Skip to main content

UpCloud Starter 2 vCPU / 2 GB

Chicago #1

Benchmark complete
Finished Oct 15, 2026
Geekbench 7 single-core
1,274
Faster than 64% of 2 vCPU plans
Geekbench 7 multi-core
Skipped
Disk 4K IOPS
19,950
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
    Chicago #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, 02:09:00 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 1,274 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
1,413
61st of 170
Single-core only
Navigation
1,487
48th of 170
Single-core only
HTML5 Browser
1,161
79th of 170
Single-core only
PDF Viewer
1,348
72nd of 170
Single-core only
Photo Library
1,135
80th of 170
Single-core only
Clang
1,212
60th of 170
Single-core only
Text Processing
1,112
78th of 170
Single-core only
Asset Compression
1,255
80th of 170
Single-core only
HDR
1,023
90th of 170
Single-core only
Photo Editor
1,405
74th of 170
Single-core only
Ray Tracer
1,346
58th of 170
Single-core only
Structure from Motion
1,383
77th of 170
Single-core only
Game Physics
1,327
58th of 170
Single-core only
Video Encoder
1,206
74th of 170
Single-core only
Audio Encoder
1,298
77th of 170
Single-core only
Video Player
1,375
76th 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 58.5 GB/s 3 0.957%
Scale higher is better 39.2 GB/s 3 0.572%
Add higher is better 43 GB/s 3 0.367%
Triad higher is better 44.6 GB/s 3 1.08%

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 461/s 3 0.507%
RSA 4096 verifies higher is better 30,039/s 3 0.111%
SHA-256 higher is better 1.33 GB/s 3 0.283%
AES-256-GCM higher is better 6.95 GB/s 3 0.356%
ChaCha20-Poly1305 higher is better 3.54 GB/s 3 0.106%

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 4.12 ms 3 0.225%
Requests per second, 90th percentile higher is better 481/s 3 0.12%
Request latency, 99.9th percentile lower is better 7.66 ms 3 1.22%
Requests per second, average higher is better 479/s 3 0.275%

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

Disk

Block size Read Write Total
4K 38.9 MB/s (9,963 IOPS) 39 MB/s (9,987 IOPS) 77.9 MB/s (19,950 IOPS)
64K 399 MB/s (6,384 IOPS) 401.1 MB/s (6,418 IOPS) 800.2 MB/s (12,802 IOPS)
512K 382.1 MB/s (764 IOPS) 402.4 MB/s (804 IOPS) 784.5 MB/s (1,568 IOPS)
1M 378.9 MB/s (378 IOPS) 404.1 MB/s (404 IOPS) 783 MB/s (782 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 1.08 Gbps 1.09 Gbps
Eranium, Amsterdam, NL (100G) IPv4 1.1 Gbps 1.11 Gbps
Leaseweb, Singapore, SG (10G) IPv4 348 Mbps 926 Mbps
Clouvider, Los Angeles, CA, US (10G) IPv4 1.11 Gbps 1.11 Gbps
Leaseweb, NYC, NY, US (10G) IPv4 1.15 Gbps 1.15 Gbps

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 3,932 0.254 ms
fdatasync 3,787 0.264 ms
fsync 2,150 0.465 ms
fsync_writethrough Not supported here n/a
open_sync 2,324 0.43 ms
Two 8 kB writes
open_datasync 1,917 0.522 ms
fdatasync 3,386 0.295 ms
fsync 1,974 0.507 ms
fsync_writethrough Not supported here n/a
open_sync 1,219 0.82 ms
open_sync at different write sizes
1 * 16kB open_sync write 2,174 0.46 ms
2 * 8kB open_sync writes 1,188 0.842 ms
4 * 4kB open_sync writes 594 1.68 ms
8 * 2kB open_sync writes 306 3.27 ms
16 * 1kB open_sync writes 155 6.43 ms
fsync on a non-write descriptor
write, fsync, close 2,183 0.458 ms
write, close, fsync 2,302 0.434 ms
Non-synced 8 kB writes
write 535,856 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 1,443 0.609 ms 0.817 ms 2.1 ms 17.5 ms 0
Read/write (TPC-B like) 8 3,829 1.79 ms 3.45 ms 5.94 ms 34.2 ms 0
Read/write (TPC-B like) 32 3,849 6.14 ms 20.8 ms 38.4 ms 80.6 ms 0
Read only 1 22,492 0.042 ms 0.055 ms 0.065 ms 0.129 ms 0
Read only 8 45,872 0.156 ms 0.251 ms 0.31 ms 0.617 ms 0
Read only 32 48,338 0.529 ms 0.909 ms 1.28 ms 2.89 ms 0

Scale 10 (1,000,000 accounts), loaded in 1.64 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) 1 930 0.847 ms 1.48 ms 4.81 ms 28.1 ms 0
Read/write (TPC-B like) 8 2,533 2.2 ms 5.25 ms 21.8 ms 87.9 ms 0
Read/write (TPC-B like) 32 3,228 7.32 ms 18.4 ms 81.9 ms 98.9 ms 0
Read only 1 5,934 0.165 ms 0.323 ms 0.982 ms 2.42 ms 0
Read only 8 18,352 0.25 ms 0.617 ms 1.48 ms 34.7 ms 0
Read only 32 20,378 0.911 ms 1.96 ms 31.2 ms 38.3 ms 0

Scale 100 (10,000,000 accounts), loaded in 20.2 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 1 282 5,640 2.91 ms 4.91 ms 17 ms 0
Read/write 8 670 13,404 10.5 ms 23.9 ms 52.9 ms 0
Read/write 32 792 15,848 39.7 ms 66.8 ms 92.4 ms 0
Read only 1 858 13,721 1.12 ms 1.34 ms 1.64 ms 0
Read only 8 1,550 24,800 4.91 ms 7.17 ms 8.13 ms 0
Read only 32 1,527 24,435 20.4 ms 26.7 ms 29.2 ms 0

10 tables of 100,000 rows, loaded in 9.1 s. 60 s per run, one connection per thread.

Redis

memtier

Mix Operations/s Hits/s Median p99 p99.9
1:10 set:get 52,535 47,759 0.839 ms 3.23 ms 4.61 ms
1:1 set:get 51,994 25,997 0.887 ms 3.31 ms 4.8 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 423 1,700 2,142 1.82 s
Express express-postgresjs 7,690 11,075 31,397 132 ms
Fastify fastify-postgres 7,416 11,717 35,463 139 ms
NestJS nestjs 4,991 5,713 18,200 100 ms
Nuxt nuxt 6,751 10,835 29,077 392 ms
FastAPI fastapi 3,900 4,840 17,622 282 ms
Django django-postgresql 1,966 2,280 4,945 193 ms
Rails rails 3,162 4,284 13,894 115 ms
Laravel laravel 851 917 1,767 387 ms
Symfony symfony 1,080 1,186 3,305 276 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 2.28 697 ms 799 ms 826 ms 0%
Shop page 2.28 935 ms 1.08 s 1.12 s 0%
Category page 2.28 603 ms 1.03 s 1.08 s 0%
Product page 2.28 658 ms 757 ms 775 ms 0%
Product search 2.28 566 ms 676 ms 702 ms 0%
32 virtual users
Home page 2.28 2.54 s 2.86 s 2.99 s 0%
Shop page 2.28 3.37 s 3.78 s 3.88 s 0%
Category page 2.28 2.99 s 3.56 s 3.72 s 0%
Product page 2.28 2.59 s 2.76 s 2.81 s 0%
Product search 2.28 2.38 s 2.61 s 2.67 s 0%

Cart and checkout

Step Requests/s Median p95 p99 Error rate
8 virtual users
Add to cart 4.38 747 ms 881 ms 903 ms 0%
Cart 4.38 610 ms 722 ms 747 ms 0%
Checkout 4.38 481 ms 574 ms 591 ms 0%
32 virtual users
Add to cart 4.44 2.44 s 2.98 s 3.07 s 0%
Cart 4.44 2.59 s 2.89 s 2.96 s 0%
Checkout 4.44 2.07 s 2.38 s 2.52 s 0%

k6 with a fixed number of virtual users, 62 to 70 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 2.48 179 ms 289 ms 371 ms 0%
Topic JSON 1.26 93.2 ms 107 ms 131 ms 0%
Home page 1.24 160 ms 174 ms 216 ms 0%
Categories page 0.629 185 ms 197 ms 303 ms 0%
User activity page 0.612 108 ms 234 ms 254 ms 0%
4 virtual users
Topic page 4.24 393 ms 551 ms 698 ms 0%
Topic JSON 2.11 287 ms 409 ms 547 ms 0%
Home page 2.09 358 ms 468 ms 521 ms 0%
Categories page 1.07 410 ms 528 ms 702 ms 0%
User activity page 1.05 311 ms 490 ms 585 ms 0%
16 virtual users
Topic page 4.34 1.29 s 1.58 s 1.74 s 0%
Topic JSON 2.18 1.18 s 1.47 s 1.64 s 0%
Home page 2.21 1.28 s 1.55 s 1.69 s 0%
Categories page 1.1 1.3 s 1.57 s 1.64 s 0%
User activity page 1.1 1.24 s 1.56 s 1.73 s 0%

Anonymous

Step Requests/s Median p95 p99 Error rate
16 virtual users
Topic page 97.5 59.8 ms 108 ms 127 ms 0%
Topic JSON 48.8 62.1 ms 111 ms 129 ms 0%
Home page 48.7 65.2 ms 111 ms 128 ms 0%
Categories page 24.4 66.5 ms 112 ms 131 ms 0%
User activity page 24.4 99.4 ms 159 ms 201 ms 0%

k6 with a fixed number of virtual users, 60 to 62 s per level, after a 21 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 355 MB of it. The container peaked at 1,379 MB.

Ghost

Readers

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 8.92 33.6 ms 38.3 ms 54.9 ms 0%
Post page 22.3 15.8 ms 19.2 ms 33.8 ms 0%
Tag page 4.46 21.9 ms 25 ms 35.5 ms 0%
Author page 4.44 22.6 ms 25.4 ms 39.9 ms 0%
RSS feed 4.44 27.2 ms 31.2 ms 36.8 ms 0%
4 virtual users
Home page 10.2 106 ms 138 ms 183 ms 0%
Post page 25.6 71 ms 103 ms 142 ms 0%
Tag page 5.11 61.3 ms 92.9 ms 134 ms 0%
Author page 5.11 64.8 ms 92.2 ms 125 ms 0%
RSS feed 5.09 69.7 ms 97.5 ms 110 ms 0%
16 virtual users
Home page 10.3 392 ms 483 ms 515 ms 0%
Post page 25.5 326 ms 415 ms 453 ms 0%
Tag page 5.11 214 ms 296 ms 319 ms 0%
Author page 5.09 207 ms 293 ms 315 ms 0%
RSS feed 5.06 223 ms 304 ms 328 ms 0%

Staff in Ghost Admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Post list 5.06 30.6 ms 37.8 ms 71.1 ms 0%
Post editor 15.2 10.8 ms 14.5 ms 24.7 ms 0%
Saving a draft 15.2 27.2 ms 37.4 ms 50.7 ms 0%
Member list 5.06 37.9 ms 44.5 ms 70.1 ms 0%
4 virtual users
Post list 6.07 41.2 ms 50.4 ms 79.4 ms 0%
Post editor 18.3 18.5 ms 25.8 ms 47.3 ms 0%
Saving a draft 18.3 161 ms 222 ms 274 ms 0%
Member list 6.09 47.2 ms 61.3 ms 99.2 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 363 MB and MySQL at 585 MB.

Wagtail

Visitors

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 1.95 68.7 ms 74 ms 80.9 ms 0%
Blog index 1.93 230 ms 240 ms 244 ms 0%
Blog post 5.79 22.6 ms 33.4 ms 35.2 ms 0%
Bread page 5.79 25 ms 27.4 ms 28.8 ms 0%
Location page 1.93 23.8 ms 27 ms 28.6 ms 0%
Site search 1.93 38.8 ms 62.6 ms 67 ms 0%
4 virtual users
Home page 3.18 182 ms 276 ms 308 ms 0%
Blog index 3.19 583 ms 811 ms 996 ms 0%
Blog post 9.54 52.1 ms 93.2 ms 126 ms 0%
Bread page 9.56 58.1 ms 85.8 ms 96.4 ms 0%
Location page 3.23 56 ms 83.8 ms 93.6 ms 0%
Site search 3.16 81.2 ms 161 ms 202 ms 0%
16 virtual users
Home page 3.54 533 ms 714 ms 845 ms 0%
Blog index 3.59 1.28 s 1.49 s 1.64 s 0%
Blog post 10.6 299 ms 452 ms 569 ms 0%
Bread page 10.6 312 ms 474 ms 576 ms 0%
Location page 3.55 302 ms 453 ms 630 ms 0%
Site search 3.54 363 ms 558 ms 691 ms 0%

Editors in the Wagtail admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Admin dashboard 0.727 74.2 ms 79.9 ms 98.6 ms 0%
Page explorer 1.45 330 ms 404 ms 453 ms 0%
Page editor 2.18 156 ms 189 ms 269 ms 0%
Image library 0.727 57.7 ms 66 ms 486 ms 0%
Admin page search 0.727 31 ms 68.7 ms 70.3 ms 0%
4 virtual users
Admin dashboard 1.18 258 ms 527 ms 597 ms 0%
Page explorer 2.42 767 ms 1.34 s 1.68 s 0%
Page editor 3.62 360 ms 650 ms 733 ms 0%
Image library 1.2 201 ms 401 ms 458 ms 0%
Admin page search 1.18 87.5 ms 249 ms 315 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 303 MB, Postgres at 175 MB, and Redis at 26 MB.

Advertised vs. measured

Advertised Measured
vCPU 2 2
CPU Shared vCPU 0% 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% 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
Chicago #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, 02:10:29 UTC
Parser version
5

Run timeline

Queued
Oct 15, 2026, 02:09:00 UTC
Server created
Oct 15, 2026, 02:10:22 UTC
First update from the server
Oct 15, 2026, 02:10:22 UTC
Completed
Oct 15, 2026, 03:41:15 UTC
Server deleted
Oct 15, 2026, 03:41:15 UTC
Cost of this run
€0.023 EUR
Watch party 0 watching

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

Watch party

Loading the party