Commit Graph

11 Commits

Author SHA1 Message Date
Jan-Otto Kröpke
9e59bf920f
Post rebase issues
Signed-off-by: Jan-Otto Kröpke <mail@jkroepke.de>
2023-07-15 10:05:51 +02:00
Jan-Otto Kröpke
11218a95d0
Implement Lazy Loading of NameTable
Signed-off-by: Jan-Otto Kröpke <mail@jkroepke.de>
2023-07-15 10:01:46 +02:00
Jan-Otto Kröpke
750225775b
Integrate perflib
Signed-off-by: Jan-Otto Kröpke <mail@jkroepke.de>
2023-07-15 09:59:43 +02:00
Jan-Otto Kröpke
6890f391d4
fix lint
Signed-off-by: Jan-Otto Kröpke <mail@jkroepke.de>
2023-07-09 22:42:00 +02:00
Jan-Otto Kröpke
8509bc69a6
switch to go-kit logger
Signed-off-by: Jan-Otto Kröpke <mail@jkroepke.de>
2023-07-09 22:37:27 +02:00
Steffen Higel
187dbfc4ae Add cpu metrics based on newer and more accurate perflib sources
This change adds 4 new CPU related metrics:

 * process_mperf_total
 * processor_rtc_total
 * processor_utility_total
 * processor_privileged_utility_total

and renames the existing process_performance to
processor_performance_total, since it was previously misunderstood and
was unlikely to be have been useful without the above new metrics

The data sources for these are not particularly well understood, and the
examples show that in some cases, arbitrary scaling factors are required
to actually make them useful, but in my testing on hundreds of systems
with a broad range of CPUs and operating systems from 2012r2 through to
2019 has proved out that we can use them to accurately display actual
CPU frequencies and CPU utilisation as it is represented in taskmgr.

Things I don't particularly like and would like input on:

 * I would have preferred to do the scaling of processor_mperf_total in
the code, but there isn't an elegant way of doing this right now.
 * Maybe processor_mperf_total should be called
processor_mperformance_total.

See #787 for discussion.

Signed-off-by: Steffen Higel <higels@valvesoftware.com>
2022-11-02 14:34:04 -07:00
Calle Pettersson
c5a545540d Take over prometheus/common/log into local log package
Signed-off-by: Calle Pettersson <carlpett@users.noreply.github.com>
2021-01-30 11:53:51 +01:00
Calle Pettersson
21a02c4fbe Only query the perflib objects we need 2020-02-29 10:40:53 +01:00
Calle Pettersson
123a055242 Simple test of Perflib unmarshalling 2019-08-03 14:39:28 +02:00
Calle Pettersson
9308108284 Don't fail when a perflib counter isn't found 2019-08-03 13:15:45 +02:00
Calle Pettersson
33879449a2 Refactor cpu collector to use perflib instead of WMI. 2019-05-25 13:48:40 +02:00