Skip to main content

DigitalOcean Basic 2 vCPU / 2 GB

San Francisco 2

Benchmark complete
Finished Oct 15, 2026
Geekbench 7 single-core
694
Faster than 12% of 2 vCPU plans
Geekbench 7 multi-core
Skipped
Disk 4K IOPS
56,881
fio random read and write, 50/50
Monthly price at test time
$18.00
Same price today

Server

  • Provider
    DigitalOcean
  • Plan
    Basic 2 vCPU / 2 GB
  • Location
    San Francisco 2
  • vCPU
    2
  • RAM
    2 GB
  • Storage
    60 GB SSD
  • Network
    2 Gbps
  • OS image
    ubuntu-24-04-x64
  • Trigger
    Scheduled
  • Queued at
    Oct 15, 2026, 04:24:00 UTC
Visit DigitalOcean

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

Latest runs of this plan

Full history of this plan

CPU

Version Single-core Multi-core
Geekbench 7 694 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
808
156th of 178
Single-core only
Navigation
888
158th of 178
Single-core only
HTML5 Browser
643
158th of 178
Single-core only
PDF Viewer
711
162nd of 178
Single-core only
Photo Library
619
156th of 178
Single-core only
Clang
714
154th of 178
Single-core only
Text Processing
603
159th of 178
Single-core only
Asset Compression
656
163rd of 178
Single-core only
HDR
699
155th of 178
Single-core only
Photo Editor
821
138th of 178
Single-core only
Ray Tracer
694
157th of 178
Single-core only
Structure from Motion
814
156th of 178
Single-core only
Game Physics
541
170th of 178
Single-core only
Video Encoder
637
156th of 178
Single-core only
Audio Encoder
773
157th of 178
Single-core only
Video Player
585
162nd of 178
Single-core only

Rank among the 178 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 18.8 GB/s 3 0.277%
Scale higher is better 19.2 GB/s 3 0.54%
Add higher is better 24.5 GB/s 3 1.15%
Triad higher is better 24 GB/s 3 1.15%

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 353/s 3 9.21%
RSA 4096 verifies higher is better 22,536/s 3 8.22%
SHA-256 higher is better 383 MB/s 3 9.39%
AES-256-GCM higher is better 5.54 GB/s 3 3.03%
ChaCha20-Poly1305 higher is better 2.59 GB/s 3 5.58%

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 4.7 ms 3 1.02%
Requests per second, 90th percentile higher is better 412/s 3 2.07%
Request latency, 99.9th percentile lower is better 10.7 ms 3 7.95%
Requests per second, average higher is better 373/s 3 2.71%

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

Disk

Block size Read Write Total
4K 111 MB/s (28,403 IOPS) 111.2 MB/s (28,478 IOPS) 222.2 MB/s (56,881 IOPS)
64K 383.1 MB/s (6,129 IOPS) 385.1 MB/s (6,161 IOPS) 768.2 MB/s (12,290 IOPS)
512K 498.1 MB/s (996 IOPS) 524.6 MB/s (1,049 IOPS) 1022.7 MB/s (2,045 IOPS)
1M 543.6 MB/s (543 IOPS) 579.8 MB/s (579 IOPS) 1.1 GB/s (1,122 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 556 Mbps 1.61 Gbps
Eranium, Amsterdam, NL (100G) IPv4 1.28 Gbps 1.69 Gbps
Leaseweb, Singapore, SG (10G) IPv4 842 Mbps 1.23 Gbps
Clouvider, Los Angeles, CA, US (10G) IPv4 2 Gbps 1.05 Gbps
Leaseweb, NYC, NY, US (10G) IPv4 1.89 Gbps 1.5 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 2,677 0.374 ms
fdatasync 2,434 0.411 ms
fsync 1,325 0.755 ms
fsync_writethrough Not supported here n/a
open_sync 1,473 0.679 ms
Two 8 kB writes
open_datasync 1,375 0.727 ms
fdatasync 2,377 0.421 ms
fsync 1,238 0.808 ms
fsync_writethrough Not supported here n/a
open_sync 631 1.59 ms
open_sync at different write sizes
1 * 16kB open_sync write 1,158 0.864 ms
2 * 8kB open_sync writes 601 1.66 ms
4 * 4kB open_sync writes 317 3.16 ms
8 * 2kB open_sync writes 175 5.71 ms
16 * 1kB open_sync writes 95.7 10.4 ms
fsync on a non-write descriptor
write, fsync, close 1,218 0.821 ms
write, close, fsync 1,165 0.859 ms
Non-synced 8 kB writes
write 708,346 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 1,079 0.856 ms 1.28 ms 2.1 ms 8.7 ms 0
Read/write (TPC-B like) 8 2,728 2.62 ms 5.27 ms 7.92 ms 17.4 ms 0
Read/write (TPC-B like) 32 2,812 8.73 ms 28.2 ms 47.1 ms 78 ms 0
Read only 1 23,047 0.039 ms 0.067 ms 0.088 ms 0.156 ms 0
Read only 8 30,787 0.233 ms 0.427 ms 0.552 ms 1.28 ms 0
Read only 32 27,181 0.997 ms 2.03 ms 2.85 ms 5.21 ms 0

Scale 10 (1,000,000 accounts), loaded in 2.36 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) 1 651 1.42 ms 2.39 ms 4.2 ms 15.5 ms 0
Read/write (TPC-B like) 8 1,993 3.69 ms 6.71 ms 10.9 ms 22.1 ms 0
Read/write (TPC-B like) 32 2,168 13.8 ms 24 ms 31.8 ms 44.2 ms 0
Read only 1 2,249 0.391 ms 0.828 ms 1.59 ms 3.2 ms 0
Read only 8 17,136 0.374 ms 1.01 ms 1.9 ms 3.31 ms 0
Read only 32 19,640 1.35 ms 2.98 ms 4.48 ms 8.38 ms 0

Scale 100 (10,000,000 accounts), loaded in 29 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 1 198 3,953 4.65 ms 7.43 ms 14.7 ms 0
Read/write 8 558 11,160 13.5 ms 23.1 ms 30.8 ms 0
Read/write 32 438 8,751 61.1 ms 137 ms 282 ms 0
Read only 1 443 7,088 2.11 ms 3.36 ms 5.67 ms 0
Read only 8 1,043 16,682 7.43 ms 11.4 ms 13.7 ms 0
Read only 32 863 13,815 35.6 ms 52.9 ms 60 ms 0

10 tables of 100,000 rows, loaded in 13.2 s. 60 to 61 s per run, one connection per thread.

Redis

memtier

Mix Operations/s Hits/s Median p99 p99.9
1:10 set:get 43,556 39,595 1.3 ms 4.06 ms 8.51 ms
1:1 set:get 40,394 20,197 1.4 ms 4.32 ms 7.78 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 234 706 1,358 2.69 s
Express express-postgresjs 3,732 5,111 12,117 163 ms
Fastify fastify-postgres 5,091 7,310 16,265 134 ms
NestJS nestjs 2,406 2,696 11,111 209 ms
Nuxt nuxt 3,161 4,530 15,289 175 ms
FastAPI fastapi 1,492 1,977 7,401 1.25 s
Django django-postgresql 674 855 1,661 568 ms
Rails rails 1,224 1,312 7,019 348 ms
Laravel laravel 461 467 900 766 ms
Symfony symfony 461 496 1,593 687 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 1.03 1.47 s 1.73 s 1.86 s 0%
Shop page 1.03 1.94 s 2.38 s 2.47 s 0%
Category page 1.03 1.27 s 2.2 s 2.49 s 0%
Product page 1.03 1.32 s 1.69 s 1.73 s 0%
Product search 1.03 1.12 s 1.34 s 1.46 s 0%
32 virtual users
Home page 1.35 4.8 s 7.06 s 7.41 s 0%
Shop page 1.32 7.07 s 9.01 s 9.32 s 0%
Category page 0.996 5.87 s 8.11 s 8.42 s 0%
Product page 0.898 4.73 s 5.22 s 5.43 s 0%
Product search 0.898 4.23 s 5.02 s 5.11 s 0%

Cart and checkout

Step Requests/s Median p95 p99 Error rate
8 virtual users
Add to cart 1.94 1.58 s 1.81 s 1.95 s 0%
Cart 1.94 1.27 s 1.5 s 1.63 s 0%
Checkout 1.94 956 ms 1.15 s 1.27 s 0%
32 virtual users
Add to cart 2.46 4.45 s 5.65 s 5.92 s 0%
Cart 2.46 4.61 s 5.31 s 5.61 s 0%
Checkout 2.46 3.56 s 4.12 s 4.23 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.

Discourse

Signed in

Step Requests/s Median p95 p99 Error rate
1 virtual user
Topic page 1.08 399 ms 489 ms 578 ms 0%
Topic JSON 0.557 209 ms 265 ms 492 ms 0%
Home page 0.557 359 ms 448 ms 513 ms 0%
Categories page 0.278 422 ms 584 ms 874 ms 0%
User activity page 0.262 247 ms 515 ms 554 ms 0%
4 virtual users
Topic page 1.7 1.02 s 1.4 s 2.08 s 0%
Topic JSON 0.86 559 ms 691 ms 781 ms 0%
Home page 0.844 912 ms 1.17 s 1.35 s 0%
Categories page 0.454 1.07 s 1.46 s 1.81 s 0%
User activity page 0.422 616 ms 1.02 s 1.36 s 0%
16 virtual users
Topic page 1.67 2.08 s 2.76 s 3.04 s 0%
Topic JSON 0.827 1.65 s 2.22 s 2.34 s 0%
Home page 0.811 2 s 2.76 s 3.3 s 0%
Categories page 0.398 2.15 s 2.89 s 3.5 s 0%
User activity page 0.43 1.64 s 2.21 s 2.36 s 0%

Anonymous

Step Requests/s Median p95 p99 Error rate
16 virtual users
Topic page 33.8 130 ms 323 ms 406 ms 0.195%
Topic JSON 16.9 122 ms 308 ms 430 ms 0.195%
Home page 16.9 130 ms 322 ms 442 ms 0.195%
Categories page 8.47 132 ms 322 ms 465 ms 0%
User activity page 8.48 409 ms 691 ms 832 ms 0%

k6 with a fixed number of virtual users, 61 to 63 s per level, after a 23 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 417 MB of it. The container peaked at 1,504 MB.

Ghost

Readers

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 4.49 62.8 ms 83.5 ms 98.4 ms 0%
Post page 11.2 33.6 ms 44.8 ms 66.5 ms 0%
Tag page 2.25 42.8 ms 60.2 ms 65.2 ms 0%
Author page 2.25 41.5 ms 53.8 ms 62.1 ms 0%
RSS feed 2.23 49.8 ms 66.9 ms 84.3 ms 0%
4 virtual users
Home page 5.29 190 ms 280 ms 350 ms 0%
Post page 13.3 133 ms 215 ms 273 ms 0%
Tag page 2.66 125 ms 192 ms 227 ms 0%
Author page 2.66 126 ms 209 ms 235 ms 0%
RSS feed 2.66 144 ms 231 ms 258 ms 0%
16 virtual users
Home page 5.27 751 ms 1.02 s 1.08 s 0%
Post page 13.1 626 ms 860 ms 976 ms 0%
Tag page 2.61 399 ms 575 ms 640 ms 0%
Author page 2.64 392 ms 544 ms 593 ms 0%
RSS feed 2.64 423 ms 634 ms 695 ms 0%

Staff in Ghost Admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Post list 2.15 66.6 ms 94.3 ms 108 ms 0%
Post editor 6.49 26.6 ms 38.7 ms 51.1 ms 0%
Saving a draft 6.47 68.6 ms 93.4 ms 125 ms 0%
Member list 2.15 79 ms 112 ms 194 ms 0%
4 virtual users
Post list 3 79.1 ms 117 ms 163 ms 0%
Post editor 9.02 41.5 ms 60.9 ms 77.5 ms 0%
Saving a draft 9.04 318 ms 465 ms 539 ms 0%
Member list 3.01 95.4 ms 137 ms 196 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. 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 348 MB and MySQL at 581 MB.

Wagtail

Visitors

Step Requests/s Median p95 p99 Error rate
1 virtual user
Home page 0.781 169 ms 198 ms 236 ms 0%
Blog index 0.781 598 ms 676 ms 740 ms 0%
Blog post 2.31 55.1 ms 82.9 ms 96.8 ms 0%
Bread page 2.33 58.2 ms 72.5 ms 77.2 ms 0%
Location page 0.781 52.9 ms 67.5 ms 75.7 ms 0%
Site search 0.764 94.7 ms 162 ms 172 ms 0%
4 virtual users
Home page 1.29 416 ms 625 ms 731 ms 0%
Blog index 1.33 1.38 s 2.34 s 2.69 s 0%
Blog post 3.89 122 ms 227 ms 335 ms 0%
Bread page 3.92 134 ms 210 ms 310 ms 0%
Location page 1.33 120 ms 194 ms 224 ms 0%
Site search 1.3 213 ms 467 ms 601 ms 0%
16 virtual users
Home page 1.07 1.61 s 2.17 s 2.47 s 0%
Blog index 1.2 4.11 s 4.94 s 5.23 s 0%
Blog post 3.24 918 ms 1.46 s 1.99 s 0%
Bread page 3.34 932 ms 1.56 s 2.03 s 0%
Location page 1.15 962 ms 1.52 s 1.93 s 0%
Site search 1.05 1.04 s 1.77 s 2.11 s 0%

Editors in the Wagtail admin

Step Requests/s Median p95 p99 Error rate
1 virtual user
Admin dashboard 0.326 196 ms 221 ms 226 ms 0%
Page explorer 0.685 670 ms 844 ms 953 ms 0%
Page editor 1.01 321 ms 406 ms 577 ms 0%
Image library 0.326 128 ms 231 ms 1.47 s 0%
Admin page search 0.326 72.3 ms 140 ms 148 ms 0%
4 virtual users
Admin dashboard 0.593 491 ms 718 ms 1.02 s 0%
Page explorer 1.22 1.46 s 2.28 s 2.32 s 0%
Page editor 1.81 731 ms 1.4 s 1.53 s 0%
Image library 0.593 341 ms 667 ms 813 ms 0%
Admin page search 0.593 190 ms 389 ms 435 ms 0%

k6 with a fixed number of virtual users, 60 to 63 s per level, after a 22 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 292 MB, Postgres at 175 MB, and Redis at 26 MB.

Advertised vs. measured

Advertised Measured
vCPU 2 2
CPU Shared vCPU 0.3% of busy CPU time stolen
RAM 2 GB 1.9 GiB
Storage 60 GB SSD 58 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
DO-Regular
CPU cores
2
CPU frequency
2295 MHz
AES-NI
Yes
VM-x/AMD-V
Yes
RAM reported
1.9 GiB
Swap reported
0 MiB
Disk reported
58 GiB
Virtualization reported
KVM
CPU steal
0.3% of busy CPU time stolen
Distro
Ubuntu 24.04.5 LTS
Kernel
6.8.0-142-generic
Architecture
x86_64
IPv4 reachable
Yes
IPv6 reachable
Yes

Advertised at test time

Plan
Basic 2 vCPU / 2 GB
Product line
Basic
Location
San Francisco 2
vCPU
2 shared vCPU
Architecture
x86_64
RAM
2 GB
Storage
60 GB SSD
Virtualization
KVM
Network
2 Gbps
Transfer
3 TB
Port 25
Closed
Monthly price at test time
$18.00
Hourly price at test time
$0.027
YABS version
v2026-09-20
Ran at
Oct 15, 2026, 04:25:43 UTC
Parser version
5

Run timeline

Queued
Oct 15, 2026, 04:24:00 UTC
First update from the server
Oct 15, 2026, 04:25:22 UTC
Completed
Oct 15, 2026, 06:04:00 UTC
Server deleted
Oct 15, 2026, 06:04:00 UTC
Cost of this run
$0.045
Watch party 0 watching

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

Watch party

Loading the party