aardvarklegend

Staff (l7) is no where near middle engineer. L6 is senior, l5 is engineer and l4 is entry level. L6 is also split into two bands 6a and 6b. As a 6a my total comp is around 240 and on par with my coworkers. The l5s were closer to 200. L5 is a middle engineering level.

It requires a perfect storm of just shy of 100% used memory and a lot of mmaped io. In that case the mmaped can get shunted to a handful of pages (or even one page) and so you lose all ability to have any block io larger then one page size. And every page of memory involves a fully blocking io request. It’s most certainly real for certain workloads (databases are common).

Sorry, but that’s not enough. You need more ram to actually make the ssh connection useful. You can lock sshd and then be blocked from running your shell or any commands in that shell. You really do need reserved unused memory.

I believe that’s because it’s frames per second, not an abstract percentile.

Twittitled was the term used at Twitter for people who complained about the lack of free hint water to the executives of the company when we had fresh fruit water made each day. It’s super easy to get into this mindset at the big Bay Area companies.

Surprisingly power is a huge factor. Spinning up 48/96 drives on boot can surge beyond what power supplies could handle, so things supported staggered spin ups. This allowed huge banks of drives to start without blowing a power supply, but you don’t know how many drives or if staggered spin up is enabled until it times out. This was a huge boot delay for servers.