How Discord Indexes Billions of Messages Using Elasticsearch

Re:How Discord Indexes Billions of Messages Using Elasticsearch by warriormonk5 on Thursday March 16, 2017 @08:03PM (#13890260)

At some point (roughly around your size, maybe a little larger) you'll want to add dedicated master nodes with no data.

3 small boxes, master eligible, holding no data.

I love the writeup, having a way to reproduce data if your clusters fail is a definite must with ES.

[ Parent | on HN ]

Re:How Discord Indexes Billions of Messages Using Elasticsearch by packetized on Thursday March 16, 2017 @08:34PM (#13890390)

I'd agree with this, but I also had quite a bit of success with using indexer/search nodes as master-eligible, and then basically 'pin' (manually) the master node to one completely dedicated host. That's one complaint about ES, there's no way to set master preference among a set of master-eligible nodes.

[ Parent | on HN ]

Re:How Discord Indexes Billions of Messages Using Elasticsearch by jhgg on Thursday March 16, 2017 @08:54PM (#13890472)

Yup. We're thinking about that too. We've been monitoring node performance closely to see when we'll need to shift the topology around a bit. I'd want to keep our clusters small and the topology uniform before I investigate dedicated master nodes though.

[ Parent | on HN ]

Re:How Discord Indexes Billions of Messages Using Elasticsearch by gibrown on Friday March 17, 2017 @10:19AM (#13894140)

FYI: From my experience (on older ES versions) when you hit problems with it, they will be pretty bad, catastrophic problems. We run dedicated master nodes, but have the master servers running multiple ES instances, so they can serve as masters for multiple clusters.

[ Parent | on HN ]

Re:How Discord Indexes Billions of Messages Using Elasticsearch by notyourwork on Thursday March 16, 2017 @08:06PM (#13890272)

Spot on regarding dedicated masters.

[ Parent | on HN ]