Live data from Hacker News

Viewing profile — hyc_symas

hyc_symas

HN member
Joined
Thu, Feb 21, 2013, 11:00 AM UTC
HN karma
758
Public activity
491 items

About hyc_symas

No profile information was provided.

Recent public activity

  1. comment
    Comment #49023294

    > A power outage interrupted Garage mid-write on the LMDB metadata database. LMDB uses mmap’d I/O and, by default, operates with MDB_NOMETASYNC and MDB_NOSYNC (Garage sets metadata…

  2. comment
    Comment #48794579

    The txnID was added to the page header to enable support for incremental backup. As a consequence, it's sufficient to compare a page's txnID to the current txnID to know if it's di…

  3. comment
    Comment #48794217

    write/fsync can be faster in a large dataset because writes let the filesystem know an explicit list of dirty pages, so fsync only needs to deal with them. mmap/msync gives no hint…

  4. comment
    Comment #48784166

    By the way, you're wrong on both points - the cache of page mallocs is not infinite, and it does spill dirty pages to disk when necessary. And the latter is what bounds the number …

  5. comment
    Comment #48778310

    You're dreaming. None of your explicit memory control operations mean anything in practice, because today everything runs in VMs with no actual control of the underlying hardware. …

  6. comment
    Comment #48778232

    In the time it takes for your query optimizer to dissect a query and "look ahead" LMDB would have already answered a million queries. You think your magical "future oracle" is zero…

  7. comment
    Comment #48777449

    Indeed, there's no need to use the doc website. There's nothing there that isn't embedded in the LMDB source code. All of the docs are generated from doxygen comments in the source…

  8. comment
    Comment #48776239

    If you're downloading binaries from a plaintext documentation site, I think that's on you.

  9. comment
    Comment #48776210

    Nonsense. The best you will ever do, even with full application knowledge and complete control of the machine, is an LRU cache replacement algorithm. But when you do it yourself yo…

  10. comment
    Comment #48776151

    Obligatory "that paper is garbage" https://www.symas.com/post/are-you-sure-you-want-to-use-mmap...

  11. comment
    Comment #48776102

    Irrelevant, since LMDB doesn't dirty the pages in the mmap. The mmap is read-only.

  12. comment
    Comment #48776081

    LMDB 1.0 no longer uses a P_DIRTY flag, it no longer has to explicitly mark pages as clean.

  13. comment
    Comment #48033597

    > The price is intended to decrease. No. Monero's tail emission rate was specifically chosen to be less than the rate of global gold production. Do you claim the price of gold is i…

  14. comment
    Comment #48027973

    I don't know what the current versions do, it's been a while since I touched that code. I have no reason to lie, I'm not selling anything. Bitmain is selling mining hardware, take …

  15. comment
    Comment #48025938

    FPGAs have no particular advantage. You could dedicate a chunk of their resources to implement a softcore CPU but it'd be several times slower than a real CPU. The random programs …

  16. comment
    Comment #48025585

    > Loved your 2019 talk on "is XMR still ASIC-proof" – is it still, in 2026, in your opinion? Yep. Nothing about computing architecture has changed.

  17. comment
    Comment #48025129

    >> just killing the process will never corrupt the blockchain DB > I would love to show you how easy this is to reproduce, even on fresh installs of Ubuntu and/or MacOS on otherwis…

  18. comment
    Comment #48018914

    > If you don't sync then you're not (cannot be) a fullnode / network verifyer / ringsigner. I was talking about database sync, not blockchain sync. You don't need to use safe sync …

  19. comment
    Comment #48018846

    Light mode is used mostly by the monerod, validating incoming blocks. But on a machine with sufficient free RAM, monerod can also be set to use Fast mode instead. The post describe…

  20. comment
    Comment #48018622

    The limit we set at the beginning was "no one can design a custom device for RandomX with more than a 2:1 efficiency advantage over general purpose CPUs". That is and will forever …

  21. comment
    Comment #48018455

    Since the programs are randomly generated, there's no guarantee that any particular program always uses some number of any particular instruction. There's only a probability, X/256…

  22. comment
    Comment #48013358

    Monero is disinflationary , not inflationary. The rate of new coin emission is only enough to maintain equilibrium with the rate of coins being lost (due to people losing wallet ke…

  23. comment
    Comment #48012650

    You must be on drugs. There is no separate specialized verification function. It's the same algorithm for verification as for mining.

  24. comment
    Comment #48012633

    PoW is useful in far more situations than PoS. A derivative of RandomX is now used to protect TOR too (Equi-X). https://github.com/tevador/equix/blob/master/devlog.md

  25. comment
    Comment #48012603

    > Once you kill the process, your local blockchain is [most likely] unusable. Totally false. LMDB is perfectly crash-proof in that scenario and killing the process never damages th…