Cleanup ruby sampler metricsbjk/48176_ruby_gc

* Use a simple counter for sampler duration instead of a histogram.
* Use a counter to collect GC time.
* Remove unused objects metric.
* Cleanup metric names to match Prometheus conventions.
* Prefix generic GC stats with `gc_stat`.
* Include worker label on memory and file descriptor metrics.

1 files changed, 14 insertions, 12 deletions

diff --git a/lib/gitlab/metrics/samplers/ruby_sampler.rb b/lib/gitlab/metrics/samplers/ruby_sampler.rb
index a39b3bc158c..7b2b3bedf04 100644
--- a/lib/gitlab/metrics/samplers/ruby_sampler.rb
+++ b/lib/gitlab/metrics/samplers/ruby_sampler.rb
@@ -22,27 +22,27 @@ module Gitlab
 
         def init_metrics
           metrics = {}
-          metrics[:sampler_duration] = Metrics.histogram(with_prefix(:sampler_duration, :seconds), 'Sampler time', { worker: nil })
-          metrics[:total_time] = Metrics.gauge(with_prefix(:gc, :time_total), 'Total GC time', labels, :livesum)
+          metrics[:sampler_duration] = Metrics.counter(with_prefix(:sampler, :duration_seconds_total), 'Sampler time', labels)
+          metrics[:total_time] = Metrics.counter(with_prefix(:gc, :duration_seconds_total), 'Total GC time', labels)
           GC.stat.keys.each do |key|
-            metrics[key] = Metrics.gauge(with_prefix(:gc, key), to_doc_string(key), labels, :livesum)
+            metrics[key] = Metrics.gauge(with_prefix(:gc_stat, key), to_doc_string(key), labels, :livesum)
           end
 
-          metrics[:objects_total] = Metrics.gauge(with_prefix(:objects, :total), 'Objects total', labels.merge(class: nil), :livesum)
-          metrics[:memory_usage] = Metrics.gauge(with_prefix(:memory, :usage_total), 'Memory used total', labels, :livesum)
-          metrics[:file_descriptors] = Metrics.gauge(with_prefix(:file, :descriptors_total), 'File descriptors total', labels, :livesum)
+          metrics[:memory_usage] = Metrics.gauge(with_prefix(:memory, :bytes), 'Memory used', labels, :livesum)
+          metrics[:file_descriptors] = Metrics.gauge(with_prefix(:file, :descriptors), 'File descriptors used', labels, :livesum)
 
           metrics
         end
 
         def sample
           start_time = System.monotonic_time
-          sample_gc
 
-          metrics[:memory_usage].set(labels, System.memory_usage)
-          metrics[:file_descriptors].set(labels, System.file_descriptor_count)
+          metrics[:memory_usage].set(labels.merge(worker_label), System.memory_usage)
+          metrics[:file_descriptors].set(labels.merge(worker_label), System.file_descriptor_count)
+
+          sample_gc
 
-          metrics[:sampler_duration].observe(labels.merge(worker_label), System.monotonic_time - start_time)
+          metrics[:sampler_duration].increment(labels, System.monotonic_time - start_time)
         ensure
           GC::Profiler.clear
         end
@@ -50,11 +50,13 @@ module Gitlab
         private
 
         def sample_gc
-          metrics[:total_time].set(labels, GC::Profiler.total_time * 1000)
-
+          # Collect generic GC stats.
           GC.stat.each do |key, value|
             metrics[key].set(labels, value)
           end
+
+          # Collect the GC time since last sample in float seconds.
+          metrics[:total_time].increment(labels, GC::Profiler.total_time)
         end
 
         def worker_label