Skip to main content

OVHcloud D2-4

Frankfurt

Benchmark complete
Finished Oct 14, 2026
Geekbench 7 single-core
635
Faster than 18% of 2 vCPU plans
Geekbench 7 multi-core
1,192
Faster than 15% of 2 vCPU plans
Disk 4K IOPS
20,042
fio random read and write, 50/50
Monthly price at test time
$13.50
88 multi-core points per dollar
Same price today

Server

  • Provider
    OVHcloud
  • Plan
    D2-4
  • Location
    Frankfurt
  • vCPU
    2
  • RAM
    4 GB
  • Storage
    50 GB NVMe
  • Network
    250 Mbps
  • OS image
    Ubuntu 24.04
  • Trigger
    Scheduled
  • Queued at
    Oct 13, 2026, 22:20:00 UTC
Visit OVHcloud

Latest runs of this plan

Full history of this plan

CPU

Version Single-core Multi-core
Geekbench 7 635 1,192 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
651
141st of 154
1,036
109th of 116
Navigation
764
143rd of 154
Single-core only
HTML5 Browser
574
142nd of 154
Single-core only
PDF Viewer
671
143rd of 154
Single-core only
Photo Library
496
144th of 154
1,052
106th of 116
Clang
578
145th of 154
1,100
108th of 116
Text Processing
574
142nd of 154
1,133
104th of 116
Asset Compression
678
137th of 154
1,329
102nd of 116
HDR
640
138th of 154
1,218
95th of 116
Photo Editor
673
129th of 154
1,298
100th of 116
Ray Tracer
741
134th of 154
1,431
101st of 116
Structure from Motion
759
138th of 154
Single-core only
Game Physics
583
144th of 154
Single-core only
Video Encoder
559
142nd of 154
Single-core only
Audio Encoder
709
138th of 154
Single-core only
Video Player
591
139th of 154
Single-core only

Rank among the 154 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 33.7 GB/s 3 2.45%
Scale higher is better 19.4 GB/s 3 1.25%
Add higher is better 21 GB/s 3 2.25%
Triad higher is better 20.9 GB/s 3 3.21%

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 173/s 3 7.12%
RSA 4096 verifies higher is better 10,727/s 3 10.8%
SHA-256 higher is better 307 MB/s 3 1.08%
AES-256-GCM higher is better 3.13 GB/s 3 2.66%
ChaCha20-Poly1305 higher is better 2.24 GB/s 3 2.44%

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 6.45 ms 3 3.68%
Requests per second, 90th percentile higher is better 312/s 3 1.44%
Request latency, 99.9th percentile lower is better 13.9 ms 3 7.91%
Requests per second, average higher is better 291/s 3 4%

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

Disk

Block size Read Write Total
4K 39.1 MB/s (10,009 IOPS) 39.2 MB/s (10,033 IOPS) 78.3 MB/s (20,042 IOPS)
64K 641.1 MB/s (10,258 IOPS) 644.5 MB/s (10,311 IOPS) 1.26 GB/s (20,569 IOPS)
512K 1.93 GB/s (3,946 IOPS) 2.03 GB/s (4,156 IOPS) 3.96 GB/s (8,102 IOPS)
1M 1.92 GB/s (1,962 IOPS) 2.04 GB/s (2,093 IOPS) 3.96 GB/s (4,055 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 243 Mbps 244 Mbps
Eranium, Amsterdam, NL (100G) IPv4 244 Mbps 244 Mbps
Leaseweb, Singapore, SG (10G) IPv4 222 Mbps 201 Mbps
Clouvider, Los Angeles, CA, US (10G) IPv4 186 Mbps 227 Mbps
Leaseweb, NYC, NY, US (10G) IPv4 235 Mbps 232 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 4,422 0.226 ms
fdatasync 4,162 0.24 ms
fsync 2,017 0.496 ms
fsync_writethrough Not supported here n/a
open_sync 1,690 0.592 ms
Two 8 kB writes
open_datasync 1,938 0.516 ms
fdatasync 3,642 0.275 ms
fsync 2,145 0.466 ms
fsync_writethrough Not supported here n/a
open_sync 1,230 0.813 ms
open_sync at different write sizes
1 * 16kB open_sync write 2,480 0.403 ms
2 * 8kB open_sync writes 1,452 0.689 ms
4 * 4kB open_sync writes 700 1.43 ms
8 * 2kB open_sync writes 309 3.24 ms
16 * 1kB open_sync writes 199 5.02 ms
fsync on a non-write descriptor
write, fsync, close 2,257 0.443 ms
write, close, fsync 1,723 0.58 ms
Non-synced 8 kB writes
write 435,048 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) 1 930 1 ms 1.54 ms 2.69 ms 4.76 ms 0
Read/write (TPC-B like) 8 2,232 3.32 ms 5.89 ms 7.97 ms 13.6 ms 0
Read/write (TPC-B like) 32 2,177 12 ms 32.2 ms 53.5 ms 92.1 ms 0
Read only 1 11,794 0.077 ms 0.136 ms 0.189 ms 0.468 ms 0
Read only 8 21,614 0.334 ms 0.612 ms 0.809 ms 2.09 ms 0
Read only 32 23,586 1.17 ms 2.25 ms 3.09 ms 5.39 ms 0

Scale 10 (1,000,000 accounts), loaded in 2.39 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) 1 849 1.08 ms 1.75 ms 3.35 ms 7.44 ms 0
Read/write (TPC-B like) 8 1,733 3.98 ms 9.11 ms 16 ms 34.8 ms 0
Read/write (TPC-B like) 32 2,184 13.8 ms 23.8 ms 31.1 ms 44.6 ms 0
Read only 1 6,567 0.126 ms 0.315 ms 0.636 ms 1.52 ms 0
Read only 8 15,942 0.455 ms 0.848 ms 1.35 ms 2.72 ms 0
Read only 32 17,900 1.6 ms 2.94 ms 3.97 ms 6.58 ms 0

Scale 100 (10,000,000 accounts), loaded in 21.4 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 1 184 3,674 5.09 ms 7.84 ms 11.9 ms 0
Read/write 8 391 7,811 20.4 ms 33.1 ms 41.1 ms 0
Read/write 32 394 7,884 80 ms 137 ms 174 ms 0
Read only 1 401 6,408 2.39 ms 3.43 ms 4.41 ms 0
Read only 8 733 11,723 10.8 ms 15.3 ms 18.3 ms 0
Read only 32 692 11,078 45.8 ms 62.2 ms 70.5 ms 0

10 tables of 100,000 rows, loaded in 13.6 s. 60 s per run, one connection per thread.

Redis

memtier

Mix Operations/s Hits/s Median p99 p99.9
1:10 set:get 37,584 34,167 1.58 ms 4.64 ms 7.42 ms
1:1 set:get 38,200 19,100 1.54 ms 4.61 ms 7.81 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 234 942 1,368 1.86 s
Express express-postgresjs 4,269 5,194 11,583 540 ms
Fastify fastify-postgres 4,142 5,520 11,379 525 ms
NestJS nestjs 2,065 2,262 7,021 229 ms
Nuxt nuxt 3,382 4,732 8,589 167 ms
FastAPI fastapi 1,743 2,050 7,313 517 ms
Django django-postgresql 652 738 1,699 687 ms
Rails rails 1,035 1,489 4,814 361 ms
Laravel laravel 342 354 654 951 ms
Symfony symfony 479 482 1,416 630 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 1.04 1.46 s 1.78 s 1.88 s 0%
Shop page 1.04 2.03 s 2.46 s 2.59 s 0%
Category page 1.04 1.2 s 1.98 s 2.12 s 0%
Product page 1.04 1.36 s 1.75 s 1.9 s 0%
Product search 1.04 1.19 s 1.55 s 1.63 s 0%
32 virtual users
Home page 1.28 5.2 s 6.43 s 6.65 s 0%
Shop page 1.13 7.51 s 8.68 s 8.96 s 0%
Category page 0.9 6.5 s 7.85 s 8.34 s 0%
Product page 0.9 5.4 s 5.77 s 5.89 s 0%
Product search 0.9 4.82 s 5.28 s 5.37 s 0%

Cart and checkout

Step Requests/s Median p95 p99 Error rate
8 virtual users
Add to cart 1.92 1.6 s 2.04 s 2.16 s 0%
Cart 1.92 1.29 s 1.46 s 1.53 s 0%
Checkout 1.92 1.01 s 1.21 s 1.27 s 0%
32 virtual users
Add to cart 2.02 5.3 s 7.25 s 7.45 s 0%
Cart 2.02 5.49 s 6.52 s 6.7 s 0%
Checkout 2.02 4.38 s 5.08 s 5.43 s 0%

k6 with a fixed number of virtual users, 65 to 71 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 0.981 435 ms 566 ms 769 ms 0%
Topic JSON 0.49 239 ms 359 ms 424 ms 0%
Home page 0.507 392 ms 665 ms 889 ms 0%
Categories page 0.245 461 ms 505 ms 511 ms 0%
User activity page 0.245 263 ms 308 ms 314 ms 0%
4 virtual users
Topic page 1.74 952 ms 1.38 s 2.12 s 0%
Topic JSON 0.88 519 ms 701 ms 802 ms 0%
Home page 0.88 879 ms 1.16 s 1.6 s 0%
Categories page 0.456 1.06 s 1.44 s 2.06 s 0%
User activity page 0.44 584 ms 1.03 s 1.1 s 0%
16 virtual users
Topic page 1.75 2.17 s 3.01 s 3.37 s 0%
Topic JSON 0.845 1.73 s 2.34 s 2.59 s 0%
Home page 0.861 2.16 s 2.82 s 3.24 s 0%
Categories page 0.43 2.22 s 2.71 s 2.89 s 0%
User activity page 0.414 1.74 s 2.16 s 2.33 s 0%

Anonymous

Step Requests/s Median p95 p99 Error rate
16 virtual users
Topic page 33 140 ms 308 ms 422 ms 0.1%
Topic JSON 16.6 134 ms 306 ms 371 ms 0.199%
Home page 16.6 132 ms 302 ms 455 ms 0%
Categories page 8.31 148 ms 332 ms 799 ms 0%
User activity page 8.29 423 ms 672 ms 939 ms 0%

k6 with a fixed number of virtual users, 61 to 63 s per level, after a 22 s warmup. The error rate counts responses that weren't a 200. Discourse ran with 4 app workers and 1024 MB of Postgres shared buffers, what its installer picks for a 4 GB box. It added a 2 GB swapfile first, the way its installer does, and didn't need it. The container peaked at 2,337 MB.

Ghost

Readers

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 3.58 76.8 ms 103 ms 120 ms 0%
Post page 8.92 42 ms 56.4 ms 82.1 ms 0%
Tag page 1.78 53.9 ms 75.3 ms 82 ms 0%
Author page 1.78 52.9 ms 71.8 ms 86.6 ms 0%
RSS feed 1.78 65.7 ms 88.7 ms 153 ms 0%
4 virtual users
Home page 4.29 245 ms 312 ms 368 ms 0%
Post page 10.7 168 ms 238 ms 288 ms 0%
Tag page 2.18 161 ms 236 ms 240 ms 0%
Author page 2.13 162 ms 227 ms 298 ms 0%
RSS feed 2.13 181 ms 233 ms 258 ms 0%
16 virtual users
Home page 4.11 974 ms 1.25 s 1.42 s 0%
Post page 10.3 804 ms 1.07 s 1.22 s 0%
Tag page 2.04 522 ms 790 ms 939 ms 0%
Author page 2.06 542 ms 750 ms 853 ms 0%
RSS feed 2.04 525 ms 715 ms 821 ms 0%

Staff in Ghost Admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Post list 1.74 85.4 ms 115 ms 137 ms 0%
Post editor 5.26 32.2 ms 50.2 ms 62.8 ms 0%
Saving a draft 5.24 78.3 ms 112 ms 164 ms 0%
Member list 1.75 109 ms 151 ms 167 ms 0%
4 virtual users
Post list 2.27 107 ms 139 ms 173 ms 0%
Post editor 6.88 55.9 ms 79.9 ms 94.5 ms 0%
Saving a draft 6.92 421 ms 579 ms 674 ms 0%
Member list 2.32 137 ms 189 ms 233 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. 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 284 MB and MySQL at 618 MB.

Wagtail

Visitors

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 0.78 169 ms 212 ms 298 ms 0%
Blog index 0.764 584 ms 706 ms 801 ms 0%
Blog post 2.31 54.2 ms 88.6 ms 99.6 ms 0%
Bread page 2.31 58.7 ms 71.9 ms 104 ms 0%
Location page 0.78 57.8 ms 72.3 ms 88.3 ms 0%
Site search 0.764 87 ms 155 ms 187 ms 0%
4 virtual users
Home page 1.21 474 ms 616 ms 640 ms 0%
Blog index 1.24 1.57 s 2.08 s 2.19 s 0%
Blog post 3.67 133 ms 227 ms 299 ms 0%
Bread page 3.67 148 ms 218 ms 268 ms 0%
Location page 1.26 137 ms 204 ms 215 ms 0%
Site search 1.22 214 ms 333 ms 492 ms 0%
16 virtual users
Home page 1.06 1.76 s 2.43 s 2.55 s 0%
Blog index 1.09 4.48 s 5.26 s 5.65 s 0%
Blog post 3.12 969 ms 1.75 s 1.88 s 0%
Bread page 3.17 997 ms 1.64 s 1.81 s 0%
Location page 1.04 904 ms 1.45 s 1.78 s 0%
Site search 1.01 1.2 s 1.9 s 2.04 s 0%

Editors in the Wagtail admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Admin dashboard 0.276 191 ms 215 ms 232 ms 0%
Page explorer 0.569 802 ms 988 ms 1.24 s 0%
Page editor 0.845 372 ms 531 ms 648 ms 0%
Image library 0.276 141 ms 454 ms 1.4 s 0%
Admin page search 0.276 106 ms 185 ms 199 ms 0%
4 virtual users
Admin dashboard 0.479 501 ms 856 ms 967 ms 0%
Page explorer 0.991 1.95 s 2.87 s 3.02 s 0%
Page editor 1.47 867 ms 1.39 s 1.47 s 0%
Image library 0.495 473 ms 884 ms 927 ms 0%
Admin page search 0.479 300 ms 452 ms 553 ms 0%

k6 with a fixed number of virtual users, 60 to 63 s per level, after a 21 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 293 MB, Postgres at 162 MB, and Redis at 26 MB.

Advertised vs. measured

Advertised Measured
vCPU 2 2
CPU Shared vCPU 0.5% of busy CPU time stolen
RAM 4 GB 3.7 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
Intel Core Processor (Haswell, no TSX)
CPU cores
2
CPU frequency
2400 MHz
AES-NI
Yes
VM-x/AMD-V
Yes
RAM reported
3.7 GiB
Swap reported
0 MiB
Disk reported
48.4 GiB
Virtualization reported
KVM
CPU steal
0.5% 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
D2-4
Product line
Discovery D2
Location
Frankfurt
vCPU
2 shared vCPU
Architecture
x86_64
RAM
4 GB
Storage
50 GB NVMe
Virtualization
KVM
Network
250 Mbps
Transfer
Unmetered
Port 25
Unknown
Monthly price at test time
$13.50
Hourly price at test time
$0.024
YABS version
v2026-09-20
Ran at
Oct 13, 2026, 22:22:50 UTC
Parser version
5

Run timeline

Queued
Oct 13, 2026, 22:20:00 UTC
Server created
Oct 13, 2026, 22:21:42 UTC
First update from the server
Oct 13, 2026, 22:21:42 UTC
Completed
Oct 14, 2026, 00:15:00 UTC
Server deleted
Oct 14, 2026, 00:15:00 UTC
Cost of this run
$0.047
Watch party 0 watching

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

Watch party

Loading the party