How is this possible? Hot plug connectors have uneven edge connectors so ground pins contact before signal pins or, at the very least, initialize links with in a high-Z state or have protection diodes. Did PCIe add any of these features?
How is this possible? Hot plug connectors have uneven edge connectors so ground pins contact before signal pins or, at the very least, initialize links with in a high-Z state or have protection diodes. Did PCIe add any of these features?
* https://www.fujitsu.com/downloads/SFTWR/manual/s_e/b23pav1h0...
Being able to hot-plug cards in/out of slots has been a thing for higher-end gear for a long time.
I'm sure the IBM Mainframe folks did it many decades ago like they've seem to have done for many things that the 'commodity' server folks are only now catching up to.
They could do that with CPU modules a couple generations back. I don't think the newer ones can do it though, at least not a CPU at a time. It's probably possible to power off a CPU drawer (4 CPUs on the Z15, IIRC) without too much hassle.
I remember seeing a colleague of mine doing it with memory and CPUs on a live Ultra Enterprise 4000, again, with memory and CPU. IIRC, he had to tell the OS the board was going to be pulled out before doing so and a light would signal it was safe to proceed. He was doing that because we used one machine to process a lot of logs overnight (in 1997).
A card cage design was used on some IBM machines, where you attach the card a slim sled with a lever attached, this allowed you to "slide in" the card into running computer then use the lever to push it into edge connector (this also handled powering up/down the connector, iirc).
Some servers have cases which instead implement that completely in the case itself, though usually that means you need more effort to do the replacement.
Then there are alternative PCI-E connectors - ExpressCard, U.2 & SATAExpress (used in SSDs), OcuLink and related (cabled PCI-E)
That said, hot plugging is definitely a "pets" thing and as for large scale data center computing, nobody cares. The machine fails as a unit and it's OK to take a machine offline to fix it.
Or I'm just paranoid. A ZIF PCI-E socket would be swell for this.
Real server hotswap hardware is not putting any force on the motherboard; it goes into a caged connector.