metricgroup_..._metric_list(9)

πŸ“¦ version 7.3.1, in nixpkgs unstable

✨ metricgroup__add_metric_list πŸ’…

okay so bestie, welcome to the Kernel API Manual πŸŽ€ β€” this one's <pink>metricgroup__add_metric_list(9)</pink>, and no cap it's giving "find the metrics you asked for and actually add them" energy. Let's get into it 🫢


🌸 NAME 🌸

metricgroup__add_metric_list β€” Find and add metrics, or metric groups, specified in a list. Literally its whole job πŸ’–


πŸ¦‹ SYNOPSIS πŸ¦‹

int metricgroup__add_metric_list (const char *pmu , const char *list ,
       bool metric_no_group , bool metric_no_threshold , const char
       *user_requested_cpu_list , bool system_wide , struct list_head
       *metric_list , const struct pmu_metrics_table *table );

it returns an int, bestie β€” write it down πŸ“


⭐ ARGUMENTS ⭐

  • pmu β€” a pmu to restrict the metrics to, or "all" for all PMUS. like, "all" is the main character option here πŸ‘‘
  • list β€” the list of metrics or metric groups. For example, "IPC,CPI,TopDownL1" would match the IPC and CPI metrics, and TopDownL1 would match all the metrics in the TopDownL1 group. so TopDownL1 is out here collecting the whole group, iconic 🌈
  • metric_no_group β€” should events written to events be grouped "{}" or global. Grouping is the default but due to multiplexing the user may override. yeah β€” default is grouping, but multiplexing exists so the user gets to override, iykyk πŸ’…
  • metric_no_threshold β€” -- undescribed --. that's it. that's the description. the docs literally said nothing on this one πŸ˜­πŸ’€ we're not gonna invent lore for it, moving on
  • user_requested_cpu_list β€” Command line specified CPUs to record on. so, the cpus you asked for from the command line 🧚
  • system_wide β€” Are events for all processes recorded. yes this is phrased as a question. yes it's still the argument πŸ“
  • metric_list β€” The list that metrics are added to. this is where the good stuff goes πŸ’œ
  • table β€” The table that is searched for metrics, most commonly the table for the architecture perf is running upon. so like, the arch table for whatever perf is running on πŸ¦‹

πŸ’… SEE ALSO πŸ’…

and also the kernel file ./tools/perf/util/metricgroup.c β€” literally the source, go read it, it's serving context πŸ’–


🫢 quick reminder bestie: the metric_no_threshold description is <red>genuinely listed as -- undescribed -- in the original. that's not me being lazy, that's Just What It Says. keep that energy.

and that's the whole page!! mwah πŸ’‹ this one ships from ./tools/perf/util, dated October 2026, filed under metricgroup_..._metric_list(9) β€” slay, go add some metrics βœ¨πŸŽ€πŸ”₯

πŸ“¦ where this page comes from