• tetris11@feddit.uk
    link
    fedilink
    English
    arrow-up
    23
    arrow-down
    2
    ·
    edit-2
    2 days ago

    Surely that only works on a USB that is already zero’d out (meaning nothing to change)?

    I wonder if this benchmark holds true on a USB that has seen some action and needs to commit large number of zeroes in random dereferenced space?

      • tetris11@feddit.uk
        link
        fedilink
        English
        arrow-up
        24
        arrow-down
        2
        ·
        2 days ago

        This is reading, not writing

        Ah I see thanks

        Ben Eater has a great video on it.

        I’m not watching a video, but appreciate the pointing in the right direction

        USB sends a dummy zero every few consecutive 1s for framing purposes

        Huh, TIL about Bit-Stuffing and Framing Bits

        Bit stuffing is the insertion of non-information bits into data … is used for various purposes, such as for bringing bit streams that do not necessarily have the same or rationally related bit rates up to a common rate

        Framing is the process by which, while receiving a stream of fixed-length frames, the receiver identifies the frame boundaries, permitting the data bits within the frame to be extracted for decoding or retransmission. A common practice is to insert in a dedicated time slot within the frame, a noninformation framing bit that is used for synchronization of the incoming data with the receiver.

    • Consti@lemmy.world
      link
      fedilink
      English
      arrow-up
      7
      ·
      2 days ago

      They’re reading from the USB into /dev/null (effectively throwing the read data away), not writing