Cherry Servers Cloud ARM VDS 1

Lithuania

Benchmark complete

Finished Oct 12, 2026

Geekbench 7 single-core

810

Geekbench 7 multi-core

801

Disk 4K IOPS

45,511

fio random read and write, 50/50

Monthly price at test time

$22.23

36 multi-core points per dollar

Same price today

Server

Cherry Servers Cloud ARM VDS 1

Provider

Cherry Servers
Plan

Cloud ARM VDS 1
Location

Lithuania
vCPU

1
RAM

6 GB
Storage

25 GB NVMe
Network

1 Gbps
OS image

ubuntu_24_04_64bit
Trigger

Scheduled
Queued at

Oct 12, 2026, 01:09:00 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	Result link
Geekbench 7	810	801	Geekbench Browser

Scores from different Geekbench versions aren't comparable with each other. Charts only use Geekbench 7.

Memory, TLS and scheduler

Memory bandwidth (STREAM)

Test	Result	Runs	Spread
Copy higher is better	9.29 GB/s	3	0.502%
Scale higher is better	7.78 GB/s	3	0.469%
Add higher is better	8.91 GB/s	3	0.601%
Triad higher is better	8.64 GB/s	3	0.28%

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	162/s	3	0.107%
RSA 4096 verifies higher is better	11,313/s	3	0.215%
SHA-256 higher is better	871 MB/s	3	1.57%
AES-256-GCM higher is better	2.72 GB/s	3	0.092%
ChaCha20-Poly1305 higher is better	1.05 GB/s	3	0.0724%

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	5.1 ms	3	0%
Requests per second, 90th percentile higher is better	194/s	3	0.297%
Request latency, 99.9th percentile lower is better	9.56 ms	3	1.02%
Requests per second, average higher is better	194/s	3	0.0621%

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

Disk

Block size	Read	Write	Total
4K	88.9 MB/s (22,763 IOPS)	88.9 MB/s (22,748 IOPS)	177.8 MB/s (45,511 IOPS)
64K	536.7 MB/s (8,587 IOPS)	552.7 MB/s (8,842 IOPS)	1.06 GB/s (17,429 IOPS)
512K	507.8 MB/s (1,015 IOPS)	551.2 MB/s (1,102 IOPS)	1.03 GB/s (2,117 IOPS)
1M	494.4 MB/s (494 IOPS)	551.6 MB/s (551 IOPS)	1.02 GB/s (1,045 IOPS)

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

Network

IPv4 transfer speed

Target	Protocol	Send	Receive
Clouvider, London, UK (10G)	IPv4	1.06 Gbps	937 Mbps
Eranium, Amsterdam, NL (100G)	IPv4	1.05 Gbps	938 Mbps
Leaseweb, Singapore, SG (10G)	IPv4	584 Mbps	767 Mbps
Clouvider, Los Angeles, CA, US (10G)	IPv4	934 Mbps	70.3 Mbps
Leaseweb, NYC, NY, US (10G)	IPv4	1.01 Gbps	878 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	6,279	0.159 ms
fdatasync	6,128	0.163 ms
fsync	4,697	0.213 ms
fsync_writethrough	Not supported here	n/a
open_sync	4,945	0.202 ms
Two 8 kB writes
open_datasync	3,287	0.304 ms
fdatasync	5,829	0.172 ms
fsync	4,331	0.231 ms
fsync_writethrough	Not supported here	n/a
open_sync	2,458	0.407 ms
open_sync at different write sizes
1 * 16kB open_sync write	4,705	0.213 ms
2 * 8kB open_sync writes	2,578	0.388 ms
4 * 4kB open_sync writes	1,305	0.767 ms
8 * 2kB open_sync writes	670	1.49 ms
16 * 1kB open_sync writes	344	2.91 ms
fsync on a non-write descriptor
write, fsync, close	4,456	0.224 ms
write, close, fsync	4,528	0.221 ms
Non-synced 8 kB writes
write	868,275	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
Read/write (TPC-B like)	1	1,846	0.509 ms	0.623 ms	1.32 ms	3.19 ms
Read/write (TPC-B like)	8	1,691	4.38 ms	6.98 ms	8.76 ms	14.4 ms
Read/write (TPC-B like)	32	1,306	20.6 ms	50.8 ms	82.1 ms	131 ms
Read only	1	22,083	0.04 ms	0.072 ms	0.092 ms	0.323 ms
Read only	8	14,904	0.544 ms	0.783 ms	0.996 ms	1.87 ms
Read only	32	13,035	2.25 ms	3.21 ms	4.48 ms	5.62 ms

Scale 10 (1,000,000 accounts), loaded in 1.97 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
Read/write (TPC-B like)	1	1,590	0.587 ms	0.728 ms	1.73 ms	6.13 ms
Read/write (TPC-B like)	8	1,541	4.99 ms	6.93 ms	10 ms	15.9 ms
Read/write (TPC-B like)	32	1,433	21.3 ms	29.8 ms	39.6 ms	85.3 ms
Read only	1	15,416	0.054 ms	0.106 ms	0.154 ms	1.29 ms
Read only	8	11,382	0.673 ms	1.02 ms	1.75 ms	2.47 ms
Read only	32	10,053	2.92 ms	5.07 ms	6.24 ms	8.66 ms

Scale 100 (10,000,000 accounts), loaded in 22.4 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
Read/write	1	246	4,926	3.62 ms	7.99 ms	11.9 ms
Read/write	8	251	5,026	28.7 ms	55.8 ms	80 ms
Read/write	32	280	5,595	105 ms	197 ms	267 ms
Read only	1	775	12,406	1.23 ms	1.52 ms	2.43 ms
Read only	8	645	10,320	12.3 ms	14.7 ms	18.3 ms
Read only	32	557	8,906	56.8 ms	68.1 ms	74.5 ms

10 tables of 100,000 rows, loaded in 17.3 s. 60 s per run, one connection per thread.

Redis

memtier

Mix	Operations/s	Hits/s	Median	p99	p99.9
1:10 set:get	36,616	33,287	1.69 ms	3.23 ms	5.34 ms
1:1 set:get	35,959	17,979	1.71 ms	3.28 ms	5.7 ms

1,000,000 keys of 32 bytes. 64 connections over 1 thread, 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	215	688	959	4.45 s
Express express-postgresjs	2,304	4,022	12,902	4.59 s
Fastify fastify-postgres	2,286	4,118	14,497	4.63 s
NestJS nestjs	1,616	1,657	7,866	317 ms
Nuxt nuxt	2,026	3,827	11,037	5.46 s
FastAPI fastapi	1,269	1,572	8,994	809 ms
Django django-postgresql	699	757	2,172	426 ms
Rails rails	895	1,261	6,160	308 ms
Laravel laravel	260	275	493	1.01 s
Symfony symfony	327	352	1,012	840 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	0.758	1.97 s	2.22 s	2.51 s	0%
Shop page	0.758	2.51 s	2.91 s	2.99 s	0%
Category page	0.758	2.07 s	2.69 s	2.85 s	0%
Product page	0.758	1.98 s	2.14 s	2.19 s	0%
Product search	0.758	1.77 s	1.98 s	2.06 s	0%
32 virtual users
Home page	0.903	6.94 s	7.88 s	8.05 s	0%
Shop page	0.903	9.06 s	10.5 s	10.6 s	0%
Category page	0.903	8.76 s	10.1 s	10.1 s	0%
Product page	0.649	7.81 s	8.19 s	8.23 s	0%
Product search	0.452	7.48 s	7.93 s	8.05 s	0%

Cart and checkout

Step	Requests/s	Median	p95	p99	Error rate
8 virtual users
Add to cart	1.39	1.98 s	2.27 s	2.33 s	0%
Cart	1.39	1.82 s	2.08 s	2.16 s	0%
Checkout	1.39	1.47 s	1.72 s	1.86 s	0%
32 virtual users
Add to cart	1.54	6.72 s	8.51 s	8.95 s	0%
Cart	1.52	7.7 s	8.47 s	8.83 s	0%
Checkout	1.37	6.05 s	7.11 s	7.22 s	0%

k6 with a fixed number of virtual users, 63 to 71 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	1.14	360 ms	534 ms	1.17 s	0%
Topic JSON	0.587	186 ms	233 ms	269 ms	0%
Home page	0.587	314 ms	522 ms	900 ms	0%
Categories page	0.294	375 ms	648 ms	979 ms	0%
User activity page	0.277	226 ms	335 ms	535 ms	0%
4 virtual users
Topic page	0.837	1.94 s	2.81 s	3.45 s	0%
Topic JSON	0.435	1.56 s	1.78 s	1.98 s	0%
Home page	0.419	1.84 s	2.84 s	3.35 s	0%
Categories page	0.242	1.87 s	2.36 s	2.48 s	0%
User activity page	0.193	1.55 s	2.04 s	2.36 s	0%
16 virtual users
Topic page	0.832	2.02 s	2.67 s	3.23 s	0%
Topic JSON	0.4	1.64 s	2.21 s	2.67 s	0%
Home page	0.4	1.95 s	2.23 s	2.38 s	0%
Categories page	0.192	2.06 s	3.17 s	3.71 s	0%
User activity page	0.24	1.63 s	1.97 s	2.05 s	0%

Anonymous

Step	Requests/s	Median	p95	p99	Error rate
16 virtual users
Topic page	17.4	328 ms	607 ms	769 ms	0.855%
Topic JSON	8.75	304 ms	602 ms	713 ms	0.567%
Home page	8.74	351 ms	633 ms	807 ms	0%
Categories page	4.37	334 ms	651 ms	912 ms	0.758%
User activity page	4.34	570 ms	937 ms	1.19 s	0.763%

k6 with a fixed number of virtual users, 60 to 63 s per level, after a 24 s warmup. The error rate counts responses that weren't a 200. Discourse ran with 2 app workers and 1536 MB of Postgres shared buffers, what its installer picks for a 6 GB box. Its installer adds no swap on a box this big. The container peaked at 1,757 MB.

Ghost

Readers

Step	Requests/s	Median	p95	p99	Error rate
1 virtual user
Home page	4.28	64.3 ms	86.7 ms	113 ms	0%
Post page	10.7	35.6 ms	51.6 ms	68.5 ms	0%
Tag page	2.15	41.3 ms	54.3 ms	89.6 ms	0%
Author page	2.13	46.4 ms	59.8 ms	92.1 ms	0%
RSS feed	2.13	49.2 ms	62 ms	67.2 ms	0%
4 virtual users
Home page	4.65	235 ms	285 ms	338 ms	0%
Post page	11.6	159 ms	206 ms	237 ms	0%
Tag page	2.33	143 ms	186 ms	205 ms	0%
Author page	2.33	149 ms	196 ms	212 ms	0%
RSS feed	2.33	157 ms	193 ms	207 ms	0%
16 virtual users
Home page	4.44	908 ms	1.07 s	1.22 s	0%
Post page	11.1	759 ms	911 ms	1.06 s	0%
Tag page	2.23	488 ms	585 ms	730 ms	0%
Author page	2.23	491 ms	576 ms	637 ms	0%
RSS feed	2.2	503 ms	590 ms	615 ms	0%

Staff in Ghost Admin

Step	Requests/s	Median	p95	p99	Error rate
1 virtual user
Post list	2.16	62 ms	98.7 ms	117 ms	0%
Post editor	6.49	29.7 ms	43.1 ms	54.1 ms	0%
Saving a draft	6.47	65.8 ms	87.5 ms	116 ms	0%
Member list	2.16	72.6 ms	110 ms	160 ms	0%
4 virtual users
Post list	2.29	98.2 ms	119 ms	143 ms	0%
Post editor	6.91	60.2 ms	77.7 ms	90.7 ms	0%
Saving a draft	6.94	441 ms	518 ms	549 ms	0%
Member list	2.3	120 ms	138 ms	149 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. 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 614 MB and MySQL at 612 MB.

Wagtail

Visitors

Step	Requests/s	Median	p95	p99	Error rate
1 virtual user
Home page	1.26	103 ms	111 ms	115 ms	0%
Blog index	1.25	363 ms	373 ms	417 ms	0%
Blog post	3.76	33.9 ms	50.6 ms	53.7 ms	0%
Bread page	3.76	37.2 ms	42.1 ms	44.7 ms	0%
Location page	1.26	35.1 ms	40.8 ms	42.3 ms	0%
Site search	1.25	57.9 ms	95.9 ms	101 ms	0%
4 virtual users
Home page	1.05	519 ms	635 ms	650 ms	0%
Blog index	1.09	1.79 s	1.98 s	2.19 s	0%
Blog post	3.16	147 ms	238 ms	299 ms	0%
Bread page	3.21	164 ms	201 ms	218 ms	0%
Location page	1.1	154 ms	179 ms	205 ms	0%
Site search	1.04	229 ms	449 ms	503 ms	0%
16 virtual users
Home page	1.04	1.84 s	2.5 s	3.36 s	0%
Blog index	1.02	4.62 s	5.69 s	6.29 s	0%
Blog post	2.96	984 ms	1.94 s	2.25 s	0%
Bread page	2.96	1.02 s	1.76 s	2.41 s	0%
Location page	0.961	956 ms	1.61 s	2.24 s	0%
Site search	1.01	1.15 s	1.96 s	2.56 s	0%

Editors in the Wagtail admin

Step	Requests/s	Median	p95	p99	Error rate
1 virtual user
Admin dashboard	0.579	107 ms	123 ms	144 ms	0%
Page explorer	1.17	386 ms	400 ms	641 ms	0%
Page editor	1.75	192 ms	237 ms	333 ms	0%
Image library	0.579	78.2 ms	168 ms	806 ms	0%
Admin page search	0.579	67.6 ms	93.2 ms	323 ms	0%
4 virtual users
Admin dashboard	0.46	632 ms	828 ms	1.31 s	0%
Page explorer	0.986	2.01 s	2.52 s	2.75 s	0%
Page editor	1.43	932 ms	1.24 s	1.79 s	0%
Image library	0.476	556 ms	762 ms	1.26 s	0%
Admin page search	0.46	194 ms	372 ms	454 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. 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 289 MB, Postgres at 150 MB, and Redis at 9 MB.

Advertised vs. measured

Spec	Advertised	Measured
vCPU	1	1
CPU	Dedicated vCPU	0.1% of busy CPU time stolen
RAM	6 GB	5.8 GiB
Storage	25 GB NVMe	24.1 GiB
Architecture	arm64	arm64
Virtualization	KVM	KVM

Guests usually report slightly less RAM and disk than advertised because of kernel reservations and filesystem overhead.

Detected hardware

CPU model: Ampere-1a
CPU cores: 1
CPU frequency: Unknown
AES-NI: Yes
VM-x/AMD-V: No
RAM reported: 5.8 GiB
Swap reported: 0 MiB
Disk reported: 24.1 GiB
Virtualization reported: KVM
CPU steal: 0.1% of busy CPU time stolen
Distro: Ubuntu 24.04.2 LTS
Kernel: 6.8.0-62-generic
Architecture: arm64
IPv4 reachable: Yes
IPv6 reachable: No

Advertised at test time

Plan: Cloud ARM VDS 1
Product line: Cloud ARM VDS
Location: Lithuania
vCPU: 1 dedicated vCPU
Architecture: arm64
RAM: 6 GB
Storage: 25 GB NVMe
Virtualization: KVM
Network: 1 Gbps
Transfer: 5 TB
Port 25: Unknown
Monthly price at test time: $22.23
Hourly price at test time: $0.039
YABS version: v2026-09-20
Ran at: Oct 12, 2026, 09:11:23 UTC
Parser version: 5

Run timeline

Queued: Oct 12, 2026, 01:09:00 UTC
Server created: Oct 12, 2026, 06:09:44 UTC
First update from the server: Oct 12, 2026, 06:09:44 UTC
Completed: Oct 12, 2026, 08:00:39 UTC
Server deleted: Oct 12, 2026, 08:00:39 UTC
Cost of this run: $0.074

TestResultTime

Watch party 0 watching

This party closed at 09:00 UTC. It's read only now.

Loading the party

RackCensus

Browse

Server

CPU

Memory, TLS and scheduler

Memory bandwidth (STREAM)

TLS and crypto (OpenSSL)

Scheduler latency (schbench)

Disk

Network

IPv4 transfer speed

Datastores

PostgreSQL

fsync speed (pg_test_fsync)

pgbench at scale 10

pgbench at scale 100

MySQL

sysbench OLTP

Redis

memtier

Web frameworks

WooCommerce

Page mix

Cart and checkout

Discourse

Signed in

Anonymous

Ghost

Readers

Staff in Ghost Admin

Wagtail

Visitors

Editors in the Wagtail admin

Advertised vs. measured

Detected hardware

Advertised at test time

Run timeline

Watch party