<EAL>
Coremask "0x1"
MemoryChannels "4"
- ProcessType "secondary"
FilePrefix "rte"
</EAL>
<Event "link_status">
=head3 The EAL block
-=over 5
+=over 4
=item B<Coremask> I<Mask>
Number of memory channels per processor socket.
-=item B<ProcessType> I<type>
-
-The type of DPDK process instance.
-
=item B<FilePrefix> I<File>
The prefix text used for hugepage filenames. The filename will be set to
=head4 Link Status event
-=over 5
+=over 4
=item B<SendEventOnUpdate> I<true|false>
=head4 Keep Alive event
-=over 5
+=over 4
=item B<SendEventOnUpdate> I<true|false>
<EAL>
Coremask "0x4"
MemoryChannels "4"
- ProcessType "secondary"
FilePrefix "rte"
SocketMemory "1024"
</EAL>
=head3 The EAL block
-=over 5
+=over 4
=item B<Coremask> I<Mask>
A string containing a number of memory channels per processor socket.
-=item B<ProcessType> I<type>
-
-A string containing the type of DPDK process instance.
-
=item B<FilePrefix> I<File>
The prefix text used for hugepage filenames. The filename will be set to
=over 3
=item B<SharedMemObj> I<Mask>
+
A string containing the name of the shared memory object that should be used to
share stats from the DPDK secondary process to the collectd dpdkstat plugin.
Defaults to dpdk_collectd_stats if no other value is configured.
=back
+=head2 Plugin C<intel_pmu>
+
+The I<intel_pmu> plugin collects performance counters data on Intel CPUs using
+Linux perf interface. All events are reported on a per core basis.
+
+B<Synopsis:>
+
+ <Plugin intel_pmu>
+ ReportHardwareCacheEvents true
+ ReportKernelPMUEvents true
+ ReportSoftwareEvents true
+ EventList "/var/cache/pmu/GenuineIntel-6-2D-core.json"
+ HardwareEvents "L2_RQSTS.CODE_RD_HIT,L2_RQSTS.CODE_RD_MISS" "L2_RQSTS.ALL_CODE_RD"
+ </Plugin>
+
+B<Options:>
+
+=over 4
+
+=item B<ReportHardwareCacheEvents> B<false>|B<true>
+
+Enable or disable measuring of hardware CPU cache events:
+ - L1-dcache-loads
+ - L1-dcache-load-misses
+ - L1-dcache-stores
+ - L1-dcache-store-misses
+ - L1-dcache-prefetches
+ - L1-dcache-prefetch-misses
+ - L1-icache-loads
+ - L1-icache-load-misses
+ - L1-icache-prefetches
+ - L1-icache-prefetch-misses
+ - LLC-loads
+ - LLC-load-misses
+ - LLC-stores
+ - LLC-store-misses
+ - LLC-prefetches
+ - LLC-prefetch-misses
+ - dTLB-loads
+ - dTLB-load-misses
+ - dTLB-stores
+ - dTLB-store-misses
+ - dTLB-prefetches
+ - dTLB-prefetch-misses
+ - iTLB-loads
+ - iTLB-load-misses
+ - branch-loads
+ - branch-load-misses
+
+=item B<ReportKernelPMUEvents> B<false>|B<true>
+
+Enable or disable measuring of the following events:
+ - cpu-cycles
+ - instructions
+ - cache-references
+ - cache-misses
+ - branches
+ - branch-misses
+ - bus-cycles
+
+=item B<ReportSoftwareEvents> B<false>|B<true>
+
+Enable or disable measuring of software events provided by kernel:
+ - cpu-clock
+ - task-clock
+ - context-switches
+ - cpu-migrations
+ - page-faults
+ - minor-faults
+ - major-faults
+ - alignment-faults
+ - emulation-faults
+
+=item B<EventList> I<filename>
+
+JSON performance counter event list file name. To be able to monitor all Intel
+CPU specific events JSON event list file should be downloaded. Use the pmu-tools
+event_download.py script to download event list for current CPU.
+
+=item B<HardwareEvents> I<events>
+
+This field is a list of event names or groups of comma separated event names.
+This option requires B<EventList> option to be configured.
+
+=back
+
=head2 Plugin C<intel_rdt>
The I<intel_rdt> plugin collects information provided by monitoring features of
=item B<IgnoreSelected> I<true>|I<false>
-If no configuration if given, the B<interface>-plugin will collect data from
+If no configuration is given, the B<interface>-plugin will collect data from
all interfaces. This may not be practical, especially for loopback- and
similar interfaces. Thus, you can use the B<Interface>-option to pick the
interfaces you're interested in. Sometimes, however, it's easier/preferred
Example usage:
C<c_rehash /path/to/certs/folder>
+=item B<ConnectTimeout> I<Milliseconds>
+
+The B<ConnectTimeout> option sets the connect timeout, in milliseconds.
+By default, the configured B<Interval> is used to set the timeout.
+
=back
=head2 Plugin C<olsrd>
When the C<rrdtool> plugin uses a cache (by setting B<CacheTimeout>, see below)
it writes all values for a certain RRD-file if the oldest value is older than
-(or equal to) the number of seconds specified. If some RRD-file is not updated
+(or equal to) the number of seconds specified by B<CacheTimeout>.
+That check happens on new values arriwal. If some RRD-file is not updated
anymore for some reason (the computer was shut down, the network is broken,
-etc.) some values may still be in the cache. If B<CacheFlush> is set, then the
-entire cache is searched for entries older than B<CacheTimeout> seconds and
-written to disk every I<Seconds> seconds. Since this is kind of expensive and
-does nothing under normal circumstances, this value should not be too small.
-900 seconds might be a good value, though setting this to 7200 seconds doesn't
-normally do much harm either.
+etc.) some values may still be in the cache. If B<CacheFlush> is set, then
+every I<Seconds> seconds the entire cache is searched for entries older than
+B<CacheTimeout> + B<RandomTimeout> seconds. The entries found are written to
+disk. Since scanning the entire cache is kind of expensive and does nothing
+under normal circumstances, this value should not be too small. 900 seconds
+might be a good value, though setting this to 7200 seconds doesn't normally
+do much harm either.
+
+Defaults to 10x B<CacheTimeout>.
+B<CacheFlush> must be larger than or equal to B<CacheTimeout>, otherwise the
+above default is used.
=item B<CacheTimeout> I<Seconds>
<Plugin snmp_agent>
<Data "memAvailReal">
Plugin "memory"
+ #PluginInstance "some"
Type "memory"
TypeInstance "free"
OIDs "1.3.6.1.4.1.2021.4.6.0"
Read plugin name whose collected data will be mapped to specified OIDs.
+=item B<PluginInstance> I<String>
+
+Read plugin instance whose collected data will be mapped to specified OIDs.
+The field is optional and by default there is no plugin instance check.
+Allowed only if B<Data> block defines scalar data type.
+
=item B<Type> I<String>
Collectd's type that is to be used for specified OID, e.E<nbsp>g. "if_octets"
=item B<OIDs> I<OID> [I<OID> ...]
Configures the OIDs to be handled by I<snmp_agent> plugin. Values for these OIDs
-are taken from collectd data type specified by B<Plugin>, B<Type>,
-B<TypeInstance> fields of this B<Data> block. Number of the OIDs configured
-should correspond to number of values in specified B<Type>.
+are taken from collectd data type specified by B<Plugin>, B<PluginInstance>,
+B<Type>, B<TypeInstance> fields of this B<Data> block. Number of the OIDs
+configured should correspond to number of values in specified B<Type>.
For example two OIDs "IF-MIB::ifInOctets" "IF-MIB::ifOutOctets" can be mapped to
"rx" and "tx" values of "if_octets" type.
projects / collectd.git / blobdiff