SSD

Hardware: Raspberry Pi 4 Boot Disk Optimization

I recently looked at my 2008 Mac Pro to optimize it's startup disk; today let's have a look at the Raspberry Pi 4 to see what kind of setup provides the fastest read speed on it's boot disk. We can take it for granted that the Pi 4's USB3 port will provide better throughput than the on-board microSD reader; I've seen people using different USB3 peripherals for their boot disks, though. Today, I'll have a look at how a USB3 flash drive performs against a 2.5" solid state.

Quick Background

I previously posted on the feasibility of the Raspberry Pi 4 as a desktop computer--particularly in regard to whether it could handle my web-development workflow; there are really three major issues at stake with regard to whether the Pi 4 can pull it off:

Hardware: Optimizing Startup Disk Throughput on Linux -- SATA vs PCIe

Okay... BIG qualifier here: this post pertains to a 2008 Mac Pro running Ubuntu 18.04.5 LTS. If you're expecting some sort of cutting edge hardware review, this isn't it. However, I fetishize old computers and my 2008 Mac Pro holds well enough against contemporary computers that it can handle just about anything I throw at it as a web-developer in 2021. This computer has been an ongoing project, and I enjoy tweaking it here and there to see just how well it can keep up. I recently purchased some PCIe cards (adapters, really) to run hard-disks on, and in this post I'd like to casually review which card, which drive, and which connection gets me the best performance. I'll also discuss what kinds of tools on Ubuntu/Linux help me assess this.

Background

Now, technically speaking, most of the information in this review could easily be found in product descriptions. Product descriptions, however, aren't always what they're cut out to be. I really prefer not to take it for granted that the maximum throughput listed on a product is the same as what you'll get on your own computer. It seems like there are enough variables in data throughput (reading and writing hard disks) that use-case is inevitably a factor. If my testing turns out to be redundant, that's fine.