Skip to main content

RamNode 3GB Storage

Los Angeles, CA

Benchmark complete
Finished Oct 17, 2026
Geekbench 7 single-core
854
Faster than 19% of 2 vCPU plans
Geekbench 7 multi-core
Skipped
Disk 4K IOPS
453
fio random read and write, 50/50
Monthly price at test time
$17.00
Same price today

Server

  • Provider
    RamNode
  • Plan
    3GB Storage
  • Location
    Los Angeles, CA
  • vCPU
    2
  • RAM
    3 GB
  • Storage
    1 TB HDD
  • Network
    Unknown
  • OS image
    Ubuntu 24.04 Server Cloud
  • Trigger
    Scheduled
  • Queued at
    Oct 17, 2026, 19:25:00 UTC
Visit RamNode

CPU

Version Single-core Multi-core
Geekbench 7 854 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
843
208th of 241
Single-core only
Navigation
1,108
169th of 241
Single-core only
HTML5 Browser
813
195th of 241
Single-core only
PDF Viewer
897
198th of 241
Single-core only
Photo Library
650
203rd of 241
Single-core only
Clang
795
194th of 241
Single-core only
Text Processing
852
186th of 241
Single-core only
Asset Compression
877
190th of 241
Single-core only
HDR
778
192nd of 241
Single-core only
Photo Editor
864
183rd of 241
Single-core only
Ray Tracer
1,018
157th of 241
Single-core only
Structure from Motion
1,017
182nd of 241
Single-core only
Game Physics
856
194th of 241
Single-core only
Video Encoder
796
191st of 241
Single-core only
Audio Encoder
809
206th of 241
Single-core only
Video Player
797
189th of 241
Single-core only

Rank among the 241 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 36.3 GB/s 3 1.11%
Scale higher is better 21.3 GB/s 3 1.07%
Add higher is better 22.8 GB/s 3 0.428%
Triad higher is better 23 GB/s 3 0.334%

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 228/s 3 0.374%
RSA 4096 verifies higher is better 15,091/s 3 0.165%
SHA-256 higher is better 406 MB/s 3 0.776%
AES-256-GCM higher is better 3.73 GB/s 3 0.781%
ChaCha20-Poly1305 higher is better 2.69 GB/s 3 1.17%

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 5.07 ms 3 0.182%
Requests per second, 90th percentile higher is better 390/s 3 0.148%
Request latency, 99.9th percentile lower is better 10.2 ms 3 6.53%
Requests per second, average higher is better 388/s 3 0.293%

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

Disk

Block size Read Write Total
4K 0.9 MB/s (224 IOPS) 0.9 MB/s (229 IOPS) 1.8 MB/s (453 IOPS)
64K 13.7 MB/s (218 IOPS) 14.2 MB/s (227 IOPS) 27.9 MB/s (445 IOPS)
512K 15.5 MB/s (31 IOPS) 16.8 MB/s (33 IOPS) 32.3 MB/s (64 IOPS)
1M 14.8 MB/s (14 IOPS) 16 MB/s (16 IOPS) 30.8 MB/s (30 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 1.27 Gbps 1.11 Gbps
Eranium, Amsterdam, NL (100G) IPv4 1.49 Gbps 1.55 Gbps
Leaseweb, Singapore, SG (10G) IPv4 968 Mbps 1.39 Gbps
Clouvider, Los Angeles, CA, US (10G) IPv4 8.8 Gbps 3.94 Gbps
Leaseweb, NYC, NY, US (10G) IPv4 2.33 Gbps 3.1 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 574 1.74 ms
fdatasync 648 1.54 ms
fsync 30.2 33.1 ms
fsync_writethrough Not supported here n/a
open_sync 63.6 15.7 ms
Two 8 kB writes
open_datasync 236 4.24 ms
fdatasync 538 1.86 ms
fsync 12.3 81.1 ms
fsync_writethrough Not supported here n/a
open_sync 2.62 381 ms
open_sync at different write sizes
1 * 16kB open_sync write 12.9 77.4 ms
2 * 8kB open_sync writes 73.3 13.6 ms
4 * 4kB open_sync writes 45.4 22 ms
8 * 2kB open_sync writes 10.4 96 ms
16 * 1kB open_sync writes 4.48 223 ms
fsync on a non-write descriptor
write, fsync, close 47.3 21.2 ms
write, close, fsync 66.3 15.1 ms
Non-synced 8 kB writes
write 674,337 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) 1 273 2 ms 3.89 ms 14.6 ms 434 ms 0
Read/write (TPC-B like) 8 263 4.18 ms 20.7 ms 343 ms 4.26 s 0
Read/write (TPC-B like) 32 109 13.3 ms 176 ms 7.5 s n/a 0
Read only 1 5,692 0.066 ms 0.103 ms 0.144 ms 0.858 ms 0
Read only 8 24,864 0.286 ms 0.47 ms 0.608 ms 2.18 ms 0
Read only 32 28,815 0.994 ms 1.6 ms 2.03 ms 3.67 ms 0

Scale 10 (1,000,000 accounts), loaded in 3.7 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 45.3 2.54 ms 64.5 ms 212 ms n/a 0
Read/write (TPC-B like) 8 156 5.51 ms 124 ms 603 ms n/a 0
Read/write (TPC-B like) 32 13 1.94 s 5.29 s 7 s n/a 0
Read only 1 53.7 0.275 ms 58.8 ms 184 ms n/a 0
Read only 8 400 0.304 ms 86.1 ms 338 ms 968 ms 0
Read only 32 1,008 0.412 ms 180 ms 470 ms 767 ms 0

Scale 100 (10,000,000 accounts), loaded in 156 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 12.6 251 28.7 ms 215 ms 1.09 s 0
Read/write 8 21.5 429 183 ms 1.43 s 4.44 s 0
Read/write 32 21.4 427 707 ms 4.77 s 5.51 s 0
Read only 1 95.3 1,525 3.55 ms 45 ms 130 ms 0
Read only 8 946 15,134 7.17 ms 11.2 ms 47.5 ms 0
Read only 32 944 15,098 33.1 ms 41.1 ms 53.9 ms 0

10 tables of 100,000 rows, loaded in 26.4 s. 60 to 64 s per run, one connection per thread.

Redis

memtier

Mix Operations/s Hits/s Median p99 p99.9
1:10 set:get 58,595 53,268 0.639 ms 3.18 ms 5.22 ms
1:1 set:get 56,622 28,311 0.727 ms 3.06 ms 5.06 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 380 1,288 1,662 984 ms
Express express-postgresjs 5,317 6,813 15,595 110 ms
Fastify fastify-postgres 5,338 7,197 15,381 208 ms
NestJS nestjs 2,599 2,959 9,225 164 ms
Nuxt nuxt 4,568 6,205 12,472 541 ms
FastAPI fastapi 2,277 2,811 12,022 415 ms
Django django-postgresql 991 1,099 2,198 340 ms
Rails rails 1,490 1,988 7,259 247 ms
Laravel laravel 537 577 1,013 492 ms
Symfony symfony 665 754 1,894 400 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 1.6 975 ms 1.1 s 1.19 s 0%
Shop page 1.6 1.33 s 1.46 s 1.51 s 0%
Category page 1.6 833 ms 1.31 s 1.34 s 0%
Product page 1.6 895 ms 1 s 1.1 s 0%
Product search 1.6 784 ms 872 ms 904 ms 0%
32 virtual users
Home page 1.8 3.47 s 4.13 s 4.24 s 0%
Shop page 1.8 4.68 s 5.24 s 5.33 s 0%
Category page 1.6 4.07 s 4.94 s 5.2 s 0%
Product page 1.35 3.49 s 5.38 s 5.79 s 0%
Product search 1.35 3.27 s 4.08 s 4.21 s 0%

Cart and checkout

Step Requests/s Median p95 p99 Error rate
8 virtual users
Add to cart 2 1.09 s 4.61 s 4.78 s 0%
Cart 2 909 ms 4.43 s 6.27 s 0%
Checkout 2 643 ms 739 ms 782 ms 0%
32 virtual users
Add to cart 2.95 3.55 s 4.47 s 5.04 s 0%
Cart 2.95 3.71 s 6.86 s 7.35 s 0%
Checkout 2.95 2.87 s 3.31 s 4.14 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 1.27 342 ms 476 ms 645 ms 0%
Topic JSON 0.635 177 ms 210 ms 246 ms 0%
Home page 0.635 298 ms 380 ms 485 ms 0%
Categories page 0.326 371 ms 578 ms 601 ms 0%
User activity page 0.309 210 ms 283 ms 410 ms 0%
4 virtual users
Topic page 2.76 632 ms 941 ms 1.14 s 0%
Topic JSON 1.39 335 ms 395 ms 481 ms 0%
Home page 1.36 558 ms 807 ms 1.38 s 0%
Categories page 0.703 654 ms 752 ms 818 ms 0%
User activity page 0.687 388 ms 1.01 s 1.31 s 0%
16 virtual users
Topic page 2.72 1.77 s 2.22 s 2.43 s 0%
Topic JSON 1.33 1.46 s 1.79 s 2.18 s 0%
Home page 1.33 1.63 s 2.32 s 2.55 s 0%
Categories page 0.641 1.78 s 2.3 s 2.64 s 0%
User activity page 0.689 1.53 s 2.04 s 2.27 s 0%

Anonymous

Step Requests/s Median p95 p99 Error rate
16 virtual users
Topic page 60.2 76.8 ms 165 ms 219 ms 0%
Topic JSON 30.1 74.5 ms 171 ms 220 ms 0%
Home page 30.1 80.4 ms 175 ms 226 ms 0%
Categories page 15 76 ms 162 ms 231 ms 0%
User activity page 15.1 234 ms 350 ms 465 ms 0%

k6 with a fixed number of virtual users, 60 to 62 s per level, after a 32 s warmup. The error rate counts responses that weren't a 200. Discourse ran with 4 app workers and 768 MB of Postgres shared buffers, what its installer picks for a 3 GB box. It added a 2 GB swapfile first, the way its installer does, and didn't need it. The container peaked at 2,154 MB.

Ghost

Readers

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 5 55.3 ms 75.1 ms 98.1 ms 0%
Post page 12.5 28.5 ms 41.5 ms 57 ms 0%
Tag page 2.5 37.7 ms 50.6 ms 65.3 ms 0%
Author page 2.5 38.6 ms 51.4 ms 60.4 ms 0%
RSS feed 2.5 48.9 ms 59.6 ms 69.2 ms 0%
4 virtual users
Home page 6.02 177 ms 222 ms 262 ms 0%
Post page 15.1 119 ms 171 ms 220 ms 0%
Tag page 3.03 115 ms 155 ms 207 ms 0%
Author page 3.03 115 ms 161 ms 185 ms 0%
RSS feed 2.99 123 ms 168 ms 206 ms 0%
16 virtual users
Home page 6.14 656 ms 779 ms 852 ms 0%
Post page 15.3 552 ms 672 ms 740 ms 0%
Tag page 3.04 363 ms 462 ms 505 ms 0%
Author page 3.08 355 ms 446 ms 475 ms 0%
RSS feed 3.03 376 ms 487 ms 526 ms 0%

Staff in Ghost Admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Post list 1.65 55.9 ms 90.8 ms 113 ms 0%
Post editor 4.99 20.3 ms 35.4 ms 42.5 ms 0%
Saving a draft 4.99 60.6 ms 157 ms 1.45 s 0%
Member list 1.65 72.9 ms 110 ms 145 ms 0%
4 virtual users
Post list 2.52 70.8 ms 94.7 ms 182 ms 0%
Post editor 7.56 27.1 ms 41.3 ms 54.4 ms 0%
Saving a draft 7.59 334 ms 761 ms 2.77 s 0%
Member list 2.52 83.7 ms 114 ms 149 ms 0%

k6 with a fixed number of virtual users, 60 to 63 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 404 MB and MySQL at 600 MB.

Wagtail

Visitors

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 0.848 143 ms 179 ms 195 ms 0%
Blog index 0.831 501 ms 599 ms 644 ms 0%
Blog post 2.51 56.4 ms 73.8 ms 91.2 ms 0%
Bread page 2.51 60 ms 75 ms 79.2 ms 0%
Location page 0.831 53.7 ms 71.5 ms 73.5 ms 0%
Site search 0.831 91.5 ms 596 ms 685 ms 0%
4 virtual users
Home page 1.92 288 ms 407 ms 450 ms 0%
Blog index 1.92 1.03 s 1.32 s 1.39 s 0%
Blog post 5.73 81.2 ms 142 ms 177 ms 0%
Bread page 5.71 89.5 ms 130 ms 150 ms 0%
Location page 1.92 85.1 ms 131 ms 236 ms 0%
Site search 1.92 130 ms 336 ms 963 ms 0%
16 virtual users
Home page 1.89 978 ms 1.49 s 1.67 s 0%
Blog index 1.95 2.47 s 2.91 s 3.26 s 0%
Blog post 5.67 527 ms 980 ms 1.22 s 0%
Bread page 5.67 532 ms 903 ms 1.14 s 0%
Location page 1.91 488 ms 851 ms 1.08 s 0%
Site search 1.89 645 ms 1.2 s 1.85 s 0%

Editors in the Wagtail admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Admin dashboard 0.358 148 ms 205 ms 210 ms 0%
Page explorer 0.732 585 ms 743 ms 890 ms 0%
Page editor 1.07 272 ms 512 ms 1.87 s 0%
Image library 0.358 134 ms 155 ms 1.05 s 0%
Admin page search 0.358 82.2 ms 168 ms 233 ms 0%
4 virtual users
Admin dashboard 0.74 306 ms 623 ms 667 ms 0%
Page explorer 1.5 1.18 s 1.99 s 2.15 s 0%
Page editor 2.24 570 ms 1.02 s 1.26 s 0%
Image library 0.756 315 ms 584 ms 620 ms 0%
Admin page search 0.74 146 ms 363 ms 623 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 294 MB, Postgres at 203 MB, and Redis at 57 MB.

Advertised vs. measured

Advertised Measured
vCPU 2 2
CPU Shared vCPU 0% of busy CPU time stolen
RAM 3 GB 2.9 GiB
Storage 1 TB HDD 968.6 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 Core Processor (Haswell, no TSX, IBRS)
CPU cores
2
CPU frequency
2300 MHz
AES-NI
Yes
VM-x/AMD-V
Yes
RAM reported
2.9 GiB
Swap reported
0 MiB
Disk reported
968.6 GiB
Virtualization reported
KVM
CPU steal
0% of busy CPU time stolen
Distro
Ubuntu 24.04.1 LTS
Kernel
6.8.0-51-generic
Architecture
x86_64
IPv4 reachable
Yes
IPv6 reachable
No

Advertised at test time

Plan
3GB Storage
Product line
Storage VPS
Location
Los Angeles, CA
vCPU
2 shared vCPU
Architecture
x86_64
RAM
3 GB
Storage
1 TB HDD
Virtualization
KVM
Network
Unknown
Transfer
10 TB
Port 25
Unknown
Monthly price at test time
$17.00
Hourly price at test time
$0.025
YABS version
v2026-09-20
Ran at
Oct 17, 2026, 19:31:28 UTC
Parser version
5

Run timeline

Queued
Oct 17, 2026, 19:25:00 UTC
Server created
Oct 17, 2026, 19:28:37 UTC
First update from the server
Oct 17, 2026, 19:28:37 UTC
Completed
Oct 17, 2026, 21:44:00 UTC
Server deleted
Oct 17, 2026, 21:44:00 UTC
Cost of this run
$0.058
Watch party 0 watching

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

Watch party

Loading the party