Comment by walrus01
6 hours ago
> Sun or Digital (DEC) and someone like Dell.
In a time frame like 1999 to 2002, much more broadly than that, just the increasing gap in cost vs what you would get between buying any hardware+OS package from a legacy Unix-like vendor (Sun, DEC, SGI) and doing your own thing on a FreeBSD, OpenBSD or Linux on x86 hardware.
Dell was obviously a top choice, but by 2000 or so, Linux or FreeBSD had become good enough that you could do exactly the same thing for a fraction of the cost and run it on x86 hardware you had purchased from either Dell or one of the top 5 or 6 Dell-competitors.
As compared to, as you say, sitting through sales meetings, price quotes, revisions, a long slow and arduous process to arrive at a figure where you come to a conclusion "yeah you can spend $60,000 on these Sun servers or we can buy $20,000 of x86 servers and get creative with our own software stack to do the same thing in house".
At a certain point 1U and 2U server hardware got fast enough on boring standard x86 single or dual socket motherboards from Taiwan, in the era of like the 1.2 GHz Pentium 3 with 512KB cache, that the performance was pretty damn good and the machine cost a fraction of what the equivalent Sun or SGI rackmount machine would cost. This is in the era before a multi core x86 CPU existed. And you could be sure that its BIOS and motherboard were already OK for use with a current Linux kernel, we're talking about motherboards from Supermicro, Tyan, intel whitebox reference server boards, etc.
It's easier to see in hindsight but servers have eaten a lot of macro economic headwinds.
1999 and 2002 correspond roughly to telecom and dotcom bubbles popping. So open source operating systems were also pulled up into these positions through a lot of work and by the early 2000s it was kind of obvious this was the way forward.
2008 financial crisis really knocked the high end (RISC/UNIX/Itanium) and started the long migration to renting vs owning. In hindsight it's remarkable how much money used to just be there in the economy of all this. But I guess it still is, considering how expensive public cloud is.
> But I guess it still is, considering how expensive public cloud is.
It's not like there's less servers being sold, they're just bespoke designs from companies like the big Taiwanese ODMs that go straight into hyperscaler facilities, and we don't get to see public marketing websites and product info about them. The open compute platform stuff that's been publicly shown is like the tip of an iceberg.
I'm referencing the premium you pay to get some paltry VM in a public cloud with bizarre storage and networking that primarily make sense for the market maker versus the actual cost of the hardware. There are ways to make cloud economics work as a user, but only where staffing costs would dwarf spend (i.e. small businesses) and I've never seen them in practice.
> The open compute platform stuff that's been publicly shown is like the tip of an iceberg.
I find it a real shame it's not easier to get OCP hardware for our homelabs. Would be so much easier to operate, upgrade, and so on. And where would you even get decommissioned OCP gear?
2 replies →