News for hackers. Stuff that matters.
Re:Learn how to design large-scale systems by lossolo on Friday July 13, 2018 @12:46PM (#17524507)
I am running top-1000 site in one of EU countries on one 4 core machine with 20-30% load. Around 1000 http/https reqs/s. Most of those requests do couple of postgres reqs (read and write) and couple of redis reqs.

Elasticsearch - for searching/recommendations

Redis - hot data (certain data is only kept in redis)

Postgres - for the rest of data

Clickhouse - analytics

Most of the system is written in Go. Whole system was tuned for performance from day one. As to latency, data from the last 21 million requests today:

p99: 17.37 ms

p95: 6.86 ms

avg: 2.37 ms

Re:Learn how to design large-scale systems by digikata on Friday July 13, 2018 @02:23PM (#17525414)
Is postgres on the same machine or on a separate one?
Re:Learn how to design large-scale systems by lossolo on Friday July 13, 2018 @02:39PM (#17525575)
Same machine, everything is on the same machine (dedicated server aka bare metal, not vps/cloud).
Re:Learn how to design large-scale systems by digikata on Friday July 13, 2018 @07:55PM (#17527820)
Thanks for the reply! May I ask how far you go with respect to reliability/availability? Do you have a live replicated server on stand by or just replicate a log stream elsewhere, something else?
Re:Learn how to design large-scale systems by tmaly on Friday July 13, 2018 @01:21PM (#17524851)
are you using any specific Go web framework or just the standard library?
Re:Learn how to design large-scale systems by lossolo on Friday July 13, 2018 @01:39PM (#17524985)
I am using fasthttp[1]

1. https://github.com/valyala/fasthttp