Skip to main content

OVHcloud B3-8

Beauharnois

Benchmark complete
Finished Oct 17, 2026
Geekbench 7 single-core
1,422
Faster than 72% of 2 vCPU plans
Geekbench 7 multi-core
2,670
Faster than 68% of 2 vCPU plans
Disk 4K IOPS
40,035
fio random read and write, 50/50
Monthly price at test time
$44.17
60 multi-core points per dollar
Same price today

Server

  • Provider
    OVHcloud
  • Plan
    B3-8
  • Location
    Beauharnois
  • vCPU
    2
  • RAM
    8 GB
  • Storage
    50 GB NVMe
  • Network
    500 Mbps
  • OS image
    Ubuntu 24.04
  • Trigger
    Scheduled
  • Queued at
    Oct 16, 2026, 23:06:00 UTC
Visit OVHcloud

CPU

Version Single-core Multi-core
Geekbench 7 1,422 2,670 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
1,478
61st of 216
2,586
69th of 147
Navigation
1,455
67th of 216
Single-core only
HTML5 Browser
1,374
71st of 216
Single-core only
PDF Viewer
1,483
72nd of 216
Single-core only
Photo Library
1,282
80th of 216
2,606
73rd of 147
Clang
1,204
80th of 216
2,423
83rd of 147
Text Processing
1,269
75th of 216
2,285
79th of 147
Asset Compression
1,415
78th of 216
2,818
76th of 147
HDR
1,432
65th of 216
2,684
62nd of 147
Photo Editor
1,606
67th of 216
3,206
61st of 147
Ray Tracer
1,451
50th of 216
2,855
73rd of 147
Structure from Motion
1,554
74th of 216
Single-core only
Game Physics
1,317
75th of 216
Single-core only
Video Encoder
1,397
63rd of 216
Single-core only
Audio Encoder
1,496
56th of 216
Single-core only
Video Player
1,614
53rd of 216
Single-core only

Rank among the 216 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 53.8 GB/s 3 16.3%
Scale higher is better 31.3 GB/s 3 9.31%
Add higher is better 38.2 GB/s 3 12.8%
Triad higher is better 33.8 GB/s 3 8.82%

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 426/s 3 2.43%
RSA 4096 verifies higher is better 28,714/s 3 0.474%
SHA-256 higher is better 1.63 GB/s 3 0.325%
AES-256-GCM higher is better 7.71 GB/s 3 0.81%
ChaCha20-Poly1305 higher is better 4.3 GB/s 3 0.361%

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 4.6 ms 3 0.348%
Requests per second, 90th percentile higher is better 428/s 3 0.135%
Request latency, 99.9th percentile lower is better 8.42 ms 3 0.439%
Requests per second, average higher is better 423/s 3 0.213%

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

Disk

Block size Read Write Total
4K 78.1 MB/s (19,991 IOPS) 78.3 MB/s (20,044 IOPS) 156.4 MB/s (40,035 IOPS)
64K 1.29 GB/s (21,167 IOPS) 1.3 GB/s (21,278 IOPS) 2.59 GB/s (42,445 IOPS)
512K 1.9 GB/s (3,896 IOPS) 2 GB/s (4,103 IOPS) 3.91 GB/s (7,999 IOPS)
1M 1.97 GB/s (2,012 IOPS) 2.1 GB/s (2,146 IOPS) 4.06 GB/s (4,158 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 465 Mbps 473 Mbps
Eranium, Amsterdam, NL (100G) IPv4 465 Mbps 467 Mbps
Leaseweb, Singapore, SG (10G) IPv4 390 Mbps 364 Mbps
Clouvider, Los Angeles, CA, US (10G) IPv4 277 Mbps 475 Mbps
Leaseweb, NYC, NY, US (10G) IPv4 488 Mbps 489 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 7,435 0.134 ms
fdatasync 7,274 0.137 ms
fsync 5,547 0.18 ms
fsync_writethrough Not supported here n/a
open_sync 5,781 0.173 ms
Two 8 kB writes
open_datasync 3,672 0.272 ms
fdatasync 6,442 0.155 ms
fsync 4,609 0.217 ms
fsync_writethrough Not supported here n/a
open_sync 2,696 0.371 ms
open_sync at different write sizes
1 * 16kB open_sync write 5,447 0.184 ms
2 * 8kB open_sync writes 2,898 0.345 ms
4 * 4kB open_sync writes 1,451 0.689 ms
8 * 2kB open_sync writes 786 1.27 ms
16 * 1kB open_sync writes 426 2.35 ms
fsync on a non-write descriptor
write, fsync, close 4,889 0.205 ms
write, close, fsync 4,776 0.209 ms
Non-synced 8 kB writes
write 627,461 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 2,189 0.445 ms 0.533 ms 0.664 ms 2.79 ms 0
Read/write (TPC-B like) 8 4,767 1.57 ms 2.64 ms 3.55 ms 5.97 ms 0
Read/write (TPC-B like) 32 4,638 5.7 ms 15 ms 23.5 ms 41.6 ms 0
Read only 1 24,887 0.038 ms 0.054 ms 0.066 ms 0.154 ms 0
Read only 8 50,413 0.14 ms 0.232 ms 0.287 ms 0.495 ms 0
Read only 32 52,044 0.496 ms 0.79 ms 1.11 ms 2.02 ms 0

Scale 10 (1,000,000 accounts), loaded in 1.23 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 1,884 0.494 ms 0.597 ms 1.25 ms 5.62 ms 0
Read/write (TPC-B like) 8 4,171 1.68 ms 2.66 ms 10.6 ms 16.1 ms 0
Read/write (TPC-B like) 32 5,278 5.53 ms 10.1 ms 16.3 ms 28.5 ms 0
Read only 1 19,785 0.046 ms 0.067 ms 0.09 ms 0.596 ms 0
Read only 8 40,277 0.179 ms 0.305 ms 0.399 ms 0.847 ms 0
Read only 32 43,486 0.632 ms 0.987 ms 1.37 ms 2.59 ms 0

Scale 100 (10,000,000 accounts), loaded in 11.8 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 1 427 8,545 2.22 ms 2.91 ms 5.77 ms 0
Read/write 8 844 16,890 9.22 ms 13.7 ms 17.3 ms 0
Read/write 32 905 18,102 35.6 ms 56.8 ms 74.5 ms 0
Read only 1 945 15,121 1.03 ms 1.32 ms 1.58 ms 0
Read only 8 1,646 26,337 4.74 ms 6.67 ms 7.57 ms 0
Read only 32 1,526 24,417 20.7 ms 26.7 ms 29.7 ms 0

10 tables of 100,000 rows, loaded in 6.2 s. 60 s per run, one connection per thread.

Redis

memtier

Mix Operations/s Hits/s Median p99 p99.9
1:10 set:get 60,167 54,697 0.599 ms 3.12 ms 4.64 ms
1:1 set:get 60,573 30,286 0.575 ms 3.14 ms 4.74 ms

1,000,000 keys of 32 bytes. 64 connections over 2 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 763 2,520 3,654 446 ms
Express express-postgresjs 7,736 11,121 30,202 73.8 ms
Fastify fastify-postgres 7,660 11,942 34,962 59 ms
NestJS nestjs 4,855 5,422 17,362 75.4 ms
Nuxt nuxt 6,894 10,836 30,710 103 ms
FastAPI fastapi 3,703 4,519 18,649 299 ms
Django django-postgresql 1,398 1,556 3,336 285 ms
Rails rails 2,333 3,193 12,257 130 ms
Laravel laravel 826 887 1,585 330 ms
Symfony symfony 1,041 1,110 2,955 264 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 2.44 659 ms 742 ms 776 ms 0%
Shop page 2.44 886 ms 1.01 s 1.06 s 0%
Category page 2.44 556 ms 900 ms 954 ms 0%
Product page 2.44 599 ms 688 ms 733 ms 0%
Product search 2.44 521 ms 600 ms 631 ms 0%
32 virtual users
Home page 2.44 2.38 s 2.65 s 2.71 s 0%
Shop page 2.44 3.17 s 3.54 s 3.6 s 0%
Category page 2.44 2.82 s 3.33 s 3.56 s 0%
Product page 2.44 2.42 s 2.63 s 2.73 s 0%
Product search 2.44 2.22 s 2.41 s 2.46 s 0%

Cart and checkout

Step Requests/s Median p95 p99 Error rate
8 virtual users
Add to cart 4.66 703 ms 796 ms 832 ms 0%
Cart 4.66 565 ms 652 ms 687 ms 0%
Checkout 4.66 443 ms 508 ms 527 ms 0%
32 virtual users
Add to cart 4.7 2.31 s 2.8 s 2.88 s 0%
Cart 4.7 2.43 s 2.66 s 2.75 s 0%
Checkout 4.7 1.95 s 2.19 s 2.28 s 0%

k6 with a fixed number of virtual users, 61 to 66 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 2.53 176 ms 203 ms 252 ms 0%
Topic JSON 1.28 91.1 ms 122 ms 255 ms 0%
Home page 1.28 159 ms 200 ms 370 ms 0%
Categories page 0.63 183 ms 208 ms 240 ms 0%
User activity page 0.63 108 ms 237 ms 280 ms 0%
4 virtual users
Topic page 4.23 420 ms 537 ms 894 ms 0%
Topic JSON 2.11 219 ms 280 ms 308 ms 0%
Home page 2.13 379 ms 537 ms 845 ms 0%
Categories page 1.07 421 ms 737 ms 1 s 0%
User activity page 1.06 265 ms 351 ms 645 ms 0%
16 virtual users
Topic page 4.5 1.41 s 1.7 s 1.93 s 0%
Topic JSON 2.28 1.25 s 1.53 s 1.67 s 0%
Home page 2.22 1.36 s 1.64 s 1.77 s 0%
Categories page 1.14 1.43 s 1.72 s 2 s 0%
User activity page 1.12 1.26 s 1.49 s 1.67 s 0%

Anonymous

Step Requests/s Median p95 p99 Error rate
16 virtual users
Topic page 100 44.8 ms 106 ms 127 ms 0%
Topic JSON 50.1 45.2 ms 108 ms 127 ms 0%
Home page 50.1 46.7 ms 110 ms 128 ms 0%
Categories page 25.1 42.7 ms 103 ms 127 ms 0%
User activity page 25.1 145 ms 216 ms 290 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 4 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 2,179 MB.

Ghost

Readers

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 10.8 26.3 ms 30.9 ms 38.6 ms 0%
Post page 26.9 13.7 ms 16.8 ms 26.1 ms 0%
Tag page 5.38 18.1 ms 21.1 ms 27.5 ms 0%
Author page 5.38 18.2 ms 21.9 ms 27.5 ms 0%
RSS feed 5.36 23.2 ms 27.3 ms 36.1 ms 0%
4 virtual users
Home page 13.1 80.1 ms 99.8 ms 111 ms 0%
Post page 32.6 57.3 ms 76.4 ms 88.7 ms 0%
Tag page 6.53 50.3 ms 69.3 ms 77.5 ms 0%
Author page 6.53 52.3 ms 70.9 ms 80.6 ms 0%
RSS feed 6.53 57.5 ms 75.2 ms 84.6 ms 0%
16 virtual users
Home page 12.9 317 ms 375 ms 398 ms 0%
Post page 32.2 261 ms 314 ms 341 ms 0%
Tag page 6.45 174 ms 225 ms 239 ms 0%
Author page 6.43 174 ms 216 ms 237 ms 0%
RSS feed 6.42 177 ms 221 ms 252 ms 0%

Staff in Ghost Admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Post list 5.98 25.4 ms 31.2 ms 42 ms 0%
Post editor 17.9 9.55 ms 12.3 ms 16 ms 0%
Saving a draft 17.9 24 ms 29.7 ms 38.6 ms 0%
Member list 5.98 30.6 ms 37.9 ms 44.6 ms 0%
4 virtual users
Post list 7.39 33.5 ms 40.1 ms 52.4 ms 0%
Post editor 22.2 16.9 ms 21.7 ms 25 ms 0%
Saving a draft 22.2 134 ms 170 ms 190 ms 0%
Member list 7.41 41.4 ms 49 ms 52.9 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 600 MB and MySQL at 622 MB.

Wagtail

Visitors

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 1.82 73 ms 83.4 ms 88.7 ms 0%
Blog index 1.82 242 ms 265 ms 273 ms 0%
Blog post 5.44 23.8 ms 36.9 ms 39.2 ms 0%
Bread page 5.46 26.3 ms 29.7 ms 33.2 ms 0%
Location page 1.82 25.1 ms 27.7 ms 29.5 ms 0%
Site search 1.81 39.3 ms 68.7 ms 74.3 ms 0%
4 virtual users
Home page 2.81 198 ms 279 ms 316 ms 0%
Blog index 2.84 689 ms 896 ms 969 ms 0%
Blog post 8.42 57.1 ms 98.5 ms 118 ms 0%
Bread page 8.44 63.7 ms 93.4 ms 106 ms 0%
Location page 2.84 58.6 ms 84.7 ms 118 ms 0%
Site search 2.79 93.5 ms 189 ms 226 ms 0%
16 virtual users
Home page 2.62 690 ms 917 ms 1 s 0%
Blog index 2.72 1.83 s 2.17 s 2.25 s 0%
Blog post 7.91 394 ms 631 ms 696 ms 0%
Bread page 7.92 403 ms 640 ms 729 ms 0%
Location page 2.67 399 ms 608 ms 736 ms 0%
Site search 2.65 463 ms 757 ms 859 ms 0%

Editors in the Wagtail admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Admin dashboard 0.711 77 ms 85.5 ms 98.4 ms 0%
Page explorer 1.44 339 ms 376 ms 476 ms 0%
Page editor 2.13 156 ms 186 ms 278 ms 0%
Image library 0.711 59.1 ms 69.1 ms 528 ms 0%
Admin page search 0.711 33.4 ms 69.2 ms 71.1 ms 0%
4 virtual users
Admin dashboard 1.16 254 ms 498 ms 563 ms 0%
Page explorer 2.36 770 ms 1.21 s 1.35 s 0%
Page editor 3.48 372 ms 693 ms 794 ms 0%
Image library 1.16 265 ms 446 ms 582 ms 0%
Admin page search 1.16 106 ms 231 ms 344 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 298 MB, Postgres at 151 MB, and Redis at 25 MB.

Advertised vs. measured

Advertised Measured
vCPU 2 2
CPU Dedicated vCPU 0.1% of busy CPU time stolen
RAM 8 GB 7.6 GiB
Storage 50 GB NVMe 48.4 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-Milan Processor
CPU cores
2
CPU frequency
2445 MHz
AES-NI
Yes
VM-x/AMD-V
Yes
RAM reported
7.6 GiB
Swap reported
0 MiB
Disk reported
48.4 GiB
Virtualization reported
KVM
CPU steal
0.1% of busy CPU time stolen
Distro
Ubuntu 24.04.4 LTS
Kernel
6.8.0-136-generic
Architecture
x86_64
IPv4 reachable
Yes
IPv6 reachable
Yes

Advertised at test time

Plan
B3-8
Product line
General Purpose B3
Location
Beauharnois
vCPU
2 dedicated vCPU
Architecture
x86_64
RAM
8 GB
Storage
50 GB NVMe
Virtualization
KVM
Network
500 Mbps
Transfer
Unmetered
Port 25
Unknown
Monthly price at test time
$44.17
Hourly price at test time
$0.061
YABS version
v2026-09-20
Ran at
Oct 16, 2026, 23:07:20 UTC
Parser version
5

Run timeline

Queued
Oct 16, 2026, 23:06:00 UTC
First update from the server
Oct 16, 2026, 23:07:14 UTC
Completed
Oct 17, 2026, 00:42:00 UTC
Server deleted
Oct 17, 2026, 00:42:00 UTC
Cost of this run
$0.097
Watch party 0 watching

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

Watch party

Loading the party