1 .. This work is licensed under a Creative Commons Attribution 4.0 International License.
2 .. http://creativecommons.org/licenses/by/4.0
3 .. (c) <optionally add copywriters name>
5 ===================================
6 OPNFV Barometer User Guide
7 ===================================
13 Barometer collectd plugins description
14 ---------------------------------------
15 .. Describe the specific features and how it is realised in the scenario in a brief manner
16 .. to ensure the user understand the context for the user guide instructions to follow.
18 collectd is a daemon which collects system performance statistics periodically
19 and provides a variety of mechanisms to publish the collected metrics. It
20 supports more than 90 different input and output plugins. Input plugins
21 retrieve metrics and publish them to the collectd deamon, while output plugins
22 publish the data they receive to an end point. collectd also has infrastructure
23 to support thresholding and notification.
25 Barometer has enabled the following collectd plugins:
27 * *dpdkstat plugin*: A read plugin that retrieve stats from the DPDK extended
30 * *dpdkevents plugin*: A read plugin that retrieves DPDK link status and DPDK
31 forwarding cores liveliness status (DPDK Keep Alive).
33 * `ceilometer plugin`_: A write plugin that pushes the retrieved stats to
34 Ceilometer. It's capable of pushing any stats read through collectd to
35 Ceilometer, not just the DPDK stats.
37 * *hugepages plugin*: A read plugin that retrieves the number of available
38 and free hugepages on a platform as well as what is available in terms of
41 * *Open vSwitch events Plugin*: A read plugin that retrieves events from OVS.
43 * *Open vSwitch stats Plugin*: A read plugin that retrieve flow and interface
46 * *mcelog plugin*: A read plugin that uses mcelog client protocol to check for
47 memory Machine Check Exceptions and sends the stats for reported exceptions
49 * *RDT plugin*: A read plugin that provides the last level cache utilization and
50 memory bandwidth utilization
52 All the plugins above are available on the collectd master, except for the
53 ceilometer plugin as it's a python based plugin and only C plugins are accepted
54 by the collectd community. The ceilometer plugin lives in the OpenStack
57 Other plugins existing as a pull request into collectd master:
59 * *SNMP Agent*: A write plugin that will act as a AgentX subagent that receives
60 and handles queries from SNMP master agent and returns the data collected
61 by read plugins. The SNMP Agent plugin handles requests only for OIDs
62 specified in configuration file. To handle SNMP queries the plugin gets data
63 from collectd and translates requested values from collectd's internal format
64 to SNMP format. Supports SNMP: get, getnext and walk requests.
66 * *Legacy/IPMI*: A read plugin that reports platform thermals, voltages,
67 fanspeed, current, flow, power etc. Also, the plugin monitors Intelligent
68 Platform Management Interface (IPMI) System Event Log (SEL) and sends the
71 **Plugins included in the Danube release:**
78 collectd capabilities and usage
79 ------------------------------------
80 .. Describe the specific capabilities and usage for <XYZ> feature.
81 .. Provide enough information that a user will be able to operate the feature on a deployed scenario.
83 .. note:: Plugins included in the OPNFV D release will be built-in to the fuel
84 plugin and available in the /opt/opnfv directory on the fuel master. You don't
85 need to clone the barometer/collectd repos to use these, but you can configure
86 them as shown in the examples below.
88 The collectd plugins in OPNFV are configured with reasonable defaults, but can
91 Building all Barometer upstreamed plugins from scratch
92 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
93 The plugins that have been merged to the collectd master branch can all be
94 built and configured through the barometer repository.
97 * sudo permissions are required to install collectd.
98 * These are instructions for Ubuntu 16.04
100 To build and install these dependencies, clone the barometer repo:
104 $ git clone https://gerrit.opnfv.org/gerrit/barometer
106 Install the build dependencies
110 $ ./src/install_build_deps.sh
112 To install collectd as a service and install all it's dependencies:
116 $ cd barometer/src && sudo make && sudo make install
118 This will install collectd as a service and the base install directory
119 will be /opt/collectd.
121 Sample configuration files can be found in '/opt/collectd/etc/collectd.conf.d'
124 - If you plan on using the Exec plugin, the plugin requires non-root
125 user to execute scripts. By default, `collectd_exec` user is used. Barometer
126 scripts do *not* create this user. It needs to be manually added or exec plugin
127 configuration has to be changed to use other, existing user before starting
130 - If you don't want to use one of the Barometer plugins, simply remove the
131 sample config file from '/opt/collectd/etc/collectd.conf.d'
133 - If you are using any Open vSwitch plugins you need to run:
137 $ sudo ovs-vsctl set-manager ptcp:6640
140 Below is the per plugin installation and configuration guide, if you only want
141 to install some/particular plugins.
143 DPDK statistics plugin
144 ^^^^^^^^^^^^^^^^^^^^^^
145 Repo: https://github.com/collectd/collectd
149 Dependencies: DPDK (http://dpdk.org/) Min_Version: 16.04
151 To build and install DPDK to /usr please see:
152 https://github.com/collectd/collectd/blob/master/docs/BUILD.dpdkstat.md
154 Building and installing collectd:
158 $ git clone https://github.com/collectd/collectd.git
161 $ ./configure --enable-syslog --enable-logfile --enable-debug
166 This will install collectd to /opt/collectd
167 The collectd configuration file can be found at /opt/collectd/etc
168 To configure the dpdkstats plugin you need to modify the configuration file to
178 ProcessType "secondary"
181 EnabledPortMask 0xffff
182 PortName "interface1"
183 PortName "interface2"
186 For more information on the plugin parameters, please see:
187 https://github.com/collectd/collectd/blob/master/src/collectd.conf.pod
189 .. note:: If you are not building and installing DPDK system-wide
190 you will need to specify the specific paths to the header files and libraries
191 using LIBDPDK_CPPFLAGS and LIBDPDK_LDFLAGS. You will also need to add the DPDK
192 library symbols to the shared library path using ldconfig. Note that this
193 update to the shared library path is not persistent (i.e. it will not survive a
196 .. note:: Plugin initialization time depends on read interval. It requires
197 5 read cycles to set up internal buffers and states. During that time
198 no statistics are submitted. Also if plugin is running and the number of DPDK
199 ports is increased, internal buffers are resized. That requires 3 read cycles
200 and no port statistics are submitted in that time.
203 ^^^^^^^^^^^^^^^^^^^^^^
204 Repo: https://github.com/collectd/collectd
208 Dependencies: DPDK (http://dpdk.org/)
210 To build and install DPDK to /usr please see:
211 https://github.com/collectd/collectd/blob/master/docs/BUILD.dpdkstat.md
213 Building and installing collectd:
217 $ git clone https://github.com/collectd/collectd.git
220 $ ./configure --enable-syslog --enable-logfile --enable-debug
224 This will install collectd to /opt/collectd
225 The collectd configuration file can be found at /opt/collectd/etc
226 To configure the dpdkevents plugin you need to modify the configuration file to
231 LoadPlugin dpdkevents
232 <Plugin "dpdkevents">
237 ProcessType "secondary"
240 <Event "link_status">
241 SendEventsOnUpdate true
242 EnabledPortMask 0xffff
243 PortName "interface1"
244 PortName "interface2"
245 SendNotification false
248 SendEventsOnUpdate true
250 KeepAliveShmName "/dpdk_keepalive_shm_name"
251 SendNotification false
255 For more information on the plugin parameters, please see:
256 https://github.com/collectd/collectd/blob/master/src/collectd.conf.pod
258 .. note:: If you are not building and installing DPDK system-wide
259 you will need to specify the specific paths to the header files and libraries
260 using LIBDPDK_CPPFLAGS and LIBDPDK_LDFLAGS. You will also need to add the DPDK
261 library symbols to the shared library path using ldconfig. Note that this
262 update to the shared library path is not persistent (i.e. it will not survive a
267 $ ./configure LIBDPDK_CPPFLAGS="path to DPDK header files" LIBDPDK_LDFLAGS="path to DPDK libraries"
271 Repo: https://github.com/collectd/collectd
275 Dependencies: None, but assumes hugepages are configured.
277 To configure some hugepages:
281 sudo mkdir -p /mnt/huge
282 sudo mount -t hugetlbfs nodev /mnt/huge
283 sudo echo 14336 > /sys/devices/system/node/node0/hugepages/hugepages-2048kB/nr_hugepages
285 Building and installing collectd:
289 $ git clone https://github.com/collectd/collectd.git
292 $ ./configure --enable-syslog --enable-logfile --enable-hugepages --enable-debug
296 This will install collectd to /opt/collectd
297 The collectd configuration file can be found at /opt/collectd/etc
298 To configure the hugepages plugin you need to modify the configuration file to
309 ValuesPercentage false
312 For more information on the plugin parameters, please see:
313 https://github.com/collectd/collectd/blob/master/src/collectd.conf.pod
317 Repo: https://github.com/collectd/collectd
323 * PQoS/Intel RDT library https://github.com/01org/intel-cmt-cat.git
326 Building and installing PQoS/Intel RDT library:
330 $ git clone https://github.com/01org/intel-cmt-cat.git
333 $ make install PREFIX=/usr
335 You will need to insert the msr kernel module:
341 Building and installing collectd:
345 $ git clone https://github.com/collectd/collectd.git
348 $ ./configure --enable-syslog --enable-logfile --with-libpqos=/usr/ --enable-debug
352 This will install collectd to /opt/collectd
353 The collectd configuration file can be found at /opt/collectd/etc
354 To configure the RDT plugin you need to modify the configuration file to
359 <LoadPlugin intel_rdt>
366 For more information on the plugin parameters, please see:
367 https://github.com/collectd/collectd/blob/master/src/collectd.conf.pod
371 Repo: https://github.com/maryamtahhan/collectd
373 Branch: feat_ipmi_events, feat_ipmi_analog
375 Dependencies: OpenIPMI library
377 The IPMI plugin is already implemented in the latest collectd and sensors
378 like temperature, voltage, fanspeed, current are already supported there.
379 The list of supported IPMI sensors has been extended and sensors like flow,
380 power are supported now. Also, a System Event Log (SEL) notification feature
383 * The feat_ipmi_events branch includes new SEL feature support in collectd
384 IPMI plugin. If this feature is enabled, the collectd IPMI plugin will
385 dispatch notifications about new events in System Event Log.
387 * The feat_ipmi_analog branch includes the support of extended IPMI sensors in
388 collectd IPMI plugin.
390 On Ubuntu, install the dependencies:
394 $ sudo apt-get install libopenipmi-dev
396 Enable IPMI support in the kernel:
400 $ sudo modprobe ipmi_devintf
401 $ sudo modprobe ipmi_si
403 **Note**: If HW supports IPMI, the ``/dev/ipmi0`` character device will be
406 Clone and install the collectd IPMI plugin:
410 $ git clone https://github.com/maryamtahhan/collectd
412 $ git checkout $BRANCH
414 $ ./configure --enable-syslog --enable-logfile --enable-debug
418 Where $BRANCH is feat_ipmi_events or feat_ipmi_analog.
420 This will install collectd to default folder ``/opt/collectd``. The collectd
421 configuration file (``collectd.conf``) can be found at ``/opt/collectd/etc``. To
422 configure the IPMI plugin you need to modify the file to include:
428 SELEnabled true # only feat_ipmi_events branch supports this
431 **Note**: By default, IPMI plugin will read all available analog sensor values,
432 dispatch the values to collectd and send SEL notifications.
434 For more information on the IPMI plugin parameters and SEL feature configuration,
436 https://github.com/maryamtahhan/collectd/blob/feat_ipmi_events/src/collectd.conf.pod
438 Extended analog sensors support doesn't require additional configuration. The usual
439 collectd IPMI documentation can be used:
441 - https://collectd.org/wiki/index.php/Plugin:IPMI
442 - https://collectd.org/documentation/manpages/collectd.conf.5.shtml#plugin_ipmi
446 - https://www.kernel.org/doc/Documentation/IPMI.txt
447 - http://www.intel.com/content/www/us/en/servers/ipmi/ipmi-second-gen-interface-spec-v2-rev1-1.html
451 Repo: https://github.com/collectd/collectd
457 Start by installing mcelog. Note: The kernel has to have CONFIG_X86_MCE
458 enabled. For 32bit kernels you need at least a 2.6,30 kernel.
464 $ apt-get update && apt-get install mcelog
470 $ git clone git://git.kernel.org/pub/scm/utils/cpu/mce/mcelog.git
475 $ cp mcelog.service /etc/systemd/system/
476 $ systemctl enable mcelog.service
477 $ systemctl start mcelog.service
480 Verify you got a /dev/mcelog. You can verify the daemon is running completely
487 This should query the information in the running daemon. If it prints nothing
488 that is fine (no errors logged yet). More info @
489 http://www.mcelog.org/installation.html
491 Modify the mcelog configuration file "/etc/mcelog/mcelog.conf" to include or
496 socket-path = /var/run/mcelog-client
498 Clone and install the collectd mcelog plugin:
502 $ git clone https://github.com/maryamtahhan/collectd
504 $ git checkout feat_ras
506 $ ./configure --enable-syslog --enable-logfile --enable-debug
510 This will install collectd to /opt/collectd
511 The collectd configuration file can be found at /opt/collectd/etc
512 To configure the mcelog plugin you need to modify the configuration file to
521 McelogClientSocket "/var/run/mcelog-client"
524 For more information on the plugin parameters, please see:
525 https://github.com/maryamtahhan/collectd/blob/feat_ras/src/collectd.conf.pod
527 Simulating a Machine Check Exception can be done in one of 3 ways:
529 * Running $make test in the mcelog cloned directory - mcelog test suite
533 **mcelog test suite:**
535 It is always a good idea to test an error handling mechanism before it is
536 really needed. mcelog includes a test suite. The test suite relies on
537 mce-inject which needs to be installed and in $PATH.
539 You also need the mce-inject kernel module configured (with
540 CONFIG_X86_MCE_INJECT=y), compiled, installed and loaded:
544 $ modprobe mce-inject
546 Then you can run the mcelog test suite with
552 This will inject different classes of errors and check that the mcelog triggers
553 runs. There will be some kernel messages about page offlining attempts. The
554 test will also lose a few pages of memory in your system (not significant)
555 **Note this test will kill any running mcelog, which needs to be restarted
556 manually afterwards**.
559 A utility to inject corrected, uncorrected and fatal machine check exceptions
563 $ git clone https://git.kernel.org/pub/scm/utils/cpu/mce/mce-inject.git
566 $ modprobe mce-inject
568 Modify the test/corrected script to include the following:
573 STATUS 0xcc00008000010090
579 $ ./mce-inject < test/corrected
581 **Note: the uncorrected and fatal scripts under test will cause a platform reset.
582 Only the fatal script generates the memory errors**. In order to quickly
583 emulate uncorrected memory errors and avoid host reboot following test errors
584 from mce-test suite can be injected:
588 $ mce-inject mce-test/cases/coverage/soft-inj/recoverable_ucr/data/srao_mem_scrub
592 In addition an more in-depth test of the Linux kernel machine check facilities
593 can be done with the mce-test test suite. mce-test supports testing uncorrected
594 error handling, real error injection, handling of different soft offlining
595 cases, and other tests.
597 **Corrected memory error injection:**
599 To inject corrected memory errors:
601 * Remove sb_edac and edac_core kernel modules: rmmod sb_edac rmmod edac_core
602 * Insert einj module: modprobe einj param_extension=1
603 * Inject an error by specifying details (last command should be repeated at least two times):
607 $ APEI_IF=/sys/kernel/debug/apei/einj
608 $ echo 0x8 > $APEI_IF/error_type
609 $ echo 0x01f5591000 > $APEI_IF/param1
610 $ echo 0xfffffffffffff000 > $APEI_IF/param2
611 $ echo 1 > $APEI_IF/notrigger
612 $ echo 1 > $APEI_IF/error_inject
614 * Check the MCE statistic: mcelog --client. Check the mcelog log for injected error details: less /var/log/mcelog.
617 ^^^^^^^^^^^^^^^^^^^^^
618 OvS Events Repo: https://github.com/collectd/collectd
620 OvS Stats Repo: https://github.com/maryamtahhan/collectd
622 OvS Events Branch: master
624 OvS Stats Branch:feat_ovs_stats
626 OvS Events MIBs: The SNMP OVS interface link status is provided by standard
627 IF-MIB (http://www.net-snmp.org/docs/mibs/IF-MIB.txt)
629 Dependencies: Open vSwitch, Yet Another JSON Library (https://github.com/lloyd/yajl)
631 On Ubuntu, install the dependencies:
635 $ sudo apt-get install libyajl-dev openvswitch-switch
637 Start the Open vSwitch service:
641 $ sudo service openvswitch-switch start
643 configure the ovsdb-server manager:
647 $ sudo ovs-vsctl set-manager ptcp:6640
649 Clone and install the collectd ovs plugin:
655 $ git checkout $BRANCH
657 $ ./configure --enable-syslog --enable-logfile --enable-debug
661 where $REPO is one of the repos listed at the top of this section.
663 Where $BRANCH is master or feat_ovs_stats.
665 This will install collectd to /opt/collectd. The collectd configuration file
666 can be found at /opt/collectd/etc. To configure the OVS events plugin you
667 need to modify the configuration file to include:
671 <LoadPlugin ovs_events>
674 <Plugin "ovs_events">
676 Socket "/var/run/openvswitch/db.sock"
677 Interfaces "br0" "veth0"
678 SendNotification false
682 To configure the OVS stats plugin you need to modify the configuration file
687 <LoadPlugin ovs_stats>
693 Socket "/var/run/openvswitch/db.sock"
694 Bridges "br0" "br_ext"
697 For more information on the plugin parameters, please see:
698 https://github.com/collectd/collectd/blob/master/src/collectd.conf.pod
700 https://github.com/maryamtahhan/collectd/blob/feat_ovs_stats/src/collectd.conf.pod
704 Repo: https://github.com/maryamtahhan/collectd/
708 Dependencies: NET-SNMP library
710 Start by installing net-snmp and dependencies.
716 $ apt-get install snmp snmp-mibs-downloader snmpd libsnmp-dev
717 $ systemctl start snmpd.service
721 Become root to install net-snmp dependencies
725 $ apt-get install libperl-dev
727 Clone and build net-snmp
731 $ git clone https://github.com/haad/net-snmp.git
733 $ ./configure --with-persistent-directory="/var/net-snmp" --with-systemd --enable-shared --prefix=/usr
742 Copy default configuration to persistent folder
746 $ cp EXAMPLE.conf /usr/share/snmp/snmpd.conf
748 Set library path and default MIB configuration
753 $ echo export LD_LIBRARY_PATH=/usr/lib >> .bashrc
754 $ net-snmp-config --default-mibdirs
755 $ net-snmp-config --snmpconfpath
757 Configure snmpd as a service
762 $ cp ./dist/snmpd.service /etc/systemd/system/
763 $ systemctl enable snmpd.service
764 $ systemctl start snmpd.service
766 Add the following line to snmpd.conf configuration file
767 "/usr/share/snmp/snmpd.conf" to make all OID tree visible for SNMP clients:
771 view systemonly included .1
773 To verify that SNMP is working you can get IF-MIB table using SNMP client
774 to view the list of Linux interfaces:
778 $ snmpwalk -v 2c -c public localhost IF-MIB::interfaces
780 Clone and install the collectd snmp_agent plugin:
784 $ git clone https://github.com/maryamtahhan/collectd
786 $ git checkout feat_snmp
788 $ ./configure --enable-syslog --enable-logfile --enable-debug --enable-snmp --with-libnetsnmp
792 This will install collectd to /opt/collectd
793 The collectd configuration file can be found at /opt/collectd/etc
794 **SNMP Agent plugin is a generic plugin and cannot work without configuration**.
795 To configure the snmp_agent plugin you need to modify the configuration file to
796 include OIDs mapped to collectd types. The following example maps scalar
797 memAvailReal OID to value represented as free memory type of memory plugin:
801 LoadPlugin snmp_agent
802 <Plugin "snmp_agent">
803 <Data "memAvailReal">
807 OIDs "1.3.6.1.4.1.2021.4.6.0"
811 For more information on the plugin parameters, please see:
812 https://github.com/maryamtahhan/collectd/blob/feat_snmp/src/collectd.conf.pod
814 For more details on AgentX subagent, please see:
815 http://www.net-snmp.org/tutorial/tutorial-5/toolkit/demon/
817 Installing collectd as a service
818 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
819 **NOTE**: In an OPNFV installation, collectd is installed and configured as a
822 Collectd service scripts are available in the collectd/contrib directory.
823 To install collectd as a service:
827 $ sudo cp contrib/systemd.collectd.service /etc/systemd/system/
828 $ cd /etc/systemd/system/
829 $ sudo mv systemd.collectd.service collectd.service
830 $ sudo chmod +x collectd.service
832 Modify collectd.service
837 ExecStart=/opt/collectd/sbin/collectd
838 EnvironmentFile=-/opt/collectd/etc/
839 EnvironmentFile=-/opt/collectd/etc/
840 CapabilityBoundingSet=CAP_SETUID CAP_SETGID
846 $ sudo systemctl daemon-reload
847 $ sudo systemctl start collectd.service
848 $ sudo systemctl status collectd.service should show success
850 Additional useful plugins
851 ^^^^^^^^^^^^^^^^^^^^^^^^^^
853 * **Exec Plugin** : Can be used to show you when notifications are being
854 generated by calling a bash script that dumps notifications to file. (handy
855 for debug). Modify /opt/collectd/etc/collectd.conf:
861 # Exec "user:group" "/path/to/exec"
862 NotificationExec "user" "<path to barometer>/barometer/src/collectd/collectd_sample_configs/write_notification.sh"
865 write_notification.sh (just writes the notification passed from exec through
866 STDIN to a file (/tmp/notifications)):
871 rm -f /tmp/notifications
874 echo $x$y >> /tmp/notifications
877 output to /tmp/notifications should look like:
887 TypeInstance:link_status
888 uuid:f2aafeec-fa98-4e76-aec5-18ae9fc74589
890 linkstate of "br-ex" interface has been changed to "DOWN"
892 * **logfile plugin**: Can be used to log collectd activity. Modify
893 /opt/collectd/etc/collectd.conf to include:
900 File "/var/log/collectd.log"
906 Monitoring Interfaces and Openstack Support
907 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
908 .. Figure:: monitoring_interfaces.png
910 Monitoring Interfaces and Openstack Support
912 The figure above shows the DPDK L2 forwarding application running on a compute
913 node, sending and receiving traffic. collectd is also running on this compute
914 node retrieving the stats periodically from DPDK through the dpdkstat plugin
915 and publishing the retrieved stats to Ceilometer through the ceilometer plugin.
917 To see this demo in action please checkout: `Barometer OPNFV Summit demo`_
921 .. [1] https://collectd.org/wiki/index.php/Naming_schema
922 .. [2] https://github.com/collectd/collectd/blob/master/src/daemon/plugin.h
923 .. [3] https://collectd.org/wiki/index.php/Value_list_t
924 .. [4] https://collectd.org/wiki/index.php/Data_set
925 .. [5] https://collectd.org/documentation/manpages/types.db.5.shtml
926 .. [6] https://collectd.org/wiki/index.php/Data_source
927 .. [7] https://collectd.org/wiki/index.php/Meta_Data_Interface
929 .. _Barometer OPNFV Summit demo: https://prezi.com/kjv6o8ixs6se/software-fastpath-service-quality-metrics-demo/
930 .. _ceilometer plugin: https://github.com/openstack/collectd-ceilometer-plugin/tree/stable/mitaka