Commit Graph

198 Commits

Author SHA1 Message Date
Thomas Roehl
4a4992877c Add stats counters to collectors 2022-04-02 16:05:52 +02:00
Thomas Roehl
5d25a7bf12 Add units to InfiniBandCollector 2022-04-01 17:14:26 +02:00
Thomas Roehl
83b4343310 Likwid receives signal at first Read, check when re-initializing 2022-04-01 17:10:31 +02:00
Thomas Gruber
2a014b6fba
Read unit of values from /proc/meminfo (#68) 2022-03-31 11:56:31 +02:00
Thomas Roehl
50479f9325 Move all LIKWID related stuff to late initialization routine 2022-03-24 18:12:23 +01:00
Thomas Roehl
e0e91844bc Use late initialization of LIKWID and catch access daemon death. Fixes #70 and fixes #71. 2022-03-24 17:56:51 +01:00
Thomas Roehl
296225f3a8 Always export all metrics in NfsCollectors 2022-03-24 13:50:35 +01:00
Thomas Roehl
b66fdd1436 Add missing socket->thread_id map for LikwidCollector 2022-03-16 19:04:39 +01:00
Thomas Gruber
c182d295f4
Fix staticcheck warnings (#66) 2022-03-15 16:38:20 +01:00
Thomas Gruber
aa1afd745e
Derived metrics (#65)
* Add time-based derivatived (e.g. bandwidth) to some collectors

* Add documentation

* Add comments

* Fix: Only compute rates with a valid previous state

* Only compute rates with a valid previous state

* Define const values for net/dev fields

* Set default config values

* Add comments

* Refactor: Consolidate data structures

* Refactor: Consolidate data structures

* Refactor: Avoid struct deep copy

* Refactor: Avoid redundant tag maps

* Refactor: Use int64 type for absolut values

* Update LustreCollector

Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com>
2022-03-15 16:09:47 +01:00
Holger Obermaier
992b19d354 Move unit tag to meta data tags 2022-03-11 14:47:18 +01:00
Holger Obermaier
0b08ca9ae0 Simplified iota usage 2022-03-11 14:09:22 +01:00
Thomas Gruber
f6dae7c013
Derived metrics (#57)
* Add time-based derivatived (e.g. bandwidth) to some collectors

* Add documentation

* Add comments

* Fix: Only compute rates with a valid previous state

* Only compute rates with a valid previous state

* Define const values for net/dev fields

* Set default config values

* Add comments

* Refactor: Consolidate data structures

* Refactor: Consolidate data structures

* Refactor: Avoid struct deep copy

* Refactor: Avoid redundant tag maps

* Refactor: Use int64 type for absolut values

Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com>
2022-03-11 13:48:18 +01:00
Thomas Gruber
73f22c1041
Refactoring of LikwidCollector and metric units (#62)
* Reduce complexity of LikwidCollector and allow metric units

* Add unit to LikwidCollector docu and fix some typos

* Make library path configurable
2022-03-11 13:43:17 +01:00
Thomas Roehl
e7f7e68095 Use GBytes as unit for large memory numbers 2022-03-09 11:05:26 +01:00
Thomas Gruber
f2486abeab
Just download LIKWID to get the headers (#54)
* Just download LIKWID to get the headers

* Remove perl-Data-Dumper from BuildRequires, only required by LIKWID build
2022-03-05 17:30:40 +01:00
Thomas Gruber
21864e0ac4
Change default GpfsCollector command to mmpmon (#53)
* Set default cmd to 'mmpmon'

* Reuse looked up path

* Cast const to string
2022-03-05 14:42:04 +01:00
Mehmet Soysal
547bc0461f
Beegfs collector (#50)
* added beegfs collectors to collectors/README.md

* added beegfs collectors and docs

* added new beegfs collectors to AvailableCollectors list

* Feedback implemented

* changed error type

* changed error to only return

* changed beegfs lookup path

* fixed typo in md files

Co-authored-by: Mehmet Soysal <mehmet.soysal@kit.edu>
2022-03-04 14:35:47 +01:00
Thomas Roehl
f1d2828e1d Fix error print in LustreCollector 2022-03-04 11:32:10 +01:00
Holger Obermaier
db04c8fbae Removed infinibandPerfQueryMetric.go. infinibandMetric.go offers the same functionality without requiring root privileges. 2022-03-03 15:52:50 +01:00
Thomas Roehl
60de21c41e Switch access mode of LikwidCollector in config file 2022-03-03 13:03:58 +01:00
Thomas Roehl
276c00442a Add option to LustreCollector to call lctl with sudo 2022-03-03 13:02:00 +01:00
Thomas Roehl
092e7f6a71 Add section how to temporarly disable LIKWID access to page 2022-03-02 13:54:43 +01:00
Holger Obermaier
a5325a6535
GitHub actions (#51)
Create new GitHub action which uses unmodified AlmaLinux Docker image
2022-03-01 15:39:26 +01:00
Holger Obermaier
33fec95eac Additional comments 2022-02-28 12:16:48 +01:00
Holger Obermaier
2c08e53be4 Additional comments 2022-02-28 09:57:26 +01:00
Thomas Roehl
bac1f18b1d Add samples for collectors, sinks and receivers 2022-02-25 13:47:19 +01:00
Thomas Gruber
c8bca59de4
Numa-aware memstat collector (#45) 2022-02-24 18:27:05 +01:00
Thomas Roehl
d542f32baa Mention likwid config script in LikwidCollector README 2022-02-22 17:46:44 +01:00
Thomas Roehl
66275ecf74 DiskstatCollector: cast part_max_used metric to int 2022-02-22 15:50:49 +01:00
Thomas Roehl
eed9cd227c Remove doubled import and remove merge artifacts 2022-02-21 14:50:11 +01:00
Thomas Roehl
24a2c9992f Merge branch 'develop' into main 2022-02-21 14:32:24 +01:00
Thomas Gruber
f683f2e6da
Dynamically load liblikwid (#40)
* Check whether LIKWID library is present

* Generalize nan_to_zero option to invalid_to_zero including +Inf,+Inf and NaN

* Remove double error printing and return if measurements do not work
2022-02-21 13:29:33 +01:00
Thomas Gruber
435528fa97
Split diskstat Collector (#38)
* Split diskstats (free, total space) and iostats (reads, writes, ...

* Add iostat Collector to CollectorManager
2022-02-21 12:44:26 +01:00
Holger Obermaier
65c3106af2 Remove tags for num cores and packages 2022-02-18 16:59:59 +01:00
Holger Obermaier
635a75c64b Report maximum and critical temperature 2022-02-18 16:56:41 +01:00
Thomas Roehl
4e8ee59211 Update NetstatCollector to derive bandwidths and use an include list 2022-02-18 02:25:23 +01:00
Thomas Gruber
0152c0dc1e
Update CpustatCollector (#36)
* Update cpustat collector

* Update CpustatCollector to use percentages and add 'num_cpus' metric
2022-02-17 15:46:06 +01:00
Holger Obermaier
542520d2c0 Refactoring: Use array of pointers 2022-02-15 15:37:25 +01:00
Holger Obermaier
01faa3b531 Add comments and units to all nvidia metrics 2022-02-15 10:57:32 +01:00
Holger Obermaier
14c9d6f792 Fixed: All nvidia metrics were excluded 2022-02-15 09:47:24 +01:00
Holger Obermaier
fcfb58c31c Use slice element of m.gpus without slice index 2022-02-15 09:23:57 +01:00
Holger Obermaier
5060497abd Cleanup 2022-02-14 22:14:06 +01:00
Holger Obermaier
342f09fabf Cleanup 2022-02-14 11:19:19 +01:00
Holger Obermaier
09b1ea130e Add error handling. Cleanup. 2022-02-14 10:46:05 +01:00
Holger Obermaier
6b12baff6e Use sensor name and sensor label as metric name 2022-02-12 10:13:38 +01:00
Thomas Roehl
bd246bdacf Fix group for netstat collector 2022-02-11 18:18:10 +01:00
Thomas Roehl
23d13b2ceb Fix group for netstat collector 2022-02-11 18:09:39 +01:00
Holger Obermaier
cfc5279958 Move sensor detection to Init() 2022-02-11 17:17:25 +01:00
Thomas Roehl
b15fdf72b9 Exclude metrics and devices in Init() for NvidiaCollector 2022-02-11 14:20:06 +01:00