Skip to main content

DigitalOcean CPU-Optimized 2 vCPU / 4 GB

San Francisco 2

Benchmark complete
Finished Oct 7, 2026
Geekbench 7 single-core
1,057
Faster than 53% of 2 vCPU plans
Geekbench 7 multi-core
1,251
Faster than 18% of 2 vCPU plans
Disk 4K IOPS
60,279
fio random read and write, 50/50
Monthly price at test time
$42.00
30 multi-core points per dollar
Same price today

Server

  • Provider
    DigitalOcean
  • Plan
    CPU-Optimized 2 vCPU / 4 GB
  • Location
    San Francisco 2
  • vCPU
    2
  • RAM
    4 GB
  • Storage
    25 GB SSD
  • Network
    2 Gbps
  • OS image
    ubuntu-24-04-x64
  • Trigger
    Scheduled
  • Queued at
    Oct 7, 2026, 01:06:00 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 1,057 1,251 Geekbench Browser

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
1,084
102nd of 166
1,146
106th of 121
Navigation
1,299
77th of 166
Single-core only
HTML5 Browser
1,067
94th of 166
Single-core only
PDF Viewer
1,157
97th of 166
Single-core only
Photo Library
880
107th of 166
1,086
106th of 121
Clang
1,113
84th of 166
1,475
93rd of 121
Text Processing
901
121st of 166
1,105
110th of 121
Asset Compression
893
128th of 166
1,226
110th of 121
HDR
1,002
91st of 166
1,139
105th of 121
Photo Editor
1,170
87th of 166
1,449
96th of 121
Ray Tracer
1,047
103rd of 166
1,459
105th of 121
Structure from Motion
1,163
101st of 166
Single-core only
Game Physics
1,030
100th of 166
Single-core only
Video Encoder
1,027
98th of 166
Single-core only
Audio Encoder
1,096
104th of 166
Single-core only
Video Player
1,077
100th of 166
Single-core only

Rank among the 166 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 11.7 GB/s 3 0.194%
Scale higher is better 13.3 GB/s 3 0.542%
Add higher is better 13.9 GB/s 3 0.643%
Triad higher is better 14 GB/s 3 0.622%

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 252/s 3 1.54%
RSA 4096 verifies higher is better 16,763/s 3 0.0883%
SHA-256 higher is better 285 MB/s 3 0.102%
AES-256-GCM higher is better 3.74 GB/s 3 0.339%
ChaCha20-Poly1305 higher is better 2.6 GB/s 3 0.334%

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 7.14 ms 3 0.129%
Requests per second, 90th percentile higher is better 278/s 3 0.208%
Request latency, 99.9th percentile lower is better 13.3 ms 3 0.847%
Requests per second, average higher is better 277/s 3 0.0902%

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

Disk

Block size Read Write Total
4K 117.6 MB/s (30,100 IOPS) 117.9 MB/s (30,179 IOPS) 235.5 MB/s (60,279 IOPS)
64K 152.1 MB/s (2,433 IOPS) 152.9 MB/s (2,445 IOPS) 304.9 MB/s (4,878 IOPS)
512K 204.6 MB/s (409 IOPS) 215.4 MB/s (430 IOPS) 420 MB/s (839 IOPS)
1M 218.4 MB/s (218 IOPS) 232.9 MB/s (232 IOPS) 451.3 MB/s (450 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 873 Mbps 1.64 Gbps
Eranium, Amsterdam, NL (100G) IPv4 1.06 Gbps 1.66 Gbps
Leaseweb, Singapore, SG (10G) IPv4 1.09 Gbps 1.29 Gbps
Clouvider, Los Angeles, CA, US (10G) IPv4 1.96 Gbps 1.88 Gbps
Leaseweb, NYC, NY, US (10G) IPv4 1.73 Gbps 1.48 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 1,288 0.777 ms
fdatasync 1,519 0.658 ms
fsync 692 1.45 ms
fsync_writethrough Not supported here n/a
open_sync 742 1.35 ms
Two 8 kB writes
open_datasync 823 1.22 ms
fdatasync 1,582 0.632 ms
fsync 639 1.57 ms
fsync_writethrough Not supported here n/a
open_sync 354 2.82 ms
open_sync at different write sizes
1 * 16kB open_sync write 751 1.33 ms
2 * 8kB open_sync writes 379 2.64 ms
4 * 4kB open_sync writes 213 4.7 ms
8 * 2kB open_sync writes 97.1 10.3 ms
16 * 1kB open_sync writes 43.7 22.9 ms
fsync on a non-write descriptor
write, fsync, close 691 1.45 ms
write, close, fsync 778 1.29 ms
Non-synced 8 kB writes
write 612,131 0.002 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) 1 878 1.04 ms 1.26 ms 3.16 ms 27.2 ms 0
Read/write (TPC-B like) 8 2,417 2.75 ms 5.64 ms 11.6 ms 52.6 ms 0
Read/write (TPC-B like) 32 2,528 9.21 ms 30.3 ms 57.1 ms 186 ms 0
Read only 1 19,192 0.057 ms 0.069 ms 0.083 ms 0.191 ms 0
Read only 8 28,070 0.262 ms 0.409 ms 0.493 ms 1.39 ms 0
Read only 32 28,746 0.98 ms 1.46 ms 2.01 ms 3.92 ms 0

Scale 10 (1,000,000 accounts), loaded in 2.32 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) 1 659 1.21 ms 1.82 ms 7.08 ms 50.2 ms 0
Read/write (TPC-B like) 8 1,800 3.53 ms 8.86 ms 21 ms 70.7 ms 0
Read/write (TPC-B like) 32 2,105 10.9 ms 34.7 ms 92.5 ms 201 ms 0
Read only 1 12,596 0.068 ms 0.105 ms 0.406 ms 2.36 ms 0
Read only 8 22,170 0.336 ms 0.518 ms 0.685 ms 2.18 ms 0
Read only 32 23,075 1.25 ms 1.93 ms 2.67 ms 4.93 ms 0

Scale 100 (10,000,000 accounts), loaded in 26.9 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 1 154 3,083 5.18 ms 9.73 ms 37.6 ms 0
Read/write 8 405 8,095 15.8 ms 47.5 ms 94.1 ms 0
Read/write 32 332 6,632 65.6 ms 303 ms 580 ms 0
Read only 1 585 9,362 1.79 ms 2.26 ms 2.81 ms 0
Read only 8 995 15,912 7.84 ms 10.7 ms 12.8 ms 0
Read only 32 919 14,711 35 ms 44.2 ms 50.1 ms 0

10 tables of 100,000 rows, loaded in 17.7 s. 60 s per run, one connection per thread.

Redis

memtier

Mix Operations/s Hits/s Median p99 p99.9
1:10 set:get 42,949 39,044 1.26 ms 3.3 ms 5.89 ms
1:1 set:get 41,625 20,812 1.33 ms 3.28 ms 5.66 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 The results arrived but couldn't be read, so no numbers are shown.
Express The results arrived but couldn't be read, so no numbers are shown.
Fastify The results arrived but couldn't be read, so no numbers are shown.
NestJS The results arrived but couldn't be read, so no numbers are shown.
Nuxt The results arrived but couldn't be read, so no numbers are shown.
FastAPI The results arrived but couldn't be read, so no numbers are shown.
Django The results arrived but couldn't be read, so no numbers are shown.
Rails The results arrived but couldn't be read, so no numbers are shown.
Laravel The results arrived but couldn't be read, so no numbers are shown.
Symfony The results arrived but couldn't be read, so no numbers are shown.

Web apps

WooCommerce

Page mix

Step Requests/s Median p95 p99 Error rate
8 virtual users
Home page 1.31 1.2 s 1.3 s 1.34 s 0%
Shop page 1.31 1.62 s 1.71 s 1.77 s 0%
Category page 1.31 1.02 s 1.62 s 1.67 s 0%
Product page 1.31 1.1 s 1.27 s 1.3 s 0%
Product search 1.31 970 ms 1.07 s 1.09 s 0%
32 virtual users
Home page 1.36 4.35 s 4.84 s 4.96 s 0%
Shop page 1.36 5.78 s 6.65 s 6.75 s 0%
Category page 1.36 5.11 s 6.15 s 6.3 s 0%
Product page 1.36 4.37 s 4.68 s 4.75 s 0%
Product search 1.13 4.17 s 4.46 s 4.52 s 0%

Cart and checkout

Step Requests/s Median p95 p99 Error rate
8 virtual users
Add to cart 2.48 1.29 s 1.46 s 1.55 s 0%
Cart 2.48 1.05 s 1.21 s 1.25 s 0%
Checkout 2.48 822 ms 963 ms 975 ms 0%
32 virtual users
Add to cart 2.5 4.27 s 5.19 s 5.25 s 0%
Cart 2.5 4.6 s 4.98 s 5.03 s 0%
Checkout 2.5 3.62 s 4.07 s 4.17 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.

Advertised vs. measured

Advertised Measured
vCPU 2 2
CPU Dedicated vCPU 0% of busy CPU time stolen
RAM 4 GB 3.8 GiB
Storage 25 GB SSD 24.1 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(R) Xeon(R) Platinum 8168 CPU @ 2.70GHz
CPU cores
2
CPU frequency
2694 MHz
AES-NI
Yes
VM-x/AMD-V
Yes
RAM reported
3.8 GiB
Swap reported
0 MiB
Disk reported
24.1 GiB
Virtualization reported
KVM
CPU steal
0% 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
CPU-Optimized 2 vCPU / 4 GB
Product line
CPU-Optimized
Location
San Francisco 2
vCPU
2 dedicated vCPU
Architecture
x86_64
RAM
4 GB
Storage
25 GB SSD
Virtualization
KVM
Network
2 Gbps
Transfer
4 TB
Port 25
Closed
Monthly price at test time
$42.00
Hourly price at test time
$0.063
YABS version
v2026-09-20
Ran at
Oct 7, 2026, 01:07:20 UTC
Parser version
5

Run timeline

Queued
Oct 7, 2026, 01:06:00 UTC
Server created
Oct 7, 2026, 01:07:16 UTC
First update from the server
Oct 7, 2026, 01:07:16 UTC
Completed
Oct 7, 2026, 02:31:00 UTC
Server deleted
Oct 7, 2026, 02:31:00 UTC
Cost of this run
$0.089
Watch party 0 watching

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

Watch party

Loading the party