Files
mtusi2026lab3/scripts/scaling-summary.py
T
2026-11-05 17:56:30 +03:00

55 lines
3.5 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
#!/usr/bin/env python3
"""Build CSV and figures from preserved measurements (no invented values)."""
import csv, json, pathlib, statistics, os
os.environ.setdefault('MPLCONFIGDIR','/private/tmp/track1-mpl')
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
ROOT=pathlib.Path(__file__).resolve().parents[1]
OUT=ROOT/'evidence/track1'
rows=[]
for path in sorted(OUT.glob('*-r[12].json')):
r=json.loads(path.read_text()); label=r['label'].rsplit('-r',1)[0]
samples={}
seen=set()
for line in path.with_name(path.stem+'-stats.jsonl').read_text().splitlines():
# Docker's streaming output may prepend terminal control sequences.
line=line[line.find('{'):]
try: s=json.loads(line)
except ValueError: continue
name=s['Name']
if name not in seen:
seen.add(name)
continue # Initial Docker sample predates the measurement interval.
service=name.rsplit('-',1)[0].replace('mtusi-lab3-','')
samples.setdefault(service,[]).append(float(s['CPUPerc'].rstrip('%')))
row=dict(case=label,repeat=path.stem[-1],rps=r['successful_rps'],read_p95_ms=r['read']['p95_ms'],write_p95_ms=r['write']['p95_ms'],error_share=r['error_share'],lost=r['verify']['lost'],duplicates=r['verify']['duplicate_ids']+r['verify']['duplicate_texts'])
for s,values in samples.items(): row[s+'_cpu_mean']=statistics.mean(values)
rows.append(row)
if not rows: raise SystemExit('No results')
fields=list(dict.fromkeys(k for r in rows for k in r))
with (OUT/'summary.csv').open('w') as f:
w=csv.DictWriter(f,fields); w.writeheader(); w.writerows(rows)
def avg(label,key): return statistics.mean(r[key] for r in rows if r['case']==label)
def bounds(label):
v=[r['rps'] for r in rows if r['case']==label]; m=statistics.mean(v)
return [m-min(v),max(v)-m]
plt.rcParams.update({'font.size':10})
fig,axes=plt.subplots(1,2,figsize=(10,3.5))
for labels,title,ax in [(['fixed-1','fixed-2','fixed-4'],'Общий бюджет API: 2 CPU / 1 ГиБ',axes[0]),(['grow-1','fixed-2','grow-4'],'На реплику: 1 CPU / 512 МиБ',axes[1])]:
means=[avg(l,'rps') for l in labels]
ax.errorbar([1,2,4],means,yerr=list(zip(*(bounds(l) for l in labels))),fmt='o-',capsize=5)
ax.set(xticks=[1,2,4],xlabel='Реплики API',ylabel='Успешные запросы/с',title=title,ylim=(0,max(means)*1.2)); ax.grid(alpha=.25)
fig.tight_layout(); fig.savefig(OUT/'scaling.png',dpi=160); plt.close(fig)
labels=['grow-4','lb2-4','db4-4']
if all(any(r['case']==l for r in rows) for l in labels):
fig,axes=plt.subplots(1,2,figsize=(10,3.5))
axes[0].bar(['Исходный','LB: 2 CPU','БД: 4 CPU'],[avg(l,'rps') for l in labels],yerr=list(zip(*(bounds(l) for l in labels))),capsize=5)
axes[0].set(ylabel='Успешные запросы/с',title='Проверка узкого места: 4 API × 1 CPU')
for s,limit in [('api',100),('lb',100),('postgres',200),('valkey',100)]:
axes[1].bar(s,avg('grow-4',s+'_cpu_mean')/limit*100)
axes[1].axhline(100,color='red',linestyle='--'); axes[1].set(ylabel='% от CPU-лимита',title='Средняя загрузка до улучшения')
fig.tight_layout(); fig.savefig(OUT/'bottleneck.png',dpi=160); plt.close(fig)
for l in dict.fromkeys(r['case'] for r in rows):
print(l, 'RPS', round(avg(l,'rps')), 'read p95',round(avg(l,'read_p95_ms'),2),'write p95',round(avg(l,'write_p95_ms'),2), 'CPU', {s:round(avg(l,s+'_cpu_mean')) for s in ['api','lb','postgres','valkey']})