Live data from Hacker News

Viewing profile — pashkinelfe

pashkinelfe

HN member
Joined
Mon, Oct 03, 2022, 2:35 PM UTC
HN karma
7
Public activity
18 items

About pashkinelfe

No profile information was provided.

Recent public activity

  1. comment
    Comment #43615629

    A nice performance review for Orioledb. I'm impressed with the results. These measurements use sysbench, and complement already published benchmarks using TPC-b, and TPC-c workload…

  2. comment
  3. story
  4. story
  5. comment
    Comment #43464787

    It's a thorough explanation for those who understand PostgreSQL internals. It probably needs some time to understand the ideas. They are elegant in my opinion. Thanks to the author…

  6. comment
    Comment #42293936

    I'll explore performance with this parameter. Thanks for the advice!

  7. comment
    Comment #40170371

    Author is here. Tables occupying more space than expected is a common complaint from Postgres users. I explained in simple terms what could (or should) be done to avoid this in rea…

  8. comment
    Comment #37416710

    Pgvector 0.5.0 got HNSW indexes that is much faster for AI application than IVF in most cases. We measured pgvector performance in Supabase and present recommendations on its effic…

  9. story
  10. comment
    Comment #37305833

    Interesting thing about faster distance calculations is that a very small change in the dot product calculation makes code compile to much more efficient CPU instructions and up to…

  11. comment
    Comment #37088423

    If you have 10M or bigger dataset of real-world OpenAI- dimensional vectors, please share, I'll use it in the next benchmarks. Random datasets are too misleading for vector search …

  12. comment
    Comment #37088351

    Pgvector doesn't need to store everything in memory. It behaves similar to almost any Postgres AM's and store index data on disk. Performance-wise it's better to have enough memory…

  13. comment
    Comment #37081882

    I like these measurements with ANN-benckmark! They allow to compare performance of different index implementations apples-to-apples i.e. at the same build parameters set rather tha…

  14. comment
    Comment #36756960

    I suppose that more CPU load is because more cores are loaded by doing tasks in parallel. Less CPU load is actually indicator that performance is limited by something else (IO, loc…

  15. comment
    Comment #35513171

    [flagged]

  16. comment
    Comment #33359592

    It is possible if core team decides they are better with something else. No doubt, there is some conservatism in the community.

  17. comment
    Comment #33359508

    It's not easy to have a list of what is important to be done as there're so many different things. Generally it's good 1. To find already proposed patch of a moderate complexity an…

  18. comment
    Comment #33068423

    For me it's interesting can this work without the need of external proxy server which seems to be needed only to overcome browser connections limitations and nothing else. May ther…