Top all-time · #11981
Zach Bjornson
Personal blog · blog.zachbjornson.comsystemsdata
Zach Bjornson's personal blog at blog.zachbjornson.com covers systems and data. Since 2016, 6 different Hacker News readers have linked it 9 times, most often “Feeding data to 1000 CPUs – comparison of S3, Google, Azure storage”. The last post was in 2019, but the archive is still widely read.
Too few sampled comments (6) to say how often HN recommends it.?
Why HN links it
Cloud storage benchmark post comparing AWS S3, Google Cloud Storage and Azure storage, with lots of numbers and performance graphs. HN commenters point people to it as a neutral comparison of the three providers.
Summarised by Claude from a sample of 6 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
High-performance cloud computing, bioinformatics, and other fun stuff.
Most-linked posts?
- Feeding data to 1000 CPUs – comparison of S3, Google, Azure storage6 people · 8 mentions · first linked 2016-01-04
What Hacker News says?
Disclosure: I work on Google Cloud. Yeah, the underlying system is optimized for throughput (though we're working on small file latency). AWS clearly has a small file optimization and caching that we don't (yet). I often point people at Zach Bjornson's blogpost [1] since he compared all three providers and is a neutral third party. [1] http://blog.zachbjornson.com/2015/12/29/cloud-storage-perfor...
Comment linking /2015/12/29/cloud-storage-performance.html
on “Degraded performance after forced reboot due to AWS instance maintenance”Submitted Feeding data to 1000 CPUs – comparison of S3, Google, Azure storage as a story · 216 points
HN discussionHere's an old article with lots of numbers and performance graphs: http://blog.zachbjornson.com/2015/12/29/cloud-storage-perfor...
Comment linking /2015/12/29/cloud-storage-performance.html
on “New storage classes for Google Cloud Storage”Submitted AWS S3 vs. Google Cloud vs. Azure: Cloud Storage Performance as a story · 7 points
HN discussionhurstdog can speak to this more, but we absolutely don't scream on latency (particularly time to first byte). Internally, we rely heavily on caching, and that's just now been made available (in Alpha) for Cloud CDN to wrap GCS. Does <100ms for cache fill matter, or just aggregate p95 < 100ms including caching? I'd also like to point everyone at Zach Bjornson's wonderful blogpost from last year [1], which was both th…
Comment linking /2015/12/29/cloud-storage-performance.html
on “New storage classes for Google Cloud Storage”Submitted [2015] AWS S3 vs. Google Cloud vs. Azure: Cloud Storage Performance as a story · 2 points
HN discussionThere are several accurate summation algorithms; Kahan is one of them. Looks like Postgresql uses an accurate summation method[0] (and not Kahan), so that's probably a big factor in why theirs is so much slower and also makes for an unfair comparison. FWIW I posted AVX2 and AVX512 Kahan summation implementations here[1]. [0] https://github.com/postgres/postgres/blob/3ed2005ff595d34927... [1] http://blog.zachbjornson…
Comment linking /2019/08/11/fast-float-summation.html
on “Using SIMD to aggregate billions of values per second”Finished a lot of stuff: - First blog post, benchmarking AWS S3, Google Cloud Storage and Azure storage, http://blog.zachbjornson.com/2015/12/29/cloud-storage-perfor... - MongoDB driver for Mathematica, https://github.com/zbjornson/MongoDBLink - Started packaging bioinformatics tools for Mathematica (a la Bioconductor), https://github.com/zbjornson/BioTools
Comment linking /2015/12/29/cloud-storage-performance.html
on “Ask HN: What are you currently building?”honestly i think http://blog.zachbjornson.com/2015/12/29/cloud-storage-perfor... does a better job than i could* * benchmarks are easily fakeable - please don't bet your company on one
Comment linking /2015/12/29/cloud-storage-performance.html
on “Now Open – AWS Asia Pacific (Seoul) Region”