Performance: surfaces, the candle ring and the equalizer curve as shaders, the pill's bars as quads; tools/perf.sh

A playing pill cost the iGPU about 2.9 ms and the CPU 3.7 ms a frame, 60 frames a
second: two vello passes over the whole island window for the surface's shadow and
gradients (vello keeps no gradient between frames) and one for the bars. Now 0.4 ms
GPU and 1.2 ms CPU. The open card went from 5.2 to 2.6 ms GPU and 6.2 to 3.4 ms CPU
a frame. surface.wgsl draws every design's shadow, fill and inner gradient in one
pass, with vello's own blurred-rectangle formula

tools/perf.sh

@@ -0,0 +1,29 @@
+#!/bin/sh
+# perf.sh PID [SECONDS]: a process's cpu %, the cpu % of the commands it ran and waited for
+# (children), its gpu busy % per engine (drm fdinfo, xe and i915) and its resident memory
+# over SECONDS (default 10). cpu 100 % is one core
+pid=${1:?pid}; secs=${2:-10}
+
+sample() {
+    # utime + stime in clock ticks, then engine cycles summed over every drm fd as "engine used total"
+    awk '{print "cpu", $14 + $15, $16 + $17}' /proc/$pid/stat
+    cat /proc/$pid/fdinfo/* 2>/dev/null | awk '
+        /^drm-cycles-/ {e=substr($1, 12); sub(":", "", e); used[e]+=$2}
+        /^drm-total-cycles-/ {e=substr($1, 18); sub(":", "", e); total[e]=$2}
+        /^drm-engine-[a-z]+:/ && $3 == "ns" {e=substr($1, 12); sub(":", "", e); ns[e]+=$2}
+        END {for (e in used) print "cyc", e, used[e], total[e]; for (e in ns) print "ns", e, ns[e]}'
+}
+
+a=$(sample); start=$(date +%s%N); sleep "$secs"; b=$(sample); end=$(date +%s%N)
+
+printf '%s\n--\n%s\n' "$a" "$b" | awk -v tck="$(getconf CLK_TCK)" -v wall="$(( (end - start) / 1000 ))" '
+    $1 == "--" {second=1; next}
+    $1 == "cpu" {if (second) {cpu1=$2; kid1=$3} else {cpu0=$2; kid0=$3}}
+    $1 == "cyc" {if (second) {u1[$2]=$3; t1[$2]=$4} else {u0[$2]=$3; t0[$2]=$4}}
+    $1 == "ns" {if (second) n1[$2]=$3; else n0[$2]=$3}
+    END {
+        printf "cpu %.1f %%  children %.1f %%", (cpu1 - cpu0) / tck * 1e6 / wall * 100, (kid1 - kid0) / tck * 1e6 / wall * 100
+        for (e in u1) if (t1[e] > t0[e]) printf "  %s %.2f %%", e, (u1[e] - u0[e]) / (t1[e] - t0[e]) * 100
+        for (e in n1) printf "  %s %.2f %%", e, (n1[e] - n0[e]) / (wall * 1000) * 100
+    }'
+printf '  rss %s MiB\n' "$(awk '/^VmRSS/ {printf "%.0f", $2 / 1024}' /proc/$pid/status)"