joshtronic

Posted in VPS Showdown

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

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

While spring isn't officially here yet, it's definitely starting to feel like winter is over. More of the same this month, as we finish off the first quarter of 2024.

Next month, I'm hoping to finally get some MongoDB benchmarks into the mix. By the end of the second quarter, Ubuntu 24.04 LTS will be released as well. It's always fun to see which providers make it available the fastest.

One small observation this month, all of the Linode instances had the same first 3 parts to their IP addresses. This makes me think that all three instances may have resided on the same physical host. Fortunately, It didn't seem like running benchmarks choked itself out (noisy neighbor problem) so my theory may not be correct.

As always, I've spun up 3 instances with each VPS provided, all running Ubuntu 22.04 LTS. Where it made sense, I averaged out the results.

Overview - DigitalOcean vs. Linode vs. Vultr

Version
Linux Distro Ubuntu 22.04 LTS
Kernel Version 5.15.0
MySQL Version 8.0.36
Redis Version 6.0.16
DigitalOcean Linode Vultr
Location New York 1 Newark, NJ New York (NJ)
Monthly Price $6/month $5/month $5/month
Hourly Price $0.009/hour $0.0075/hour $0.007/hour
RAM 1 GB 1 GB 1 GB
CPU 1 Core 1 Core 1 Core
Storage 25 GB 25 GB 25 GB
Storage Type SSD SSD SSD
Transfer 1 TB 1 TB 1 TB
Transfer Overage $0.01/GB $0.01/GB $0.01/GB
Backups $1.2/month $2/month $1/month

CPU Info

Model Name
DigitalOcean - All Instances DO-Regular
Linode - All Instances AMD EPYC 7713 64-Core Processor
Vultr - All Instances AMD EPYC-Rome Processor
DigitalOcean Linode Vultr
CPU MHz 2,361.12 2,000.00 1,996.25
Cache Size (KB) 4,096.00 512.00 512.00
BogoMips n/a 2,666.67 2,661.67

CPU

DigitalOcean Linode Vultr
Events per Second 924.04 3,658.83 2,786.73
Minimum (ms) 0.93 0.24 0.30
Average (ms) 1.09 0.28 0.36
Maximum (ms) 113.46 2.73 7.47

Memory

Read

DigitalOcean Linode Vultr
Ops per Second 3,827,942.45 5,831,931.62 3,913,171.02
Minimum (ms) 0.00 0.00 0.00
Average (ms) 0.00 0.00 0.00
Maximum (ms) 5.66 2.15 4.06

Write

DigitalOcean Linode Vultr
Ops per Second 3,807,736.92 5,642,745.07 3,541,016.02
Minimum (ms) 0.00 0.00 0.00
Average (ms) 0.00 0.00 0.00
Maximum (ms) 2.96 2.39 9.28

File I/O

DigitalOcean Linode Vultr
Reads per Second 877.64 2,984.06 1,170.10
Writes per Second 585.07 1,989.36 780.07
Fsyncs per Second 1,879.08 6,372.39 2,499.77
Minimum (ms) 0.00 0.00 0.00
Average (ms) 0.32 0.09 0.23
Maximum (ms) 108.43 8.89 47.56

MySQL

Read Only

DigitalOcean Linode Vultr
Transactions per Second 4,206.67 8,121.67 3,777.33
Queries per Second 67,306.67 129,946.67 60,437.33
Minimum (ms) 1.18 0.93 1.33
Average (ms) 2.47 1.23 2.65
Maximum (ms) 84.83 15.25 52.02

Write Only

DigitalOcean Linode Vultr
Transactions per Second 969.33 7,748.67 1,468.00
Queries per Second 5,816.00 46,492.00 8,808.00
Minimum (ms) 3.51 0.68 1.54
Average (ms) 13.06 1.29 8.50
Maximum (ms) 419.36 13.02 112.00

Read Write

DigitalOcean Linode Vultr
Transactions per Second 917.00 3,288.67 703.33
Queries per Second 18,340.00 65,773.33 14,066.67
Minimum (ms) 5.32 1.82 3.83
Average (ms) 12.13 3.05 14.36
Maximum (ms) 86.78 14.56 139.78

Redis

DigitalOcean Linode Vultr
PING_INLINE 28,561.80 55,847.69 34,060.93
PING_BULK 28,902.86 51,983.23 31,409.95
SET 29,158.33 57,841.21 34,251.53
GET 27,464.52 55,262.83 31,371.76
INCR 27,597.95 55,819.26 33,459.05
LPUSH 28,597.00 59,834.67 35,552.53
RPUSH 28,375.56 57,361.23 36,647.47
LPOP 29,128.89 58,815.69 35,015.51
RPOP 28,511.25 56,883.47 33,206.44
SADD 28,374.77 55,638.04 33,050.31
HSET 30,318.04 59,094.81 36,487.43
SPOP 28,819.91 52,753.40 33,581.67
LRANGE_100 (first 100 elements) 17,952.71 23,374.36 21,579.72
LRANGE_300 (first 300 elements) 7,804.52 11,225.60 8,587.71
LRANGE_500 (first 500 elements) 6,007.52 8,625.96 5,754.97
LRANGE_600 (first 600 elements) 4,898.07 7,162.38 4,933.25
MSET (10 keys) 30,343.59 70,253.91 28,691.15

Conclusion

Even though DigitalOcean is touting a faster CPU, Linode's still looking quite strong as of late with their shared CPU offering. As always, if you're shopping for a new VPS hosting provider, it's always good to take some time to do your own independent benchmarking, and not just relying on what you read on the Internet.

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: