This new Linux patch can speed up Reading Requests

Поделиться
HTML-код
  • Опубликовано: 24 ноя 2024

Комментарии • 20

  • @sebschrader
    @sebschrader 7 часов назад +1

    5:41 RSS in this case does not stand for memory, it stands for receive side scaling

  • @Ivy_Inquisitor
    @Ivy_Inquisitor 3 дня назад +4

    Awesome videos as always thanks a lot.
    Are they using io_uring to copy the data from kernel space to the user space?
    In an io_uring you have a submit queue event and completion queue event. Normally you put data in sqe and once the kernel processes it you get the response from cqe. I think here it might be nic driver code might submit sqe to kernel and kernel will put the results in userspace but maintain the pointer to it in cqe that can be requested by the application. It's my wild guess though.
    It is interesting how these developments will affect the tech space, especially dpdk space but I am sure we are not yet there to completely discard dpdk since the kernel still introduces a lot of latency.

  • @sanjeevkumar5051
    @sanjeevkumar5051 Месяц назад +2

    Love this stuff .. 👍👍

  • @siya.abc123
    @siya.abc123 3 дня назад +1

    Love the low level stuff

  • @kartikkaushik4743
    @kartikkaushik4743 19 часов назад

    Amazing share

  • @sebschrader
    @sebschrader 7 часов назад

    15:48 TCP header/data split requires NIC hardware support, which can be queried with ethtool -g

  • @tobyboulton8340
    @tobyboulton8340 2 дня назад +3

    Can't wait for this to hit the server kernels in 10 years.

  • @OwenRubel
    @OwenRubel 3 дня назад

    Well presented. Thank you.

  • @Linuxme
    @Linuxme 3 дня назад

    Thank you for sharing.

  • @stevez5134
    @stevez5134 3 дня назад

    another banger

  • @roganl
    @roganl 3 дня назад +1

    I would direct you to a pair of projects that have gone through this journey previously: DPDK & VPP - using low level driver hooks to skip relaying packet contents through the kernel.
    ruclips.net/video/06qrssJ2RQs/видео.html
    These projects have been around for almost a decade, hopefully the proposed change provides a standardized zero-copy integration with more historically normal linux networking intrinsics. Using VPP and dedicating an entire core to polling the device from user space, seems crude and wasteful when compared with a kernel packet notification scheme that this patch is attempting to implement.

  • @helloworlditsworld
    @helloworlditsworld 3 дня назад

    Nice thumbnail :^)

  • @monireol
    @monireol 3 дня назад

    How mounting works internally. Like mount same volume to multiple containers

  • @RajeshNadar7
    @RajeshNadar7 3 дня назад

    What data will be in the header, and if we need to access that info, will it be another read?

  • @abmmhasan
    @abmmhasan 2 дня назад

    Is it something similar to DMA of Windows? It looks kinda similar to me.

  • @ConsumedKing
    @ConsumedKing 3 дня назад +1

    haha 2:01

  • @AnantaAkash.Podder
    @AnantaAkash.Podder 3 дня назад

    I just loved the Low Level Stuff... I just HATE so much abstractions...

  • @kareemnewpers
    @kareemnewpers 3 дня назад +4

    They are trying to find every possible spit of performance improvement but unfortunately this is no longer in the context of ordinary computing and quantum computing is much more effort worthy now and on

    • @jan-Juta
      @jan-Juta 3 дня назад +4

      Quantum computing as been improving leaps and bounds on terms of ability and usability. Not in cost or size. Even if we had functionally useful quantum computing right now we'd still be decades away from consumer quantum. There's still plenty of reason to improve non-quantum programs.