Skip to main content

CubePath dc.starter

Houston

Benchmark complete
Finished Oct 15, 2026
Geekbench 7 single-core
1,259
Faster than 69% of 4 vCPU plans
Geekbench 7 multi-core
4,426
Faster than 79% of 4 vCPU plans
Disk 4K IOPS
15,678
fio random read and write, 50/50
Monthly price at test time
$30.42
145 multi-core points per dollar
Same price today

Server

  • Provider
    CubePath
  • Plan
    dc.starter
  • Location
    Houston
  • vCPU
    4
  • RAM
    8 GB
  • Storage
    100 GB NVMe
  • Network
    Unknown
  • OS image
    ubuntu-24
  • Trigger
    Scheduled
  • Queued at
    Oct 15, 2026, 01:54:00 UTC
Visit CubePath

CPU

Version Single-core Multi-core
Geekbench 7 1,259 4,426 Geekbench Browser

Scores from different Geekbench versions aren't comparable with each other. Charts only use Geekbench 7.

Geekbench 7 workloads

Workload Single-core Multi-core
File Compression
1,404
66th of 170
4,216
25th of 124
Navigation
1,440
53rd of 170
Single-core only
HTML5 Browser
1,144
83rd of 170
Single-core only
PDF Viewer
1,332
77th of 170
Single-core only
Photo Library
1,143
78th of 170
4,432
28th of 124
Clang
1,149
73rd of 170
4,556
29th of 124
Text Processing
1,082
84th of 170
3,897
34th of 124
Asset Compression
1,237
84th of 170
4,919
33rd of 124
HDR
1,034
88th of 170
3,269
37th of 124
Photo Editor
1,410
72nd of 170
5,319
17th of 124
Ray Tracer
1,301
67th of 170
5,190
26th of 124
Structure from Motion
1,411
72nd of 170
Single-core only
Game Physics
1,308
61st of 170
Single-core only
Video Encoder
1,175
84th of 170
Single-core only
Audio Encoder
1,300
76th of 170
Single-core only
Video Player
1,377
73rd of 170
Single-core only

Rank among the 170 runs with Geekbench 7 workload scores. Bars are relative to the best run. Geekbench doesn't run every workload multi-core, so some rows only have a single-core score.

Memory, TLS and scheduler

Memory bandwidth (STREAM)

Test Result Runs Spread
Copy higher is better 74.7 GB/s 3 17.7%
Scale higher is better 61.3 GB/s 3 13%
Add higher is better 62.9 GB/s 3 17.3%
Triad higher is better 63.8 GB/s 3 16.5%

Average of 3 runs. Spread is the standard deviation as a share of the average.

TLS and crypto (OpenSSL)

Test Result Runs Spread
RSA 4096 signs higher is better 923/s 3 0.322%
RSA 4096 verifies higher is better 60,097/s 3 0.202%
SHA-256 higher is better 2.73 GB/s 3 0.663%
AES-256-GCM higher is better 14 GB/s 3 0.224%
ChaCha20-Poly1305 higher is better 7.1 GB/s 3 0.254%

Average of 3 runs. Spread is the standard deviation as a share of the average.

Scheduler latency (schbench)

Test Result Runs Spread
Request latency, median lower is better 4.13 ms 3 0.448%
Requests per second, 90th percentile higher is better 938/s 3 0.492%
Request latency, 99.9th percentile lower is better 8.93 ms 3 3.62%
Requests per second, average higher is better 927/s 3 0.348%

Average of 3 runs. Spread is the standard deviation as a share of the average.

Disk

Block size Read Write Total
4K 30.6 MB/s (7,834 IOPS) 30.6 MB/s (7,844 IOPS) 61.2 MB/s (15,678 IOPS)
64K 260.6 MB/s (4,170 IOPS) 262 MB/s (4,192 IOPS) 522.6 MB/s (8,362 IOPS)
512K 586.4 MB/s (1,172 IOPS) 617.6 MB/s (1,235 IOPS) 1.18 GB/s (2,407 IOPS)
1M 579 MB/s (579 IOPS) 617.6 MB/s (617 IOPS) 1.17 GB/s (1,196 IOPS)

fio random read and write, 50/50, run by YABS against the boot disk.

Network

IPv4 transfer speed

Loading...
Target Protocol Send Receive
Clouvider, London, UK (10G) IPv4 156 Mbps 695 Mbps
Eranium, Amsterdam, NL (100G) IPv4 160 Mbps 721 Mbps
Leaseweb, Singapore, SG (10G) IPv4 241 Mbps 730 Mbps
Clouvider, Los Angeles, CA, US (10G) IPv4 502 Mbps 981 Mbps
Leaseweb, NYC, NY, US (10G) IPv4 669 Mbps 984 Mbps

Public iperf3 servers vary in capacity and availability. Compare a target only with itself over time.

Datastores

PostgreSQL

fsync speed (pg_test_fsync)

Method Operations per second Time per operation
One 8 kB write
open_datasync 602 1.66 ms
fdatasync 611 1.64 ms
fsync 277 3.61 ms
fsync_writethrough Not supported here n/a
open_sync 256 3.91 ms
Two 8 kB writes
open_datasync 307 3.26 ms
fdatasync 504 1.99 ms
fsync 248 4.03 ms
fsync_writethrough Not supported here n/a
open_sync 88.4 11.3 ms
open_sync at different write sizes
1 * 16kB open_sync write 207 4.83 ms
2 * 8kB open_sync writes 138 7.27 ms
4 * 4kB open_sync writes 73 13.7 ms
8 * 2kB open_sync writes 36.6 27.3 ms
16 * 1kB open_sync writes 17.5 57.1 ms
fsync on a non-write descriptor
write, fsync, close 283 3.54 ms
write, close, fsync 292 3.42 ms
Non-synced 8 kB writes
write 534,481 0.002 ms

pg_test_fsync against the Docker volume Postgres keeps its data on. fdatasync is Linux's default wal_sync_method.

pgbench at scale 10

Workload Clients Transactions/s Median p95 p99 p99.9 Failed
Read/write (TPC-B like) 1 422 2.53 ms 3.34 ms 4.12 ms 7.14 ms 0
Read/write (TPC-B like) 8 1,349 4.74 ms 11.8 ms 17.5 ms 25.9 ms 0
Read/write (TPC-B like) 32 1,964 11.1 ms 47.6 ms 88.3 ms 159 ms 0
Read only 1 18,345 0.053 ms 0.074 ms 0.086 ms 0.11 ms 0
Read only 8 82,544 0.088 ms 0.157 ms 0.195 ms 0.301 ms 0
Read only 32 97,751 0.279 ms 0.458 ms 0.573 ms 1.23 ms 0

Scale 10 (1,000,000 accounts), loaded in 1.58 s. 60 s per run, prepared statements. Latency comes from sampled transaction logs, and p99.9 is left out when fewer than 1,000 were sampled.

pgbench at scale 100

Workload Clients Transactions/s Median p95 p99 p99.9 Failed
Read/write (TPC-B like) 1 443 1.93 ms 3.03 ms 3.82 ms 4.82 ms 0
Read/write (TPC-B like) 8 1,733 3.99 ms 7.68 ms 17 ms 33.8 ms 0
Read/write (TPC-B like) 32 3,979 5.97 ms 17.6 ms 36.2 ms 77.1 ms 0
Read only 1 14,327 0.066 ms 0.092 ms 0.109 ms 0.266 ms 0
Read only 8 65,658 0.111 ms 0.198 ms 0.249 ms 0.912 ms 0
Read only 32 73,962 0.384 ms 0.597 ms 0.781 ms 2.54 ms 0

Scale 100 (10,000,000 accounts), loaded in 16.2 s. 60 s per run, prepared statements. Latency comes from sampled transaction logs, and p99.9 is left out when fewer than 1,000 were sampled.

MySQL

sysbench OLTP

Workload Threads Transactions/s Queries/s Median p95 p99 Errors
Read/write 1 104 2,082 9.22 ms 13.2 ms 20 ms 0
Read/write 8 384 7,682 20 ms 30.8 ms 44.2 ms 0
Read/write 32 1,096 21,928 27.2 ms 46.6 ms 66.8 ms 0
Read only 1 744 11,901 1.37 ms 1.58 ms 1.76 ms 0
Read only 8 3,333 53,327 2.35 ms 3.36 ms 4.49 ms 0
Read only 32 3,219 51,503 9.91 ms 12.8 ms 15 ms 0

10 tables of 100,000 rows, loaded in 9.7 s. 60 s per run, one connection per thread.

Redis

memtier

Mix Operations/s Hits/s Median p99 p99.9
1:10 set:get 59,271 53,882 1.06 ms 2.1 ms 2.32 ms
1:1 set:get 58,204 29,102 1.07 ms 2.13 ms 2.35 ms

1,000,000 keys of 32 bytes. 64 connections over 4 threads, 60 s per ratio.

Web frameworks

Framework Fortunes req/s Single query req/s JSON req/s Fortunes p99 at 256 connections
Next.js nextjs 1,331 4,921 6,754 338 ms
Express express-postgresjs 16,165 22,232 59,174 33.3 ms
Fastify fastify-postgres 15,867 23,099 59,563 36 ms
NestJS nestjs 9,528 11,128 39,257 48.5 ms
Nuxt nuxt 14,032 21,501 56,900 46.8 ms
FastAPI fastapi 7,467 9,683 31,889 224 ms
Django django-postgresql 3,771 4,323 10,104 166 ms
Rails rails 5,734 7,782 29,317 62.2 ms
Laravel laravel 1,663 1,731 3,459 171 ms
Symfony symfony 2,126 2,282 6,494 130 ms

Peak requests per second across the 64 and 256 connection levels, measured with wrk. Each test has to pass the TechEmpower response checks first, or it's marked invalid.

Web apps

WooCommerce

Page mix

Step Requests/s Median p95 p99 Error rate
8 virtual users
Home page 4.73 344 ms 451 ms 487 ms 0%
Shop page 4.73 444 ms 566 ms 605 ms 0%
Category page 4.73 293 ms 486 ms 526 ms 0%
Product page 4.73 312 ms 421 ms 450 ms 0%
Product search 4.73 275 ms 376 ms 408 ms 0%
32 virtual users
Home page 4.51 1.34 s 1.59 s 1.71 s 0%
Shop page 4.51 1.75 s 1.95 s 2.02 s 0%
Category page 4.51 1.4 s 1.76 s 1.87 s 0%
Product page 4.51 1.33 s 1.52 s 1.58 s 0%
Product search 4.51 1.19 s 1.37 s 1.42 s 0%

Cart and checkout

Step Requests/s Median p95 p99 Error rate
8 virtual users
Add to cart 8.94 349 ms 460 ms 498 ms 0%
Cart 8.94 303 ms 394 ms 436 ms 0%
Checkout 8.94 243 ms 321 ms 347 ms 0%
32 virtual users
Add to cart 8.54 1.38 s 1.62 s 1.68 s 0%
Cart 8.54 1.28 s 1.49 s 1.57 s 0%
Checkout 8.54 1.06 s 1.25 s 1.32 s 0%

k6 with a fixed number of virtual users, 61 to 64 s per level. The error rate counts responses that weren't a 200.

Discourse

Signed in

Step Requests/s Median p95 p99 Error rate
1 virtual user
Topic page 2.45 183 ms 206 ms 440 ms 0%
Topic JSON 1.22 95.2 ms 107 ms 133 ms 0%
Home page 1.22 165 ms 185 ms 229 ms 0%
Categories page 0.612 192 ms 205 ms 208 ms 0%
User activity page 0.612 111 ms 163 ms 313 ms 0%
4 virtual users
Topic page 8.38 212 ms 247 ms 467 ms 0%
Topic JSON 4.2 108 ms 129 ms 191 ms 0%
Home page 4.18 191 ms 241 ms 472 ms 0%
Categories page 2.12 221 ms 256 ms 592 ms 0%
User activity page 2.08 132 ms 195 ms 303 ms 0%
16 virtual users
Topic page 7.99 836 ms 1.04 s 1.52 s 0%
Topic JSON 4.03 607 ms 761 ms 1.03 s 0%
Home page 4.03 778 ms 1.01 s 1.27 s 0%
Categories page 2.03 815 ms 1.03 s 1.43 s 0%
User activity page 2.01 685 ms 833 ms 1.01 s 0%

Anonymous

Step Requests/s Median p95 p99 Error rate
16 virtual users
Topic page 166 23.5 ms 47.4 ms 72 ms 0%
Topic JSON 83 21.7 ms 45.3 ms 73.1 ms 0%
Home page 83 23.7 ms 48.5 ms 73.6 ms 0%
Categories page 41.5 23.1 ms 46.1 ms 75.4 ms 0%
User activity page 41.5 142 ms 197 ms 332 ms 0%

k6 with a fixed number of virtual users, 60 to 61 s per level, after a 21 s warmup. The error rate counts responses that weren't a 200. Discourse ran with 8 app workers and 2048 MB of Postgres shared buffers, what its installer picks for a 8 GB box. Its installer adds no swap on a box this big. The container peaked at 2,683 MB.

Ghost

Readers

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 10.2 29 ms 31.9 ms 37.3 ms 0%
Post page 25.5 14.8 ms 17.1 ms 22.8 ms 0%
Tag page 5.1 19.5 ms 21.8 ms 24.3 ms 0%
Author page 5.1 19.7 ms 21.8 ms 22.8 ms 0%
RSS feed 5.1 21.2 ms 26.5 ms 28.8 ms 0%
4 virtual users
Home page 11.8 90.2 ms 108 ms 121 ms 0%
Post page 29.5 63.4 ms 83.9 ms 94.1 ms 0%
Tag page 5.91 58.7 ms 76.7 ms 87.6 ms 0%
Author page 5.88 56.8 ms 76.8 ms 83.9 ms 0%
RSS feed 5.88 62.7 ms 84.4 ms 92.3 ms 0%
16 virtual users
Home page 11.8 350 ms 390 ms 410 ms 0%
Post page 29.4 289 ms 333 ms 353 ms 0%
Tag page 5.84 190 ms 237 ms 250 ms 0%
Author page 5.87 190 ms 231 ms 246 ms 0%
RSS feed 5.87 194 ms 236 ms 253 ms 0%

Staff in Ghost Admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Post list 5 28.8 ms 31.9 ms 34.5 ms 0%
Post editor 15 9.85 ms 12.3 ms 14.6 ms 0%
Saving a draft 15 32.7 ms 37.5 ms 41.5 ms 0%
Member list 5.02 34.6 ms 39.4 ms 45.7 ms 0%
4 virtual users
Post list 6.54 35.6 ms 39.3 ms 41.8 ms 0%
Post editor 19.7 12.8 ms 19.4 ms 21.4 ms 0%
Saving a draft 19.7 160 ms 189 ms 203 ms 0%
Member list 6.58 40.5 ms 44.8 ms 47.8 ms 0%

k6 with a fixed number of virtual users, 60 s per level, after a 20 s warmup. The error rate counts responses that weren't a 200. Ghost ran the way its ghost-docker setup runs it: one Node process, and MySQL with its stock 128 MB buffer pool. Memory peaked with Ghost at 539 MB and MySQL at 625 MB.

Wagtail

Visitors

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 1.95 69 ms 72.8 ms 74.1 ms 0%
Blog index 1.93 230 ms 240 ms 246 ms 0%
Blog post 5.79 22 ms 33.7 ms 36.1 ms 0%
Bread page 5.79 24.4 ms 26.3 ms 27.4 ms 0%
Location page 1.93 23.6 ms 24.9 ms 26.2 ms 0%
Site search 1.93 40.4 ms 65.5 ms 67.1 ms 0%
4 virtual users
Home page 3.01 181 ms 284 ms 326 ms 0%
Blog index 3.05 694 ms 954 ms 1.04 s 0%
Blog post 9.03 51.6 ms 88.9 ms 127 ms 0%
Bread page 9.06 54.4 ms 86.5 ms 101 ms 0%
Location page 3.05 52.2 ms 81.1 ms 92.7 ms 0%
Site search 3 82.7 ms 166 ms 192 ms 0%
16 virtual users
Home page 3.33 538 ms 718 ms 799 ms 0%
Blog index 3.41 1.49 s 1.69 s 1.81 s 0%
Blog post 10 307 ms 435 ms 534 ms 0%
Bread page 10.1 322 ms 480 ms 577 ms 0%
Location page 3.38 328 ms 500 ms 570 ms 0%
Site search 3.33 363 ms 564 ms 700 ms 0%

Editors in the Wagtail admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Admin dashboard 0.694 75.8 ms 90.3 ms 158 ms 0%
Page explorer 1.42 337 ms 358 ms 505 ms 0%
Page editor 2.13 161 ms 193 ms 273 ms 0%
Image library 0.71 58.7 ms 65.5 ms 553 ms 0%
Admin page search 0.694 33.3 ms 68.1 ms 71.8 ms 0%
4 virtual users
Admin dashboard 1.2 256 ms 512 ms 599 ms 0%
Page explorer 2.43 734 ms 1.22 s 1.5 s 0%
Page editor 3.61 363 ms 713 ms 933 ms 0%
Image library 1.2 173 ms 418 ms 517 ms 0%
Admin page search 1.2 102 ms 354 ms 448 ms 0%

k6 with a fixed number of virtual users, 60 to 61 s per level, after a 20 s warmup. The error rate counts responses that weren't a 200. Wagtail ran the way bakerydemo ships it: uWSGI with 2 workers of 4 threads each, whatever the box, and Postgres and Redis on stock settings. Memory peaked with Wagtail at 299 MB, Postgres at 151 MB, and Redis at 26 MB.

Advertised vs. measured

Advertised Measured
vCPU 4 4
CPU Dedicated vCPU 0.2% of busy CPU time stolen
RAM 8 GB 7.7 GiB
Storage 100 GB NVMe 96.8 GiB
Architecture x86_64 x86_64
Virtualization KVM KVM

Guests usually report slightly less RAM and disk than advertised because of kernel reservations and filesystem overhead.

Detected hardware

CPU model
AMD EPYC Processor
CPU cores
4
CPU frequency
2500 MHz
AES-NI
Yes
VM-x/AMD-V
No
RAM reported
7.7 GiB
Swap reported
0 MiB
Disk reported
96.8 GiB
Virtualization reported
KVM
CPU steal
0.2% of busy CPU time stolen
Distro
Ubuntu 24.04.5 LTS
Kernel
6.8.0-142-generic
Architecture
x86_64
IPv4 reachable
Yes
IPv6 reachable
Yes

Advertised at test time

Plan
dc.starter
Product line
Dedicated CPU
Location
Houston
vCPU
4 dedicated vCPU
Architecture
x86_64
RAM
8 GB
Storage
100 GB NVMe
Virtualization
KVM
Network
Unknown
Transfer
10 TB
Port 25
On request
Monthly price at test time
$30.42
Hourly price at test time
$0.042
YABS version
v2026-09-20
Ran at
Oct 15, 2026, 01:55:17 UTC
Parser version
5

Run timeline

Queued
Oct 15, 2026, 01:54:00 UTC
First update from the server
Oct 15, 2026, 01:55:13 UTC
Completed
Oct 15, 2026, 03:31:27 UTC
Server deleted
Oct 15, 2026, 03:31:27 UTC
Cost of this run
$0.068
Watch party 0 watching

This party closed at . It's read only now.

Watch party

Loading the party