Module: check_mk Branch: master Commit: 512cbf9c904ef316422a0b9f495d47adc0323492 URL: http://git.mathias-kettner.de/git/?p=check_mk.git;a=commit;h=512cbf9c904ef3… Author: Mathias Kettner <mk(a)mathias-kettner.de> Date: Thu Mar 17 14:00:55 2011 +0100 diskstat: updated man page --- checkman/diskstat | 97 ++++++++++++++++++++++++++++++++++++++++++++--------- 1 files changed, 81 insertions(+), 16 deletions(-) diff --git a/checkman/diskstat b/checkman/diskstat index 9ef5a5b..928034a 100644 --- a/checkman/diskstat +++ b/checkman/diskstat @@ -4,27 +4,92 @@ author: Mathias Kettner <mk(a)mathias-kettner.de> license: GPL distribution: check_mk description: - This check measures the cumulative throughput of - all block (disk) devices of a Linux host. In the current - version this check is always OK. There is now way - to define levels. This might come in a future release, - but is not trivial: A sensible level would have to - be matched against an average throughput over a - longer period of time, not just over one check cycle. + + This check measures the throughput of block devices (disks) on Linux + hosts. You can either have a single check for every single disk + (which is the default) or a summary check summing up the throughput + of all disks. + + For legacy reasons it is also possible (but not advisable) to have all disks + summarized but with a separate check for read and write (this is how this + check worked up to version 1.1.10). + + You can apply separate warning and critical levels for the read + and write throughput. Optionally you can have the check compute + average values on a configurable time period and have the levels + applied on the average instead of the current values. This makes + it possible to ignore short "peaks" and only trigger and longer + phases of high disk activity. item: - Either {"read"}- for input - or {"write"}- for output. + Either {"SUMMARY"} for a summarized check of alls disks or the + name of the disk device, e.g. {"sda"}. In order to support configurations + up to version 1.1.10 also the items {"read"} and {"write"} are supported. examples: - checks = [ - ("zbghora12", "diskstat", "read", None), - ("zbghora12", "diskstat", "write", None), - ] + # switch inventory behaviour to 1.1.10 mode + diskstat_inventory_mode = "legacy" + + # alternative: create one check for all disks + diskstat_inventory_mode = "summary" + + # Set default levels for diskstat + diskstat_default_levels = { + "read" : (10, 20), # level for read MB/sec + "write" : (20, 40), # level for write MB/sec + "average" : 15, # averaging in minutes + } + + # Alternative: just enable averaging over 10 minutes, + # do not apply levels: + diskstat_default_levels = { + "average" : 15 + } + + # Settings for certain hosts: + check_parameters += [ + ( {"write" : (20, 50), "average" : 10 }, [ "oracle" ], ALL_HOSTS, [ "Disk IO" ]) + ] perfdata: - One variable: the throughput since the last check - in in bytes(!) per second. + The disk throughput for read and write in bytes per second. If averaging + is turned on, then two additional values are sent: the averaged read and + write throughput. + + In the legacy mode only one variable: the throughput since the last check + in in bytes(!) per second, either for read or for write. inventory: - The inventory will automatically find two services: - one for {read} and one for {write}. + The inventory is configured via {diskstat_inventory_mode}. If this is set + to {"single"} (the default), then one check will be created for each + disk. If it is set to {"summary"} then only one service per host will be + created that has at least one hard disk. If set to {"legacy"} then a + separate check for read and write will be created (deprecated). + +[parameters] +"read": The levels to be applied to the read throughput. It this entry is + {None} or missing in the dictionary, then no levels are applied. This is + the defaut. The values are in MB per second. Setting {"read"} to {(20, 40)} + will warn if 20 MB/s is exceeded and make the check critical at 40 MB/s. + If averaging is turned on, then the levels are applied to the averaged + values! + +"write": The levels for the write throughput. + +"average": If this is not {None}, it will be interpreted as a time range + in minutes to do averaging over. Set this to {15} in order to have + the levels applied to a 15-minute average instead of the current + values (approx.). Turning the average on will also create two additional + performance values. Make sure that your graphing tool is setup to + a changing number of variables. + +[configuration] +diskstat_defaul_levels(dict): The default parameter used for inventorized + checks. This is preset to the empty dictionary. + That means that no averaging is done and no + levels are applied. + +diskstat_inventory_mode(string): Either {"single"} for one service per disk + or {"summary"} for the throughput of all disks summed up in one service. + Also possible is {"legacy"} for the old style mode (see above). Default + is {"single"}.