Skip to main content

UpCloud Starter 2 vCPU / 2 GB

New York #1

Benchmark complete
Finished Oct 13, 2026
Geekbench 7 single-core
1,310
Faster than 70% of 2 vCPU plans
Geekbench 7 multi-core
Skipped
Disk 4K IOPS
15,468
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
    New York #1
  • vCPU
    2
  • RAM
    2 GB
  • Storage
    30 GB
  • Network
    Unknown
  • OS image
    01000000-0000-4000-8000-000030240200
  • Trigger
    Scheduled
  • Queued at
    Oct 12, 2026, 23:52:00 UTC
Visit UpCloud

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

CPU

Version Single-core Multi-core
Geekbench 7 1,310 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
1,452
45th of 129
Single-core only
Navigation
1,560
33rd of 129
Single-core only
HTML5 Browser
1,180
62nd of 129
Single-core only
PDF Viewer
1,378
56th of 129
Single-core only
Photo Library
1,177
59th of 129
Single-core only
Clang
1,206
49th of 129
Single-core only
Text Processing
1,111
65th of 129
Single-core only
Asset Compression
1,284
65th of 129
Single-core only
HDR
1,056
68th of 129
Single-core only
Photo Editor
1,436
56th of 129
Single-core only
Ray Tracer
1,405
40th of 129
Single-core only
Structure from Motion
1,454
55th of 129
Single-core only
Game Physics
1,375
45th of 129
Single-core only
Video Encoder
1,242
55th of 129
Single-core only
Audio Encoder
1,324
59th of 129
Single-core only
Video Player
1,440
51st of 129
Single-core only

Rank among the 129 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 34.9 GB/s 3 0.364%
Scale higher is better 23.8 GB/s 3 0.461%
Add higher is better 25.1 GB/s 3 0.479%
Triad higher is better 25.3 GB/s 3 0.0542%

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 468/s 3 0.634%
RSA 4096 verifies higher is better 30,670/s 3 0.0839%
SHA-256 higher is better 1.41 GB/s 3 0.187%
AES-256-GCM higher is better 7.16 GB/s 3 0.0735%
ChaCha20-Poly1305 higher is better 3.62 GB/s 3 0.207%

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 4.02 ms 3 0.23%
Requests per second, 90th percentile higher is better 493/s 3 0.31%
Request latency, 99.9th percentile lower is better 7.68 ms 3 1.88%
Requests per second, average higher is better 492/s 3 0.255%

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

Disk

Block size Read Write Total
4K 30.2 MB/s (7,730 IOPS) 30.2 MB/s (7,738 IOPS) 60.4 MB/s (15,468 IOPS)
64K 312.8 MB/s (5,004 IOPS) 314.5 MB/s (5,031 IOPS) 627.3 MB/s (10,035 IOPS)
512K 382.5 MB/s (764 IOPS) 402.8 MB/s (805 IOPS) 785.3 MB/s (1,569 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 996 Mbps 1.01 Gbps
Eranium, Amsterdam, NL (100G) IPv4 1.01 Gbps 1.02 Gbps
Leaseweb, Singapore, SG (10G) IPv4 613 Mbps 859 Mbps
Clouvider, Los Angeles, CA, US (10G) IPv4 962 Mbps 983 Mbps
Leaseweb, NYC, NY, US (10G) IPv4 1.07 Gbps 1.07 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 3,624 0.276 ms
fdatasync 3,743 0.267 ms
fsync 1,902 0.526 ms
fsync_writethrough Not supported here n/a
open_sync 2,049 0.488 ms
Two 8 kB writes
open_datasync 1,806 0.554 ms
fdatasync 3,371 0.297 ms
fsync 1,754 0.57 ms
fsync_writethrough Not supported here n/a
open_sync 1,045 0.957 ms
open_sync at different write sizes
1 * 16kB open_sync write 1,819 0.55 ms
2 * 8kB open_sync writes 1,011 0.989 ms
4 * 4kB open_sync writes 490 2.04 ms
8 * 2kB open_sync writes 256 3.91 ms
16 * 1kB open_sync writes 130 7.7 ms
fsync on a non-write descriptor
write, fsync, close 1,823 0.549 ms
write, close, fsync 1,917 0.522 ms
Non-synced 8 kB writes
write 541,853 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 1,598 0.573 ms 0.867 ms 1.56 ms 3.53 ms 0
Read/write (TPC-B like) 8 4,286 1.62 ms 3.2 ms 4.84 ms 12.2 ms 0
Read/write (TPC-B like) 32 4,511 5.19 ms 16.6 ms 29.8 ms 54.7 ms 0
Read only 1 29,487 0.032 ms 0.043 ms 0.053 ms 0.073 ms 0
Read only 8 55,318 0.13 ms 0.203 ms 0.246 ms 0.391 ms 0
Read only 32 58,320 0.473 ms 0.655 ms 0.831 ms 1.63 ms 0

Scale 10 (1,000,000 accounts), loaded in 1.53 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 1,035 0.795 ms 1.36 ms 2.68 ms 12.6 ms 0
Read/write (TPC-B like) 8 2,785 1.96 ms 4.03 ms 11.8 ms 89.2 ms 0
Read/write (TPC-B like) 32 3,634 6.29 ms 13 ms 81.7 ms 97.6 ms 0
Read only 1 6,419 0.158 ms 0.312 ms 0.925 ms 2.02 ms 0
Read only 8 19,241 0.206 ms 0.539 ms 1.05 ms 42 ms 0
Read only 32 20,468 0.801 ms 1.72 ms 40 ms 46.2 ms 0

Scale 100 (10,000,000 accounts), loaded in 19.4 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 1 315 6,303 2.66 ms 4.18 ms 11 ms 0
Read/write 8 745 14,897 8.9 ms 16.1 ms 74.5 ms 0
Read/write 32 945 18,890 33.7 ms 53.9 ms 71.8 ms 0
Read only 1 1,021 16,329 0.954 ms 1.04 ms 1.55 ms 0
Read only 8 1,811 28,971 4.25 ms 5.67 ms 6.32 ms 0
Read only 32 1,711 27,378 18.3 ms 22.7 ms 24.8 ms 0

10 tables of 100,000 rows, loaded in 8 s. 60 s per run, one connection per thread.

Redis

memtier

Mix Operations/s Hits/s Median p99 p99.9
1:10 set:get 67,389 61,262 0.527 ms 3.15 ms 4.74 ms
1:1 set:get 67,451 33,725 0.599 ms 3.04 ms 4.58 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 483 1,873 2,337 1.14 s
Express express-postgresjs 7,706 11,591 31,460 67.8 ms
Fastify fastify-postgres 7,537 12,247 38,819 61.3 ms
NestJS nestjs 5,329 6,072 19,573 97.7 ms
Nuxt nuxt 6,835 11,322 31,677 124 ms
FastAPI fastapi 4,047 5,045 18,155 292 ms
Django django-postgresql 2,034 2,357 5,173 173 ms
Rails rails 3,325 4,545 15,604 101 ms
Laravel laravel 904 954 1,845 293 ms
Symfony symfony 1,146 1,253 3,573 264 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.

WooCommerce

Page mix

Step Requests/s Median p95 p99 Error rate
8 virtual users
Home page 2.32 686 ms 789 ms 796 ms 0%
Shop page 2.32 930 ms 1.07 s 1.08 s 0%
Category page 2.32 592 ms 966 ms 1.04 s 0%
Product page 2.32 625 ms 746 ms 772 ms 0%
Product search 2.32 546 ms 655 ms 690 ms 0%
32 virtual users
Home page 2.34 2.48 s 2.84 s 2.91 s 0%
Shop page 2.34 3.31 s 3.7 s 3.78 s 0%
Category page 2.34 2.93 s 3.39 s 3.61 s 0%
Product page 2.34 2.53 s 2.75 s 2.82 s 0%
Product search 2.34 2.3 s 2.57 s 2.63 s 0%

Cart and checkout

Step Requests/s Median p95 p99 Error rate
8 virtual users
Add to cart 4.49 727 ms 857 ms 876 ms 0%
Cart 4.49 593 ms 708 ms 723 ms 0%
Checkout 4.49 464 ms 550 ms 569 ms 0%
32 virtual users
Add to cart 4.52 2.42 s 2.89 s 2.96 s 0%
Cart 4.52 2.54 s 2.78 s 2.85 s 0%
Checkout 4.52 2.01 s 2.34 s 2.44 s 0%

k6 with a fixed number of virtual users, 62 to 68 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 2.55 171 ms 206 ms 365 ms 0%
Topic JSON 1.29 87.4 ms 103 ms 185 ms 0%
Home page 1.28 155 ms 262 ms 394 ms 0%
Categories page 0.646 181 ms 267 ms 420 ms 0%
User activity page 0.629 106 ms 123 ms 222 ms 0%
4 virtual users
Topic page 4.13 397 ms 643 ms 793 ms 0%
Topic JSON 2.08 278 ms 399 ms 452 ms 0%
Home page 2.06 354 ms 464 ms 493 ms 0%
Categories page 1.06 461 ms 727 ms 867 ms 0%
User activity page 1.06 292 ms 400 ms 553 ms 0%
16 virtual users
Topic page 4.47 1.25 s 1.53 s 1.72 s 0%
Topic JSON 2.24 1.16 s 1.38 s 1.56 s 0%
Home page 2.26 1.28 s 1.56 s 1.69 s 0%
Categories page 1.11 1.25 s 1.63 s 1.82 s 0%
User activity page 1.15 1.23 s 1.39 s 1.63 s 0%

Anonymous

Step Requests/s Median p95 p99 Error rate
16 virtual users
Topic page 101 61.4 ms 108 ms 129 ms 0%
Topic JSON 50.7 62.4 ms 110 ms 137 ms 0%
Home page 50.7 63 ms 108 ms 134 ms 0%
Categories page 25.3 61.1 ms 107 ms 132 ms 0%
User activity page 25.4 101 ms 154 ms 179 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 269 MB of it. The container peaked at 1,340 MB.

Ghost

Readers

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 9.83 29.1 ms 33.1 ms 44.8 ms 0%
Post page 24.5 14.7 ms 17.6 ms 28.2 ms 0%
Tag page 4.91 20.3 ms 24.3 ms 37.5 ms 0%
Author page 4.9 19.9 ms 22.3 ms 26.7 ms 0%
RSS feed 4.9 25.6 ms 28.8 ms 35.2 ms 0%
4 virtual users
Home page 11.4 92.5 ms 120 ms 153 ms 0%
Post page 28.4 63.2 ms 93.9 ms 114 ms 0%
Tag page 5.69 60.3 ms 84 ms 104 ms 0%
Author page 5.69 59.7 ms 85.5 ms 105 ms 0%
RSS feed 5.66 65 ms 91 ms 102 ms 0%
16 virtual users
Home page 11.3 359 ms 432 ms 455 ms 0%
Post page 28.2 295 ms 370 ms 391 ms 0%
Tag page 5.67 198 ms 263 ms 295 ms 0%
Author page 5.66 197 ms 262 ms 291 ms 0%
RSS feed 5.64 201 ms 261 ms 285 ms 0%

Staff in Ghost Admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Post list 5.43 28.8 ms 35.7 ms 60 ms 0%
Post editor 16.3 9.85 ms 12.8 ms 17.2 ms 0%
Saving a draft 16.3 25.9 ms 33 ms 45.2 ms 0%
Member list 5.45 35.2 ms 40.9 ms 47.9 ms 0%
4 virtual users
Post list 6.33 35.9 ms 46.4 ms 83.3 ms 0%
Post editor 19.1 17.6 ms 24.7 ms 37.7 ms 0%
Saving a draft 19.1 155 ms 208 ms 245 ms 0%
Member list 6.36 45.8 ms 53.4 ms 92.2 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 362 MB and MySQL at 588 MB.

Wagtail

Visitors

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 2.09 64 ms 66.9 ms 70.7 ms 0%
Blog index 2.09 215 ms 221 ms 287 ms 0%
Blog post 6.24 20.3 ms 31.5 ms 33.2 ms 0%
Bread page 6.26 22.5 ms 23.8 ms 25.7 ms 0%
Location page 2.09 21.5 ms 23 ms 23.9 ms 0%
Site search 2.07 34.1 ms 59.3 ms 61.2 ms 0%
4 virtual users
Home page 3.38 170 ms 239 ms 316 ms 0%
Blog index 3.38 573 ms 722 ms 750 ms 0%
Blog post 10.1 49.2 ms 79.8 ms 106 ms 0%
Bread page 10.2 55 ms 79 ms 96.2 ms 0%
Location page 3.43 49.7 ms 72.9 ms 77.8 ms 0%
Site search 3.36 87.2 ms 161 ms 193 ms 0%
16 virtual users
Home page 3.59 542 ms 681 ms 762 ms 0%
Blog index 3.59 1.27 s 1.46 s 1.56 s 0%
Blog post 10.7 311 ms 483 ms 544 ms 0%
Bread page 10.7 311 ms 446 ms 528 ms 0%
Location page 3.57 302 ms 440 ms 505 ms 0%
Site search 3.55 363 ms 519 ms 595 ms 0%

Editors in the Wagtail admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Admin dashboard 0.757 70.1 ms 74.3 ms 115 ms 0%
Page explorer 1.55 317 ms 341 ms 432 ms 0%
Page editor 2.29 149 ms 173 ms 278 ms 0%
Image library 0.757 53.5 ms 59 ms 526 ms 0%
Admin page search 0.757 28.6 ms 65.6 ms 66.1 ms 0%
4 virtual users
Admin dashboard 1.25 228 ms 465 ms 539 ms 0%
Page explorer 2.5 771 ms 1.13 s 1.3 s 0%
Page editor 3.76 363 ms 608 ms 736 ms 0%
Image library 1.25 203 ms 426 ms 497 ms 0%
Admin page search 1.25 91.3 ms 220 ms 311 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 302 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
New York #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 12, 2026, 23:53:14 UTC
Parser version
5

Run timeline

Queued
Oct 12, 2026, 23:52:00 UTC
First update from the server
Oct 12, 2026, 23:53:08 UTC
Completed
Oct 13, 2026, 01:22:39 UTC
Server deleted
Oct 13, 2026, 01:22:39 UTC
Cost of this run
€0.022 EUR
Watch party 0 watching

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

Watch party

Loading the party