Serverless Computing: One Step Forward, Two Steps Back · HackerPapers discussions

Serverless Computing: One Step Forward, Two Steps Back — mentioned by ozychhi

Tue, 01 Jan 2019 15:58:46 GMT

Have you tried doing serverless? I have and my experience with it was quite bad. Here are other people sharing the same opinion https://arxiv.org/pdf/1812.03651.pdf

Paper and discussion history. A mention is not an endorsement.

Serverless Computing: One Step Forward, Two Steps Back — mentioned by bfirsh

Sat, 15 Dec 2018 21:54:47 GMT

Here's a web version if you're on a phone: https://www.arxiv-vanity.com/papers/1812.03651/

Paper and discussion history. A mention is not an endorsement.

Serverless Computing: One Step Forward, Two Steps Back — mentioned by sytse

Sat, 15 Dec 2018 19:12:14 GMT

I loved the article https://arxiv.org/pdf/1812.03651.pdf It mentions two temporary bottlenecks: 1. Functions can run only for 15 minutes and experience cold-starts. 2. You can't use specialized hardware like GPUs. It also mentions two fundamental bottlenecks: 1. Serverless functions are run on isolated VMs, separate from data. In addition, serverless functions are short-lived and non-addressable, so their capacity to cache state internally to service repeated requests is limited. Hence FaaS routinely “ships data to code” rather than “shipping code to data.” 2. Because there is no network…

Paper and discussion history. A mention is not an endorsement.

Serverless Computing: One Step Forward, Two Steps Back — HN submission

Sat, 15 Dec 2018 18:11:55 GMT

Serverless Computing: One Step Forward, Two Steps Back

465 points; 222 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Serverless Computing: One Step Forward, Two Steps Back — HN submission

Tue, 11 Dec 2018 09:17:18 GMT

Serverless Computing: One Step Forward, Two Steps Back

4 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.