Skip to main content

Kamatera 2T 2GB 40GB

Atlanta

Benchmark complete
Finished Oct 13, 2026
Geekbench 7 single-core
1,277
Faster than 70% of 2 vCPU plans
Geekbench 7 multi-core
Skipped
Disk 4K IOPS
95,568
fio random read and write, 50/50
Monthly price at test time
$13.00
Same price today

Server

  • Provider
    Kamatera
  • Plan
    2T 2GB 40GB
  • Location
    Atlanta
  • vCPU
    2
  • RAM
    2 GB
  • Storage
    40 GB SSD
  • Network
    Unknown
  • OS image
    ubuntu_server_24.04_64-bit
  • Trigger
    Scheduled
  • Queued at
    Oct 13, 2026, 14:51:00 UTC
Visit Kamatera

CPU

Version Single-core Multi-core
Geekbench 7 1,277 Skipped Geekbench Browser

Multi-core was skipped because Geekbench 7 needs about 3.1 GB of free memory to run 2 threads, and this server didn't have that much. Single-core needs much less, so it still ran.

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
1,348
68th of 150
Single-core only
Navigation
1,197
92nd of 150
Single-core only
HTML5 Browser
1,210
61st of 150
Single-core only
PDF Viewer
1,434
55th of 150
Single-core only
Photo Library
1,337
47th of 150
Single-core only
Clang
1,295
42nd of 150
Single-core only
Text Processing
1,294
46th of 150
Single-core only
Asset Compression
1,527
39th of 150
Single-core only
HDR
1,078
73rd of 150
Single-core only
Photo Editor
1,442
59th of 150
Single-core only
Ray Tracer
1,153
80th of 150
Single-core only
Structure from Motion
1,491
55th of 150
Single-core only
Game Physics
1,203
69th of 150
Single-core only
Video Encoder
1,164
75th of 150
Single-core only
Audio Encoder
1,251
78th of 150
Single-core only
Video Player
1,115
88th of 150
Single-core only

Rank among the 150 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 39 GB/s 3 10.7%
Scale higher is better 22.5 GB/s 3 14.2%
Add higher is better 28.1 GB/s 3 12.1%
Triad higher is better 28 GB/s 3 11.8%

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 1,026/s 3 2.18%
RSA 4096 verifies higher is better 28,464/s 3 0.612%
SHA-256 higher is better 1.63 GB/s 3 2.75%
AES-256-GCM higher is better 23.6 GB/s 3 1.38%
ChaCha20-Poly1305 higher is better 6.89 GB/s 3 0.309%

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 2.5 ms 3 1.03%
Requests per second, 90th percentile higher is better 756/s 3 1.6%
Request latency, 99.9th percentile lower is better 5.7 ms 3 7.91%
Requests per second, average higher is better 696/s 3 5.62%

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

Disk

Block size Read Write Total
4K 186.4 MB/s (47,721 IOPS) 186.9 MB/s (47,847 IOPS) 373.3 MB/s (95,568 IOPS)
64K 2.14 GB/s (35,066 IOPS) 2.15 GB/s (35,251 IOPS) 4.29 GB/s (70,317 IOPS)
512K 4.74 GB/s (9,708 IOPS) 4.99 GB/s (10,223 IOPS) 9.73 GB/s (19,931 IOPS)
1M 4.61 GB/s (4,719 IOPS) 4.92 GB/s (5,033 IOPS) 9.52 GB/s (9,752 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 2.06 Gbps 2.48 Gbps
Eranium, Amsterdam, NL (100G) IPv4 1.97 Gbps 2.39 Gbps
Leaseweb, Singapore, SG (10G) IPv4 690 Mbps 1.05 Gbps
Clouvider, Los Angeles, CA, US (10G) IPv4 1.68 Gbps 2.79 Gbps
Leaseweb, NYC, NY, US (10G) IPv4 8.01 Gbps 7.52 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 7,465 0.134 ms
fdatasync 7,072 0.141 ms
fsync 4,323 0.231 ms
fsync_writethrough Not supported here n/a
open_sync 4,971 0.201 ms
Two 8 kB writes
open_datasync 3,577 0.28 ms
fdatasync 6,828 0.146 ms
fsync 4,670 0.214 ms
fsync_writethrough Not supported here n/a
open_sync 2,666 0.375 ms
open_sync at different write sizes
1 * 16kB open_sync write 5,593 0.179 ms
2 * 8kB open_sync writes 3,003 0.333 ms
4 * 4kB open_sync writes 1,453 0.688 ms
8 * 2kB open_sync writes 753 1.33 ms
16 * 1kB open_sync writes 376 2.66 ms
fsync on a non-write descriptor
write, fsync, close 5,241 0.191 ms
write, close, fsync 4,915 0.203 ms
Non-synced 8 kB writes
write 1,535,098 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 Failed
Read/write (TPC-B like) 1 1,743 0.507 ms 0.921 ms 2.03 ms 4.76 ms 0
Read/write (TPC-B like) 8 5,962 1.17 ms 2.59 ms 4.47 ms 7.56 ms 0
Read/write (TPC-B like) 32 5,376 4.45 ms 15 ms 25.9 ms 51.4 ms 0
Read only 1 22,568 0.043 ms 0.066 ms 0.113 ms 0.258 ms 0
Read only 8 77,280 0.093 ms 0.163 ms 0.207 ms 0.362 ms 0
Read only 32 71,596 0.383 ms 0.727 ms 1.05 ms 1.72 ms 0

Scale 10 (1,000,000 accounts), loaded in 1.22 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 1,548 0.556 ms 1.07 ms 2.75 ms 5.94 ms 0
Read/write (TPC-B like) 8 4,819 1.38 ms 3.67 ms 6.46 ms 11.6 ms 0
Read/write (TPC-B like) 32 5,485 5.38 ms 9.7 ms 13 ms 19 ms 0
Read only 1 8,274 0.103 ms 0.273 ms 0.506 ms 2.52 ms 0
Read only 8 44,415 0.139 ms 0.396 ms 0.631 ms 2.15 ms 0
Read only 32 42,197 0.619 ms 1.37 ms 2.08 ms 3.45 ms 0

Scale 100 (10,000,000 accounts), loaded in 12.4 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 Errors
Read/write 1 430 8,607 2.03 ms 4.18 ms 7.04 ms 0
Read/write 8 1,140 22,797 6.55 ms 11.2 ms 15 ms 0
Read/write 32 1,200 23,991 24.8 ms 45.8 ms 61.1 ms 0
Read only 1 886 14,182 1.06 ms 1.5 ms 1.86 ms 0
Read only 8 2,528 40,452 3.3 ms 4.65 ms 5.88 ms 0
Read only 32 2,295 36,719 13.7 ms 19 ms 22.7 ms 0

10 tables of 100,000 rows, loaded in 7.9 s. 60 s per run, one connection per thread.

Redis

memtier

Mix Operations/s Hits/s Median p99 p99.9
1:10 set:get 95,241 86,582 0.471 ms 2.46 ms 4.22 ms
1:1 set:get 95,745 47,872 0.415 ms 2.51 ms 4.35 ms

1,000,000 keys of 32 bytes. 64 connections over 2 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 387 1,625 1,871 920 ms
Express express-postgresjs 7,361 12,021 57,429 61.3 ms
Fastify fastify-postgres 7,253 12,890 65,225 78.8 ms
NestJS nestjs 6,481 6,449 34,405 90.8 ms
Nuxt nuxt 6,288 11,467 50,904 84.7 ms
FastAPI fastapi 4,223 5,657 23,133 217 ms
Django django-postgresql 1,267 1,443 3,926 451 ms
Rails rails 3,625 5,677 25,318 106 ms
Laravel laravel 741 765 1,353 409 ms
Symfony symfony 884 1,010 2,833 337 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 2.2 721 ms 819 ms 854 ms 0%
Shop page 2.2 994 ms 1.08 s 1.21 s 0%
Category page 2.2 599 ms 1 s 1.07 s 0%
Product page 2.2 661 ms 762 ms 801 ms 0%
Product search 2.2 570 ms 668 ms 706 ms 0%
32 virtual users
Home page 2.27 2.65 s 3.02 s 3.17 s 0%
Shop page 2.27 3.57 s 4.1 s 4.14 s 0%
Category page 2.27 3.12 s 3.68 s 3.9 s 0%
Product page 2.11 2.71 s 3.02 s 3.17 s 0%
Product search 1.83 2.45 s 2.7 s 2.73 s 0%

Cart and checkout

Step Requests/s Median p95 p99 Error rate
8 virtual users
Add to cart 4.22 781 ms 935 ms 1.01 s 0%
Cart 4.22 623 ms 734 ms 776 ms 0%
Checkout 4.22 471 ms 561 ms 607 ms 0%
32 virtual users
Add to cart 4.27 2.64 s 3.22 s 3.55 s 0%
Cart 4.27 2.68 s 3.07 s 3.2 s 0%
Checkout 4.27 2.06 s 2.41 s 2.54 s 0%

k6 with a fixed number of virtual users, 62 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 2.02 222 ms 293 ms 491 ms 0%
Topic JSON 1.03 109 ms 152 ms 295 ms 0%
Home page 1.03 195 ms 236 ms 339 ms 0%
Categories page 0.514 216 ms 266 ms 299 ms 0%
User activity page 0.497 138 ms 169 ms 178 ms 0%
4 virtual users
Topic page 3.71 484 ms 670 ms 944 ms 0%
Topic JSON 1.85 251 ms 333 ms 391 ms 0%
Home page 1.83 434 ms 585 ms 725 ms 0%
Categories page 0.94 491 ms 620 ms 1.04 s 0%
User activity page 0.923 328 ms 563 ms 689 ms 0%
16 virtual users
Topic page 3.52 1.61 s 1.97 s 2.39 s 0%
Topic JSON 1.72 1.34 s 1.66 s 1.74 s 0%
Home page 1.77 1.55 s 1.85 s 2.19 s 0%
Categories page 0.859 1.58 s 2.02 s 2.21 s 0%
User activity page 0.891 1.37 s 1.8 s 1.94 s 0%

Anonymous

Step Requests/s Median p95 p99 Error rate
16 virtual users
Topic page 70.7 64.4 ms 152 ms 189 ms 0%
Topic JSON 35.3 65.2 ms 152 ms 189 ms 0%
Home page 35.3 63.2 ms 149 ms 180 ms 0%
Categories page 17.6 66.6 ms 156 ms 217 ms 0%
User activity page 17.7 198 ms 315 ms 509 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 4 app workers and 256 MB of Postgres shared buffers, what its installer picks for a 2 GB box. It added a 2 GB swapfile first, the way its installer does, and used up to 512 MB of it. The container peaked at 1,460 MB.

Ghost

Readers

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 8.18 34.8 ms 45.1 ms 52.8 ms 0%
Post page 20.4 18.6 ms 24.3 ms 33 ms 0%
Tag page 4.08 22 ms 28.2 ms 35.6 ms 0%
Author page 4.08 23.1 ms 31.2 ms 33.2 ms 0%
RSS feed 4.08 25.7 ms 35.2 ms 44 ms 0%
4 virtual users
Home page 10.4 103 ms 138 ms 157 ms 0%
Post page 25.8 69.8 ms 106 ms 138 ms 0%
Tag page 5.17 62.1 ms 92.1 ms 124 ms 0%
Author page 5.16 66.2 ms 90 ms 115 ms 0%
RSS feed 5.16 67.6 ms 97 ms 125 ms 0%
16 virtual users
Home page 10.9 373 ms 453 ms 493 ms 0%
Post page 27.1 310 ms 396 ms 444 ms 0%
Tag page 5.44 202 ms 277 ms 308 ms 0%
Author page 5.39 201 ms 271 ms 312 ms 0%
RSS feed 5.39 207 ms 286 ms 312 ms 0%

Staff in Ghost Admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Post list 4.45 31.6 ms 43 ms 66.8 ms 0%
Post editor 13.4 13.6 ms 18.5 ms 25.3 ms 0%
Saving a draft 13.4 33.9 ms 42.8 ms 57.7 ms 0%
Member list 4.47 35.3 ms 44.6 ms 51.5 ms 0%
4 virtual users
Post list 5.64 43.4 ms 60.7 ms 109 ms 0%
Post editor 17 23.2 ms 32.9 ms 49.5 ms 0%
Saving a draft 17 171 ms 232 ms 274 ms 0%
Member list 5.64 45.1 ms 62.1 ms 107 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 366 MB and MySQL at 597 MB.

Wagtail

Visitors

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 1.56 83.2 ms 103 ms 116 ms 0%
Blog index 1.55 285 ms 330 ms 364 ms 0%
Blog post 4.64 27.2 ms 41 ms 45.8 ms 0%
Bread page 4.64 29.7 ms 36.1 ms 39.9 ms 0%
Location page 1.55 28.7 ms 35 ms 37.8 ms 0%
Site search 1.55 48.2 ms 82.4 ms 90.7 ms 0%
4 virtual users
Home page 2.6 220 ms 298 ms 415 ms 0%
Blog index 2.62 721 ms 1 s 1.06 s 0%
Blog post 7.79 64.2 ms 103 ms 132 ms 0%
Bread page 7.84 69.2 ms 100 ms 113 ms 0%
Location page 2.62 65.1 ms 97.8 ms 111 ms 0%
Site search 2.6 99.9 ms 204 ms 297 ms 0%
16 virtual users
Home page 2.52 756 ms 977 ms 1.14 s 0%
Blog index 2.54 1.85 s 2.46 s 2.7 s 0%
Blog post 7.51 425 ms 667 ms 865 ms 0%
Bread page 7.59 443 ms 657 ms 747 ms 0%
Location page 2.52 433 ms 621 ms 835 ms 0%
Site search 2.49 536 ms 804 ms 902 ms 0%

Editors in the Wagtail admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Admin dashboard 0.709 88.9 ms 121 ms 192 ms 0%
Page explorer 1.45 324 ms 433 ms 504 ms 0%
Page editor 2.14 152 ms 187 ms 223 ms 0%
Image library 0.709 62.8 ms 73.8 ms 607 ms 0%
Admin page search 0.709 37.7 ms 70.6 ms 74.3 ms 0%
4 virtual users
Admin dashboard 1.22 219 ms 487 ms 583 ms 0%
Page explorer 2.46 757 ms 1.31 s 1.43 s 0%
Page editor 3.74 350 ms 687 ms 792 ms 0%
Image library 1.24 219 ms 436 ms 504 ms 0%
Admin page search 1.22 107 ms 271 ms 482 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. 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 296 MB, Postgres at 179 MB, and Redis at 26 MB.

Advertised vs. measured

Advertised Measured
vCPU 2 2
CPU Shared vCPU 0% of busy CPU time stolen
RAM 2 GB 1.9 GiB
Storage 40 GB SSD 39.3 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
2
CPU frequency
2700 MHz
AES-NI
Yes
VM-x/AMD-V
Yes
RAM reported
1.9 GiB
Swap reported
0 MiB
Disk reported
39.3 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
2T 2GB 40GB
Product line
Type T Burstable
Location
Atlanta
vCPU
2 shared vCPU
Architecture
x86_64
RAM
2 GB
Storage
40 GB SSD
Virtualization
KVM
Network
Unknown
Transfer
5 TB
Port 25
Unknown
Monthly price at test time
$13.00
Hourly price at test time
$0.018
YABS version
v2026-09-20
Ran at
Oct 13, 2026, 14:53:10 UTC
Parser version
5

Run timeline

Queued
Oct 13, 2026, 14:51:00 UTC
First update from the server
Oct 13, 2026, 14:53:05 UTC
Completed
Oct 13, 2026, 16:25:00 UTC
Server deleted
Oct 13, 2026, 16:25:00 UTC
Cost of this run
$0.028
Watch party 0 watching

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

Watch party

Loading the party