Simple Systems Have Less Downtime

Re:Simple Systems Have Less Downtime by ignoramous on Tuesday March 03, 2020 @09:59AM (#22474914)

I am not sure if WhatsApp engs chose ejabberd because it was written in Erlang or because ejabberd was the defacto implementation of XMPP. They stumbled upon and fixed bugs in BEAM/OTP at their scale [0][1][2]. They also ran FreeBSD (for its superior networking?) on bare-metal hosts running customised system-images [3] and employed networking experts at some point.

[0] https://www.youtube-nocookie.com/embed/c12cYAUTXXs

[1] https://www.youtube-nocookie.com/embed/wDk6l3tPBuw

[2] https://www.youtube-nocookie.com/embed/93MA0VUWP9w

[3] https://www.youtube-nocookie.com/embed/TneLO5TdW_M

[ Parent | on HN ]

Re:Simple Systems Have Less Downtime by scurvy on Tuesday March 03, 2020 @11:51AM (#22476193)

They ran FreeBSD because Jan came from Yahoo, and that's what Yahoo ran.

[ Parent | on HN ]

Re:Simple Systems Have Less Downtime by vaingloriole on Wednesday March 04, 2020 @01:25PM (#22486298)

'customized systems (kernel)..FreeBSD..bare metal': Which is what most of us still do if we care about performance for a single application. Running openmp fortran code for both host/accelerator on oversubscribed vmware or vanilla kvm/qemu for a good laugh and a lot of pain. Simple systems approaches are best even when what you are doing is complicated.

[ Parent | on HN ]

Re:Simple Systems Have Less Downtime by dnautics on Tuesday March 03, 2020 @11:48AM (#22476163)

I could be wrong but I think freebsd allowed multiplexing connections per port before Linux? Please correct me I am mistaken about this.

[ Parent | on HN ]