UpCloud Starter 1 vCPU / 1 GB

New York #1

Benchmark complete

Finished Oct 8, 2026

Geekbench 7 single-core

Skipped

Geekbench 7 multi-core

Skipped

Disk 4K IOPS

16,263

fio random read and write, 50/50

Median here: 17,097 over 3 runs in 90 days

Monthly price at test time

€3.50 EUR

Same price today

Server

UpCloud Starter 1 vCPU / 1 GB

Provider

UpCloud
Plan

Starter 1 vCPU / 1 GB
Location

New York #1
vCPU

1
RAM

1 GB
Storage

10 GB
Network

Unknown
OS image

01000000-0000-4000-8000-000030240200
Trigger

Scheduled
Queued at

Oct 8, 2026, 01:29:00 UTC

Visit UpCloud

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

Skip the referral How this works

Latest runs of this plan

Full history of this plan

CPU

Geekbench was skipped because this plan has less than 2 GB of RAM, which isn't enough for Geekbench 7 to run without swap.

Memory, TLS and scheduler

Memory bandwidth (STREAM)

Test	Result	Runs	Spread
Copy higher is better	30.9 GB/s	3	0.785%
Scale higher is better	19.2 GB/s	3	0.205%
Add higher is better	22.9 GB/s	3	0.311%
Triad higher is better	22.7 GB/s	3	0.646%

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	231/s	3	1.15%
RSA 4096 verifies higher is better	14,962/s	3	1.24%
SHA-256 higher is better	687 MB/s	3	0.976%
AES-256-GCM higher is better	3.52 GB/s	3	0.922%
ChaCha20-Poly1305 higher is better	1.78 GB/s	3	0.513%

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	4.09 ms	3	0.246%
Requests per second, 90th percentile higher is better	242/s	3	0.239%
Request latency, 99.9th percentile lower is better	7.43 ms	3	2.77%
Requests per second, average higher is better	241/s	3	0.51%

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

Disk

Block size	Read	Write	Total
4K	31.7 MB/s (8,124 IOPS)	31.8 MB/s (8,139 IOPS)	63.5 MB/s (16,263 IOPS)
64K	320.4 MB/s (5,125 IOPS)	322 MB/s (5,152 IOPS)	642.4 MB/s (10,277 IOPS)
512K	381.7 MB/s (763 IOPS)	402 MB/s (804 IOPS)	783.8 MB/s (1,567 IOPS)
1M	379.8 MB/s (379 IOPS)	405.1 MB/s (405 IOPS)	784.8 MB/s (784 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	busy	1.02 Gbps
Eranium, Amsterdam, NL (100G)	IPv4	1.02 Gbps	1.02 Gbps
Leaseweb, Singapore, SG (10G)	IPv4	647 Mbps	873 Mbps
Clouvider, Los Angeles, CA, US (10G)	IPv4	busy	busy
Leaseweb, NYC, NY, US (10G)	IPv4	1.07 Gbps	1.07 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	3,409	0.293 ms
fdatasync	3,311	0.302 ms
fsync	1,975	0.506 ms
fsync_writethrough	Not supported here	n/a
open_sync	2,066	0.484 ms
Two 8 kB writes
open_datasync	1,780	0.562 ms
fdatasync	2,950	0.339 ms
fsync	1,754	0.57 ms
fsync_writethrough	Not supported here	n/a
open_sync	1,022	0.979 ms
open_sync at different write sizes
1 * 16kB open_sync write	1,939	0.516 ms
2 * 8kB open_sync writes	1,062	0.942 ms
4 * 4kB open_sync writes	503	1.99 ms
8 * 2kB open_sync writes	260	3.84 ms
16 * 1kB open_sync writes	129	7.73 ms
fsync on a non-write descriptor
write, fsync, close	1,927	0.519 ms
write, close, fsync	1,796	0.557 ms
Non-synced 8 kB writes
write	527,892	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
Read/write (TPC-B like)	1	1,606	0.551 ms	0.879 ms	1.7 ms	4.66 ms
Read/write (TPC-B like)	8	2,812	2.54 ms	4.54 ms	6.36 ms	15.9 ms
Read/write (TPC-B like)	32	2,687	9.45 ms	25.9 ms	43.7 ms	95.6 ms
Read only	1	26,295	0.035 ms	0.049 ms	0.06 ms	0.22 ms
Read only	8	28,447	0.239 ms	0.433 ms	0.502 ms	1.16 ms
Read only	32	28,754	0.943 ms	1.36 ms	1.61 ms	2.65 ms

Scale 10 (1,000,000 accounts), loaded in 2.13 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	983	0.885 ms	1.56 ms	3.12 ms	13.2 ms
Read/write (TPC-B like)	8	1,869	3.34 ms	7.24 ms	20.6 ms	85.3 ms
Read/write (TPC-B like)	32	2,098	13.1 ms	21.9 ms	80.4 ms	94 ms
Read only	1	3,328	0.287 ms	0.503 ms	1.32 ms	2.67 ms
Read only	8	6,097	0.805 ms	1.75 ms	33.1 ms	40.7 ms
Read only	32	6,172	2.58 ms	38.4 ms	48.9 ms	52.1 ms

Scale 100 (10,000,000 accounts), loaded in 22.8 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	279	5,577	2.97 ms	4.91 ms	13.2 ms
Read/write	8	462	9,239	16.1 ms	25.7 ms	38.9 ms
Read/write	32	481	9,628	61.1 ms	109 ms	140 ms
Read only	1	910	14,562	1.04 ms	1.34 ms	2 ms
Read only	8	884	14,151	8.9 ms	10.5 ms	13 ms
Read only	32	827	13,231	37.6 ms	45.8 ms	53.9 ms

10 tables of 100,000 rows, loaded in 14.8 s. 60 s per run, one connection per thread.

Redis

memtier

Mix	Operations/s	Hits/s	Median	p99	p99.9
1:10 set:get	35,137	31,942	1.71 ms	3.26 ms	5.34 ms
1:1 set:get	34,491	17,245	1.79 ms	3.31 ms	5.31 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	The results arrived but couldn't be read, so no numbers are shown.
Express	The results arrived but couldn't be read, so no numbers are shown.
Fastify	The results arrived but couldn't be read, so no numbers are shown.
NestJS	The results arrived but couldn't be read, so no numbers are shown.
Nuxt	The results arrived but couldn't be read, so no numbers are shown.
FastAPI	The results arrived but couldn't be read, so no numbers are shown.
Django	The results arrived but couldn't be read, so no numbers are shown.
Rails	The results arrived but couldn't be read, so no numbers are shown.
Laravel	The results arrived but couldn't be read, so no numbers are shown.
Symfony	The results arrived but couldn't be read, so no numbers are shown.

WooCommerce

Page mix

Step	Requests/s	Median	p95	p99	Error rate
8 virtual users
Home page	1.19	1.22 s	1.34 s	1.36 s	0%
Shop page	1.19	1.59 s	1.83 s	1.87 s	0%
Category page	1.19	1.45 s	1.71 s	1.81 s	0%
Product page	1.19	1.22 s	1.33 s	1.39 s	0%
Product search	1.19	1.13 s	1.24 s	1.26 s	0%
32 virtual users
Home page	1.36	4.69 s	5.26 s	5.32 s	0%
Shop page	1.36	6.04 s	6.79 s	6.97 s	0%
Category page	1.36	5.66 s	6.62 s	6.83 s	0%
Product page	1.05	4.79 s	4.9 s	4.96 s	0%
Product search	0.905	4.6 s	4.76 s	4.81 s	0%

Cart and checkout

Step	Requests/s	Median	p95	p99	Error rate
8 virtual users
Add to cart	2.34	1.15 s	1.33 s	1.41 s	0%
Cart	2.34	1.18 s	1.27 s	1.35 s	0%
Checkout	2.34	950 ms	1.05 s	1.07 s	0%
32 virtual users
Add to cart	2.41	4.29 s	5.25 s	5.39 s	0%
Cart	2.41	4.88 s	5.28 s	5.4 s	0%
Checkout	2.41	3.84 s	4.4 s	4.48 s	0%

k6 with a fixed number of virtual users, 65 to 71 s per level. The error rate counts responses that weren't a 200.

Advertised vs. measured

Spec	Advertised	Measured
vCPU	1	1
CPU	Shared vCPU	0.1% of busy CPU time stolen
RAM	1 GB	849 MiB
Storage	10 GB	9.8 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: 1
CPU frequency: 2895 MHz
AES-NI: Yes
VM-x/AMD-V: No
RAM reported: 849 MiB
Swap reported: 0 MiB
Disk reported: 9.8 GiB
Virtualization reported: KVM
CPU steal: 0.1% 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 1 vCPU / 1 GB
Product line: Starter
Location: New York #1
vCPU: 1 shared vCPU
Architecture: x86_64
RAM: 1 GB
Storage: 10 GB
Virtualization: KVM
Network: Unknown
Transfer: 512 GB
Port 25: Unknown
Monthly price at test time: €3.50 EUR
Hourly price at test time: €0.0052 EUR
YABS version: v2026-09-20
Ran at: Oct 8, 2026, 01:31:19 UTC
Parser version: 5

Run timeline

Queued: Oct 8, 2026, 01:29:00 UTC
First update from the server: Oct 8, 2026, 01:30:17 UTC
Completed: Oct 8, 2026, 02:41:06 UTC
Server deleted: Oct 8, 2026, 02:41:06 UTC
Cost of this run: €0.0063 EUR

TestResultTimevs last run

Watch party 0 watching

This party closed at 02:36 UTC. It's read only now.

Loading the party

RackCensus

Server

Latest runs of this plan

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

Advertised vs. measured

Detected hardware

Advertised at test time

Run timeline

Watch party