Skip to main content

OVHcloud D2-4

Gravelines

Benchmark complete
Finished Oct 14, 2026
Geekbench 7 single-core
676
Faster than 17% of 2 vCPU plans
Geekbench 7 multi-core
1,134
Faster than 11% of 2 vCPU plans
Disk 4K IOPS
20,036
fio random read and write, 50/50
Monthly price at test time
$13.50
84 multi-core points per dollar
Same price today

Server

  • Provider
    OVHcloud
  • Plan
    D2-4
  • Location
    Gravelines
  • vCPU
    2
  • RAM
    4 GB
  • Storage
    50 GB NVMe
  • Network
    250 Mbps
  • OS image
    Ubuntu 24.04
  • Trigger
    Scheduled
  • Queued at
    Oct 14, 2026, 21:52:00 UTC
Visit OVHcloud

Latest runs of this plan

Full history of this plan

CPU

Version Single-core Multi-core
Geekbench 7 676 1,134 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
705
144th of 162
1,042
112th of 120
Navigation
873
144th of 162
Single-core only
HTML5 Browser
666
142nd of 162
Single-core only
PDF Viewer
777
142nd of 162
Single-core only
Photo Library
516
150th of 162
1,007
111th of 120
Clang
621
148th of 162
1,187
111th of 120
Text Processing
664
141st of 162
1,153
107th of 120
Asset Compression
734
139th of 162
1,293
107th of 120
HDR
611
149th of 162
1,056
110th of 120
Photo Editor
631
142nd of 162
947
111th of 120
Ray Tracer
755
141st of 162
1,470
103rd of 120
Structure from Motion
780
145th of 162
Single-core only
Game Physics
638
143rd of 162
Single-core only
Video Encoder
645
141st of 162
Single-core only
Audio Encoder
699
146th of 162
Single-core only
Video Player
584
147th of 162
Single-core only

Rank among the 162 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 30.4 GB/s 3 6.83%
Scale higher is better 18.2 GB/s 3 11.6%
Add higher is better 20.4 GB/s 3 7.69%
Triad higher is better 20.7 GB/s 3 6.28%

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 174/s 3 5.7%
RSA 4096 verifies higher is better 12,176/s 3 3.7%
SHA-256 higher is better 337 MB/s 3 3.47%
AES-256-GCM higher is better 3.32 GB/s 3 1.63%
ChaCha20-Poly1305 higher is better 2.4 GB/s 3 1.56%

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 5.67 ms 3 0.977%
Requests per second, 90th percentile higher is better 342/s 3 0.337%
Request latency, 99.9th percentile lower is better 11.9 ms 3 6.07%
Requests per second, average higher is better 328/s 3 0.0916%

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 (10,006 IOPS) 39.2 MB/s (10,030 IOPS) 78.3 MB/s (20,036 IOPS)
64K 640.9 MB/s (10,254 IOPS) 644.3 MB/s (10,308 IOPS) 1.26 GB/s (20,562 IOPS)
512K 864.8 MB/s (1,729 IOPS) 910.7 MB/s (1,821 IOPS) 1.73 GB/s (3,550 IOPS)
1M 870.1 MB/s (870 IOPS) 928 MB/s (928 IOPS) 1.76 GB/s (1,798 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 245 Mbps 245 Mbps
Eranium, Amsterdam, NL (100G) IPv4 244 Mbps 245 Mbps
Leaseweb, Singapore, SG (10G) IPv4 223 Mbps 205 Mbps
Clouvider, Los Angeles, CA, US (10G) IPv4 137 Mbps 228 Mbps
Leaseweb, NYC, NY, US (10G) IPv4 236 Mbps 237 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 5,420 0.184 ms
fdatasync 5,347 0.187 ms
fsync 3,181 0.314 ms
fsync_writethrough Not supported here n/a
open_sync 3,851 0.26 ms
Two 8 kB writes
open_datasync 2,712 0.369 ms
fdatasync 5,150 0.194 ms
fsync 3,273 0.305 ms
fsync_writethrough Not supported here n/a
open_sync 1,492 0.67 ms
open_sync at different write sizes
1 * 16kB open_sync write 3,330 0.3 ms
2 * 8kB open_sync writes 1,621 0.617 ms
4 * 4kB open_sync writes 945 1.06 ms
8 * 2kB open_sync writes 507 1.97 ms
16 * 1kB open_sync writes 254 3.94 ms
fsync on a non-write descriptor
write, fsync, close 2,851 0.351 ms
write, close, fsync 2,920 0.342 ms
Non-synced 8 kB writes
write 603,217 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 1,138 0.828 ms 1.18 ms 1.59 ms 4.53 ms 0
Read/write (TPC-B like) 8 2,588 2.88 ms 5.02 ms 6.81 ms 10.5 ms 0
Read/write (TPC-B like) 32 2,502 10.4 ms 27.9 ms 46 ms 72.6 ms 0
Read only 1 12,765 0.07 ms 0.125 ms 0.157 ms 0.434 ms 0
Read only 8 23,489 0.307 ms 0.551 ms 0.705 ms 2.05 ms 0
Read only 32 25,837 1.06 ms 2.03 ms 2.74 ms 4.36 ms 0

Scale 10 (1,000,000 accounts), loaded in 2.57 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) 1 899 1.01 ms 1.59 ms 3.66 ms 7.7 ms 0
Read/write (TPC-B like) 8 2,023 3.47 ms 7.36 ms 12 ms 28 ms 0
Read/write (TPC-B like) 32 2,471 12.1 ms 21.2 ms 29.7 ms 55.5 ms 0
Read only 1 7,132 0.117 ms 0.249 ms 0.545 ms 1.38 ms 0
Read only 8 18,224 0.402 ms 0.72 ms 1.04 ms 2.59 ms 0
Read only 32 18,449 1.53 ms 2.88 ms 3.89 ms 7.3 ms 0

Scale 100 (10,000,000 accounts), loaded in 23.3 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 1 199 3,972 4.74 ms 7.17 ms 11.4 ms 0
Read/write 8 452 9,040 17.3 ms 28.2 ms 34.3 ms 0
Read/write 32 447 8,936 70.5 ms 126 ms 159 ms 0
Read only 1 355 5,680 2.71 ms 3.96 ms 5.67 ms 0
Read only 8 741 11,854 10.3 ms 16.7 ms 19.3 ms 0
Read only 32 749 11,977 41.9 ms 57.9 ms 68.1 ms 0

10 tables of 100,000 rows, loaded in 12.4 s. 60 s per run, one connection per thread.

Redis

memtier

Mix Operations/s Hits/s Median p99 p99.9
1:10 set:get 41,773 37,975 1.39 ms 3.84 ms 6.56 ms
1:1 set:get 41,073 20,536 1.38 ms 4.02 ms 6.88 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 316 1,046 1,401 2 s
Express express-postgresjs 4,677 5,957 12,541 248 ms
Fastify fastify-postgres 4,733 6,458 13,792 178 ms
NestJS nestjs 2,238 2,405 7,388 194 ms
Nuxt nuxt 2,949 4,828 10,197 1.29 s
FastAPI fastapi 1,964 2,300 8,824 683 ms
Django django-postgresql 730 729 1,415 516 ms
Rails rails 998 1,527 5,529 373 ms
Laravel laravel 405 435 814 708 ms
Symfony symfony 527 525 1,407 556 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 1.23 1.3 s 1.46 s 1.56 s 0%
Shop page 1.23 1.73 s 1.91 s 1.93 s 0%
Category page 1.23 1.06 s 1.78 s 1.89 s 0%
Product page 1.23 1.17 s 1.35 s 1.41 s 0%
Product search 1.23 1.01 s 1.18 s 1.23 s 0%
32 virtual users
Home page 1.35 4.59 s 5.32 s 5.39 s 0%
Shop page 1.35 6.26 s 7.11 s 7.18 s 0%
Category page 1.34 5.5 s 6.41 s 6.58 s 0%
Product page 1.03 4.88 s 5.15 s 5.18 s 0%
Product search 0.9 4.37 s 4.67 s 4.88 s 0%

Cart and checkout

Step Requests/s Median p95 p99 Error rate
8 virtual users
Add to cart 2.11 1.46 s 1.69 s 1.75 s 0%
Cart 2.11 1.19 s 1.39 s 1.45 s 0%
Checkout 2.11 926 ms 1.07 s 1.1 s 0%
32 virtual users
Add to cart 2.36 4.56 s 5.74 s 5.9 s 0%
Cart 2.36 4.85 s 5.4 s 5.52 s 0%
Checkout 2.36 3.77 s 4.39 s 4.64 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 1.06 417 ms 491 ms 658 ms 0%
Topic JSON 0.538 208 ms 276 ms 416 ms 0%
Home page 0.538 375 ms 616 ms 833 ms 0%
Categories page 0.277 413 ms 461 ms 475 ms 0%
User activity page 0.261 264 ms 311 ms 328 ms 0%
4 virtual users
Topic page 1.93 897 ms 1.34 s 1.64 s 0%
Topic JSON 0.975 459 ms 592 ms 680 ms 0%
Home page 0.975 788 ms 1.09 s 1.7 s 0%
Categories page 0.52 958 ms 1.12 s 1.46 s 0%
User activity page 0.471 534 ms 735 ms 941 ms 0%
16 virtual users
Topic page 1.68 2.08 s 2.68 s 3.4 s 0%
Topic JSON 0.879 1.66 s 2.42 s 2.58 s 0%
Home page 0.863 2.01 s 2.48 s 2.85 s 0%
Categories page 0.399 2.01 s 2.65 s 2.89 s 0%
User activity page 0.415 1.75 s 2.72 s 3.12 s 0%

Anonymous

Step Requests/s Median p95 p99 Error rate
16 virtual users
Topic page 33 134 ms 332 ms 564 ms 0%
Topic JSON 16.5 133 ms 331 ms 498 ms 0%
Home page 16.5 133 ms 336 ms 436 ms 0.2%
Categories page 8.26 139 ms 341 ms 557 ms 0%
User activity page 8.3 417 ms 747 ms 962 ms 0.199%

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 2,227 MB.

Ghost

Readers

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 3.9 76 ms 98.6 ms 111 ms 0%
Post page 9.72 36.9 ms 52 ms 66.7 ms 0%
Tag page 1.95 48.8 ms 66.6 ms 100 ms 0%
Author page 1.95 49.3 ms 64.9 ms 75.5 ms 0%
RSS feed 1.93 57 ms 74.2 ms 82 ms 0%
4 virtual users
Home page 4.33 251 ms 362 ms 410 ms 0%
Post page 10.8 159 ms 244 ms 299 ms 0%
Tag page 2.18 151 ms 239 ms 324 ms 0%
Author page 2.16 160 ms 289 ms 372 ms 0%
RSS feed 2.14 167 ms 261 ms 328 ms 0%
16 virtual users
Home page 3.78 1.07 s 1.33 s 1.51 s 0%
Post page 9.39 896 ms 1.19 s 1.37 s 0%
Tag page 1.88 576 ms 790 ms 954 ms 0%
Author page 1.86 564 ms 805 ms 970 ms 0%
RSS feed 1.86 608 ms 802 ms 879 ms 0%

Staff in Ghost Admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Post list 2.12 71.1 ms 103 ms 139 ms 0%
Post editor 6.35 26.1 ms 39.1 ms 52.8 ms 0%
Saving a draft 6.35 63.7 ms 93.4 ms 112 ms 0%
Member list 2.12 90.1 ms 154 ms 168 ms 0%
4 virtual users
Post list 2.76 95.3 ms 133 ms 221 ms 0%
Post editor 8.34 45.9 ms 63.9 ms 86.5 ms 0%
Saving a draft 8.36 355 ms 468 ms 540 ms 0%
Member list 2.76 111 ms 140 ms 175 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 287 MB and MySQL at 617 MB.

Wagtail

Visitors

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 0.847 156 ms 205 ms 222 ms 0%
Blog index 0.847 533 ms 606 ms 646 ms 0%
Blog post 2.51 51.2 ms 80.8 ms 93.9 ms 0%
Bread page 2.52 52.5 ms 71.1 ms 78.7 ms 0%
Location page 0.847 52.9 ms 67.7 ms 70.9 ms 0%
Site search 0.83 91.7 ms 144 ms 153 ms 0%
4 virtual users
Home page 1.39 402 ms 547 ms 666 ms 0%
Blog index 1.44 1.36 s 1.8 s 1.93 s 0%
Blog post 4.22 118 ms 188 ms 241 ms 0%
Bread page 4.27 124 ms 184 ms 201 ms 0%
Location page 1.44 111 ms 177 ms 201 ms 0%
Site search 1.42 174 ms 382 ms 435 ms 0%
16 virtual users
Home page 1.37 1.31 s 1.8 s 1.99 s 0%
Blog index 1.47 3.38 s 4.06 s 4.55 s 0%
Blog post 4.18 733 ms 1.2 s 1.52 s 0%
Bread page 4.22 743 ms 1.13 s 1.46 s 0%
Location page 1.42 732 ms 1.28 s 1.51 s 0%
Site search 1.4 862 ms 1.37 s 1.5 s 0%

Editors in the Wagtail admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Admin dashboard 0.31 167 ms 202 ms 212 ms 0%
Page explorer 0.652 716 ms 866 ms 927 ms 0%
Page editor 0.978 323 ms 461 ms 716 ms 0%
Image library 0.326 126 ms 250 ms 1.42 s 0%
Admin page search 0.31 78.8 ms 161 ms 162 ms 0%
4 virtual users
Admin dashboard 0.529 572 ms 790 ms 836 ms 0%
Page explorer 1.09 1.67 s 2.63 s 2.83 s 0%
Page editor 1.6 835 ms 1.33 s 1.4 s 0%
Image library 0.529 500 ms 825 ms 835 ms 0%
Admin page search 0.529 167 ms 494 ms 600 ms 0%

k6 with a fixed number of virtual users, 60 to 62 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 293 MB, Postgres at 157 MB, and Redis at 26 MB.

Advertised vs. measured

Advertised Measured
vCPU 2 2
CPU Shared vCPU 0.3% 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
2394 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
0.3% 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
Gravelines
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 14, 2026, 21:54:51 UTC
Parser version
5

Run timeline

Queued
Oct 14, 2026, 21:52:00 UTC
First update from the server
Oct 14, 2026, 21:53:23 UTC
Completed
Oct 14, 2026, 23:46:00 UTC
Server deleted
Oct 14, 2026, 23:46:00 UTC
Cost of this run
$0.046
Watch party 0 watching

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

Watch party

Loading the party