Skip to main content

UpCloud Starter 2 vCPU / 2 GB

Frankfurt #1

Benchmark complete
Finished Oct 15, 2026
Geekbench 7 single-core
974
Faster than 34% of 2 vCPU plans
Geekbench 7 multi-core
Skipped
Disk 4K IOPS
19,851
fio random read and write, 50/50
Monthly price at test time
€10.00 EUR
Same price today

Server

  • Provider
    UpCloud
  • Plan
    Starter 2 vCPU / 2 GB
  • Location
    Frankfurt #1
  • vCPU
    2
  • RAM
    2 GB
  • Storage
    30 GB
  • Network
    Unknown
  • OS image
    01000000-0000-4000-8000-000030240200
  • Trigger
    Scheduled
  • Queued at
    Oct 15, 2026, 21:25:00 UTC
Visit UpCloud

Referral link. If you sign up through it, I may get paid. How this works

Latest runs of this plan

Full history of this plan

CPU

Version Single-core Multi-core
Geekbench 7 974 Skipped Geekbench Browser

Multi-core was skipped because Geekbench 7 needs about 3.1 GB of free memory to run 2 threads, and this server didn't have that much. Single-core needs much less, so it still ran.

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
1,139
107th of 191
Single-core only
Navigation
942
158th of 191
Single-core only
HTML5 Browser
938
129th of 191
Single-core only
PDF Viewer
1,084
126th of 191
Single-core only
Photo Library
967
108th of 191
Single-core only
Clang
877
142nd of 191
Single-core only
Text Processing
893
140th of 191
Single-core only
Asset Compression
1,073
121st of 191
Single-core only
HDR
843
132nd of 191
Single-core only
Photo Editor
1,015
126th of 191
Single-core only
Ray Tracer
895
148th of 191
Single-core only
Structure from Motion
1,033
135th of 191
Single-core only
Game Physics
971
133rd of 191
Single-core only
Video Encoder
918
132nd of 191
Single-core only
Audio Encoder
1,159
111th of 191
Single-core only
Video Player
904
139th of 191
Single-core only

Rank among the 191 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 25.9 GB/s 3 24.2%
Scale higher is better 16.8 GB/s 3 22.4%
Add higher is better 18 GB/s 3 22.6%
Triad higher is better 18.2 GB/s 3 21.9%

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 398/s 3 2.69%
RSA 4096 verifies higher is better 26,917/s 3 3.38%
SHA-256 higher is better 1.25 GB/s 3 2.34%
AES-256-GCM higher is better 6.28 GB/s 3 1.83%
ChaCha20-Poly1305 higher is better 3.27 GB/s 3 1.33%

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 4.49 ms 3 0.822%
Requests per second, 90th percentile higher is better 430/s 3 1.65%
Request latency, 99.9th percentile lower is better 8.74 ms 3 2.35%
Requests per second, average higher is better 418/s 3 1.71%

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

Disk

Block size Read Write Total
4K 38.7 MB/s (9,915 IOPS) 38.8 MB/s (9,936 IOPS) 77.5 MB/s (19,851 IOPS)
64K 390.9 MB/s (6,254 IOPS) 393 MB/s (6,287 IOPS) 783.9 MB/s (12,541 IOPS)
512K 382 MB/s (764 IOPS) 402.3 MB/s (804 IOPS) 784.4 MB/s (1,568 IOPS)
1M 379.5 MB/s (379 IOPS) 404.7 MB/s (404 IOPS) 784.2 MB/s (783 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 1.06 Gbps 1.06 Gbps
Eranium, Amsterdam, NL (100G) IPv4 1.07 Gbps 1.07 Gbps
Leaseweb, Singapore, SG (10G) IPv4 928 Mbps 946 Mbps
Clouvider, Los Angeles, CA, US (10G) IPv4 933 Mbps 975 Mbps
Leaseweb, NYC, NY, US (10G) IPv4 1.01 Gbps 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 2,776 0.36 ms
fdatasync 2,514 0.398 ms
fsync 987 1.01 ms
fsync_writethrough Not supported here n/a
open_sync 1,086 0.921 ms
Two 8 kB writes
open_datasync 1,294 0.773 ms
fdatasync 2,350 0.426 ms
fsync 958 1.04 ms
fsync_writethrough Not supported here n/a
open_sync 493 2.03 ms
open_sync at different write sizes
1 * 16kB open_sync write 1,060 0.943 ms
2 * 8kB open_sync writes 539 1.86 ms
4 * 4kB open_sync writes 249 4.02 ms
8 * 2kB open_sync writes 144 6.96 ms
16 * 1kB open_sync writes 63.3 15.8 ms
fsync on a non-write descriptor
write, fsync, close 992 1.01 ms
write, close, fsync 966 1.04 ms
Non-synced 8 kB writes
write 487,070 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 1,032 0.754 ms 1.28 ms 5.11 ms 27 ms 0
Read/write (TPC-B like) 8 2,989 2.01 ms 4.57 ms 19.1 ms 50.5 ms 0
Read/write (TPC-B like) 32 2,936 7.43 ms 30.8 ms 57.5 ms 115 ms 0
Read only 1 20,075 0.045 ms 0.074 ms 0.094 ms 0.24 ms 0
Read only 8 36,579 0.191 ms 0.334 ms 0.428 ms 0.964 ms 0
Read only 32 35,492 0.708 ms 1.42 ms 2.09 ms 3.68 ms 0

Scale 10 (1,000,000 accounts), loaded in 2.03 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) 1 737 1.04 ms 1.82 ms 9.51 ms 34.1 ms 0
Read/write (TPC-B like) 8 2,092 2.58 ms 7.24 ms 39.3 ms 87.6 ms 0
Read/write (TPC-B like) 32 2,567 9.16 ms 30.5 ms 80.4 ms 102 ms 0
Read only 1 3,905 0.229 ms 0.468 ms 1.25 ms 5.2 ms 0
Read only 8 17,024 0.316 ms 0.86 ms 2.12 ms 24.8 ms 0
Read only 32 19,487 1.22 ms 3.07 ms 8.46 ms 25.3 ms 0

Scale 100 (10,000,000 accounts), loaded in 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.

MySQL

sysbench OLTP

Workload Threads Transactions/s Queries/s Median p95 p99 Errors
Read/write 1 165 3,307 4.33 ms 14.2 ms 45 ms 0
Read/write 8 243 4,859 16.4 ms 113 ms 350 ms 0
Read/write 32 487 9,730 55.8 ms 150 ms 249 ms 0
Read only 1 696 11,132 1.32 ms 2 ms 3.02 ms 0
Read only 8 1,206 19,294 6.21 ms 9.91 ms 12.3 ms 0
Read only 32 1,091 17,451 28.2 ms 40.4 ms 46.6 ms 0

10 tables of 100,000 rows, loaded in 11.6 s. 60 s per run, one connection per thread.

Redis

memtier

Mix Operations/s Hits/s Median p99 p99.9
1:10 set:get 50,603 46,002 0.791 ms 3.65 ms 5.28 ms
1:1 set:get 50,002 25,001 0.815 ms 3.62 ms 5.31 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 269 1,127 1,647 3.67 s
Express express-postgresjs 5,865 8,534 24,692 304 ms
Fastify fastify-postgres 5,688 8,528 26,177 510 ms
NestJS nestjs 3,504 4,118 13,580 160 ms
Nuxt nuxt 4,992 8,070 22,666 165 ms
FastAPI fastapi 3,020 3,673 13,379 389 ms
Django django-postgresql 1,507 1,653 4,095 268 ms
Rails rails 2,285 3,130 11,000 185 ms
Laravel laravel 495 498 1,221 602 ms
Symfony symfony 616 785 2,500 508 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 1.47 1.08 s 1.23 s 1.35 s 0%
Shop page 1.47 1.46 s 1.68 s 1.76 s 0%
Category page 1.47 948 ms 1.48 s 1.52 s 0%
Product page 1.47 1.01 s 1.19 s 1.25 s 0%
Product search 1.47 842 ms 1.06 s 1.1 s 0%
32 virtual users
Home page 1.39 4.14 s 4.88 s 5.11 s 0%
Shop page 1.39 5.66 s 6.45 s 6.63 s 0%
Category page 1.39 4.89 s 5.87 s 6.24 s 0%
Product page 1.39 4.07 s 4.59 s 4.68 s 0%
Product search 1.39 3.86 s 4.22 s 4.32 s 0%

Cart and checkout

Step Requests/s Median p95 p99 Error rate
8 virtual users
Add to cart 2.76 1.18 s 1.39 s 1.43 s 0%
Cart 2.76 962 ms 1.11 s 1.14 s 0%
Checkout 2.76 744 ms 871 ms 918 ms 0%
32 virtual users
Add to cart 2.83 3.89 s 4.7 s 4.82 s 0%
Cart 2.83 4.04 s 4.46 s 4.6 s 0%
Checkout 2.83 3.17 s 3.64 s 3.73 s 0%

k6 with a fixed number of virtual users, 62 to 69 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 1.52 290 ms 360 ms 573 ms 0%
Topic JSON 0.758 144 ms 182 ms 198 ms 0%
Home page 0.758 260 ms 325 ms 539 ms 0%
Categories page 0.379 300 ms 396 ms 780 ms 0%
User activity page 0.379 186 ms 250 ms 552 ms 0%
4 virtual users
Topic page 2.85 565 ms 950 ms 1.11 s 0%
Topic JSON 1.46 428 ms 582 ms 779 ms 0%
Home page 1.44 542 ms 881 ms 1.25 s 0%
Categories page 0.738 581 ms 783 ms 817 ms 0%
User activity page 0.705 469 ms 592 ms 680 ms 0%
16 virtual users
Topic page 2.77 1.39 s 1.91 s 2.14 s 0%
Topic JSON 1.38 1.26 s 1.72 s 1.95 s 0%
Home page 1.35 1.34 s 1.9 s 2.07 s 0%
Categories page 0.697 1.4 s 1.88 s 2.14 s 0%
User activity page 0.681 1.3 s 1.83 s 1.92 s 0%

Anonymous

Step Requests/s Median p95 p99 Error rate
16 virtual users
Topic page 57.1 98.4 ms 211 ms 297 ms 0%
Topic JSON 28.6 77 ms 207 ms 295 ms 0%
Home page 28.6 88.8 ms 199 ms 275 ms 0%
Categories page 14.3 97.7 ms 220 ms 303 ms 0%
User activity page 14.3 182 ms 302 ms 385 ms 0%

k6 with a fixed number of virtual users, 60 to 62 s per level, after a 22 s warmup. The error rate counts responses that weren't a 200. Discourse ran with 2 app workers and 128 MB of Postgres shared buffers, what its installer picks for a 1 GB box. It added a 2 GB swapfile first, the way its installer does, and used up to 225 MB of it. The container peaked at 1,318 MB.

Ghost

Readers

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 5.66 50.6 ms 61.9 ms 88.2 ms 0%
Post page 14.1 26.7 ms 34.4 ms 48.4 ms 0%
Tag page 2.83 32.4 ms 40.2 ms 51.2 ms 0%
Author page 2.83 33.5 ms 41.7 ms 47.2 ms 0%
RSS feed 2.82 38.2 ms 48.7 ms 50.6 ms 0%
4 virtual users
Home page 6.65 158 ms 203 ms 238 ms 0%
Post page 16.6 110 ms 159 ms 209 ms 0%
Tag page 3.36 96.5 ms 134 ms 180 ms 0%
Author page 3.33 105 ms 140 ms 171 ms 0%
RSS feed 3.31 106 ms 143 ms 179 ms 0%
16 virtual users
Home page 6.77 603 ms 749 ms 796 ms 0%
Post page 16.9 493 ms 640 ms 683 ms 0%
Tag page 3.37 326 ms 460 ms 490 ms 0%
Author page 3.38 333 ms 455 ms 492 ms 0%
RSS feed 3.38 340 ms 456 ms 515 ms 0%

Staff in Ghost Admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Post list 3.03 45.9 ms 57.8 ms 116 ms 0%
Post editor 9.13 17.9 ms 26.3 ms 34.6 ms 0%
Saving a draft 9.13 47.4 ms 81.8 ms 113 ms 0%
Member list 3.03 56.7 ms 73.7 ms 93 ms 0%
4 virtual users
Post list 3.76 56.3 ms 76.7 ms 159 ms 0%
Post editor 11.4 30.8 ms 46.8 ms 63.6 ms 0%
Saving a draft 11.4 259 ms 366 ms 424 ms 0%
Member list 3.78 71 ms 91.5 ms 156 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 352 MB and MySQL at 585 MB.

Wagtail

Visitors

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 1.33 101 ms 132 ms 138 ms 0%
Blog index 1.31 326 ms 401 ms 502 ms 0%
Blog post 3.95 33.1 ms 49.6 ms 59 ms 0%
Bread page 3.95 35.7 ms 44.6 ms 52.4 ms 0%
Location page 1.31 34.2 ms 42.8 ms 47.2 ms 0%
Site search 1.31 60.9 ms 93.3 ms 112 ms 0%
4 virtual users
Home page 2.12 266 ms 373 ms 426 ms 0%
Blog index 2.15 902 ms 1.22 s 1.47 s 0%
Blog post 6.41 76.3 ms 133 ms 165 ms 0%
Bread page 6.4 86.3 ms 131 ms 148 ms 0%
Location page 2.15 81.1 ms 125 ms 154 ms 0%
Site search 2.15 117 ms 255 ms 290 ms 0%
16 virtual users
Home page 2.1 909 ms 1.19 s 1.24 s 0%
Blog index 2.18 2.13 s 2.5 s 2.7 s 0%
Blog post 6.25 502 ms 832 ms 935 ms 0%
Bread page 6.3 508 ms 814 ms 1.01 s 0%
Location page 2.12 495 ms 802 ms 906 ms 0%
Site search 2.07 590 ms 909 ms 1.05 s 0%

Editors in the Wagtail admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Admin dashboard 0.494 113 ms 136 ms 147 ms 0%
Page explorer 1.02 450 ms 525 ms 735 ms 0%
Page editor 1.52 225 ms 307 ms 556 ms 0%
Image library 0.494 79.9 ms 93.9 ms 900 ms 0%
Admin page search 0.494 45.9 ms 88.4 ms 109 ms 0%
4 virtual users
Admin dashboard 0.788 396 ms 857 ms 1.03 s 0%
Page explorer 1.62 1.14 s 1.98 s 2.04 s 0%
Page editor 2.41 503 ms 973 ms 1.16 s 0%
Image library 0.788 344 ms 729 ms 796 ms 0%
Admin page search 0.788 121 ms 330 ms 680 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. 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 295 MB, Postgres at 175 MB, and Redis at 26 MB.

Advertised vs. measured

Advertised Measured
vCPU 2 2
CPU Shared vCPU 0.4% of busy CPU time stolen
RAM 2 GB 1.8 GiB
Storage 30 GB 29.4 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 7542 32-Core Processor
CPU cores
2
CPU frequency
2895 MHz
AES-NI
Yes
VM-x/AMD-V
No
RAM reported
1.8 GiB
Swap reported
0 MiB
Disk reported
29.4 GiB
Virtualization reported
KVM
CPU steal
0.4% of busy CPU time stolen
Distro
Ubuntu 24.04.4 LTS
Kernel
6.8.0-137-generic
Architecture
x86_64
IPv4 reachable
Yes
IPv6 reachable
Yes

Advertised at test time

Plan
Starter 2 vCPU / 2 GB
Product line
Starter
Location
Frankfurt #1
vCPU
2 shared vCPU
Architecture
x86_64
RAM
2 GB
Storage
30 GB
Virtualization
KVM
Network
Unknown
Transfer
1.02 TB
Port 25
Unknown
Monthly price at test time
€10.00 EUR
Hourly price at test time
€0.015 EUR
YABS version
v2026-09-20
Ran at
Oct 15, 2026, 21:28:40 UTC
Parser version
5

Run timeline

Queued
Oct 15, 2026, 21:25:00 UTC
Server created
Oct 15, 2026, 21:27:08 UTC
First update from the server
Oct 15, 2026, 21:27:08 UTC
Completed
Oct 15, 2026, 23:03:07 UTC
Server deleted
Oct 15, 2026, 23:03:07 UTC
Cost of this run
€0.024 EUR
Watch party 0 watching

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

Watch party

Loading the party