Skip to main content

Gcore CPU-Optimized A1 2 vCPU / 2 GB

Manassas

Benchmark complete
Finished Oct 14, 2026
Geekbench 7 single-core
Skipped
Geekbench 7 multi-core
Skipped
Disk 4K IOPS
894
fio random read and write, 50/50
Monthly price at test time
€23.48 EUR
Same price today

Server

  • Provider
    Gcore
  • Plan
    CPU-Optimized A1 2 vCPU / 2 GB
  • Location
    Manassas
  • vCPU
    2
  • RAM
    2 GB
  • Storage
  • Network
    1 Gbps
  • OS image
    ubuntu-24.04
  • Trigger
    Scheduled
  • Queued at
    Oct 14, 2026, 13:19:00 UTC
Visit Gcore

CPU

Geekbench was skipped because this plan doesn't have enough RAM for Geekbench 7's multi-core run, and the arm64 build can't run single-core only.

Memory, TLS and scheduler

Memory bandwidth (STREAM)

Test Result Runs Spread
Copy higher is better 48.1 GB/s 3 0.979%
Scale higher is better 47.3 GB/s 3 0.267%
Add higher is better 43.6 GB/s 3 0.709%
Triad higher is better 43.3 GB/s 3 2.25%

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 97.4/s 3 0.258%
RSA 4096 verifies higher is better 7,932/s 3 0.119%
SHA-256 higher is better 1.45 GB/s 3 0.249%
AES-256-GCM higher is better 4.69 GB/s 3 0.0384%
ChaCha20-Poly1305 higher is better 1.72 GB/s 3 0.0896%

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 15 ms 3 0%
Requests per second, 90th percentile higher is better 132/s 3 0%
Request latency, 99.9th percentile lower is better 22.3 ms 3 1.03%
Requests per second, average higher is better 132/s 3 0.149%

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

Disk

Block size Read Write Total
4K 1.7 MB/s (444 IOPS) 1.8 MB/s (450 IOPS) 3.5 MB/s (894 IOPS)
64K 37.1 MB/s (594 IOPS) 38.2 MB/s (611 IOPS) 75.4 MB/s (1,205 IOPS)
512K 48.3 MB/s (96 IOPS) 52.5 MB/s (104 IOPS) 100.8 MB/s (200 IOPS)
1M 47.7 MB/s (47 IOPS) 53.3 MB/s (53 IOPS) 101 MB/s (100 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 1.41 Gbps 1.38 Gbps
Eranium, Amsterdam, NL (100G) IPv4 1.39 Gbps 1.36 Gbps
Leaseweb, Singapore, SG (10G) IPv4 737 Mbps 997 Mbps
Clouvider, Los Angeles, CA, US (10G) IPv4 1.43 Gbps 1.41 Gbps
Leaseweb, NYC, NY, US (10G) IPv4 1.51 Gbps 1.45 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 374 2.67 ms
fdatasync 381 2.63 ms
fsync 122 8.23 ms
fsync_writethrough Not supported here n/a
open_sync 108 9.28 ms
Two 8 kB writes
open_datasync 184 5.44 ms
fdatasync 379 2.64 ms
fsync 98 10.2 ms
fsync_writethrough Not supported here n/a
open_sync 56.1 17.8 ms
open_sync at different write sizes
1 * 16kB open_sync write 114 8.77 ms
2 * 8kB open_sync writes 55.5 18 ms
4 * 4kB open_sync writes 26.5 37.8 ms
8 * 2kB open_sync writes 14.2 70.2 ms
16 * 1kB open_sync writes 8.23 122 ms
fsync on a non-write descriptor
write, fsync, close 125 7.99 ms
write, close, fsync 123 8.12 ms
Non-synced 8 kB writes
write 985,802 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) 1 256 3.37 ms 6.27 ms 10 ms 48.7 ms 0
Read/write (TPC-B like) 8 801 7.35 ms 24.4 ms 49.6 ms 94.3 ms 0
Read/write (TPC-B like) 32 1,004 19.6 ms 93.5 ms 193 ms 345 ms 0
Read only 1 20,722 0.043 ms 0.072 ms 0.102 ms 0.204 ms 0
Read only 8 29,927 0.246 ms 0.409 ms 0.502 ms 1.15 ms 0
Read only 32 32,265 0.894 ms 1.36 ms 1.85 ms 3.32 ms 0

Scale 10 (1,000,000 accounts), loaded in 4.18 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) 1 174 4.63 ms 10.4 ms 18.6 ms 31.1 ms 0
Read/write (TPC-B like) 8 471 7.78 ms 78.8 ms 177 ms 312 ms 0
Read/write (TPC-B like) 32 355 53.5 ms 233 ms 787 ms 1.76 s 0
Read only 1 560 1.04 ms 3.69 ms 7.12 ms 180 ms 0
Read only 8 1,055 6.8 ms 20.2 ms 33 ms 93.5 ms 0
Read only 32 972 30.5 ms 76.2 ms 375 ms 734 ms 0

Scale 100 (10,000,000 accounts), loaded in 80.6 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 Errors
Read/write 1 4.62 92.5 107 ms 646 ms 802 ms 0
Read/write 8 7.58 152 910 ms 2.83 s 3.98 s 0
Read/write 32 13.5 270 2.16 s 4.52 s 5.31 s 0
Read only 1 466 7,450 1.47 ms 3.43 ms 14.5 ms 0
Read only 8 1,095 17,525 7.17 ms 10.1 ms 11.7 ms 0
Read only 32 1,035 16,555 30.8 ms 39.7 ms 45 ms 0

10 tables of 100,000 rows, loaded in 215 s. 60 to 63 s per run, one connection per thread.

Redis

memtier

Mix Operations/s Hits/s Median p99 p99.9
1:10 set:get 59,371 53,973 0.839 ms 2.96 ms 4.67 ms
1:1 set:get 59,962 29,981 0.791 ms 2.98 ms 4.67 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 443 1,517 2,214 1.15 s
Express express-postgresjs 5,873 7,818 17,877 84.1 ms
Fastify fastify-postgres 5,674 8,212 20,255 188 ms
NestJS nestjs 3,227 3,449 11,013 139 ms
Nuxt nuxt 5,165 7,139 16,132 440 ms
FastAPI fastapi 2,690 3,092 18,463 389 ms
Django django-postgresql 959 1,074 2,184 482 ms
Rails rails 1,072 1,466 7,108 338 ms
Laravel laravel 568 620 1,158 512 ms
Symfony symfony 731 752 2,192 393 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 1.73 925 ms 1.03 s 1.07 s 0%
Shop page 1.73 1.26 s 1.38 s 1.42 s 0%
Category page 1.73 767 ms 1.23 s 1.29 s 0%
Product page 1.73 843 ms 980 ms 1.01 s 0%
Product search 1.73 746 ms 868 ms 875 ms 0%
32 virtual users
Home page 1.81 3.31 s 3.67 s 3.81 s 0%
Shop page 1.81 4.38 s 4.9 s 5.04 s 0%
Category page 1.81 3.95 s 4.62 s 4.82 s 0%
Product page 1.74 3.43 s 3.72 s 3.79 s 0%
Product search 1.37 3.06 s 3.33 s 3.42 s 0%

Cart and checkout

Step Requests/s Median p95 p99 Error rate
8 virtual users
Add to cart 3.31 968 ms 1.09 s 1.14 s 0%
Cart 3.31 787 ms 878 ms 944 ms 0%
Checkout 3.31 596 ms 666 ms 679 ms 0%
32 virtual users
Add to cart 3.34 3.29 s 4 s 4.21 s 0%
Cart 3.34 3.44 s 3.84 s 3.99 s 0%
Checkout 3.34 2.65 s 3.06 s 3.14 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 1.47 310 ms 343 ms 373 ms 0%
Topic JSON 0.743 155 ms 174 ms 233 ms 0%
Home page 0.743 274 ms 535 ms 671 ms 0%
Categories page 0.363 319 ms 347 ms 365 ms 0%
User activity page 0.363 197 ms 218 ms 235 ms 0%
4 virtual users
Topic page 3.31 540 ms 751 ms 1.3 s 0%
Topic JSON 1.65 274 ms 354 ms 401 ms 0%
Home page 1.63 472 ms 583 ms 1 s 0%
Categories page 0.84 557 ms 693 ms 1.22 s 0%
User activity page 0.823 345 ms 465 ms 757 ms 0%
16 virtual users
Topic page 3.16 1.62 s 2.03 s 2.28 s 0%
Topic JSON 1.6 1.43 s 1.97 s 2.17 s 0%
Home page 1.6 1.6 s 2.16 s 2.51 s 0%
Categories page 0.786 1.68 s 2.17 s 2.61 s 0%
User activity page 0.786 1.41 s 1.98 s 2.11 s 0%

Anonymous

Step Requests/s Median p95 p99 Error rate
16 virtual users
Topic page 56.1 81.5 ms 188 ms 324 ms 0%
Topic JSON 28.1 78.8 ms 187 ms 303 ms 0%
Home page 28.1 79.1 ms 181 ms 313 ms 0%
Categories page 14 87.3 ms 191 ms 299 ms 0%
User activity page 14.1 239 ms 462 ms 700 ms 0%

k6 with a fixed number of virtual users, 60 to 62 s per level, after a 22 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 332 MB of it. The container peaked at 1,469 MB.

Ghost

Readers

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 6.05 47 ms 54.4 ms 74.2 ms 0%
Post page 15.1 24.7 ms 30.2 ms 40.7 ms 0%
Tag page 3.03 32.1 ms 37.7 ms 52.6 ms 0%
Author page 3.01 31.9 ms 35.5 ms 39.2 ms 0%
RSS feed 3.01 40.3 ms 45.7 ms 46.9 ms 0%
4 virtual users
Home page 7.55 139 ms 185 ms 228 ms 0%
Post page 18.9 95.2 ms 142 ms 176 ms 0%
Tag page 3.77 87.2 ms 126 ms 138 ms 0%
Author page 3.77 90.1 ms 135 ms 179 ms 0%
RSS feed 3.77 96.8 ms 137 ms 151 ms 0%
16 virtual users
Home page 7.63 526 ms 631 ms 666 ms 0%
Post page 19 445 ms 549 ms 578 ms 0%
Tag page 3.8 290 ms 360 ms 406 ms 0%
Author page 3.78 284 ms 353 ms 395 ms 0%
RSS feed 3.78 297 ms 381 ms 402 ms 0%

Staff in Ghost Admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Post list 1.37 50.2 ms 60.9 ms 68.3 ms 0%
Post editor 4.14 19.2 ms 24.6 ms 39.1 ms 0%
Saving a draft 4.14 134 ms 419 ms 700 ms 0%
Member list 1.37 63 ms 79.3 ms 127 ms 0%
4 virtual users
Post list 1.87 56.5 ms 70.6 ms 120 ms 0%
Post editor 5.7 22.6 ms 31.8 ms 53.9 ms 0%
Saving a draft 5.73 545 ms 1.03 s 2.16 s 0%
Member list 1.9 67.1 ms 76.9 ms 105 ms 0%

k6 with a fixed number of virtual users, 60 to 62 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 353 MB and MySQL at 556 MB.

Wagtail

Visitors

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 1.18 108 ms 119 ms 122 ms 0%
Blog index 1.16 394 ms 418 ms 426 ms 0%
Blog post 3.49 36.8 ms 55.1 ms 62.8 ms 0%
Bread page 3.49 40.4 ms 46.1 ms 48.1 ms 0%
Location page 1.16 38.3 ms 45.2 ms 48.9 ms 0%
Site search 1.16 72.3 ms 114 ms 162 ms 0%
4 virtual users
Home page 1.9 273 ms 417 ms 471 ms 0%
Blog index 1.95 1.03 s 1.44 s 1.51 s 0%
Blog post 5.73 80.3 ms 144 ms 196 ms 0%
Bread page 5.76 93 ms 139 ms 162 ms 0%
Location page 1.95 82.1 ms 119 ms 146 ms 0%
Site search 1.9 128 ms 242 ms 266 ms 0%
16 virtual users
Home page 1.86 962 ms 1.32 s 1.62 s 0%
Blog index 1.95 2.54 s 3.06 s 3.43 s 0%
Blog post 5.6 555 ms 864 ms 1.13 s 0%
Bread page 5.62 557 ms 928 ms 1.24 s 0%
Location page 1.91 560 ms 854 ms 982 ms 0%
Site search 1.86 651 ms 984 ms 1.32 s 0%

Editors in the Wagtail admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Admin dashboard 0.594 110 ms 127 ms 132 ms 0%
Page explorer 1.22 367 ms 457 ms 572 ms 0%
Page editor 1.8 188 ms 293 ms 371 ms 0%
Image library 0.594 73.8 ms 85.1 ms 704 ms 0%
Admin page search 0.594 42.5 ms 97.7 ms 183 ms 0%
4 virtual users
Admin dashboard 0.958 244 ms 464 ms 697 ms 0%
Page explorer 1.95 881 ms 1.64 s 2.18 s 0%
Page editor 2.89 439 ms 872 ms 973 ms 0%
Image library 0.958 234 ms 482 ms 616 ms 0%
Admin page search 0.958 109 ms 243 ms 376 ms 0%

k6 with a fixed number of virtual users, 60 to 62 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 295 MB, Postgres at 177 MB, and Redis at 26 MB.

Advertised vs. measured

Advertised Measured
vCPU 2 2
CPU Shared vCPU 5.6% of busy CPU time stolen
RAM 2 GB 1.9 GiB
Storage 19.3 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
Neoverse-N1
CPU cores
2
CPU frequency
Unknown
AES-NI
Yes
VM-x/AMD-V
No
RAM reported
1.9 GiB
Swap reported
0 MiB
Disk reported
19.3 GiB
Virtualization reported
KVM
CPU steal
5.6% of busy CPU time stolen
Distro
Ubuntu 24.04.3 LTS
Kernel
6.8.0-90-generic
Architecture
arm64
IPv4 reachable
Yes
IPv6 reachable
Yes

Advertised at test time

Plan
CPU-Optimized A1 2 vCPU / 2 GB
Product line
CPU-Optimized A1
Location
Manassas
vCPU
2 shared vCPU
Architecture
arm64
RAM
2 GB
Storage
Virtualization
KVM
Network
1 Gbps
Transfer
Unmetered
Port 25
Unknown
Monthly price at test time
€23.48 EUR
Hourly price at test time
€0.033 EUR
YABS version
v2026-09-20
Ran at
Oct 14, 2026, 13:19:57 UTC
Parser version
5

Run timeline

Queued
Oct 14, 2026, 13:19:00 UTC
Server created
Oct 14, 2026, 13:19:51 UTC
First update from the server
Oct 14, 2026, 13:19:51 UTC
Completed
Oct 14, 2026, 15:15:00 UTC
Server deleted
Oct 14, 2026, 15:15:00 UTC
Cost of this run
€0.063 EUR
Watch party 0 watching

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

Watch party

Loading the party