Stress-test ASCII video at 30/60/120 fps; fix libghostty-vt Debug build

Added a full ASCII-video benchmark suite that hammers the renderer
with 30 KiB / 70 KiB full-screen frames at 30, 60, and 120 fps
targets — both renderer-only and full-pipeline (em.Write + renderer
+ stdout). Each stream benchmark reports µs/frame, fps_ceiling, and
percent of the per-frame budget consumed.

The pipeline benchmarks revealed we were missing 120 fps by a wide
margin (190%-350% of budget at 120fps, 60-90 fps ceiling). Isolating
em.Write confirmed libghostty-vt is the bottleneck — 16-29 ms per
truecolor frame, library file at 33 MiB.

Root cause: the Makefile invoked `zig build` with no
-Doptimize, and Zig's standardOptimizeOption defaults to Debug. So
the shipped libghostty-vt was unoptimised. Fixed by pinning
ReleaseFast in the Makefile (override via GHOSTTY_VT_OPTIMIZE for
debug builds of the upstream lib).

Existing checkouts need `make clean-deps && make deps` to pick up
the rebuild.
This commit is contained in:
2026-05-15 13:43:31 +01:00
parent 1c590f8e32
commit 2f109a84fa
4 changed files with 451 additions and 3 deletions

View File

@@ -2,8 +2,11 @@ package app
import (
"fmt"
"io"
"strings"
"testing"
"github.com/hjbdev/patterm/internal/vt"
)
// Benchmarks for patterm's hot paths. Run with:
@@ -167,3 +170,377 @@ func BenchmarkRendererThroughput_ReuseInstance(b *testing.B) {
}
}
}
// Stress workloads — these model the worst things a real session
// can throw at us. The headline target is "ASCII video": every cell
// of an 80x40 viewport carries an SGR colour change and a printable
// character, rendered as one chunk per frame. Real ASCII-video CLIs
// (ascii-image-converter, asciinema-render, towel.blinkenlights, the
// Bad Apple meme) hit patterm with exactly this pattern at 24-30 fps
// for minutes at a time.
//
// We synthesise the workload rather than ship a captured corpus so
// the benchmarks stay deterministic and the repo doesn't carry tens
// of MiB of fixture data. The encoding is faithful to what those
// tools actually emit.
// buildASCIIVideoFrame builds a single full-viewport frame with
// 8-colour SGR per cell (`\x1b[3Nm`). One frame ≈ 30 KiB for an
// 80x40 viewport, which lines up with what ascii-video tools emit.
func buildASCIIVideoFrame(cols, rows int) []byte {
var b strings.Builder
b.WriteString("\x1b[H") // home cursor before the frame starts
for r := 0; r < rows; r++ {
for c := 0; c < cols; c++ {
fmt.Fprintf(&b, "\x1b[3%dm%c", (r+c)%8, byte(' '+(r*c)%(0x7e-' ')))
}
b.WriteString("\x1b[0m\r\n")
}
return []byte(b.String())
}
// buildASCIIVideoFrameTrueColor builds the same frame but with
// 24-bit RGB SGR (`\x1b[38;2;R;G;Bm`). Every cell is ~20 bytes of
// escape + 1 byte glyph, so a frame is ≈ 70 KiB. This is what
// chafa --colors=full and modern terminal video players emit, and
// it's the heaviest SGR variant the renderer's CSI path sees.
func buildASCIIVideoFrameTrueColor(cols, rows int) []byte {
var b strings.Builder
b.WriteString("\x1b[H")
for r := 0; r < rows; r++ {
for c := 0; c < cols; c++ {
rd := (r * 7) % 256
gd := (c * 11) % 256
bd := ((r + c) * 13) % 256
fmt.Fprintf(&b, "\x1b[38;2;%d;%d;%dm%c", rd, gd, bd, byte(' '+(r*c)%(0x7e-' ')))
}
b.WriteString("\x1b[0m\r\n")
}
return []byte(b.String())
}
// buildBadApplePattern builds the simplest possible ASCII video
// frame: alternating black/white cells (the Bad Apple meme is
// essentially a 1-bit silhouette video). This is the pattern that
// stresses the SGR state-machine without exercising truecolor parse
// — useful for isolating "is the cost in the colour parsing or in
// the cell-by-cell switching?"
func buildBadApplePattern(cols, rows int) []byte {
var b strings.Builder
b.WriteString("\x1b[H")
for r := 0; r < rows; r++ {
for c := 0; c < cols; c++ {
if (r+c)%2 == 0 {
b.WriteString("\x1b[37m█")
} else {
b.WriteString("\x1b[30m█")
}
}
b.WriteString("\x1b[0m\r\n")
}
return []byte(b.String())
}
// BenchmarkASCIIVideo_Frame_8Color renders a single full-screen
// frame as one chunk. The headline number is MB/s — at 30 fps a
// frame is one PTY chunk every ~33 ms, so this should comfortably
// stay well under 1 ms.
func BenchmarkASCIIVideo_Frame_8Color(b *testing.B) {
frame := buildASCIIVideoFrame(80, 40)
b.SetBytes(int64(len(frame)))
b.ReportAllocs()
b.ResetTimer()
for i := 0; i < b.N; i++ {
vr := newViewportRenderer(newTerminalLayout(120, 40))
_ = vr.Render(frame)
}
}
// BenchmarkASCIIVideo_Frame_TrueColor renders a single truecolor
// frame. ~70 KiB per frame. Compare this to the 8-colour number to
// see how much extra cost the truecolor SGR parse imposes — the
// `\x1b[38;2;R;G;Bm` form is the longest and most parameter-rich
// CSI patterm sees in practice.
func BenchmarkASCIIVideo_Frame_TrueColor(b *testing.B) {
frame := buildASCIIVideoFrameTrueColor(80, 40)
b.SetBytes(int64(len(frame)))
b.ReportAllocs()
b.ResetTimer()
for i := 0; i < b.N; i++ {
vr := newViewportRenderer(newTerminalLayout(120, 40))
_ = vr.Render(frame)
}
}
// BenchmarkASCIIVideo_Frame_BadApple is the 1-bit pattern: simplest
// SGR (two colours, alternating). Isolates the renderer's cell-by-
// cell SGR cycling cost from the truecolor parse cost.
func BenchmarkASCIIVideo_Frame_BadApple(b *testing.B) {
frame := buildBadApplePattern(80, 40)
b.SetBytes(int64(len(frame)))
b.ReportAllocs()
b.ResetTimer()
for i := 0; i < b.N; i++ {
vr := newViewportRenderer(newTerminalLayout(120, 40))
_ = vr.Render(frame)
}
}
// runStreamBench is the shared body for the per-fps stream
// benchmarks. It feeds a fixed frame N times through a single
// renderer instance and reports µs/frame + an achievable-fps
// ceiling alongside the standard ns/op + MB/s. The fps value in
// the benchmark name is the *target* — the workload itself doesn't
// rate-limit; we just decide how many frames make a benchmark op
// (3 seconds' worth) so steady-state cost dominates warm-up.
func runStreamBench(b *testing.B, frame []byte, fps int) {
frames := fps * 3 // 3 seconds at the target rate
totalBytes := int64(len(frame) * frames)
b.SetBytes(totalBytes)
b.ReportAllocs()
b.ResetTimer()
for i := 0; i < b.N; i++ {
vr := newViewportRenderer(newTerminalLayout(120, 40))
for f := 0; f < frames; f++ {
_ = vr.Render(frame)
}
}
nsPerFrame := float64(b.Elapsed().Nanoseconds()) / float64(b.N*frames)
b.ReportMetric(nsPerFrame/1000.0, "µs/frame")
b.ReportMetric(1e9/nsPerFrame, "fps_ceiling")
// budget_pct = how much of the per-frame budget at the target
// rate we burn. Under 100 means we can hit the target; over
// means we can't.
budgetNs := 1e9 / float64(fps)
b.ReportMetric(nsPerFrame/budgetNs*100, "budget_pct")
}
// BenchmarkASCIIVideo_Stream_8Color_30fps / _60fps / _120fps reuse
// one renderer across (3 × fps) frames. The headline numbers are
// µs/frame, fps_ceiling (= 1e9 / ns/frame), and budget_pct (=
// percent of the per-frame budget at the target rate we consume).
//
// 30 fps is the typical ASCII-video baseline (towel, chafa, Bad
// Apple ports). 60 is the "smooth playback" target. 120 is a
// future-proofing stress level matching modern high-refresh
// terminals.
func BenchmarkASCIIVideo_Stream_8Color_30fps(b *testing.B) {
runStreamBench(b, buildASCIIVideoFrame(80, 40), 30)
}
func BenchmarkASCIIVideo_Stream_8Color_60fps(b *testing.B) {
runStreamBench(b, buildASCIIVideoFrame(80, 40), 60)
}
func BenchmarkASCIIVideo_Stream_8Color_120fps(b *testing.B) {
runStreamBench(b, buildASCIIVideoFrame(80, 40), 120)
}
// BenchmarkASCIIVideo_Stream_TrueColor_* same set but with the
// truecolor frames. Compare against the 8-colour numbers to see
// what the longer `\x1b[38;2;R;G;Bm` parse costs us.
func BenchmarkASCIIVideo_Stream_TrueColor_30fps(b *testing.B) {
runStreamBench(b, buildASCIIVideoFrameTrueColor(80, 40), 30)
}
func BenchmarkASCIIVideo_Stream_TrueColor_60fps(b *testing.B) {
runStreamBench(b, buildASCIIVideoFrameTrueColor(80, 40), 60)
}
func BenchmarkASCIIVideo_Stream_TrueColor_120fps(b *testing.B) {
runStreamBench(b, buildASCIIVideoFrameTrueColor(80, 40), 120)
}
// BenchmarkASCIIVideo_Stream_BadApple_* tracks the 1-bit alternating
// pattern. Isolates per-cell SGR cycling cost from the truecolor
// parse cost above — useful when reading the diff between the two
// stream variants.
func BenchmarkASCIIVideo_Stream_BadApple_30fps(b *testing.B) {
runStreamBench(b, buildBadApplePattern(80, 40), 30)
}
func BenchmarkASCIIVideo_Stream_BadApple_60fps(b *testing.B) {
runStreamBench(b, buildBadApplePattern(80, 40), 60)
}
func BenchmarkASCIIVideo_Stream_BadApple_120fps(b *testing.B) {
runStreamBench(b, buildBadApplePattern(80, 40), 120)
}
// BenchmarkEmulator_Write_8Color / _TrueColor isolate the
// libghostty-vt CGO cost — same frames the Pipeline benchmarks use,
// but feeding only the emulator. The delta between this and
// BenchmarkASCIIVideo_Stream_… is the renderer's share; the rest
// is libghostty-vt.
func BenchmarkEmulator_Write_8Color_Frame(b *testing.B) {
frame := buildASCIIVideoFrame(80, 40)
b.SetBytes(int64(len(frame)))
b.ReportAllocs()
b.ResetTimer()
for i := 0; i < b.N; i++ {
em, err := vt.NewGhosttyEmulator(80, 40)
if err != nil {
b.Fatalf("emulator: %v", err)
}
if _, werr := em.Write(frame); werr != nil {
b.Fatalf("emulator.Write: %v", werr)
}
_ = em.Close()
}
}
func BenchmarkEmulator_Write_TrueColor_Frame(b *testing.B) {
frame := buildASCIIVideoFrameTrueColor(80, 40)
b.SetBytes(int64(len(frame)))
b.ReportAllocs()
b.ResetTimer()
for i := 0; i < b.N; i++ {
em, err := vt.NewGhosttyEmulator(80, 40)
if err != nil {
b.Fatalf("emulator: %v", err)
}
if _, werr := em.Write(frame); werr != nil {
b.Fatalf("emulator.Write: %v", werr)
}
_ = em.Close()
}
}
// BenchmarkEmulator_Write_Stream_120fps reuses one emulator across
// 360 frames (3 sec × 120 fps). This is the cleanest measurement
// of em.Write steady-state cost.
func BenchmarkEmulator_Write_Stream_8Color_120fps(b *testing.B) {
frame := buildASCIIVideoFrame(80, 40)
const frames = 360
b.SetBytes(int64(len(frame) * frames))
b.ReportAllocs()
b.ResetTimer()
for i := 0; i < b.N; i++ {
em, err := vt.NewGhosttyEmulator(80, 40)
if err != nil {
b.Fatalf("emulator: %v", err)
}
for f := 0; f < frames; f++ {
if _, werr := em.Write(frame); werr != nil {
b.Fatalf("emulator.Write: %v", werr)
}
}
_ = em.Close()
}
nsPerFrame := float64(b.Elapsed().Nanoseconds()) / float64(b.N*frames)
b.ReportMetric(nsPerFrame/1000.0, "µs/frame")
b.ReportMetric(1e9/nsPerFrame, "fps_ceiling")
}
func BenchmarkEmulator_Write_Stream_TrueColor_120fps(b *testing.B) {
frame := buildASCIIVideoFrameTrueColor(80, 40)
const frames = 360
b.SetBytes(int64(len(frame) * frames))
b.ReportAllocs()
b.ResetTimer()
for i := 0; i < b.N; i++ {
em, err := vt.NewGhosttyEmulator(80, 40)
if err != nil {
b.Fatalf("emulator: %v", err)
}
for f := 0; f < frames; f++ {
if _, werr := em.Write(frame); werr != nil {
b.Fatalf("emulator.Write: %v", werr)
}
}
_ = em.Close()
}
nsPerFrame := float64(b.Elapsed().Nanoseconds()) / float64(b.N*frames)
b.ReportMetric(nsPerFrame/1000.0, "µs/frame")
b.ReportMetric(1e9/nsPerFrame, "fps_ceiling")
}
// runPipelineStreamBench includes the libghostty-vt emulator.Write
// CGO call and a stdout write to io.Discard alongside the renderer
// — i.e. everything OnPTYOut does in production except the host
// terminal's own paint time (which patterm doesn't control). This
// is the honest "can we hit N fps end-to-end?" measurement.
func runPipelineStreamBench(b *testing.B, frame []byte, fps int) {
frames := fps * 3
totalBytes := int64(len(frame) * frames)
b.SetBytes(totalBytes)
b.ReportAllocs()
b.ResetTimer()
for i := 0; i < b.N; i++ {
em, err := vt.NewGhosttyEmulator(80, 40)
if err != nil {
b.Fatalf("emulator: %v", err)
}
vr := newViewportRenderer(newTerminalLayout(120, 40))
for f := 0; f < frames; f++ {
if _, werr := em.Write(frame); werr != nil {
b.Fatalf("emulator.Write: %v", werr)
}
out := vr.Render(frame)
// Match OnPTYOut's autowrap prelude/postlude wrapping so
// the byte count is faithful.
_, _ = io.Discard.Write([]byte("\x1b[?7l"))
_, _ = io.Discard.Write(out)
_, _ = io.Discard.Write([]byte("\x1b[?7h"))
}
_ = em.Close()
}
nsPerFrame := float64(b.Elapsed().Nanoseconds()) / float64(b.N*frames)
b.ReportMetric(nsPerFrame/1000.0, "µs/frame")
b.ReportMetric(1e9/nsPerFrame, "fps_ceiling")
budgetNs := 1e9 / float64(fps)
b.ReportMetric(nsPerFrame/budgetNs*100, "budget_pct")
}
// BenchmarkPipeline_ASCIIVideo_* — the FULL OnPTYOut path
// (emulator.Write CGO + viewport renderer + a stdout write to
// io.Discard) running at 30/60/120 fps targets. These are the
// numbers to trust when asking "can we sustain N fps?" The
// renderer-only Stream benchmarks above isolate one stage and
// understate the real cost.
//
// 120 fps is the explicit baseline: anything under 100% of the
// per-frame budget here means we hit 120 fps with margin to spare.
func BenchmarkPipeline_ASCIIVideo_8Color_30fps(b *testing.B) {
runPipelineStreamBench(b, buildASCIIVideoFrame(80, 40), 30)
}
func BenchmarkPipeline_ASCIIVideo_8Color_60fps(b *testing.B) {
runPipelineStreamBench(b, buildASCIIVideoFrame(80, 40), 60)
}
func BenchmarkPipeline_ASCIIVideo_8Color_120fps(b *testing.B) {
runPipelineStreamBench(b, buildASCIIVideoFrame(80, 40), 120)
}
func BenchmarkPipeline_ASCIIVideo_TrueColor_30fps(b *testing.B) {
runPipelineStreamBench(b, buildASCIIVideoFrameTrueColor(80, 40), 30)
}
func BenchmarkPipeline_ASCIIVideo_TrueColor_60fps(b *testing.B) {
runPipelineStreamBench(b, buildASCIIVideoFrameTrueColor(80, 40), 60)
}
func BenchmarkPipeline_ASCIIVideo_TrueColor_120fps(b *testing.B) {
runPipelineStreamBench(b, buildASCIIVideoFrameTrueColor(80, 40), 120)
}
// BenchmarkSessionResume_5MiBStyled simulates the user's
// motivating case: claude resuming a long chat session and dumping
// the whole history. 5 MiB of styled output as a single Render
// call. Numbers here tell us how long the visible "scrolling
// while resume loads" window will be.
func BenchmarkSessionResume_5MiBStyled(b *testing.B) {
chunk := buildStyledLinesChunk(5 * 1024 * 1024)
b.SetBytes(int64(len(chunk)))
b.ReportAllocs()
b.ResetTimer()
for i := 0; i < b.N; i++ {
vr := newViewportRenderer(newTerminalLayout(120, 40))
_ = vr.Render(chunk)
}
}
// BenchmarkSessionResume_5MiBPlain same as above but pure text.
// Lower bound — what we'd hit if the resume content were styling-
// free.
func BenchmarkSessionResume_5MiBPlain(b *testing.B) {
chunk := buildPlainASCIIChunk(5 * 1024 * 1024)
b.SetBytes(int64(len(chunk)))
b.ReportAllocs()
b.ResetTimer()
for i := 0; i < b.N; i++ {
vr := newViewportRenderer(newTerminalLayout(120, 40))
_ = vr.Render(chunk)
}
}