Kamatera 1B 1GB 20GB

Atlanta

Benchmark complete

Finished Oct 10, 2026

Geekbench 7 single-core

Skipped

Geekbench 7 multi-core

Skipped

Disk 4K IOPS

88,070

fio random read and write, 50/50

Monthly price at test time

$9.00

Same price today

Server

Kamatera 1B 1GB 20GB

Provider

Kamatera
Plan

1B 1GB 20GB
Location

Atlanta
vCPU

1
RAM

1 GB
Storage

20 GB SSD
Network

Unknown
OS image

ubuntu_server_24.04_64-bit
Trigger

Scheduled
Queued at

Oct 10, 2026, 18:11:00 UTC

Visit Kamatera

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	20.9 GB/s	3	4.03%
Scale higher is better	13.5 GB/s	3	3.03%
Add higher is better	16.3 GB/s	3	2.37%
Triad higher is better	16.1 GB/s	3	3.04%

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	494/s	3	5.48%
RSA 4096 verifies higher is better	14,520/s	3	0.0789%
SHA-256 higher is better	834 MB/s	3	1.35%
AES-256-GCM higher is better	11.7 GB/s	3	3.78%
ChaCha20-Poly1305 higher is better	3.51 GB/s	3	0.821%

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	2.42 ms	3	0.191%
Requests per second, 90th percentile higher is better	403/s	3	0.379%
Request latency, 99.9th percentile lower is better	5.68 ms	3	3.39%
Requests per second, average higher is better	385/s	3	0.714%

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

Disk

Block size	Read	Write	Total
4K	171.8 MB/s (43,977 IOPS)	172.2 MB/s (44,093 IOPS)	344 MB/s (88,070 IOPS)
64K	1.64 GB/s (26,876 IOPS)	1.65 GB/s (27,018 IOPS)	3.29 GB/s (53,894 IOPS)
512K	4.15 GB/s (8,489 IOPS)	4.37 GB/s (8,940 IOPS)	8.51 GB/s (17,429 IOPS)
1M	4.45 GB/s (4,556 IOPS)	4.75 GB/s (4,859 IOPS)	9.2 GB/s (9,415 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	2.03 Gbps	2.44 Gbps
Eranium, Amsterdam, NL (100G)	IPv4	2.34 Gbps	2.42 Gbps
Leaseweb, Singapore, SG (10G)	IPv4	801 Mbps	1.05 Gbps
Clouvider, Los Angeles, CA, US (10G)	IPv4	1.39 Gbps	2.76 Gbps
Leaseweb, NYC, NY, US (10G)	IPv4	5.69 Gbps	4.32 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	7,341	0.136 ms
fdatasync	6,644	0.151 ms
fsync	5,197	0.192 ms
fsync_writethrough	Not supported here	n/a
open_sync	5,705	0.175 ms
Two 8 kB writes
open_datasync	3,556	0.281 ms
fdatasync	6,364	0.157 ms
fsync	5,011	0.2 ms
fsync_writethrough	Not supported here	n/a
open_sync	2,579	0.388 ms
open_sync at different write sizes
1 * 16kB open_sync write	5,507	0.182 ms
2 * 8kB open_sync writes	2,709	0.369 ms
4 * 4kB open_sync writes	1,351	0.74 ms
8 * 2kB open_sync writes	685	1.46 ms
16 * 1kB open_sync writes	366	2.73 ms
fsync on a non-write descriptor
write, fsync, close	4,916	0.203 ms
write, close, fsync	4,816	0.208 ms
Non-synced 8 kB writes
write	1,560,098	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	2,940	0.275 ms	0.574 ms	1.49 ms	3.49 ms
Read/write (TPC-B like)	8	4,260	1.56 ms	3.61 ms	6.1 ms	13.6 ms
Read/write (TPC-B like)	32	3,419	7.6 ms	21 ms	35 ms	57.8 ms
Read only	1	63,768	0.014 ms	0.021 ms	0.029 ms	0.058 ms
Read only	8	51,702	0.133 ms	0.245 ms	0.315 ms	0.73 ms
Read only	32	39,328	0.729 ms	0.935 ms	1.19 ms	2.17 ms

Scale 10 (1,000,000 accounts), loaded in 1.4 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.

pgbench at scale 100

Workload	Clients	Transactions/s	Median	p95	p99	p99.9
Read/write (TPC-B like)	1	1,522	0.556 ms	1.18 ms	3.18 ms	6.26 ms
Read/write (TPC-B like)	8	3,194	2.03 ms	5.15 ms	8.82 ms	19.8 ms
Read/write (TPC-B like)	32	2,955	10 ms	16.2 ms	21.5 ms	31.3 ms
Read only	1	4,183	0.188 ms	0.472 ms	1.54 ms	3.18 ms
Read only	8	15,611	0.448 ms	1.02 ms	2.11 ms	3.67 ms
Read only	32	14,853	1.85 ms	3.51 ms	4.55 ms	6.48 ms

Scale 100 (10,000,000 accounts), loaded in 14.6 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	446	8,921	1.89 ms	3.96 ms	7.84 ms
Read/write	8	774	15,481	9.56 ms	15.5 ms	21.5 ms
Read/write	32	748	14,961	38.9 ms	70.5 ms	94.1 ms
Read only	1	1,789	28,618	0.499 ms	0.872 ms	1.27 ms
Read only	8	1,601	25,617	4.74 ms	7.43 ms	9.56 ms
Read only	32	1,386	22,170	22.7 ms	28.7 ms	33.7 ms

10 tables of 100,000 rows, loaded in 11.9 s. 60 s per run, one connection per thread.

Redis

memtier

Mix	Operations/s	Hits/s	Median	p99	p99.9
1:10 set:get	81,904	74,457	0.791 ms	1.51 ms	2.69 ms
1:1 set:get	82,964	41,482	0.791 ms	1.42 ms	2.59 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	234	898	1,482	1.78 s
Express express-postgresjs	12,197	11,737	31,923	43 ms
Fastify fastify-postgres	12,227	14,474	37,607	109 ms
NestJS nestjs	3,027	3,091	21,482	151 ms
Nuxt nuxt	7,241	11,621	25,363	1.18 s
FastAPI fastapi	2,195	2,948	12,522	365 ms
Django django-postgresql	1,027	1,047	3,176	322 ms
Rails rails	1,836	2,710	15,462	186 ms
Laravel laravel	426	445	731	655 ms
Symfony symfony	513	558	1,472	603 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	1.2	1.21 s	1.36 s	1.45 s	0%
Shop page	1.2	1.6 s	1.87 s	1.94 s	0%
Category page	1.2	1.43 s	1.8 s	1.86 s	0%
Product page	1.2	1.21 s	1.37 s	1.41 s	0%
Product search	1.2	1.12 s	1.27 s	1.31 s	0%
32 virtual users
Home page	1.36	4.8 s	5.48 s	5.54 s	0%
Shop page	1.36	6.46 s	7.77 s	7.94 s	0%
Category page	1.29	5.93 s	7.38 s	7.75 s	0%
Product page	0.907	4.81 s	5.05 s	5.1 s	0%
Product search	0.907	4.67 s	4.96 s	5.01 s	0%

Cart and checkout

Step	Requests/s	Median	p95	p99	Error rate
8 virtual users
Add to cart	2.23	1.16 s	1.41 s	1.45 s	0%
Cart	2.23	1.23 s	1.35 s	1.39 s	0%
Checkout	2.23	950 ms	1.1 s	1.25 s	0%
32 virtual users
Add to cart	2.44	4.24 s	5.42 s	5.59 s	0%
Cart	2.44	4.87 s	5.45 s	5.52 s	0%
Checkout	2.44	3.76 s	4.27 s	4.33 s	0%

k6 with a fixed number of virtual users, 66 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% of busy CPU time stolen
RAM	1 GB	960 MiB
Storage	20 GB SSD	19.6 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: Intel Xeon Processor (SapphireRapids)
CPU cores: 1
CPU frequency: 2700 MHz
AES-NI: Yes
VM-x/AMD-V: Yes
RAM reported: 960 MiB
Swap reported: 0 MiB
Disk reported: 19.6 GiB
Virtualization reported: KVM
CPU steal: 0% of busy CPU time stolen
Distro: Ubuntu 24.04.5 LTS
Kernel: 6.8.0-139-generic
Architecture: x86_64
IPv4 reachable: Yes
IPv6 reachable: No

Advertised at test time

Plan: 1B 1GB 20GB
Product line: Type B General Purpose
Location: Atlanta
vCPU: 1 shared vCPU
Architecture: x86_64
RAM: 1 GB
Storage: 20 GB SSD
Virtualization: KVM
Network: Unknown
Transfer: 5 TB
Port 25: Unknown
Monthly price at test time: $9.00
Hourly price at test time: $0.012
YABS version: v2026-09-20
Ran at: Oct 10, 2026, 18:13:12 UTC
Parser version: 5

Run timeline

Queued: Oct 10, 2026, 18:11:00 UTC
Server created: Oct 10, 2026, 18:13:09 UTC
First update from the server: Oct 10, 2026, 18:13:09 UTC
Completed: Oct 10, 2026, 19:19:00 UTC
Server deleted: Oct 10, 2026, 19:19:00 UTC
Cost of this run: $0.014

TestResultTimevs last run

Watch party 0 watching

This party closed at 19:15 UTC. It's read only now.

Loading the party

RackCensus

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

Advertised vs. measured

Detected hardware

Advertised at test time

Run timeline

Watch party