Forums before death by AOL, social media and spammers... "We can't have nice things"
|    alt.os.linux    |    Getting to be as bloated as Windows!    |    107,822 messages    |
[   << oldest   |   < older   |   list   |   newer >   |   newest >>   ]
|    Message 106,545 of 107,822    |
|    Paul to Lawrence D'Oliveiro    |
|    Re: Alternative to Optical Storage????    |
|    29 Sep 24 05:27:48    |
      XPost: comp.os.linux.advocacy, comp.os.linux.misc       From: nospam@needed.invalid              On Sun, 9/29/2024 2:28 AM, Lawrence D'Oliveiro wrote:       > On Fri, 27 Sep 2024 21:32:07 -0400, Paul wrote:       >       >> Once you get up to a certain size, they tend to use SSD controllers       >> inside, then a USB converter connected to that. This can radically       >> improve the storage characteristic. The SSD controller has static and       >> dynamic wear leveling. Very few USB sticks have that in a USB controller       >> (but there are some).       >       > The thing is, Linux has, included as standard, support for filesystems       > (e.g. f2fs, ubifs) that are specifically designed for use on flash       > storage, with features like wear-levelling directly built into their       > storage-management algorithms.       >       > Consider that SSDs (including USB sticks) incorporate elaborate interface       > controllers to pretend to the OS that they are disks and can use       > conventional disk-centric filesystems: imagine the overhead that would       > simply disappear if you could go direct to the low-level storage and use       > one of these purpose-built filesystems!       >              It would suck donkey balls of course.              Nobody wants their CPU donating a couple cores, to make       up for the ARM cores the SSD has. One of my SSDs has a       three-core ARM, two cores are for error correction on read!       And that is not particularly unusual.              Imagine if your SSD was slowed down by a slack-jawed "raw flash"       storage device. That would be awful.              The partitioning is the way that it is, for a reason.              *******              The faster that storage devices get, the more sensitive they       become to details. This is why I would keep you well away       from my PCIe Rev5 NVMe at 14000/12000 MB/sec. That still       needs an error corrector, and somehow keep up with the       need to correct every sector being read out. It's one       of the reasons those get so hot (and they put toy heatsinks       on top).              That's also how you can have devices like this. You would not       get these sorts of rates, without IOPs in the picture to help.              https://www.anandtech.com/show/21486/highpoint-updates-nvme-raid       cards-for-pcie-50-50-gbps-directattached-ssd-storage               Paul              --- SoupGate-Win32 v1.05        * Origin: you cannot sedate... all the things you hate (1:229/2)    |
[   << oldest   |   < older   |   list   |   newer >   |   newest >>   ]
(c) 1994, bbs@darkrealms.ca