Skip to main content

UpCloud Premium 2 vCPU / 2 GB

Chicago #1

Benchmark complete
Finished Oct 17, 2026
Geekbench 7 single-core
2,463
Faster than 100% of 2 vCPU plans
Geekbench 7 multi-core
Skipped
Disk 4K IOPS
18,212
fio random read and write, 50/50
Monthly price at test time
€18.00 EUR
Same price today

Server

  • Provider
    UpCloud
  • Plan
    Premium 2 vCPU / 2 GB
  • Location
    Chicago #1
  • vCPU
    2
  • RAM
    2 GB
  • Storage
    50 GB NVMe
  • Network
    Unknown
  • OS image
    01000000-0000-4000-8000-000030240200
  • Trigger
    Scheduled
  • Queued at
    Oct 17, 2026, 01:14:00 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 2,463 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
2,338
2nd of 216
Single-core only
Navigation
1,999
8th of 216
Single-core only
HTML5 Browser
2,336
5th of 216
Single-core only
PDF Viewer
2,640
2nd of 216
Single-core only
Photo Library
2,626
1st of 216
Single-core only
Clang
2,089
5th of 216
Single-core only
Text Processing
2,523
2nd of 216
Single-core only
Asset Compression
2,502
2nd of 216
Single-core only
HDR
2,564
2nd of 216
Single-core only
Photo Editor
3,598
1st of 216
Single-core only
Ray Tracer
1,900
7th of 216
Single-core only
Structure from Motion
2,819
1st of 216
Single-core only
Game Physics
2,258
4th of 216
Single-core only
Video Encoder
2,379
4th of 216
Single-core only
Audio Encoder
2,398
3rd of 216
Single-core only
Video Player
2,895
2nd 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 88.7 GB/s 3 3.69%
Scale higher is better 75.9 GB/s 3 2.68%
Add higher is better 80 GB/s 3 2.13%
Triad higher is better 81 GB/s 3 3.41%

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 1,768/s 3 1.38%
RSA 4096 verifies higher is better 47,006/s 3 1.87%
SHA-256 higher is better 2.62 GB/s 3 6.11%
AES-256-GCM higher is better 44.5 GB/s 3 1.42%
ChaCha20-Poly1305 higher is better 11.8 GB/s 3 0.655%

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 2.74 ms 3 0.608%
Requests per second, 90th percentile higher is better 726/s 3 0.421%
Request latency, 99.9th percentile lower is better 5.23 ms 3 4.29%
Requests per second, average higher is better 695/s 3 1.83%

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

Disk

Block size Read Write Total
4K 35.5 MB/s (9,095 IOPS) 35.6 MB/s (9,117 IOPS) 71.1 MB/s (18,212 IOPS)
64K 384.7 MB/s (6,154 IOPS) 386.7 MB/s (6,187 IOPS) 771.4 MB/s (12,341 IOPS)
512K 382.3 MB/s (764 IOPS) 402.6 MB/s (805 IOPS) 785 MB/s (1,569 IOPS)
1M 377.6 MB/s (377 IOPS) 402.7 MB/s (402 IOPS) 780.3 MB/s (779 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 982 Mbps 1.01 Gbps
Eranium, Amsterdam, NL (100G) IPv4 987 Mbps 1.01 Gbps
Leaseweb, Singapore, SG (10G) IPv4 756 Mbps 912 Mbps
Clouvider, Los Angeles, CA, US (10G) IPv4 1.02 Gbps 1.03 Gbps
Leaseweb, NYC, NY, US (10G) IPv4 1.06 Gbps 1.06 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 8,691 0.115 ms
fdatasync 9,074 0.11 ms
fsync 6,221 0.161 ms
fsync_writethrough Not supported here n/a
open_sync 6,006 0.166 ms
Two 8 kB writes
open_datasync 3,707 0.27 ms
fdatasync 6,517 0.153 ms
fsync 5,226 0.191 ms
fsync_writethrough Not supported here n/a
open_sync 2,803 0.357 ms
open_sync at different write sizes
1 * 16kB open_sync write 5,078 0.197 ms
2 * 8kB open_sync writes 2,768 0.361 ms
4 * 4kB open_sync writes 1,636 0.611 ms
8 * 2kB open_sync writes 708 1.41 ms
16 * 1kB open_sync writes 359 2.79 ms
fsync on a non-write descriptor
write, fsync, close 5,299 0.189 ms
write, close, fsync 6,049 0.165 ms
Non-synced 8 kB writes
write 3,005,282 0 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 4,358 0.203 ms 0.309 ms 0.51 ms 2.06 ms 0
Read/write (TPC-B like) 8 12,787 0.498 ms 1.12 ms 1.89 ms 11.5 ms 0
Read/write (TPC-B like) 32 12,273 1.81 ms 6.44 ms 12.6 ms 34.5 ms 0
Read only 1 79,700 0.012 ms 0.017 ms 0.024 ms 0.045 ms 0
Read only 8 123,787 0.056 ms 0.106 ms 0.137 ms 0.215 ms 0
Read only 32 121,141 0.222 ms 0.375 ms 0.505 ms 0.927 ms 0

Scale 10 (1,000,000 accounts), loaded in 0.83 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 2,448 0.338 ms 0.54 ms 1.64 ms 10.5 ms 0
Read/write (TPC-B like) 8 6,709 0.707 ms 2.19 ms 6 ms 65.7 ms 0
Read/write (TPC-B like) 32 9,912 2.09 ms 5.23 ms 33.8 ms 75.5 ms 0
Read only 1 21,180 0.019 ms 0.103 ms 0.176 ms 0.803 ms 0
Read only 8 86,621 0.064 ms 0.193 ms 0.292 ms 1.93 ms 0
Read only 32 84,598 0.271 ms 0.619 ms 1.37 ms 20.4 ms 0

Scale 100 (10,000,000 accounts), loaded in 13.8 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 1 613 12,254 1.37 ms 2.22 ms 6.32 ms 0
Read/write 8 1,316 26,313 5 ms 10.8 ms 36.2 ms 0
Read/write 32 2,044 40,879 14.2 ms 28.7 ms 53.9 ms 0
Read only 1 2,376 38,022 0.44 ms 0.576 ms 0.728 ms 0
Read only 8 5,384 86,149 1.39 ms 2.39 ms 2.91 ms 0
Read only 32 4,336 69,377 6.91 ms 11.4 ms 14 ms 0

10 tables of 100,000 rows, loaded in 6.1 s. 60 s per run, one connection per thread.

Redis

memtier

Mix Operations/s Hits/s Median p99 p99.9
1:10 set:get 181,368 164,880 0.199 ms 2.29 ms 3.38 ms
1:1 set:get 205,863 102,931 0.159 ms 2.22 ms 3.25 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 778 3,452 3,906 582 ms
Express express-postgresjs 11,265 19,646 94,916 54.4 ms
Fastify fastify-postgres 10,402 18,109 111,610 59.1 ms
NestJS nestjs 12,904 12,994 66,263 77.8 ms
Nuxt nuxt 9,182 17,365 88,465 59.8 ms
FastAPI fastapi 7,739 10,504 45,343 110 ms
Django django-postgresql 3,411 4,091 12,039 128 ms
Rails rails 5,798 8,591 50,218 66.7 ms
Laravel laravel 1,444 1,474 2,969 305 ms
Symfony symfony 1,899 2,116 6,790 163 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 3.62 439 ms 524 ms 550 ms 0%
Shop page 3.62 597 ms 713 ms 746 ms 0%
Category page 3.62 379 ms 610 ms 700 ms 0%
Product page 3.62 414 ms 503 ms 534 ms 0%
Product search 3.62 363 ms 441 ms 464 ms 0%
32 virtual users
Home page 3.74 1.56 s 1.78 s 1.84 s 0%
Shop page 3.74 1.99 s 2.32 s 2.4 s 0%
Category page 3.74 1.79 s 2.13 s 2.26 s 0%
Product page 3.74 1.6 s 2.03 s 2.15 s 0%
Product search 3.74 1.47 s 1.67 s 1.92 s 0%

Cart and checkout

Step Requests/s Median p95 p99 Error rate
8 virtual users
Add to cart 6.98 474 ms 594 ms 628 ms 0%
Cart 6.98 385 ms 475 ms 506 ms 0%
Checkout 6.98 300 ms 374 ms 397 ms 0%
32 virtual users
Add to cart 7.07 1.57 s 1.94 s 2.11 s 0%
Cart 7.07 1.58 s 1.92 s 2.07 s 0%
Checkout 7.07 1.29 s 1.56 s 1.72 s 0%

k6 with a fixed number of virtual users, 61 to 67 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 3.92 111 ms 142 ms 332 ms 0%
Topic JSON 1.96 55.4 ms 70.3 ms 108 ms 0%
Home page 1.98 99.5 ms 128 ms 332 ms 0%
Categories page 0.98 114 ms 144 ms 215 ms 0%
User activity page 0.98 71.5 ms 221 ms 260 ms 0%
4 virtual users
Topic page 6.49 253 ms 378 ms 596 ms 0%
Topic JSON 3.26 187 ms 293 ms 422 ms 0%
Home page 3.23 233 ms 359 ms 472 ms 0%
Categories page 1.64 249 ms 420 ms 550 ms 0%
User activity page 1.62 208 ms 304 ms 384 ms 0%
16 virtual users
Topic page 7.03 868 ms 1.19 s 1.29 s 0%
Topic JSON 3.53 838 ms 1.14 s 1.22 s 0%
Home page 3.55 862 ms 1.17 s 1.24 s 0%
Categories page 1.78 867 ms 1.09 s 1.24 s 0%
User activity page 1.78 852 ms 1.11 s 1.22 s 0%

Anonymous

Step Requests/s Median p95 p99 Error rate
16 virtual users
Topic page 150 35.2 ms 83.9 ms 113 ms 0%
Topic JSON 75 34.9 ms 80.5 ms 111 ms 0%
Home page 74.9 36.1 ms 89.7 ms 119 ms 0%
Categories page 37.5 29.3 ms 78.1 ms 113 ms 0%
User activity page 37.4 72.8 ms 129 ms 171 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 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 281 MB of it. The container peaked at 1,349 MB.

Ghost

Readers

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 15.7 16.6 ms 22.4 ms 30.4 ms 0%
Post page 39.3 9.99 ms 14.3 ms 19.4 ms 0%
Tag page 7.86 11.8 ms 16.4 ms 20.6 ms 0%
Author page 7.86 11.7 ms 16.3 ms 19.7 ms 0%
RSS feed 7.86 13.2 ms 17.9 ms 21.3 ms 0%
4 virtual users
Home page 18.7 52.9 ms 80.3 ms 106 ms 0%
Post page 46.8 39.7 ms 59.3 ms 85.8 ms 0%
Tag page 9.38 34.5 ms 52.6 ms 75.4 ms 0%
Author page 9.36 34 ms 51.8 ms 66.7 ms 0%
RSS feed 9.34 36.3 ms 55.7 ms 83.1 ms 0%
16 virtual users
Home page 18.4 214 ms 284 ms 312 ms 0%
Post page 46 178 ms 249 ms 280 ms 0%
Tag page 9.19 116 ms 176 ms 193 ms 0%
Author page 9.24 116 ms 170 ms 200 ms 0%
RSS feed 9.19 121 ms 182 ms 210 ms 0%

Staff in Ghost Admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Post list 8.18 16.6 ms 25.4 ms 36.3 ms 0%
Post editor 24.6 7.38 ms 10.9 ms 15.9 ms 0%
Saving a draft 24.6 17.9 ms 27.2 ms 34.7 ms 0%
Member list 8.2 19.3 ms 26.5 ms 33.4 ms 0%
4 virtual users
Post list 9.41 22.4 ms 34.8 ms 53.3 ms 0%
Post editor 28.3 12.4 ms 20.6 ms 26.1 ms 0%
Saving a draft 28.3 102 ms 157 ms 182 ms 0%
Member list 9.44 26.4 ms 41.7 ms 67.8 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 386 MB and MySQL at 586 MB.

Wagtail

Visitors

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 2.88 44 ms 69.5 ms 78.7 ms 0%
Blog index 2.86 138 ms 213 ms 256 ms 0%
Blog post 8.61 15.3 ms 25.3 ms 32.8 ms 0%
Bread page 8.61 16.5 ms 25 ms 27.7 ms 0%
Location page 2.86 15.6 ms 25.2 ms 27.5 ms 0%
Site search 2.86 26.3 ms 49 ms 59.7 ms 0%
4 virtual users
Home page 4.96 116 ms 168 ms 253 ms 0%
Blog index 5 368 ms 524 ms 576 ms 0%
Blog post 14.9 34.3 ms 60.2 ms 84.1 ms 0%
Bread page 14.9 37.3 ms 57 ms 70.7 ms 0%
Location page 5 35.5 ms 52.9 ms 59.3 ms 0%
Site search 4.95 52.8 ms 104 ms 133 ms 0%
16 virtual users
Home page 4.67 402 ms 625 ms 784 ms 0%
Blog index 4.69 895 ms 1.34 s 1.45 s 0%
Blog post 14 234 ms 375 ms 459 ms 0%
Bread page 14 243 ms 383 ms 451 ms 0%
Location page 4.66 239 ms 374 ms 428 ms 0%
Site search 4.64 283 ms 454 ms 553 ms 0%

Editors in the Wagtail admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Admin dashboard 1.39 46.6 ms 58.9 ms 67.1 ms 0%
Page explorer 2.82 157 ms 224 ms 330 ms 0%
Page editor 4.22 80 ms 107 ms 202 ms 0%
Image library 1.39 31.8 ms 43.2 ms 126 ms 0%
Admin page search 1.39 21 ms 46 ms 47.6 ms 0%
4 virtual users
Admin dashboard 2.12 146 ms 296 ms 414 ms 0%
Page explorer 4.28 446 ms 727 ms 863 ms 0%
Page editor 6.45 183 ms 399 ms 470 ms 0%
Image library 2.14 118 ms 313 ms 427 ms 0%
Admin page search 2.14 49.4 ms 167 ms 242 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. 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 310 MB, Postgres at 175 MB, and Redis at 26 MB.

Advertised vs. measured

Advertised Measured
vCPU 2 2
CPU Shared vCPU 0.2% of busy CPU time stolen
RAM 2 GB 1.8 GiB
Storage 50 GB NVMe 49.1 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 9575F 64-Core Processor
CPU cores
2
CPU frequency
3295 MHz
AES-NI
Yes
VM-x/AMD-V
No
RAM reported
1.8 GiB
Swap reported
0 MiB
Disk reported
49.1 GiB
Virtualization reported
KVM
CPU steal
0.2% 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
Premium 2 vCPU / 2 GB
Product line
Premium
Location
Chicago #1
vCPU
2 shared vCPU
Architecture
x86_64
RAM
2 GB
Storage
50 GB NVMe
Virtualization
KVM
Network
Unknown
Transfer
2.05 TB
Port 25
Unknown
Monthly price at test time
€18.00 EUR
Hourly price at test time
€0.027 EUR
YABS version
v2026-09-20
Ran at
Oct 17, 2026, 01:15:23 UTC
Parser version
5

Run timeline

Queued
Oct 17, 2026, 01:14:00 UTC
First update from the server
Oct 17, 2026, 01:15:17 UTC
Completed
Oct 17, 2026, 02:40:00 UTC
Server deleted
Oct 17, 2026, 02:40:00 UTC
Cost of this run
€0.038 EUR
Watch party 0 watching

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

Watch party

Loading the party