diff options
Diffstat (limited to 'collectors/python.d.plugin/megacli')
| -rw-r--r-- | collectors/python.d.plugin/megacli/Makefile.inc | 13 | ||||
| -rw-r--r-- | collectors/python.d.plugin/megacli/README.md | 86 | ||||
| -rw-r--r-- | collectors/python.d.plugin/megacli/megacli.chart.py | 278 | ||||
| -rw-r--r-- | collectors/python.d.plugin/megacli/megacli.conf | 60 |
4 files changed, 437 insertions, 0 deletions
diff --git a/collectors/python.d.plugin/megacli/Makefile.inc b/collectors/python.d.plugin/megacli/Makefile.inc new file mode 100644 index 0000000..83680d7 --- /dev/null +++ b/collectors/python.d.plugin/megacli/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 += megacli/megacli.chart.py +dist_pythonconfig_DATA += megacli/megacli.conf + +# do not install these files, but include them in the distribution +dist_noinst_DATA += megacli/README.md megacli/Makefile.inc + diff --git a/collectors/python.d.plugin/megacli/README.md b/collectors/python.d.plugin/megacli/README.md new file mode 100644 index 0000000..3c99c3d --- /dev/null +++ b/collectors/python.d.plugin/megacli/README.md @@ -0,0 +1,86 @@ +<!-- +title: "MegaRAID controller monitoring with Netdata" +custom_edit_url: https://github.com/netdata/netdata/edit/master/collectors/python.d.plugin/megacli/README.md +sidebar_label: "MegaRAID controllers" +--> + +# MegaRAID controller monitoring with Netdata + +Collects adapter, physical drives and battery stats using `megacli` command-line tool. + +Executed commands: + +- `sudo -n megacli -LDPDInfo -aAll` +- `sudo -n megacli -AdpBbuCmd -a0` + +## Requirements + +The module uses `megacli`, which can only be executed by `root`. It uses +`sudo` and assumes that it is configured such that the `netdata` user can execute `megacli` as root without a password. + +- Add to your `/etc/sudoers` file: + +`which megacli` shows the full path to the binary. + +```bash +netdata ALL=(root) NOPASSWD: /path/to/megacli +``` + +- 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 `megacli` 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 + +- Adapter State +- Physical Drives Media Errors +- Physical Drives Predictive Failures +- Battery Relative State of Charge +- Battery Cycle Count + +## Enable the collector + +The `megacli` 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 `megacli` 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/megacli.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/megacli.conf +``` + +Battery stats disabled by default. To enable them, modify `megacli.conf`. + +```yaml +do_battery: yes +``` + +Save the file and restart the Netdata Agent with `sudo systemctl restart netdata`, or the [appropriate +method](/docs/configure/start-stop-restart.md) for your system. + + diff --git a/collectors/python.d.plugin/megacli/megacli.chart.py b/collectors/python.d.plugin/megacli/megacli.chart.py new file mode 100644 index 0000000..ef35ff6 --- /dev/null +++ b/collectors/python.d.plugin/megacli/megacli.chart.py @@ -0,0 +1,278 @@ +# -*- coding: utf-8 -*- +# Description: megacli netdata python.d module +# Author: Ilya Mashchenko (ilyam8) +# SPDX-License-Identifier: GPL-3.0-or-later + + +import re + +from bases.FrameworkServices.ExecutableService import ExecutableService +from bases.collection import find_binary + +disabled_by_default = True + +update_every = 5 + + +def adapter_charts(ads): + order = [ + 'adapter_degraded', + ] + + def dims(ad): + return [['adapter_{0}_degraded'.format(a.id), 'adapter {0}'.format(a.id)] for a in ad] + + charts = { + 'adapter_degraded': { + 'options': [None, 'Adapter State', 'is degraded', 'adapter', 'megacli.adapter_degraded', 'line'], + 'lines': dims(ads) + }, + } + + return order, charts + + +def pd_charts(pds): + order = [ + 'pd_media_error', + 'pd_predictive_failure', + ] + + def dims(k, pd): + return [['slot_{0}_{1}'.format(p.id, k), 'slot {0}'.format(p.id), 'incremental'] for p in pd] + + charts = { + 'pd_media_error': { + 'options': [None, 'Physical Drives Media Errors', 'errors/s', 'pd', 'megacli.pd_media_error', 'line'], + 'lines': dims('media_error', pds) + }, + 'pd_predictive_failure': { + 'options': [None, 'Physical Drives Predictive Failures', 'failures/s', 'pd', + 'megacli.pd_predictive_failure', 'line'], + 'lines': dims('predictive_failure', pds) + } + } + + return order, charts + + +def battery_charts(bats): + order = list() + charts = dict() + + for b in bats: + order.append('bbu_{0}_relative_charge'.format(b.id)) + charts.update( + { + 'bbu_{0}_relative_charge'.format(b.id): { + 'options': [None, 'Relative State of Charge', 'percentage', 'battery', + 'megacli.bbu_relative_charge', 'line'], + 'lines': [ + ['bbu_{0}_relative_charge'.format(b.id), 'adapter {0}'.format(b.id)], + ] + } + } + ) + + for b in bats: + order.append('bbu_{0}_cycle_count'.format(b.id)) + charts.update( + { + 'bbu_{0}_cycle_count'.format(b.id): { + 'options': [None, 'Cycle Count', 'cycle count', 'battery', 'megacli.bbu_cycle_count', 'line'], + 'lines': [ + ['bbu_{0}_cycle_count'.format(b.id), 'adapter {0}'.format(b.id)], + ] + } + } + ) + + return order, charts + + +RE_ADAPTER = re.compile( + r'Adapter #([0-9]+) State(?:\s+)?: ([a-zA-Z]+)' +) + +RE_VD = re.compile( + r'Slot Number: ([0-9]+) Media Error Count: ([0-9]+) Predictive Failure Count: ([0-9]+)' +) + +RE_BATTERY = re.compile( + r'BBU Capacity Info for Adapter: ([0-9]+) Relative State of Charge: ([0-9]+) % Cycle Count: ([0-9]+)' +) + + +def find_adapters(d): + keys = ('Adapter #', 'State') + d = ' '.join(v.strip() for v in d if v.startswith(keys)) + return [Adapter(*v) for v in RE_ADAPTER.findall(d)] + + +def find_pds(d): + keys = ('Slot Number', 'Media Error Count', 'Predictive Failure Count') + d = ' '.join(v.strip() for v in d if v.startswith(keys)) + return [PD(*v) for v in RE_VD.findall(d)] + + +def find_batteries(d): + keys = ('BBU Capacity Info for Adapter', 'Relative State of Charge', 'Cycle Count') + d = ' '.join(v.strip() for v in d if v.strip().startswith(keys)) + return [Battery(*v) for v in RE_BATTERY.findall(d)] + + +class Adapter: + def __init__(self, n, state): + self.id = n + self.state = int(state == 'Degraded') + + def data(self): + return { + 'adapter_{0}_degraded'.format(self.id): self.state, + } + + +class PD: + def __init__(self, n, media_err, predict_fail): + self.id = n + self.media_err = media_err + self.predict_fail = predict_fail + + def data(self): + return { + 'slot_{0}_media_error'.format(self.id): self.media_err, + 'slot_{0}_predictive_failure'.format(self.id): self.predict_fail, + } + + +class Battery: + def __init__(self, adapt_id, rel_charge, cycle_count): + self.id = adapt_id + self.rel_charge = rel_charge + self.cycle_count = cycle_count + + def data(self): + return { + 'bbu_{0}_relative_charge'.format(self.id): self.rel_charge, + 'bbu_{0}_cycle_count'.format(self.id): self.cycle_count, + } + + +# TODO: hardcoded sudo... +class Megacli: + def __init__(self): + self.s = find_binary('sudo') + self.m = find_binary('megacli') or find_binary('MegaCli') # Binary on FreeBSD is MegaCli + self.sudo_check = [self.s, '-n', '-l'] + self.disk_info = [self.s, '-n', self.m, '-LDPDInfo', '-aAll', '-NoLog'] + self.battery_info = [self.s, '-n', self.m, '-AdpBbuCmd', '-a0', '-NoLog'] + + def __bool__(self): + return bool(self.s and self.m) + + def __nonzero__(self): + return self.__bool__() + + +class Service(ExecutableService): + def __init__(self, configuration=None, name=None): + ExecutableService.__init__(self, configuration=configuration, name=name) + self.order = list() + self.definitions = dict() + self.do_battery = self.configuration.get('do_battery') + self.megacli = Megacli() + + def check_sudo(self): + err = self._get_raw_data(command=self.megacli.sudo_check, stderr=True) + if err: + self.error(''.join(err)) + return False + return True + + def check_disk_info(self): + d = self._get_raw_data(command=self.megacli.disk_info) + if not d: + return False + + ads = find_adapters(d) + pds = find_pds(d) + + if not (ads and pds): + self.error('failed to parse "{0}" output'.format(' '.join(self.megacli.disk_info))) + return False + + o, c = adapter_charts(ads) + self.order.extend(o) + self.definitions.update(c) + + o, c = pd_charts(pds) + self.order.extend(o) + self.definitions.update(c) + + return True + + def check_battery(self): + d = self._get_raw_data(command=self.megacli.battery_info) + if not d: + return False + + bats = find_batteries(d) + + if not bats: + self.error('failed to parse "{0}" output'.format(' '.join(self.megacli.battery_info))) + return False + + o, c = battery_charts(bats) + self.order.extend(o) + self.definitions.update(c) + return True + + def check(self): + if not self.megacli: + self.error('can\'t locate "sudo" or "megacli" binary') + return None + + if not (self.check_sudo() and self.check_disk_info()): + return False + + if self.do_battery: + self.do_battery = self.check_battery() + + return True + + def get_data(self): + data = dict() + + data.update(self.get_adapter_pd_data()) + + if self.do_battery: + data.update(self.get_battery_data()) + + return data or None + + def get_adapter_pd_data(self): + raw = self._get_raw_data(command=self.megacli.disk_info) + data = dict() + + if not raw: + return data + + for a in find_adapters(raw): + data.update(a.data()) + + for p in find_pds(raw): + data.update(p.data()) + + return data + + def get_battery_data(self): + raw = self._get_raw_data(command=self.megacli.battery_info) + data = dict() + + if not raw: + return data + + for b in find_batteries(raw): + data.update(b.data()) + + return data diff --git a/collectors/python.d.plugin/megacli/megacli.conf b/collectors/python.d.plugin/megacli/megacli.conf new file mode 100644 index 0000000..1af4292 --- /dev/null +++ b/collectors/python.d.plugin/megacli/megacli.conf @@ -0,0 +1,60 @@ +# netdata python.d.plugin configuration for megacli +# +# 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 +# +# Additionally to the above, megacli also supports the following: +# +# do_battery: yes/no # default is no. Battery stats (adds additional call to megacli `megacli -AdpBbuCmd -a0`). +# +# ---------------------------------------------------------------------- +# uncomment the line below to collect battery statistics +# do_battery: yes |