Skip to main content

Cherry Servers Performance VDS 2

Chicago, US

Benchmark complete
Finished Oct 17, 2026
Geekbench 7 single-core
2,195
Faster than 95% of 2 vCPU plans
Geekbench 7 multi-core
5,207
Faster than 100% of 2 vCPU plans
Disk 4K IOPS
100,881
fio random read and write, 50/50
Monthly price at test time
$104.13
50 multi-core points per dollar
Same price today

Server

  • Provider
    Cherry Servers
  • Plan
    Performance VDS 2
  • Location
    Chicago, US
  • vCPU
    2
  • RAM
    16 GB
  • Storage
    200 GB NVMe
  • Network
    3 Gbps
  • OS image
    ubuntu_24_04_64bit
  • Trigger
    Scheduled
  • Queued at
    Oct 17, 2026, 06:24:00 UTC
Visit Cherry Servers

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

CPU

Version Single-core Multi-core
Geekbench 7 2,195 5,207 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
2,189
7th of 216
5,082
17th of 147
Navigation
2,411
2nd of 216
Single-core only
HTML5 Browser
2,176
8th of 216
Single-core only
PDF Viewer
2,203
10th of 216
Single-core only
Photo Library
2,197
6th of 216
5,623
20th of 147
Clang
2,095
3rd of 216
5,546
22nd of 147
Text Processing
2,061
7th of 216
4,946
25th of 147
Asset Compression
2,158
10th of 216
5,487
28th of 147
HDR
2,146
9th of 216
4,079
26th of 147
Photo Editor
2,491
14th of 216
4,865
27th of 147
Ray Tracer
2,197
3rd of 216
6,335
24th of 147
Structure from Motion
2,202
10th of 216
Single-core only
Game Physics
2,123
7th of 216
Single-core only
Video Encoder
2,134
8th of 216
Single-core only
Audio Encoder
2,113
9th of 216
Single-core only
Video Player
2,260
12th 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 41 GB/s 3 1.46%
Scale higher is better 30.2 GB/s 3 0.942%
Add higher is better 27.7 GB/s 3 0.346%
Triad higher is better 27.9 GB/s 3 0.964%

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 1,743/s 3 0.602%
RSA 4096 verifies higher is better 42,277/s 3 0.814%
SHA-256 higher is better 3.85 GB/s 3 0.0423%
AES-256-GCM higher is better 25.3 GB/s 3 0.0398%
ChaCha20-Poly1305 higher is better 10.7 GB/s 3 0.0315%

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 7 ms 3 0.229%
Requests per second, 90th percentile higher is better 570/s 3 0.203%
Request latency, 99.9th percentile lower is better 11.3 ms 3 1.34%
Requests per second, average higher is better 563/s 3 0.601%

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

Disk

Block size Read Write Total
4K 196.8 MB/s (50,374 IOPS) 197.3 MB/s (50,507 IOPS) 394.1 MB/s (100,881 IOPS)
64K 286.8 MB/s (4,588 IOPS) 288.3 MB/s (4,612 IOPS) 575 MB/s (9,200 IOPS)
512K 463.1 MB/s (926 IOPS) 487.7 MB/s (975 IOPS) 950.8 MB/s (1,901 IOPS)
1M 466.6 MB/s (466 IOPS) 497.6 MB/s (497 IOPS) 964.2 MB/s (963 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 1.28 Gbps 474 Mbps
Eranium, Amsterdam, NL (100G) IPv4 1.31 Gbps 2.21 Gbps
Leaseweb, Singapore, SG (10G) IPv4 878 Mbps 1.07 Gbps
Clouvider, Los Angeles, CA, US (10G) IPv4 1.38 Gbps 283 Mbps
Leaseweb, NYC, NY, US (10G) IPv4 1.42 Gbps 2.76 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 9,330 0.107 ms
fdatasync 9,074 0.11 ms
fsync 7,703 0.13 ms
fsync_writethrough Not supported here n/a
open_sync 8,069 0.124 ms
Two 8 kB writes
open_datasync 5,108 0.196 ms
fdatasync 9,148 0.109 ms
fsync 7,570 0.132 ms
fsync_writethrough Not supported here n/a
open_sync 4,380 0.228 ms
open_sync at different write sizes
1 * 16kB open_sync write 8,208 0.122 ms
2 * 8kB open_sync writes 4,291 0.233 ms
4 * 4kB open_sync writes 2,245 0.445 ms
8 * 2kB open_sync writes 1,124 0.889 ms
16 * 1kB open_sync writes 565 1.77 ms
fsync on a non-write descriptor
write, fsync, close 7,555 0.132 ms
write, close, fsync 7,805 0.128 ms
Non-synced 8 kB writes
write 991,549 0.001 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 3,193 0.301 ms 0.341 ms 0.363 ms 1.87 ms 0
Read/write (TPC-B like) 8 9,413 0.768 ms 1.34 ms 1.82 ms 3.04 ms 0
Read/write (TPC-B like) 32 10,458 2.3 ms 7.17 ms 12.4 ms 65.7 ms 0
Read only 1 44,980 0.023 ms 0.028 ms 0.035 ms 0.043 ms 0
Read only 8 133,622 0.055 ms 0.094 ms 0.113 ms 0.141 ms 0
Read only 32 144,840 0.188 ms 0.296 ms 0.366 ms 0.496 ms 0

Scale 10 (1,000,000 accounts), loaded in 1.18 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 2,863 0.331 ms 0.393 ms 0.49 ms 5.24 ms 0
Read/write (TPC-B like) 8 8,814 0.795 ms 1.1 ms 1.83 ms 24 ms 0
Read/write (TPC-B like) 32 11,978 2.22 ms 3.79 ms 13.4 ms 41.5 ms 0
Read only 1 37,573 0.024 ms 0.035 ms 0.044 ms 0.063 ms 0
Read only 8 105,781 0.07 ms 0.12 ms 0.144 ms 0.193 ms 0
Read only 32 113,774 0.249 ms 0.379 ms 0.464 ms 0.746 ms 0

Scale 100 (10,000,000 accounts), loaded in 13.1 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 1 650 12,994 1.39 ms 1.76 ms 6.55 ms 0
Read/write 8 1,533 30,662 4.91 ms 8.43 ms 12.8 ms 0
Read/write 32 2,287 45,745 13.2 ms 22.3 ms 30.8 ms 0
Read only 1 1,577 25,236 0.619 ms 0.741 ms 0.841 ms 0
Read only 8 4,233 67,735 1.86 ms 2.81 ms 3.13 ms 0
Read only 32 4,012 64,187 7.99 ms 10.3 ms 11.2 ms 0

10 tables of 100,000 rows, loaded in 4 s. 60 s per run, one connection per thread.

Redis

memtier

Mix Operations/s Hits/s Median p99 p99.9
1:10 set:get 96,582 87,802 0.655 ms 1.28 ms 1.36 ms
1:1 set:get 96,302 48,151 0.663 ms 1.28 ms 1.35 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 1,770 6,024 8,812 245 ms
Express express-postgresjs 14,933 22,210 90,878 39.7 ms
Fastify fastify-postgres 14,794 22,751 90,866 34 ms
NestJS nestjs 11,837 13,250 44,633 42.8 ms
Nuxt nuxt 13,789 21,138 80,198 42.4 ms
FastAPI fastapi 8,942 11,418 40,490 207 ms
Django django-postgresql 3,543 4,013 8,466 247 ms
Rails rails 5,688 7,880 32,693 124 ms
Laravel laravel 2,066 2,206 4,131 131 ms
Symfony symfony 2,590 2,839 7,653 105 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 5.78 283 ms 369 ms 382 ms 0%
Shop page 5.78 365 ms 496 ms 540 ms 0%
Category page 5.78 244 ms 391 ms 430 ms 0%
Product page 5.78 262 ms 359 ms 384 ms 0%
Product search 5.78 229 ms 317 ms 347 ms 0%
32 virtual users
Home page 5.56 1.11 s 1.27 s 1.36 s 0%
Shop page 5.56 1.39 s 1.59 s 1.74 s 0%
Category page 5.56 1.11 s 1.42 s 1.51 s 0%
Product page 5.56 1.08 s 1.24 s 1.3 s 0%
Product search 5.56 986 ms 1.11 s 1.16 s 0%

Cart and checkout

Step Requests/s Median p95 p99 Error rate
8 virtual users
Add to cart 11.1 294 ms 392 ms 420 ms 0%
Cart 11.1 241 ms 332 ms 358 ms 0%
Checkout 11.1 193 ms 264 ms 295 ms 0%
32 virtual users
Add to cart 10.7 1.11 s 1.3 s 1.36 s 0%
Cart 10.7 1.03 s 1.21 s 1.28 s 0%
Checkout 10.7 864 ms 1.02 s 1.07 s 0%

k6 with a fixed number of virtual users, 61 to 63 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 4.33 102 ms 115 ms 174 ms 0%
Topic JSON 2.18 52.6 ms 61.5 ms 135 ms 0%
Home page 2.18 92.3 ms 110 ms 263 ms 0%
Categories page 1.1 106 ms 205 ms 270 ms 0%
User activity page 1.08 65 ms 85.5 ms 192 ms 0%
4 virtual users
Topic page 10.9 161 ms 208 ms 408 ms 0%
Topic JSON 5.44 82.9 ms 103 ms 179 ms 0%
Home page 5.43 146 ms 190 ms 376 ms 0%
Categories page 2.74 169 ms 269 ms 457 ms 0%
User activity page 2.72 102 ms 136 ms 224 ms 0%
16 virtual users
Topic page 10.2 662 ms 861 ms 1.14 s 0%
Topic JSON 5.12 486 ms 651 ms 812 ms 0%
Home page 5.1 620 ms 809 ms 959 ms 0%
Categories page 2.54 657 ms 916 ms 1.47 s 0%
User activity page 2.57 519 ms 718 ms 999 ms 0%

Anonymous

Step Requests/s Median p95 p99 Error rate
16 virtual users
Topic page 221 17.3 ms 37.8 ms 55.2 ms 0%
Topic JSON 110 16.2 ms 35.6 ms 53.8 ms 0%
Home page 110 17.5 ms 38.5 ms 57.3 ms 0%
Categories page 55.2 16.9 ms 36.7 ms 55 ms 0%
User activity page 55.2 107 ms 159 ms 272 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 8 app workers and 4096 MB of Postgres shared buffers, what its installer picks for a 16 GB box. Its installer adds no swap on a box this big. The container peaked at 2,747 MB.

Ghost

Readers

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 18.2 15.8 ms 17.1 ms 19.3 ms 0%
Post page 45.6 8.18 ms 9.28 ms 12.1 ms 0%
Tag page 9.11 10.8 ms 12 ms 14.3 ms 0%
Author page 9.11 10.9 ms 12 ms 15 ms 0%
RSS feed 9.11 12.5 ms 15.5 ms 20 ms 0%
4 virtual users
Home page 21.4 49.2 ms 59.6 ms 65.6 ms 0%
Post page 53.5 34.6 ms 46.7 ms 52.5 ms 0%
Tag page 10.7 31.6 ms 41.6 ms 46.5 ms 0%
Author page 10.7 31.5 ms 41.2 ms 44.1 ms 0%
RSS feed 10.7 36.1 ms 48.5 ms 53.9 ms 0%
16 virtual users
Home page 21.1 194 ms 224 ms 238 ms 0%
Post page 52.6 161 ms 189 ms 201 ms 0%
Tag page 10.5 107 ms 131 ms 142 ms 0%
Author page 10.5 106 ms 132 ms 147 ms 0%
RSS feed 10.5 111 ms 136 ms 146 ms 0%

Staff in Ghost Admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Post list 9.55 16.4 ms 18.7 ms 23.1 ms 0%
Post editor 28.7 6.06 ms 7.55 ms 10.2 ms 0%
Saving a draft 28.7 15.4 ms 18.2 ms 22.1 ms 0%
Member list 9.56 18.2 ms 21.2 ms 25.4 ms 0%
4 virtual users
Post list 11.4 23.4 ms 27.3 ms 30.2 ms 0%
Post editor 34.2 11.8 ms 14.5 ms 16 ms 0%
Saving a draft 34.2 84.9 ms 108 ms 116 ms 0%
Member list 11.4 24.6 ms 28 ms 29.8 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 557 MB and MySQL at 625 MB.

Wagtail

Visitors

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 3.1 42.8 ms 45.4 ms 46.9 ms 0%
Blog index 3.1 144 ms 162 ms 163 ms 0%
Blog post 9.29 13.8 ms 21.2 ms 23 ms 0%
Bread page 9.29 15.2 ms 16.6 ms 17.3 ms 0%
Location page 3.1 14.5 ms 15.8 ms 16.6 ms 0%
Site search 3.1 23 ms 39.3 ms 40.7 ms 0%
4 virtual users
Home page 5.07 107 ms 152 ms 218 ms 0%
Blog index 5.11 403 ms 526 ms 547 ms 0%
Blog post 15.3 31.1 ms 52.6 ms 68.2 ms 0%
Bread page 15.3 33 ms 51.2 ms 58.7 ms 0%
Location page 5.11 34 ms 48.6 ms 52.2 ms 0%
Site search 5.09 49.4 ms 105 ms 122 ms 0%
16 virtual users
Home page 5.4 343 ms 437 ms 510 ms 0%
Blog index 5.44 931 ms 1.11 s 1.18 s 0%
Blog post 16.2 194 ms 303 ms 346 ms 0%
Bread page 16.2 197 ms 302 ms 350 ms 0%
Location page 5.43 190 ms 288 ms 338 ms 0%
Site search 5.4 225 ms 326 ms 382 ms 0%

Editors in the Wagtail admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Admin dashboard 1.29 44.7 ms 48.2 ms 87.1 ms 0%
Page explorer 2.62 185 ms 191 ms 282 ms 0%
Page editor 3.93 86.7 ms 95.6 ms 171 ms 0%
Image library 1.31 34.7 ms 36.9 ms 173 ms 0%
Admin page search 1.29 18.6 ms 40.1 ms 60.2 ms 0%
4 virtual users
Admin dashboard 2.02 163 ms 342 ms 374 ms 0%
Page explorer 4.07 430 ms 674 ms 766 ms 0%
Page editor 6.1 240 ms 431 ms 509 ms 0%
Image library 2.03 127 ms 304 ms 352 ms 0%
Admin page search 2.02 52.9 ms 197 ms 228 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 306 MB, Postgres at 148 MB, and Redis at 8 MB.

Advertised vs. measured

Advertised Measured
vCPU 2 4
CPU Dedicated vCPU 0.1% of busy CPU time stolen
RAM 16 GB 15.6 GiB
Storage 200 GB NVMe 193.7 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-Milan Processor
CPU cores
4
CPU frequency
4492 MHz
AES-NI
Yes
VM-x/AMD-V
No
RAM reported
15.6 GiB
Swap reported
0 MiB
Disk reported
193.7 GiB
Virtualization reported
KVM
CPU steal
0.1% of busy CPU time stolen
Distro
Ubuntu 24.04.5 LTS
Kernel
6.8.0-142-generic
Architecture
x86_64
IPv4 reachable
Yes
IPv6 reachable
No

Advertised at test time

Plan
Performance VDS 2
Product line
Performance VDS
Location
Chicago, US
vCPU
2 dedicated vCPU
Architecture
x86_64
RAM
16 GB
Storage
200 GB NVMe
Virtualization
KVM
Network
3 Gbps
Transfer
10 TB
Port 25
Unknown
Monthly price at test time
$104.13
Hourly price at test time
$0.18
YABS version
v2026-09-20
Ran at
Oct 17, 2026, 09:25:14 UTC
Parser version
5

Run timeline

Queued
Oct 17, 2026, 06:24:00 UTC
First update from the server
Oct 17, 2026, 06:25:09 UTC
Completed
Oct 17, 2026, 07:53:37 UTC
Server deleted
Oct 17, 2026, 07:53:37 UTC
Cost of this run
$0.27
Watch party 0 watching

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

Watch party

Loading the party