search for standard sites
pub-search.waow.tech
search
zig
blog
atproto
fix: increase VM memory and keep machine running
- bump RAM from 256mb to 512mb (fixes SIGABRT crashes under load)
- disable auto_stop to eliminate cold start latency
- add bench-search script for performance testing
- gitignore .loq_cache
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
+201
-2
+2
-2
backend/fly.toml
+2
-2
backend/fly.toml
···
10
10
[http_service]
11
11
internal_port = 3000
12
12
force_https = true
13
-
auto_stop_machines = 'stop'
13
+
auto_stop_machines = 'off'
14
14
auto_start_machines = true
15
15
min_machines_running = 1
16
16
processes = ['app']
···
20
20
destination = '/data'
21
21
22
22
[[vm]]
23
-
memory = '256mb'
23
+
memory = '512mb'
24
24
cpu_kind = 'shared'
25
25
cpus = 1
+198
scripts/bench-search
+198
scripts/bench-search
···
1
+
#!/usr/bin/env -S uv run --script --quiet
2
+
# /// script
3
+
# requires-python = ">=3.12"
4
+
# dependencies = ["httpx", "rich"]
5
+
# ///
6
+
"""
7
+
benchmark search API permutations to find performance issues.
8
+
9
+
Usage:
10
+
./scripts/bench-search # run with defaults
11
+
./scripts/bench-search --runs 5 # more runs per permutation
12
+
./scripts/bench-search --local # test local server
13
+
"""
14
+
15
+
import asyncio
16
+
import statistics
17
+
import sys
18
+
import time
19
+
from dataclasses import dataclass
20
+
21
+
import httpx
22
+
from rich.console import Console
23
+
24
+
BASE_URL = "https://leaflet-search-backend.fly.dev"
25
+
26
+
QUERIES = ["python", "atproto", "rust", "blog", ""]
27
+
TAGS = ["atproto", "bluesky", "rust", "Webworld", ""]
28
+
PLATFORMS = ["leaflet", "pckt", ""]
29
+
LIMITS = [10, 40, ""]
30
+
31
+
32
+
@dataclass
33
+
class Result:
34
+
name: str
35
+
params: dict
36
+
times: list[float]
37
+
count: int
38
+
status: int
39
+
40
+
@property
41
+
def avg(self) -> float:
42
+
return statistics.mean(self.times) * 1000
43
+
44
+
@property
45
+
def min(self) -> float:
46
+
return min(self.times) * 1000
47
+
48
+
@property
49
+
def max(self) -> float:
50
+
return max(self.times) * 1000
51
+
52
+
@property
53
+
def p50(self) -> float:
54
+
return statistics.median(self.times) * 1000
55
+
56
+
@property
57
+
def stdev(self) -> float:
58
+
return statistics.stdev(self.times) * 1000 if len(self.times) > 1 else 0
59
+
60
+
61
+
async def bench_search(
62
+
client: httpx.AsyncClient, params: dict, runs: int
63
+
) -> Result:
64
+
"""benchmark a single search permutation."""
65
+
times = []
66
+
count = 0
67
+
status = 0
68
+
69
+
# filter empty params
70
+
clean_params = {k: v for k, v in params.items() if v}
71
+
72
+
name = " + ".join(f"{k}={v}" for k, v in clean_params.items()) or "(empty)"
73
+
74
+
for _ in range(runs):
75
+
start = time.perf_counter()
76
+
try:
77
+
resp = await client.get("/search", params=clean_params)
78
+
elapsed = time.perf_counter() - start
79
+
times.append(elapsed)
80
+
status = resp.status_code
81
+
if resp.status_code == 200:
82
+
count = len(resp.json())
83
+
except Exception as e:
84
+
times.append(30.0) # timeout
85
+
status = 0
86
+
# small delay between runs to avoid overwhelming server
87
+
await asyncio.sleep(0.1)
88
+
89
+
return Result(name=name, params=clean_params, times=times, count=count, status=status)
90
+
91
+
92
+
async def run_benchmarks(runs: int, console: Console) -> list[Result]:
93
+
"""run all search permutations."""
94
+
results = []
95
+
96
+
# build permutations - focus on meaningful combinations
97
+
permutations = []
98
+
99
+
# query only
100
+
for q in QUERIES:
101
+
if q:
102
+
permutations.append({"q": q})
103
+
104
+
# tag only
105
+
for tag in TAGS:
106
+
if tag:
107
+
permutations.append({"tag": tag})
108
+
109
+
# query + tag
110
+
for q in ["python", "blog"]:
111
+
for tag in ["atproto", "rust"]:
112
+
permutations.append({"q": q, "tag": tag})
113
+
114
+
# platform filter
115
+
for platform in PLATFORMS:
116
+
if platform:
117
+
permutations.append({"q": "blog", "platform": platform})
118
+
119
+
# limit variations
120
+
for limit in LIMITS:
121
+
if limit:
122
+
permutations.append({"q": "python", "limit": limit})
123
+
124
+
# tag + platform
125
+
for tag in ["atproto", "bluesky"]:
126
+
permutations.append({"tag": tag, "platform": "leaflet"})
127
+
128
+
# empty (should return recent)
129
+
permutations.append({})
130
+
131
+
console.print(f"[dim]running {len(permutations)} permutations × {runs} runs each...[/dim]\n")
132
+
133
+
async with httpx.AsyncClient(base_url=BASE_URL, timeout=30) as client:
134
+
# warmup
135
+
await client.get("/health")
136
+
137
+
for i, params in enumerate(permutations):
138
+
result = await bench_search(client, params, runs)
139
+
results.append(result)
140
+
# progress dot
141
+
console.print(".", end="", style="dim")
142
+
if (i + 1) % 20 == 0:
143
+
console.print()
144
+
145
+
console.print("\n")
146
+
return results
147
+
148
+
149
+
def print_results(results: list[Result], console: Console):
150
+
"""print results as plain text."""
151
+
# sort by p50 descending to show slowest first
152
+
results.sort(key=lambda r: r.p50, reverse=True)
153
+
154
+
console.print("results (sorted by p50, slowest first):\n")
155
+
console.print(f"{'permutation':<40} {'p50':>8} {'avg':>8} {'min':>8} {'max':>8} {'count':>6}")
156
+
console.print("-" * 80)
157
+
158
+
for r in results:
159
+
p50_str = f"{r.p50:.0f}ms"
160
+
if r.p50 > 1000:
161
+
p50_str = f"[red bold]{p50_str}[/red bold]"
162
+
elif r.p50 > 500:
163
+
p50_str = f"[yellow]{p50_str}[/yellow]"
164
+
elif r.p50 < 200:
165
+
p50_str = f"[green]{p50_str}[/green]"
166
+
167
+
console.print(f"{r.name:<40} {p50_str:>8} {r.avg:>7.0f}ms {r.min:>7.0f}ms {r.max:>7.0f}ms {r.count:>6}")
168
+
169
+
# summary
170
+
console.print()
171
+
slow = [r for r in results if r.p50 > 500]
172
+
if slow:
173
+
console.print(f"[yellow]⚠ {len(slow)} slow (p50 > 500ms)[/yellow]")
174
+
else:
175
+
console.print("[green]✓ all under 500ms p50[/green]")
176
+
177
+
178
+
async def main():
179
+
global BASE_URL
180
+
181
+
runs = 3
182
+
if "--runs" in sys.argv:
183
+
idx = sys.argv.index("--runs")
184
+
if idx + 1 < len(sys.argv):
185
+
runs = int(sys.argv[idx + 1])
186
+
187
+
if "--local" in sys.argv:
188
+
BASE_URL = "http://localhost:3000"
189
+
190
+
console = Console()
191
+
console.print(f"[bold]benchmarking {BASE_URL}[/bold]\n")
192
+
193
+
results = await run_benchmarks(runs, console)
194
+
print_results(results, console)
195
+
196
+
197
+
if __name__ == "__main__":
198
+
asyncio.run(main())