Skip to main content

OneProvider Storage optimized so1.large

Seattle, US

Benchmark complete
Finished Oct 16, 2026
Geekbench 7 single-core
1,025
Faster than 42% of 4 vCPU plans
Geekbench 7 multi-core
3,647
Faster than 65% of 4 vCPU plans
Disk 4K IOPS
20,015
fio random read and write, 50/50
Monthly price at test time
$40.00
91 multi-core points per dollar
Same price today

Server

  • Provider
    OneProvider
  • Plan
    Storage optimized so1.large
  • Location
    Seattle, US
  • vCPU
    4
  • RAM
    8 GB
  • Storage
    1.02 TB
  • Network
    10 Gbps
  • OS image
    1194
  • Trigger
    Scheduled
  • Queued at
    Oct 16, 2026, 09:11:00 UTC
Visit OneProvider

CPU

Version Single-core Multi-core
Geekbench 7 1,025 3,647 Geekbench Browser

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
1,130
126th of 216
3,810
34th of 147
Navigation
994
173rd of 216
Single-core only
HTML5 Browser
1,040
130th of 216
Single-core only
PDF Viewer
1,158
129th of 216
Single-core only
Photo Library
1,164
99th of 216
3,891
39th of 147
Clang
892
161st of 216
3,581
52nd of 147
Text Processing
908
156th of 216
3,614
45th of 147
Asset Compression
989
155th of 216
4,075
50th of 147
HDR
1,018
120th of 216
3,161
47th of 147
Photo Editor
924
156th of 216
3,529
57th of 147
Ray Tracer
898
167th of 216
3,586
55th of 147
Structure from Motion
1,200
128th of 216
Single-core only
Game Physics
1,068
127th of 216
Single-core only
Video Encoder
1,004
134th of 216
Single-core only
Audio Encoder
960
162nd of 216
Single-core only
Video Player
1,133
126th 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 78.2 GB/s 3 5.76%
Scale higher is better 75.6 GB/s 3 22.9%
Add higher is better 75.4 GB/s 3 17.3%
Triad higher is better 76.8 GB/s 3 18.2%

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 1,530/s 3 5.91%
RSA 4096 verifies higher is better 39,058/s 3 9.26%
SHA-256 higher is better 2.21 GB/s 3 2%
AES-256-GCM higher is better 26.4 GB/s 3 4.26%
ChaCha20-Poly1305 higher is better 9.72 GB/s 3 8.44%

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 6.1 ms 3 3.89%
Requests per second, 90th percentile higher is better 550/s 3 1.72%
Request latency, 99.9th percentile lower is better 29.4 ms 3 1.12%
Requests per second, average higher is better 512/s 3 2.82%

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

Disk

Block size Read Write Total
4K 39 MB/s (9,995 IOPS) 39.1 MB/s (10,020 IOPS) 78.2 MB/s (20,015 IOPS)
64K 342.5 MB/s (5,479 IOPS) 344.3 MB/s (5,508 IOPS) 686.8 MB/s (10,987 IOPS)
512K 386 MB/s (772 IOPS) 406.5 MB/s (813 IOPS) 792.6 MB/s (1,585 IOPS)
1M 429.4 MB/s (429 IOPS) 458 MB/s (457 IOPS) 887.3 MB/s (886 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 667 Mbps 1.39 Gbps
Eranium, Amsterdam, NL (100G) IPv4 518 Mbps 1.68 Gbps
Leaseweb, Singapore, SG (10G) IPv4 620 Mbps 1.19 Gbps
Clouvider, Los Angeles, CA, US (10G) IPv4 1.49 Gbps 3.14 Gbps
Leaseweb, NYC, NY, US (10G) IPv4 918 Mbps 3.45 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 957 1.05 ms
fdatasync 896 1.12 ms
fsync 373 2.68 ms
fsync_writethrough Not supported here n/a
open_sync 334 2.99 ms
Two 8 kB writes
open_datasync 431 2.32 ms
fdatasync 818 1.22 ms
fsync 420 2.38 ms
fsync_writethrough Not supported here n/a
open_sync 146 6.83 ms
open_sync at different write sizes
1 * 16kB open_sync write 378 2.64 ms
2 * 8kB open_sync writes 184 5.45 ms
4 * 4kB open_sync writes 88.6 11.3 ms
8 * 2kB open_sync writes 57 17.5 ms
16 * 1kB open_sync writes 26 38.5 ms
fsync on a non-write descriptor
write, fsync, close 444 2.25 ms
write, close, fsync 381 2.63 ms
Non-synced 8 kB writes
write 435,317 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) 1 665 1.22 ms 2.89 ms 5.39 ms 37.4 ms 0
Read/write (TPC-B like) 8 2,272 2.52 ms 7.6 ms 14.6 ms 68.2 ms 0
Read/write (TPC-B like) 32 3,030 6.49 ms 30 ms 62.4 ms 187 ms 0
Read only 1 14,847 0.052 ms 0.083 ms 0.113 ms 0.277 ms 0
Read only 8 70,786 0.075 ms 0.177 ms 0.25 ms 17.1 ms 0
Read only 32 66,781 0.233 ms 0.779 ms 2.8 ms 21.7 ms 0

Scale 10 (1,000,000 accounts), loaded in 2.02 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) 1 532 1.36 ms 2.84 ms 9.06 ms 94 ms 0
Read/write (TPC-B like) 8 1,818 2.7 ms 7.72 ms 57.7 ms 104 ms 0
Read/write (TPC-B like) 32 2,207 6.49 ms 83.5 ms 171 ms 284 ms 0
Read only 1 12,277 0.052 ms 0.088 ms 0.12 ms 0.597 ms 0
Read only 8 51,460 0.098 ms 0.227 ms 0.325 ms 18.1 ms 0
Read only 32 51,888 0.331 ms 0.987 ms 4.12 ms 31.3 ms 0

Scale 100 (10,000,000 accounts), loaded in 32.5 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

Failed: sysbench prepare output didn't parse: sysbench prepare did not fill every table it created

Redis

memtier

Mix Operations/s Hits/s Median p99 p99.9
1:10 set:get 47,370 43,063 1.06 ms 19.1 ms 21 ms
1:1 set:get 45,719 22,859 1.11 ms 18.8 ms 20.6 ms

1,000,000 keys of 32 bytes. 64 connections over 4 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 896 3,279 4,720 550 ms
Express express-postgresjs 11,919 15,875 53,371 58 ms
Fastify fastify-postgres 12,023 16,676 50,867 51.7 ms
NestJS nestjs 6,588 7,170 24,807 85.8 ms
Nuxt nuxt 9,681 14,799 44,782 70.6 ms
FastAPI fastapi 5,456 6,623 25,839 192 ms
Django django-postgresql 1,956 2,075 4,935 273 ms
Rails rails 3,473 4,766 18,750 150 ms
Laravel laravel 1,090 1,207 2,164 307 ms
Symfony symfony 1,414 1,583 4,329 238 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 3.53 457 ms 636 ms 728 ms 0%
Shop page 3.53 553 ms 816 ms 876 ms 0%
Category page 3.53 375 ms 629 ms 777 ms 0%
Product page 3.53 443 ms 612 ms 645 ms 0%
Product search 3.53 357 ms 560 ms 628 ms 0%
32 virtual users
Home page 3.4 1.78 s 2.24 s 2.37 s 0%
Shop page 3.4 2.34 s 2.81 s 2.98 s 0%
Category page 3.4 1.85 s 2.45 s 2.75 s 0%
Product page 3.4 1.7 s 2.21 s 2.37 s 0%
Product search 3.4 1.5 s 1.91 s 2.08 s 0%

Cart and checkout

Step Requests/s Median p95 p99 Error rate
8 virtual users
Add to cart 6.89 467 ms 644 ms 729 ms 0%
Cart 6.89 385 ms 559 ms 621 ms 0%
Checkout 6.89 290 ms 438 ms 495 ms 0%
32 virtual users
Add to cart 6.75 1.74 s 2.24 s 2.38 s 0%
Cart 6.75 1.59 s 2.01 s 2.21 s 0%
Checkout 6.75 1.35 s 1.71 s 1.79 s 0%

k6 with a fixed number of virtual users, 61 to 66 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 2.05 215 ms 324 ms 536 ms 0%
Topic JSON 1.02 112 ms 136 ms 243 ms 0%
Home page 1.02 197 ms 242 ms 426 ms 0%
Categories page 0.512 224 ms 275 ms 308 ms 0%
User activity page 0.512 130 ms 158 ms 288 ms 0%
4 virtual users
Topic page 6.07 289 ms 424 ms 672 ms 0%
Topic JSON 3.04 148 ms 189 ms 211 ms 0%
Home page 3.06 263 ms 350 ms 644 ms 0%
Categories page 1.54 302 ms 442 ms 642 ms 0%
User activity page 1.51 181 ms 387 ms 450 ms 0%
16 virtual users
Topic page 5.42 1.19 s 1.82 s 2.25 s 0%
Topic JSON 2.73 897 ms 1.23 s 1.38 s 0%
Home page 2.71 1.11 s 1.5 s 2.43 s 0%
Categories page 1.38 1.22 s 1.7 s 2.08 s 0%
User activity page 1.33 1.02 s 1.29 s 1.51 s 0%

Anonymous

Step Requests/s Median p95 p99 Error rate
16 virtual users
Topic page 105 36.9 ms 79.8 ms 107 ms 0%
Topic JSON 52.6 34.7 ms 78.1 ms 111 ms 0%
Home page 52.6 37.7 ms 80.6 ms 115 ms 0%
Categories page 26.3 36.9 ms 78.6 ms 116 ms 0%
User activity page 26.3 226 ms 343 ms 467 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 8 app workers and 2048 MB of Postgres shared buffers, what its installer picks for a 8 GB box. Its installer adds no swap on a box this big. The container peaked at 2,636 MB.

Ghost

Readers

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 7.57 37 ms 50 ms 53.8 ms 0%
Post page 18.9 19.5 ms 31 ms 35.9 ms 0%
Tag page 3.78 24.3 ms 36.5 ms 44.9 ms 0%
Author page 3.78 24.2 ms 37.6 ms 40.5 ms 0%
RSS feed 3.78 29.6 ms 43 ms 45.3 ms 0%
4 virtual users
Home page 8.88 115 ms 165 ms 182 ms 0%
Post page 22.2 85.1 ms 124 ms 141 ms 0%
Tag page 4.45 76 ms 103 ms 122 ms 0%
Author page 4.46 77.2 ms 104 ms 120 ms 0%
RSS feed 4.41 84.3 ms 119 ms 139 ms 0%
16 virtual users
Home page 8.8 455 ms 570 ms 605 ms 0%
Post page 22.1 384 ms 485 ms 524 ms 0%
Tag page 4.42 255 ms 328 ms 365 ms 0%
Author page 4.45 252 ms 336 ms 369 ms 0%
RSS feed 4.39 261 ms 327 ms 353 ms 0%

Staff in Ghost Admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Post list 3.9 33.5 ms 42.8 ms 49.6 ms 0%
Post editor 11.7 13.3 ms 18.3 ms 21.3 ms 0%
Saving a draft 11.7 40.8 ms 57.6 ms 131 ms 0%
Member list 3.9 39 ms 51.1 ms 58 ms 0%
4 virtual users
Post list 4.65 46.8 ms 66.9 ms 73.6 ms 0%
Post editor 14 18.7 ms 37.8 ms 43.2 ms 0%
Saving a draft 14 220 ms 287 ms 381 ms 0%
Member list 4.66 51.8 ms 74.5 ms 79.6 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 522 MB and MySQL at 625 MB.

Wagtail

Visitors

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 1.43 90.9 ms 118 ms 126 ms 0%
Blog index 1.43 321 ms 390 ms 416 ms 0%
Blog post 4.25 30 ms 43.3 ms 52.3 ms 0%
Bread page 4.26 32.7 ms 42.8 ms 47.8 ms 0%
Location page 1.43 32 ms 40.2 ms 42 ms 0%
Site search 1.41 56.5 ms 108 ms 187 ms 0%
4 virtual users
Home page 2.7 204 ms 341 ms 366 ms 0%
Blog index 2.74 708 ms 1.1 s 1.17 s 0%
Blog post 8.12 55.1 ms 100 ms 124 ms 0%
Bread page 8.12 61.4 ms 102 ms 129 ms 0%
Location page 2.74 60.5 ms 100 ms 116 ms 0%
Site search 2.72 89.6 ms 195 ms 233 ms 0%
16 virtual users
Home page 2.9 633 ms 853 ms 942 ms 0%
Blog index 3 1.73 s 2.07 s 2.24 s 0%
Blog post 8.73 350 ms 556 ms 687 ms 0%
Bread page 8.8 375 ms 585 ms 663 ms 0%
Location page 2.95 367 ms 594 ms 701 ms 0%
Site search 2.9 416 ms 644 ms 729 ms 0%

Editors in the Wagtail admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Admin dashboard 0.563 98.6 ms 114 ms 122 ms 0%
Page explorer 1.16 429 ms 515 ms 580 ms 0%
Page editor 1.72 197 ms 279 ms 407 ms 0%
Image library 0.579 70 ms 90 ms 607 ms 0%
Admin page search 0.563 43.6 ms 90 ms 94.6 ms 0%
4 virtual users
Admin dashboard 1.04 258 ms 524 ms 610 ms 0%
Page explorer 2.11 799 ms 1.48 s 2.67 s 0%
Page editor 3.19 397 ms 778 ms 970 ms 0%
Image library 1.06 280 ms 480 ms 591 ms 0%
Admin page search 1.06 112 ms 351 ms 448 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. 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 297 MB, Postgres at 151 MB, and Redis at 26 MB.

Advertised vs. measured

Advertised Measured
vCPU 4 4
CPU Shared vCPU 17.1% of busy CPU time stolen
RAM 8 GB 7.8 GiB
Storage 1.02 TB 999.9 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 9354 32-Core Processor
CPU cores
4
CPU frequency
3245 MHz
AES-NI
Yes
VM-x/AMD-V
Yes
RAM reported
7.8 GiB
Swap reported
8 GiB
Disk reported
999.9 GiB
Virtualization reported
KVM
CPU steal
17.1% of busy CPU time stolen
Distro
Ubuntu 24.04.3 LTS
Kernel
6.8.0-79-generic
Architecture
x86_64
IPv4 reachable
Yes
IPv6 reachable
No

Advertised at test time

Plan
Storage optimized so1.large
Product line
Storage optimized
Location
Seattle, US
vCPU
4 shared vCPU
Architecture
x86_64
RAM
8 GB
Storage
1.02 TB
Virtualization
KVM
Network
10 Gbps
Transfer
Unknown
Port 25
Unknown
Monthly price at test time
$40.00
Hourly price at test time
$0.056
YABS version
v2026-09-20
Ran at
Oct 16, 2026, 09:14:44 UTC
Parser version
5

Run timeline

Queued
Oct 16, 2026, 09:11:00 UTC
Server created
Oct 16, 2026, 09:14:40 UTC
First update from the server
Oct 16, 2026, 09:14:40 UTC
Completed
Oct 16, 2026, 10:47:49 UTC
Server deleted
Oct 16, 2026, 10:47:49 UTC
Cost of this run
$0.090
TestResultTime
Watch party 0 watching

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

Watch party

Loading the party