mirror of
https://github.com/ClusterCockpit/cc-metric-collector.git
synced 2024-09-20 07:27:25 +02:00
8d85bd53f1
* Cleanup: Remove unused code * Use Golang duration parser for 'interval' and 'duration' in main config * Update handling of LIKWID headers. Download only if not already present in the system. Fixes #73 * Units with cc-units (#64) * Add option to normalize units with cc-unit * Add unit conversion to router * Add option to change unit prefix in the router * Add to MetricRouter README * Add order of operations in router to README * Use second add_tags/del_tags only if metric gets renamed * Skip disks in DiskstatCollector that have size=0 * Check readability of sensor files in TempCollector * Fix for --once option * Rename `cpu` type to `hwthread` (#69) * Rename 'cpu' type to 'hwthread' to avoid naming clashes with MetricStore and CC-Webfrontend * Collectors in parallel (#74) * Provide info to CollectorManager whether the collector can be executed in parallel with others * Split serial and parallel collectors. Read in parallel first * Update NvidiaCollector with new metrics, MIG and NvLink support (#75) * CC topology module update (#76) * Rename CPU to hardware thread, write some comments * Do renaming in other parts * Remove CpuList and SocketList function from metricCollector. Available in ccTopology * Option to use MIG UUID as subtype-id in NvidiaCollector * Option to use MIG slice name as subtype-id in NvidiaCollector * MetricRouter: Fix JSON in README * Fix for Github Action to really use the selected version * Remove Ganglia installation in runonce Action and add Go 1.18 * Fix daemon options in init script * Add separate go.mod files to use it with deprecated 1.16 * Minor updates for Makefiles * fix string comparison * AMD ROCm SMI collector (#77) * Add collector for AMD ROCm SMI metrics * Fix import path * Fix imports * Remove Board Number * store GPU index explicitly * Remove board number from description * Use http instead of ftp to download likwid * Fix serial number in rocmCollector * Improved http sink (#78) * automatic flush in NatsSink * tweak default options of HttpSink * shorter cirt. section and retries for HttpSink * fix error handling * Remove file added by mistake. * Use http instead of ftp to download likwid * Fix serial number in rocmCollector Co-authored-by: Thomas Roehl <thomas.roehl@fau.de> Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> Co-authored-by: Lou <lou.knauer@gmx.de>
84 lines
2.4 KiB
Python
Executable File
84 lines
2.4 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
|
|
import os, os.path, sys, getopt, re, json
|
|
|
|
def which(cmd):
|
|
ospath = os.environ.get("PATH", "")
|
|
for p in ospath.split(":"):
|
|
testcmd = os.path.join(p, cmd)
|
|
if os.access(testcmd, os.X_OK):
|
|
return testcmd
|
|
return None
|
|
|
|
def group_to_json(groupfile):
|
|
gdata = []
|
|
with open(groupfile, "r") as fp:
|
|
gdata = fp.read().strip().split("\n")
|
|
events = {}
|
|
metrics = []
|
|
parse_events = False
|
|
parse_metrics = False
|
|
for line in gdata:
|
|
if line == "EVENTSET":
|
|
parse_events = True
|
|
parse_metrics = False
|
|
continue
|
|
if line == "METRICS":
|
|
parse_events = False
|
|
parse_metrics = True
|
|
continue
|
|
if len(line) == 0 or line.startswith("SHORT") or line == "LONG":
|
|
parse_events = False
|
|
parse_metrics = False
|
|
continue
|
|
if parse_events:
|
|
m = re.match("([\w\d]+)\s+([\w\d_]+)", line)
|
|
if m:
|
|
events[m.group(1)] = m.group(2)
|
|
if parse_metrics:
|
|
llist = re.split("\s+", line)
|
|
calc = llist[-1]
|
|
metric = " ".join(llist[:-1])
|
|
scope = "hwthread"
|
|
if "BOX" in calc:
|
|
scope = "socket"
|
|
if "PWR" in calc:
|
|
scope = "socket"
|
|
|
|
m = {"name" : metric, "calc": calc, "scope" : scope, "publish" : True}
|
|
metrics.append(m)
|
|
return {"events" : events, "metrics" : metrics}
|
|
|
|
if len(sys.argv) != 3:
|
|
print("Usage: $0 <likwid-arch> <group-name>")
|
|
sys.exit(1)
|
|
|
|
|
|
arch = sys.argv[1]
|
|
group = sys.argv[2]
|
|
|
|
ltopo = which("likwid-topology")
|
|
if not ltopo:
|
|
print("Cannot find LIKWID installation. Please add LIKWID bin folder to your PATH.")
|
|
sys.exit(1)
|
|
|
|
bindir = os.path.dirname(ltopo)
|
|
|
|
groupdir = os.path.normpath(os.path.join(bindir, "../share/likwid/perfgroups"))
|
|
if not os.path.exists(groupdir):
|
|
print("Cannot find LIKWID performance groups in default install location")
|
|
sys.exit(1)
|
|
|
|
archdir = os.path.join(groupdir, arch)
|
|
if not os.path.exists(archdir):
|
|
print("Cannot find LIKWID performance groups for architecture {}".format(arch))
|
|
sys.exit(1)
|
|
|
|
groupfile = os.path.join(archdir, "{}.txt".format(group))
|
|
if not os.path.exists(groupfile):
|
|
print("Cannot find LIKWID performance group {} for architecture {}".format(group, arch))
|
|
sys.exit(1)
|
|
|
|
gdata = group_to_json(groupfile)
|
|
print(json.dumps(gdata, sort_keys=True, indent=2))
|