Skip to main content

UpCloud Premium 2 vCPU / 2 GB

New York #1

Benchmark complete
Finished Oct 17, 2026
Geekbench 7 single-core
Skipped
Median here: 1,886 over 2 runs in 90 days
Geekbench 7 multi-core
Skipped
Disk 4K IOPS
56,290
fio random read and write, 50/50
Median here: 41,759 over 2 runs in 90 days
Monthly price at test time
€18.00 EUR
Same price today

Server

  • Provider
    UpCloud
  • Plan
    Premium 2 vCPU / 2 GB
  • Location
    New York #1
  • vCPU
    2
  • RAM
    2 GB
  • Storage
    50 GB NVMe
  • Network
    Unknown
  • OS image
    01000000-0000-4000-8000-000030240200
  • Trigger
    Scheduled
  • Queued at
    Oct 16, 2026, 23:21:00 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

Geekbench was skipped because this server didn't have the free memory for the multi-core run and couldn't run single-core only either. The run log has the details.

Memory, TLS and scheduler

Memory bandwidth (STREAM)

Test Result Runs Spread
Copy higher is better 68.9 GB/s 3 7.59%
Scale higher is better 58.9 GB/s 3 13.7%
Add higher is better 63.6 GB/s 3 8.65%
Triad higher is better 64.4 GB/s 3 9.97%

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 1,618/s 3 1.76%
RSA 4096 verifies higher is better 44,129/s 3 1.72%
SHA-256 higher is better 2.34 GB/s 3 1.17%
AES-256-GCM higher is better 38.5 GB/s 3 2.38%
ChaCha20-Poly1305 higher is better 10.7 GB/s 3 1.8%

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 3.27 ms 3 1.53%
Requests per second, 90th percentile higher is better 616/s 3 3.25%
Request latency, 99.9th percentile lower is better 6.29 ms 3 12.8%
Requests per second, average higher is better 561/s 3 6.55%

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

Disk

Block size Read Write Total
4K 109.8 MB/s (28,108 IOPS) 110.1 MB/s (28,182 IOPS) 219.9 MB/s (56,290 IOPS)
64K 377.1 MB/s (6,034 IOPS) 379.1 MB/s (6,066 IOPS) 756.3 MB/s (12,100 IOPS)
512K 382.8 MB/s (765 IOPS) 403.2 MB/s (806 IOPS) 786 MB/s (1,571 IOPS)
1M 378.2 MB/s (378 IOPS) 403.4 MB/s (403 IOPS) 781.7 MB/s (781 IOPS)

fio random read and write, 50/50, run by YABS against the boot disk.

Network

iperf3 didn't report network results for this run.

Datastores

PostgreSQL

fsync speed (pg_test_fsync)

Method Operations per second Time per operation
One 8 kB write
open_datasync 7,158 0.14 ms
fdatasync 6,673 0.15 ms
fsync 4,368 0.229 ms
fsync_writethrough Not supported here n/a
open_sync 4,342 0.23 ms
Two 8 kB writes
open_datasync 2,787 0.359 ms
fdatasync 5,767 0.173 ms
fsync 3,239 0.309 ms
fsync_writethrough Not supported here n/a
open_sync 1,757 0.569 ms
open_sync at different write sizes
1 * 16kB open_sync write 3,304 0.303 ms
2 * 8kB open_sync writes 2,065 0.484 ms
4 * 4kB open_sync writes 1,076 0.93 ms
8 * 2kB open_sync writes 566 1.77 ms
16 * 1kB open_sync writes 279 3.58 ms
fsync on a non-write descriptor
write, fsync, close 4,596 0.218 ms
write, close, fsync 5,065 0.197 ms
Non-synced 8 kB writes
write 2,670,081 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 3,538 0.238 ms 0.374 ms 0.775 ms 7.81 ms 0
Read/write (TPC-B like) 8 10,823 0.593 ms 1.36 ms 2.48 ms 13.6 ms 0
Read/write (TPC-B like) 32 9,937 2.23 ms 8.3 ms 16.7 ms 45.2 ms 0
Read only 1 65,718 0.014 ms 0.023 ms 0.033 ms 0.076 ms 0
Read only 8 120,345 0.059 ms 0.104 ms 0.135 ms 0.223 ms 0
Read only 32 108,542 0.247 ms 0.431 ms 0.56 ms 0.984 ms 0

Scale 10 (1,000,000 accounts), loaded in 0.87 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 2,241 0.353 ms 0.584 ms 1.67 ms 18.1 ms 0
Read/write (TPC-B like) 8 7,372 0.728 ms 2.09 ms 5.79 ms 66.8 ms 0
Read/write (TPC-B like) 32 8,641 2.54 ms 6.68 ms 35.6 ms 75.3 ms 0
Read only 1 20,221 0.021 ms 0.108 ms 0.192 ms 0.846 ms 0
Read only 8 83,027 0.068 ms 0.209 ms 0.33 ms 2.05 ms 0
Read only 32 78,864 0.317 ms 0.72 ms 1.4 ms 10 ms 0

Scale 100 (10,000,000 accounts), loaded in 13.7 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 1 515 10,308 1.55 ms 2.71 ms 8.13 ms 0
Read/write 8 1,143 22,854 5.77 ms 12.3 ms 40.4 ms 0
Read/write 32 1,662 33,245 17 ms 36.2 ms 70.5 ms 0
Read only 1 2,217 35,476 0.424 ms 0.619 ms 0.856 ms 0
Read only 8 4,340 69,440 1.76 ms 2.76 ms 3.68 ms 0
Read only 32 3,419 54,709 8.9 ms 13.5 ms 16.4 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 197,719 179,744 0.175 ms 2.26 ms 3.76 ms
1:1 set:get 200,459 100,229 0.175 ms 2.26 ms 3.5 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 521 2,402 3,067 660 ms
Express express-postgresjs 8,817 15,622 92,348 171 ms
Fastify fastify-postgres 9,131 16,031 115,491 71.1 ms
NestJS nestjs 9,821 10,535 59,504 75.5 ms
Nuxt nuxt 8,308 14,005 73,693 170 ms
FastAPI fastapi 6,990 7,951 35,038 171 ms
Django django-postgresql 2,893 3,204 9,899 131 ms
Rails rails 4,706 7,618 36,131 79.7 ms
Laravel laravel 939 1,054 2,130 399 ms
Symfony symfony 1,326 1,494 5,232 229 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 2.43 654 ms 799 ms 881 ms 0%
Shop page 2.43 899 ms 1.11 s 1.18 s 0%
Category page 2.43 566 ms 909 ms 1.08 s 0%
Product page 2.43 608 ms 733 ms 770 ms 0%
Product search 2.43 511 ms 640 ms 701 ms 0%
32 virtual users
Home page 2.46 2.36 s 2.62 s 2.72 s 0%
Shop page 2.46 3.04 s 3.74 s 3.96 s 0%
Category page 2.46 2.8 s 3.49 s 3.74 s 0%
Product page 2.46 2.39 s 2.73 s 2.82 s 0%
Product search 2.46 2.22 s 2.42 s 2.47 s 0%

Cart and checkout

Step Requests/s Median p95 p99 Error rate
8 virtual users
Add to cart 4.8 706 ms 834 ms 1.02 s 0%
Cart 4.8 552 ms 661 ms 751 ms 0%
Checkout 4.8 421 ms 508 ms 542 ms 0%
32 virtual users
Add to cart 4.91 2.31 s 2.88 s 2.98 s 0%
Cart 4.91 2.38 s 2.74 s 2.83 s 0%
Checkout 4.91 1.78 s 2.14 s 2.24 s 0%

k6 with a fixed number of virtual users, 61 to 65 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 2.87 152 ms 197 ms 347 ms 0%
Topic JSON 1.43 78.9 ms 99.8 ms 143 ms 0%
Home page 1.43 133 ms 192 ms 441 ms 0%
Categories page 0.726 159 ms 244 ms 349 ms 0%
User activity page 0.709 95.6 ms 144 ms 258 ms 0%
4 virtual users
Topic page 5.04 333 ms 499 ms 640 ms 0%
Topic JSON 2.51 236 ms 351 ms 458 ms 0%
Home page 2.53 302 ms 402 ms 636 ms 0%
Categories page 1.27 349 ms 671 ms 783 ms 0%
User activity page 1.26 247 ms 509 ms 648 ms 0%
16 virtual users
Topic page 5.35 1.17 s 1.46 s 1.57 s 0%
Topic JSON 2.72 1.09 s 1.37 s 1.46 s 0%
Home page 2.67 1.17 s 1.48 s 1.57 s 0%
Categories page 1.33 1.14 s 1.47 s 1.55 s 0%
User activity page 1.33 1.15 s 1.4 s 1.51 s 0%

Anonymous

Step Requests/s Median p95 p99 Error rate
16 virtual users
Topic page 112 49.6 ms 107 ms 144 ms 0%
Topic JSON 56.2 51.8 ms 104 ms 145 ms 0%
Home page 56.1 49.8 ms 107 ms 149 ms 0%
Categories page 28.1 53.4 ms 110 ms 154 ms 0%
User activity page 28.1 90 ms 163 ms 219 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 1,319 MB.

Ghost

Readers

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 10.4 27.2 ms 33.3 ms 43.2 ms 0%
Post page 25.9 15.6 ms 20.3 ms 26.6 ms 0%
Tag page 5.18 17.3 ms 22.1 ms 24.5 ms 0%
Author page 5.16 18.1 ms 23.7 ms 33 ms 0%
RSS feed 5.16 19 ms 24.2 ms 30.6 ms 0%
4 virtual users
Home page 13.6 76.4 ms 110 ms 140 ms 0%
Post page 33.9 54.6 ms 80.7 ms 107 ms 0%
Tag page 6.78 45.5 ms 71.7 ms 91.9 ms 0%
Author page 6.76 48.9 ms 72 ms 88 ms 0%
RSS feed 6.76 48.9 ms 71.3 ms 90 ms 0%
16 virtual users
Home page 14 284 ms 373 ms 417 ms 0%
Post page 35.1 237 ms 321 ms 355 ms 0%
Tag page 7.03 153 ms 222 ms 243 ms 0%
Author page 7.05 152 ms 219 ms 250 ms 0%
RSS feed 7 161 ms 232 ms 259 ms 0%

Staff in Ghost Admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Post list 5.66 22.3 ms 33.2 ms 47.9 ms 0%
Post editor 17 10.7 ms 16 ms 22.5 ms 0%
Saving a draft 17 25.9 ms 52.3 ms 89.3 ms 0%
Member list 5.66 25.7 ms 34.5 ms 43.6 ms 0%
4 virtual users
Post list 7.45 28.4 ms 38.7 ms 46.8 ms 0%
Post editor 22.4 15.6 ms 24 ms 34.4 ms 0%
Saving a draft 22.4 132 ms 200 ms 252 ms 0%
Member list 7.47 34.6 ms 48.5 ms 78.8 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 370 MB and MySQL at 585 MB.

Wagtail

Visitors

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 2.38 57.5 ms 75.7 ms 83.5 ms 0%
Blog index 2.38 170 ms 218 ms 278 ms 0%
Blog post 7.1 19.3 ms 30.7 ms 34.8 ms 0%
Bread page 7.11 21.3 ms 26.9 ms 29.3 ms 0%
Location page 2.38 19.7 ms 25.4 ms 26.7 ms 0%
Site search 2.36 35.3 ms 63.4 ms 71.8 ms 0%
4 virtual users
Home page 3.62 153 ms 229 ms 281 ms 0%
Blog index 3.67 509 ms 709 ms 771 ms 0%
Blog post 10.9 45.1 ms 83.7 ms 96.3 ms 0%
Bread page 10.9 49.6 ms 76.1 ms 99.4 ms 0%
Location page 3.67 48.8 ms 73.2 ms 80.1 ms 0%
Site search 3.62 70.9 ms 154 ms 223 ms 0%
16 virtual users
Home page 3.93 465 ms 645 ms 800 ms 0%
Blog index 3.99 1.13 s 1.42 s 1.65 s 0%
Blog post 11.8 269 ms 420 ms 509 ms 0%
Bread page 11.8 283 ms 450 ms 543 ms 0%
Location page 3.98 273 ms 471 ms 517 ms 0%
Site search 3.91 349 ms 520 ms 607 ms 0%

Editors in the Wagtail admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Admin dashboard 1.04 66.3 ms 80 ms 123 ms 0%
Page explorer 2.12 213 ms 289 ms 432 ms 0%
Page editor 3.15 108 ms 139 ms 204 ms 0%
Image library 1.04 42.3 ms 53.9 ms 296 ms 0%
Admin page search 1.04 28.7 ms 60.9 ms 169 ms 0%
4 virtual users
Admin dashboard 1.48 198 ms 408 ms 511 ms 0%
Page explorer 3.04 637 ms 1.02 s 1.13 s 0%
Page editor 4.52 265 ms 551 ms 716 ms 0%
Image library 1.5 145 ms 427 ms 561 ms 0%
Admin page search 1.48 78.4 ms 216 ms 283 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 304 MB, Postgres at 173 MB, and Redis at 26 MB.

Advertised vs. measured

Advertised Measured
vCPU 2 2
CPU Shared vCPU 1.5% 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
1.5% 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
New York #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 16, 2026, 23:22:32 UTC
Parser version
5

Run timeline

Queued
Oct 16, 2026, 23:21:00 UTC
First update from the server
Oct 16, 2026, 23:22:17 UTC
Completed
Oct 17, 2026, 00:42:01 UTC
Server deleted
Oct 17, 2026, 00:42:01 UTC
Cost of this run
€0.036 EUR
Watch party 0 watching

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

Watch party

Loading the party