Document the switch to HW counters

Author: Kobzol

site/frontend/templates/pages/detailed-query.html

@@ -80,6 +80,8 @@ <h4>Artifact Size</h4>
             </tbody>
         </table>
         <p>'Instructions (%)' is the percentage of instructions executed on this query.</p>
+        <p><b>Note: self-profile measurements have been <a href="https://github.com/rust-lang/rustc-perf/pull/1647">recently switched</a>
+          from wall-time to HW counters (instruction count). If comparing with an older artifact, the timings might not be directly comparable.</b></p>
         <p>Executions do not include cached executions.</p>
         <table>
             <thead>

site/src/api.rs

@@ -471,19 +471,23 @@ pub mod self_profile {
         pub artifact_sizes: Option<Vec<ArtifactSize>>,
     }
 
+    // Due to backwards compatibility, self profile event timing data is represented as durations,
+    // however since https://github.com/rust-lang/rustc-perf/pull/1647 it actually represents
+    // HW counter data (instruction counts).
     #[derive(Serialize, Deserialize, Clone, Debug)]
     pub struct QueryData {
         pub label: QueryLabel,
-        // Nanoseconds
+        // Instruction count
         pub time: u64,
+        // Instruction count
         pub self_time: u64,
         pub percent_total_time: f32,
         pub number_of_cache_misses: u32,
         pub number_of_cache_hits: u32,
         pub invocation_count: u32,
-        // Nanoseconds
+        // Instruction count
         pub blocked_time: u64,
-        // Nanoseconds
+        // Instruction count
         pub incremental_load_time: u64,
     }
 

site/src/request_handlers/self_profile.rs

@@ -541,17 +541,17 @@ pub async fn handle_self_profile(
     }
     let commits = Arc::new(commits);
 
-    let mut cpu_responses = ctxt.statistic_series(query, commits.clone()).await?;
-    assert_eq!(cpu_responses.len(), 1, "all selectors are exact");
-    let mut cpu_response = cpu_responses.remove(0).series;
+    let mut instructions_responses = ctxt.statistic_series(query, commits.clone()).await?;
+    assert_eq!(instructions_responses.len(), 1, "all selectors are exact");
+    let mut instructions_response = instructions_responses.remove(0).series;
 
     let mut self_profile = get_or_download_self_profile(
         ctxt,
         commits.first().unwrap().clone(),
         bench_name,
         profile,
         scenario,
-        cpu_response.next().unwrap().1,
+        instructions_response.next().unwrap().1,
     )
     .await?;
     let base_self_profile = match commits.get(1) {
@@ -562,7 +562,7 @@ pub async fn handle_self_profile(
                 bench_name,
                 profile,
                 scenario,
-                cpu_response.next().unwrap().1,
+                instructions_response.next().unwrap().1,
             )
             .await?,
         ),

site/src/self_profile.rs

@@ -318,7 +318,7 @@ pub(crate) async fn get_or_download_self_profile(
 }
 
 fn get_self_profile_data(
-    cpu_clock: Option<f64>,
+    total_instructions: Option<f64>,
     profile: &analyzeme::AnalysisResults,
 ) -> ServerResult<self_profile::SelfProfile> {
     let total_self_time: Duration = profile.query_data.iter().map(|qd| qd.self_time).sum();
@@ -345,7 +345,7 @@ fn get_self_profile_data(
         time: profile.total_time.as_nanos() as u64,
         self_time: total_self_time.as_nanos() as u64,
         // TODO: check against wall-time from perf stats
-        percent_total_time: cpu_clock
+        percent_total_time: total_instructions
             .map(|w| ((total_self_time.as_secs_f64() / w) * 100.0) as f32)
             // sentinel "we couldn't compute this time"
             .unwrap_or(-100.0),