ogical [dD]evice\s+: ([a-zA-Z]+)'
+)
+
+
+def find_lds(d):
+    d = ' '.join(v.strip() for v in d)
+    return [LD(*v) for v in RE_LD.findall(d)]
+
+
+def find_pds(d):
+    pds = list()
+    pd = PD()
+
+    for row in d:
+        row = row.strip()
+        if row.startswith('Device #'):
+            pd = PD()
+            pd.id = row.split('#')[-1]
+        elif not pd.id:
+            continue
+
+        if row.startswith('State'):
+            v = row.split()[-1]
+            pd.state = v
+        elif row.startswith('S.M.A.R.T. warnings'):
+            v = row.split()[-1]
+            pd.smart_warnings = v
+        elif row.startswith('Temperature'):
+            v = row.split(':')[-1].split()[0]
+            pd.temperature = v
+        elif row.startswith('NCQ status'):
+            if pd.id and pd.state and pd.smart_warnings:
+                pds.append(pd)
+            pd = PD()
+
+    return pds
+
+
+class LD:
+    def __init__(self, ld_id, status):
+        self.id = ld_id
+        self.status = status
+
+    def data(self):
+        return {
+            'ld_{0}_status'.format(self.id): int(self.status in BAD_LD_STATUS)
+        }
+
+
+class PD:
+    def __init__(self):
+        self.id = None
+        self.state = None
+        self.smart_warnings = None
+        self.temperature = None
+
+    def data(self):
+        data = {
+            'pd_{0}_state'.format(self.id): int(self.state not in GOOD_PD_STATUS),
+            'pd_{0}_smart_warnings'.format(self.id): self.smart_warnings,
+        }
+        if self.temperature and self.temperature.isdigit():
+            data['pd_{0}_temperature'.format(self.id)] = self.temperature
+
+        return data
+
+
+class Arcconf:
+    def __init__(self, arcconf):
+        self.arcconf = arcconf
+
+    def ld_info(self):
+        return [self.arcconf, 'GETCONFIG', '1', 'LD']
+
+    def pd_info(self):
+        return [self.arcconf, 'GETCONFIG', '1', 'PD']
+
+
+# TODO: hardcoded sudo...
+class SudoArcconf:
+    def __init__(self, arcconf, sudo):
+        self.arcconf = Arcconf(arcconf)
+        self.sudo = sudo
+
+    def ld_info(self):
+        return [self.sudo, '-n'] + self.arcconf.ld_info()
+
+    def pd_info(self):
+        return [self.sudo, '-n'] + self.arcconf.pd_info()
+
+
+class Service(ExecutableService):
+    def __init__(self, configuration=None, name=None):
+        ExecutableService.__init__(self, configuration=configuration, name=name)
+        self.order = ORDER
+        self.definitions = deepcopy(CHARTS)
+        self.use_sudo = self.configuration.get('use_sudo', True)
+        self.arcconf = None
+
+    def execute(self, command, stderr=False):
+        return self._get_raw_data(command=command, stderr=stderr)
+
+    def check(self):
+        arcconf = find_binary(ARCCONF)
+        if not arcconf:
+            self.error('can\'t locate "{0}" binary'.format(ARCCONF))
+            return False
+
+        sudo = find_binary(SUDO)
+        if self.use_sudo:
+            if not sudo:
+                self.error('can\'t locate "{0}" binary'.format(SUDO))
+                return False
+            err = self.execute([sudo, '-n', '-v'], True)
+            if err:
+                self.error(' '.join(err))
+                return False
+
+        if self.use_sudo:
+            self.arcconf = SudoArcconf(arcconf, sudo)
+        else:
+            self.arcconf = Arcconf(arcconf)
+
+        lds = self.get_lds()
+        if not lds:
+            return False
+
+        self.debug('discovered logical devices ids: {0}'.format([ld.id for ld in lds]))
+
+        pds = self.get_pds()
+        if not pds:
+            return False
+
+        self.debug('discovered physical devices ids: {0}'.format([pd.id for pd in pds]))
+
+        self.update_charts(lds, pds)
+        return True
+
+    def get_data(self):
+        data = dict()
+
+        for ld in self.get_lds():
+            data.update(ld.data())
+
+        for pd in self.get_pds():
+            data.update(pd.data())
+
+        return data
+
+    def get_lds(self):
+        raw_lds = self.execute(self.arcconf.ld_info())
+        if not raw_lds:
+            return None
+
+        lds = find_lds(raw_lds)
+        if not lds:
+            self.error('failed to parse "{0}" output'.format(' '.join(self.arcconf.ld_info())))
+            self.debug('output: {0}'.format(raw_lds))
+            return None
+        return lds
+
+    def get_pds(self):
+        raw_pds = self.execute(self.arcconf.pd_info())
+        if not raw_pds:
+            return None
+
+        pds = find_pds(raw_pds)
+        if not pds:
+            self.error('failed to parse "{0}" output'.format(' '.join(self.arcconf.pd_info())))
+            self.debug('output: {0}'.format(raw_pds))
+            return None
+        return pds
+
+    def update_charts(self, lds, pds):
+        charts = self.definitions
+        for ld in lds:
+            dim = ['ld_{0}_status'.format(ld.id), 'ld {0}'.format(ld.id)]
+            charts['ld_status']['lines'].append(dim)
+
+        for pd in pds:
+            dim = ['pd_{0}_state'.format(pd.id), 'pd {0}'.format(pd.id)]
+            charts['pd_state']['lines'].append(dim)
+
+            dim = ['pd_{0}_smart_warnings'.format(pd.id), 'pd {0}'.format(pd.id)]
+            charts['pd_smart_warnings']['lines'].append(dim)
+
+            dim = ['pd_{0}_temperature'.format(pd.id), 'pd {0}'.format(pd.id)]
+            charts['pd_temperature']['lines'].append(dim)
diff --git a/collectors/python.d.plugin/adaptec_raid/adaptec_raid.conf b/collectors/python.d.plugin/adaptec_raid/adaptec_raid.conf
new file mode 100644
index 0000000..fa462ec
--- /dev/null
+++ b/collectors/python.d.plugin/adaptec_raid/adaptec_raid.conf
@@ -0,0 +1,53 @@
+# netdata python.d.plugin configuration for adaptec raid
+#
+# This file is in YaML format. Generally the format is:
+#
+# name: value
+#
+
+# ----------------------------------------------------------------------
+# Global Variables
+# These variables set the defaults for all JOBs, however each JOB
+# may define its own, overriding the defaults.
+
+# update_every sets the default data collection frequency.
+# If unset, the python.d.plugin default is used.
+# update_every: 1
+
+# priority controls the order of charts at the netdata dashboard.
+# Lower numbers move the charts towards the top of the page.
+# If unset, the default for python.d.plugin is used.
+# priority: 60000
+
+# penalty indicates whether to apply penalty to update_every in case of failures.
+# Penalty will increase every 5 failed updates in a row. Maximum penalty is 10 minutes.
+# penalty: yes
+
+# autodetection_retry sets the job re-check interval in seconds.
+# The job is not deleted if check fails.
+# Attempts to start the job are made once every autodetection_retry.
+# This feature is disabled by default.
+# autodetection_retry: 0
+
+# ----------------------------------------------------------------------
+# JOBS (data collection sources)
+#
+# The default JOBS share the same *name*. JOBS with the same name
+# are mutually exclusive. Only one of them will be allowed running at
+# any time. This allows autodetection to try several alternatives and
+# pick the one that works.
+#
+# Any number of jobs is supported.
+#
+# All python.d.plugin JOBS (for all its modules) support a set of
+# predefined parameters. These are:
+#
+# job_name:
+#     name: myname            # the JOB's name as it will appear at the
+#                             # dashboard (by default is the job_name)
+#                             # JOBs sharing a name are mutually exclusive
+#     update_every: 1         # the JOB's data collection frequency
+#     priority: 60000         # the JOB's order on the dashboard
+#     penalty: yes            # the JOB's penalty
+#     autodetection_retry: 0  # the JOB's re-check interval in seconds
+# ----------------------------------------------------------------------