Skip to main content

UpCloud Starter 2 vCPU / 2 GB

San Jose #1

Benchmark complete
Finished Oct 14, 2026
Geekbench 7 single-core
1,298
Faster than 73% of 2 vCPU plans
Geekbench 7 multi-core
Skipped
Disk 4K IOPS
19,952
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
    San Jose #1
  • vCPU
    2
  • RAM
    2 GB
  • Storage
    30 GB
  • Network
    Unknown
  • OS image
    01000000-0000-4000-8000-000030240200
  • Trigger
    Scheduled
  • Queued at
    Oct 14, 2026, 02:37:00 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 1,298 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
1,432
51st of 150
Single-core only
Navigation
1,519
38th of 150
Single-core only
HTML5 Browser
1,172
69th of 150
Single-core only
PDF Viewer
1,371
61st of 150
Single-core only
Photo Library
1,181
63rd of 150
Single-core only
Clang
1,190
53rd of 150
Single-core only
Text Processing
1,111
69th of 150
Single-core only
Asset Compression
1,282
71st of 150
Single-core only
HDR
1,055
76th of 150
Single-core only
Photo Editor
1,432
62nd of 150
Single-core only
Ray Tracer
1,389
42nd of 150
Single-core only
Structure from Motion
1,436
61st of 150
Single-core only
Game Physics
1,359
48th of 150
Single-core only
Video Encoder
1,225
63rd of 150
Single-core only
Audio Encoder
1,326
63rd of 150
Single-core only
Video Player
1,403
58th of 150
Single-core only

Rank among the 150 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 58.7 GB/s 3 0.108%
Scale higher is better 39.4 GB/s 3 1.72%
Add higher is better 43.2 GB/s 3 0.919%
Triad higher is better 44.9 GB/s 3 1.26%

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 472/s 3 0.0367%
RSA 4096 verifies higher is better 30,560/s 3 0.537%
SHA-256 higher is better 1.4 GB/s 3 0.766%
AES-256-GCM higher is better 7.14 GB/s 3 0.209%
ChaCha20-Poly1305 higher is better 3.62 GB/s 3 0.381%

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 4.03 ms 3 0.115%
Requests per second, 90th percentile higher is better 492/s 3 0.117%
Request latency, 99.9th percentile lower is better 6.94 ms 3 13.4%
Requests per second, average higher is better 490/s 3 0.127%

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 (9,964 IOPS) 39 MB/s (9,988 IOPS) 77.9 MB/s (19,952 IOPS)
64K 399.4 MB/s (6,390 IOPS) 401.5 MB/s (6,424 IOPS) 800.9 MB/s (12,814 IOPS)
512K 382.5 MB/s (764 IOPS) 402.8 MB/s (805 IOPS) 785.3 MB/s (1,569 IOPS)
1M 379.3 MB/s (379 IOPS) 404.6 MB/s (404 IOPS) 783.9 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 1.05 Gbps 1.09 Gbps
Eranium, Amsterdam, NL (100G) IPv4 847 Mbps 1.07 Gbps
Leaseweb, Singapore, SG (10G) IPv4 866 Mbps 983 Mbps
Clouvider, Los Angeles, CA, US (10G) IPv4 1.16 Gbps 1.17 Gbps
Leaseweb, NYC, NY, US (10G) IPv4 1.08 Gbps 15.8 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 3,467 0.288 ms
fdatasync 3,301 0.303 ms
fsync 1,668 0.599 ms
fsync_writethrough Not supported here n/a
open_sync 1,801 0.555 ms
Two 8 kB writes
open_datasync 1,646 0.608 ms
fdatasync 2,848 0.351 ms
fsync 1,528 0.654 ms
fsync_writethrough Not supported here n/a
open_sync 918 1.09 ms
open_sync at different write sizes
1 * 16kB open_sync write 1,483 0.674 ms
2 * 8kB open_sync writes 821 1.22 ms
4 * 4kB open_sync writes 401 2.49 ms
8 * 2kB open_sync writes 228 4.38 ms
16 * 1kB open_sync writes 107 9.32 ms
fsync on a non-write descriptor
write, fsync, close 1,461 0.684 ms
write, close, fsync 1,632 0.613 ms
Non-synced 8 kB writes
write 540,902 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 1,348 0.667 ms 1.01 ms 2.16 ms 7.46 ms 0
Read/write (TPC-B like) 8 3,800 1.81 ms 3.82 ms 5.96 ms 20 ms 0
Read/write (TPC-B like) 32 3,941 6.05 ms 20.5 ms 36 ms 70.2 ms 0
Read only 1 23,334 0.041 ms 0.053 ms 0.061 ms 0.083 ms 0
Read only 8 49,068 0.146 ms 0.23 ms 0.28 ms 0.612 ms 0
Read only 32 50,712 0.516 ms 0.828 ms 1.13 ms 1.97 ms 0

Scale 10 (1,000,000 accounts), loaded in 1.65 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) 1 900 0.945 ms 1.72 ms 4.08 ms 15.4 ms 0
Read/write (TPC-B like) 8 2,535 2.25 ms 5.27 ms 19 ms 86.5 ms 0
Read/write (TPC-B like) 32 3,306 7.24 ms 15.3 ms 80.4 ms 100 ms 0
Read only 1 5,473 0.18 ms 0.349 ms 0.937 ms 2.86 ms 0
Read only 8 19,064 0.24 ms 0.611 ms 1.48 ms 34.8 ms 0
Read only 32 20,164 0.91 ms 1.96 ms 32.1 ms 38.9 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 1 277 5,534 3.19 ms 5.67 ms 11.4 ms 0
Read/write 8 724 14,485 10.1 ms 17 ms 50.1 ms 0
Read/write 32 840 16,798 37.6 ms 58.9 ms 78.6 ms 0
Read only 1 859 13,739 1.12 ms 1.37 ms 1.7 ms 0
Read only 8 1,579 25,271 4.74 ms 7.04 ms 7.84 ms 0
Read only 32 1,554 24,860 20 ms 26.2 ms 28.7 ms 0

10 tables of 100,000 rows, loaded in 8.8 s. 60 s per run, one connection per thread.

Redis

memtier

Mix Operations/s Hits/s Median p99 p99.9
1:10 set:get 54,604 49,640 0.879 ms 3.26 ms 4.67 ms
1:1 set:get 53,993 26,996 0.871 ms 3.26 ms 4.67 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 429 1,737 2,170 1.82 s
Express express-postgresjs 7,614 11,224 28,096 77.4 ms
Fastify fastify-postgres 7,679 11,865 35,573 162 ms
NestJS nestjs 5,120 5,901 18,829 109 ms
Nuxt nuxt 6,896 10,835 29,354 83.7 ms
FastAPI fastapi 3,978 4,944 17,613 268 ms
Django django-postgresql 1,958 2,281 4,978 194 ms
Rails rails 3,253 4,399 14,197 114 ms
Laravel laravel 868 927 1,797 367 ms
Symfony symfony 1,117 1,215 3,423 252 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 2.36 673 ms 789 ms 799 ms 0%
Shop page 2.36 914 ms 1.06 s 1.09 s 0%
Category page 2.36 559 ms 917 ms 1.04 s 0%
Product page 2.36 616 ms 738 ms 760 ms 0%
Product search 2.36 543 ms 649 ms 686 ms 0%
32 virtual users
Home page 2.36 2.47 s 2.71 s 2.78 s 0%
Shop page 2.36 3.24 s 3.65 s 3.78 s 0%
Category page 2.36 2.94 s 3.49 s 3.61 s 0%
Product page 2.36 2.47 s 2.7 s 2.76 s 0%
Product search 2.36 2.29 s 2.51 s 2.58 s 0%

Cart and checkout

Step Requests/s Median p95 p99 Error rate
8 virtual users
Add to cart 4.59 714 ms 831 ms 847 ms 0%
Cart 4.59 579 ms 679 ms 697 ms 0%
Checkout 4.59 457 ms 531 ms 541 ms 0%
32 virtual users
Add to cart 4.61 2.36 s 2.85 s 2.96 s 0%
Cart 4.61 2.48 s 2.75 s 2.83 s 0%
Checkout 4.61 1.99 s 2.27 s 2.35 s 0%

k6 with a fixed number of virtual users, 61 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 2.51 176 ms 211 ms 442 ms 0%
Topic JSON 1.26 91 ms 104 ms 225 ms 0%
Home page 1.26 156 ms 179 ms 278 ms 0%
Categories page 0.629 186 ms 276 ms 352 ms 0%
User activity page 0.629 107 ms 136 ms 249 ms 0%
4 virtual users
Topic page 4.67 359 ms 483 ms 639 ms 0%
Topic JSON 2.36 275 ms 363 ms 482 ms 0%
Home page 2.34 340 ms 441 ms 534 ms 0%
Categories page 1.19 372 ms 597 ms 712 ms 0%
User activity page 1.19 287 ms 347 ms 436 ms 0%
16 virtual users
Topic page 4.54 1.26 s 1.5 s 1.58 s 0%
Topic JSON 2.27 1.19 s 1.43 s 1.49 s 0%
Home page 2.27 1.25 s 1.49 s 1.65 s 0%
Categories page 1.12 1.26 s 1.48 s 1.68 s 0%
User activity page 1.15 1.25 s 1.4 s 1.54 s 0%

Anonymous

Step Requests/s Median p95 p99 Error rate
16 virtual users
Topic page 86.4 64.7 ms 130 ms 172 ms 0%
Topic JSON 43.2 64.1 ms 122 ms 166 ms 0%
Home page 43.2 65.8 ms 128 ms 174 ms 0%
Categories page 21.6 69.3 ms 132 ms 198 ms 0%
User activity page 21.6 117 ms 196 ms 249 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 174 MB of it. The container peaked at 1,297 MB.

Ghost

Readers

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 9.32 30.5 ms 35.5 ms 53 ms 0%
Post page 23.3 15.6 ms 19.1 ms 28.3 ms 0%
Tag page 4.66 21.5 ms 25.7 ms 29.5 ms 0%
Author page 4.64 21.1 ms 24.5 ms 33.2 ms 0%
RSS feed 4.64 26.5 ms 31.6 ms 48.4 ms 0%
4 virtual users
Home page 10.7 96.7 ms 136 ms 170 ms 0%
Post page 26.9 67.9 ms 98.7 ms 131 ms 0%
Tag page 5.37 60.8 ms 81 ms 98.6 ms 0%
Author page 5.36 60.5 ms 84.7 ms 127 ms 0%
RSS feed 5.36 68.9 ms 101 ms 132 ms 0%
16 virtual users
Home page 10.5 379 ms 475 ms 505 ms 0%
Post page 26.2 318 ms 404 ms 432 ms 0%
Tag page 5.25 206 ms 272 ms 307 ms 0%
Author page 5.26 204 ms 273 ms 319 ms 0%
RSS feed 5.23 212 ms 292 ms 321 ms 0%

Staff in Ghost Admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Post list 5.15 29.7 ms 37.7 ms 69.7 ms 0%
Post editor 15.5 10.4 ms 13.8 ms 20.5 ms 0%
Saving a draft 15.5 27 ms 37.9 ms 59.1 ms 0%
Member list 5.16 36.7 ms 43.4 ms 57.9 ms 0%
4 virtual users
Post list 6.22 40 ms 50.6 ms 89.2 ms 0%
Post editor 18.7 17.1 ms 24.5 ms 40.1 ms 0%
Saving a draft 18.7 156 ms 215 ms 262 ms 0%
Member list 6.22 45.8 ms 56 ms 94.2 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 357 MB and MySQL at 586 MB.

Wagtail

Visitors

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 2 66.8 ms 70.9 ms 75.5 ms 0%
Blog index 2 222 ms 232 ms 236 ms 0%
Blog post 5.97 21.8 ms 32.6 ms 34.9 ms 0%
Bread page 5.97 24.3 ms 26.2 ms 28.4 ms 0%
Location page 2 23.2 ms 25.8 ms 27.4 ms 0%
Site search 2 37.6 ms 61.6 ms 63.2 ms 0%
4 virtual users
Home page 3.22 169 ms 254 ms 276 ms 0%
Blog index 3.23 562 ms 845 ms 915 ms 0%
Blog post 9.63 52.1 ms 88.7 ms 111 ms 0%
Bread page 9.63 57.3 ms 89 ms 105 ms 0%
Location page 3.23 52.6 ms 82.1 ms 103 ms 0%
Site search 3.22 82.6 ms 187 ms 204 ms 0%
16 virtual users
Home page 3.61 532 ms 711 ms 810 ms 0%
Blog index 3.67 1.24 s 1.45 s 1.53 s 0%
Blog post 10.8 295 ms 476 ms 582 ms 0%
Bread page 10.8 300 ms 471 ms 531 ms 0%
Location page 3.62 290 ms 452 ms 537 ms 0%
Site search 3.62 352 ms 531 ms 595 ms 0%

Editors in the Wagtail admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Admin dashboard 0.741 72.5 ms 79.3 ms 93 ms 0%
Page explorer 1.5 321 ms 354 ms 457 ms 0%
Page editor 2.22 152 ms 182 ms 287 ms 0%
Image library 0.741 55.8 ms 61.1 ms 503 ms 0%
Admin page search 0.741 30.7 ms 66.6 ms 70.5 ms 0%
4 virtual users
Admin dashboard 1.23 238 ms 461 ms 522 ms 0%
Page explorer 2.52 764 ms 1.12 s 1.19 s 0%
Page editor 3.78 357 ms 659 ms 747 ms 0%
Image library 1.27 209 ms 480 ms 526 ms 0%
Admin page search 1.23 90.6 ms 228 ms 266 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 176 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
San Jose #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 14, 2026, 02:39:17 UTC
Parser version
5

Run timeline

Queued
Oct 14, 2026, 02:37:00 UTC
Server created
Oct 14, 2026, 02:38:25 UTC
First update from the server
Oct 14, 2026, 02:38:25 UTC
Completed
Oct 14, 2026, 04:16:07 UTC
Server deleted
Oct 14, 2026, 04:16:07 UTC
Cost of this run
€0.025 EUR
Watch party 0 watching

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

Watch party

Loading the party