Readymetrics #81
Merged
Readymetrics #81
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…process start or end time was given.
- Added -NoPriority flag to get old output
- Print idle and non-idle ready times - Fixed column algnment
…nAdaptationMode> to use server GC with a dynamic number of GC Heaps instead of the currently hard coded 4. This shows significant memory savings in high memory pressure scenarios.
…ull for processes which are still existing as ID but no name can be retrieved.
- Reordered CSV columns and added NonIdle Ready Times
The idle and non idle cswitch counts can be off by the total context switch count because for each method
we only calculate percentiles if at least 50 CSwitch events were found.
- Fix output regressions due to new column in tests
…n the idle process (it is always 0) instead slice?.Wait?.ReadyThreadEvent?.ReadyingProcess?.Id is the correct one to get the extracted data to match with WPA. - Adapted test data to match with values displayed in WPA
Renamed properties to reflect that we measure C1 states from idle and own process which we call DeeSleep Read Times. All others are non deep sleep states.
Added sum of all values which are >99% of all events to make it easy to check if some mount everest outliers are responsible for the majority of delays
…est outliers to be able to judge the overal distribution shape. - Fixed formatting when only stacktags are visible - Added to CSV data Sum and 99% sum columns
…s if we have collected Frequency data.
- Renamed ReadyTimes to stay consistent with file naming
Parse events not exposed by TraceProcessing on our own: Autonomous Mode BaseProfile HeteroPolicy HeteroThread HeteroThreadShort - Dump Power print newly exposed properties - Dump Power fixed issue where too many files were supressed in diff mode
… extract and displayed data.
…Id == WindowsConstants.IdleProcessId and use slice.PreviousActivityOnProcessor.Process.Id == WindowsConstants.IdleProcessId && slice?.SwitchIn?.ContextSwitch?.PreviousCState == 1 again which is the correct way. When PreviousCState is 1 it must have been switched by the dile thread.
…g but in the end 0 files are printed. Now we print the skipped files and keep of each group the first file so we print one file of an identical power settings group.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
-Extract
-NoCSwitchand-NoSamplingto ignore CPU sampling or context switch data when extracing CPU or stacktag data.-Dump Stats
-Dump Power
-Dump CPU
Prioritywhich only sorts in CPU total mode.-NoPriorityflag to get old outputFixes
Update target framework from .NET 6.0 to .NET 8.0.
Remove superfluous Exception overloads
Updated dependent libraries