bench: scale bisect harness and report (improvise-felo.10)

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VdfEGXA7aJ6ftMsCc9PJze

bench/edge.py

@@ -0,0 +1,8 @@
+import sys; sys.path.insert(0,'bench')
+from scale_bisect import run
+cfgs=[dict(k=k,prune=0) for k in (16,17,18,26,27)]+[dict(k=k,prune=1) for k in (7,11,12,13,14,21,22)]+[dict(k=1000,n=n,mode='records') for n in (1000,1200,1500,1800,2000,4600,14500)]
+for c in cfgs:
+    c.setdefault('n',100000); c['ops']='open,key,window'
+    v=[run('/tmp/sb',c,timeout=200) for _ in range(3)]
+    f=lambda k:'/'.join(f"{r[k][1]:.1f}" if k in r else '-' for r in v)
+    print({k:c[k] for k in c if k!='ops'},'rows',v[0].get('rows'),'open',f('open'),'key',f('keypress_down'),'win',f('browser_grid_of_top'),'tuiframe',f('tui_frame_grid_of_whole'),flush=True)

bench/full.py

@@ -0,0 +1,10 @@
+import sys, json; sys.path.insert(0,'bench')
+from scale_bisect import run
+cfgs=[dict(k=9,prune=0),dict(k=10,prune=0),dict(k=17,prune=0,groups=1),dict(k=26,prune=0,groups=1),
+      dict(k=8,prune=1),dict(k=13,prune=1,groups=1),
+      dict(k=1000,n=1300,mode='records'),dict(k=1000,n=4400,mode='records'),dict(k=1000,n=14000,mode='records')]
+for c in cfgs:
+    c.setdefault('n',100000)
+    for rep in range(3):
+        r=run('/tmp/sb',c,timeout=300)
+        print(json.dumps({'cfg':c,'rep':rep,**r}),flush=True)

bench/scale_bisect.py

@@ -0,0 +1,38 @@
+"""Drive benches/scale_bisect one configuration per process; parse its lines.
+usage: scale_bisect.py BIN k=.. n=.. [cats=..] [prune=..] [mode=..] [ops=..] [--timeout S]
+"""
+import subprocess, sys, re, json
+
+def run(binary, cfg, timeout=90):
+    args = [binary] + [f"{k}={v}" for k, v in cfg.items()]
+    try:
+        p = subprocess.run(args, capture_output=True, text=True, timeout=timeout)
+        out, status = p.stdout, "ok"
+    except subprocess.TimeoutExpired as e:
+        out, status = (e.stdout or b"").decode() if isinstance(e.stdout, bytes) else (e.stdout or ""), "timeout"
+    res = {"status": status}
+    for line in out.splitlines():
+        if line.startswith("REFUSED"):
+            res["status"] = "refused"
+        m = re.match(r"(\w+) min=([\d.]+) med=([\d.]+) max=([\d.]+)", line)
+        if m:
+            res[m[1]] = (float(m[2]), float(m[3]), float(m[4]))
+        for kv in re.findall(r"(\w+)=([\d.]+)", line):
+            if kv[0] in ("rows", "cols", "maxrss_mb", "improv_mb", "snapshot_kb", "rss_after_open_mb", "cells"):
+                res[kv[0]] = float(kv[1])
+        m = re.match(r"json_encode_setcell_updates ms=(.*)", line)
+        if m:
+            res["json_setcell"] = m[1]
+    return res
+
+if __name__ == "__main__":
+    binary = sys.argv[1]
+    cfg, timeout = {}, 90
+    rest = sys.argv[2:]
+    for a in rest:
+        if a.startswith("--timeout"):
+            timeout = int(a.split("=")[1])
+        else:
+            k, v = a.split("=", 1)
+            cfg[k] = v
+    print(json.dumps(run(binary, cfg, timeout)))

bench/sweep.py

@@ -0,0 +1,10 @@
+import sys; sys.path.insert(0,'bench')
+from scale_bisect import run
+import itertools
+OPS=sys.argv[1]; 
+cfgs=eval(sys.argv[2])
+cols=sys.argv[3].split(',')
+for c in cfgs:
+    c=dict(c); c['ops']=OPS
+    r=run('/tmp/sb',c,timeout=int(sys.argv[4]) if len(sys.argv)>4 else 90)
+    print(c, r['status'], 'rows',r.get('rows'), *[f"{k}={r[k][1]:.1f}" if k in r else f"{k}=-" for k in cols], f"rss={r.get('maxrss_mb')}", flush=True)