joshtronic

Posted in VPS Showdown

VPS Showdown – September 2024 – DigitalOcean vs. Linode vs. Vultr

This post is old news – Get fresh benchmarks at VPS Showdown (daily updates!)

Labor Day weekend, and I'm trying to drum up the inspiration to run some VPS benchmarks. I'm sticking to the theme of comparing like processors, of the AMD variety. I spun up 3 (or 4, more on that later) instances with each provider, all running Ubuntu 24.04 LTS. The results have been averaged, when applicable.

Overview - DigitalOcean vs. Linode vs. Vultr

Version
Linux Distro Ubuntu 24.04 LTS
Kernel Version 6.8.0
MySQL Version 8.0.39
Redis Version 7.0.15
DigitalOcean Linode Vultr
Location New York 1 Newark, NJ New York (NJ)
Monthly Price $7/month $5/month $6/month
Hourly Price $0.01/hour $0.0075/hour $0.009/hour
RAM 1 GB 1 GB 1 GB
CPU 1 Core 1 Core 1 Core
Storage 25 GB 25 GB 25 GB
Storage Type NVMe SSD NVMe
Transfer 1 TB 1 TB 1 TB
Transfer Overage $0.01/GB $0.01/GB $0.01/GB
Backups Standard $1.40/monthDaily $2.10/month $2/month $1.2/month

CPU Info

Model Name
DigitalOcean - All Instances DO-Premium-AMD
Linode - All Instances AMD EPYC 7642 48-Core Processor
Vultr - Instance #1 AMD EPYC-Milan Processor
Vultr - Instance #2 AMD EPYC-Milan Processor
Vultr - Instance #3 AMD EPYC-Rome Processor
DigitalOcean Linode Vultr
CPU MHz 1,996.25 2,300.00 2,832.08
Cache Size (KB) 512.00 512.00 512.00
BogoMips 2,661.67 3,067.00 3,497.67

CPU

DigitalOcean Linode Vultr
Events per Second 1,370.21 1,447.63 3,642.89
Minimum (ms) 0.63 0.60 0.24
Average (ms) 0.73 0.70 0.28
Maximum (ms) 3.52 8.48 4.67

Memory

Read

DigitalOcean Linode Vultr
Ops per Second 4,218,351.05 4,977,966.38 5,262,104.33
Minimum (ms) 0.00 0.00 0.00
Average (ms) 0.00 0.00 0.00
Maximum (ms) 2.05 3.77 2.13

Write

DigitalOcean Linode Vultr
Ops per Second 4,154,348.17 4,768,090.68 5,196,340.27
Minimum (ms) 0.00 0.00 0.00
Average (ms) 0.00 0.00 0.00
Maximum (ms) 1.13 9.89 2.01

File I/O

DigitalOcean Linode Vultr
Reads per Second 1,355.24 2,242.67 1,999.73
Writes per Second 903.45 1,495.11 1,333.12
Fsyncs per Second 2,896.29 4,788.76 4,275.69
Minimum (ms) 0.00 0.00 0.00
Average (ms) 0.20 0.12 0.13
Maximum (ms) 11.44 57.21 22.44

MySQL

Read Only

DigitalOcean Linode Vultr
Transactions per Second 4,309.00 5,009.00 5,984.33
Queries per Second 68,944.00 80,144.00 95,749.33
Minimum (ms) 1.46 1.38 0.98
Average (ms) 2.36 2.07 1.77
Maximum (ms) 25.51 28.51 26.36

Write Only

DigitalOcean Linode Vultr
Transactions per Second 1,836.00 3,665.67 3,570.33
Queries per Second 11,016.00 21,994.00 21,422.00
Minimum (ms) 1.96 1.28 1.05
Average (ms) 5.60 2.82 3.00
Maximum (ms) 100.73 19.27 38.39

Read Write

DigitalOcean Linode Vultr
Transactions per Second 1,116.67 1,836.67 1,730.67
Queries per Second 22,333.33 36,733.33 34,613.33
Minimum (ms) 4.39 3.08 2.71
Average (ms) 9.27 5.65 6.44
Maximum (ms) 37.13 54.65 46.66

Redis

DigitalOcean Linode Vultr
PING_INLINE 31,667.46 38,227.03 36,913.69
PING_MBULK 32,539.55 40,505.34 38,208.83
SET 31,720.08 36,289.96 37,853.12
GET 30,229.17 36,886.41 39,564.47
INCR 29,702.45 37,873.45 38,164.14
LPUSH 28,114.57 38,355.53 37,587.95
RPUSH 30,173.38 35,987.36 37,080.19
LPOP 30,424.79 38,814.10 37,761.97
RPOP 29,800.66 39,811.67 37,000.76
SADD 27,555.22 39,228.60 37,360.41
HSET 27,095.25 38,907.94 38,479.75
SPOP 29,755.87 36,280.26 37,893.51
LRANGE_100 (first 100 elements) 20,069.27 25,946.85 26,437.27
LRANGE_300 (first 300 elements) 10,977.35 13,933.05 14,920.00
LRANGE_500 (first 500 elements) 7,809.86 8,968.16 10,343.35
LRANGE_600 (first 600 elements) 6,895.21 8,338.39 9,491.90
MSET (10 keys) 26,594.89 31,181.96 35,371.29

Conclusion

Linode is still leading the pack in most categories, while being the most budget friendly of the bunch. This month's oddity was with the Vultr instances I spun up. One of the three instances took an exceptionally long time to spin up. After it spun up, I wasn't able to connect to it at all.

My initial Vultr instances were all spun up at the same time, with the same configuration, so it wasn't like I had goofed spinning up one of them. I did spin up a fourth instance, as it's usually not worth my time to figure out what went wrong with an instance I'll be deleting quickly anyway.

Otherwise, everything else seemed to run smoothly. Of course, if you found this comparison helpful, and you're planning to sign up for a new VPS provider, it would be awesome if you used my referral links below.

If you have found these posts informative and helpful in searching for a new hosting provider, please consider using one of the links below when signing up: