Announcement

Collapse
No announcement yet.

EXT4 Gets A Nice Batch Of Fixes For Linux 5.8

Collapse
X
 
  • Filter
  • Time
  • Show
Clear All
new posts

  • Originally posted by kloczek View Post

    SGI Ultraviolet it is partitioned HW with exactly that extremely low latency interconnect between partitions.
    So again you are pointing on non-SIS example.
    And it doesn't matter in this case, because we were talking what OS kernel sees. Furthermore, you got examples from SAP.

    What has asynchronous IO with paged memory management? Nothing ..
    A feature Solaris lacks. Ping pong.

    Live kernel live patching it is not the same. BTW: Solaris had this functionality long time before it was possible to have that on Linux.
    Fine, but I can give you a lot of other Linux features Solaris doesn't have, so I don't see too much sense in this.

    nvdimm it is completely different story. I'm talking about regular RAM. To preserve RAM content you need to carefully shutdown system and preserve RAM content before new kernel will be downloaded and booted.
    I'll take a look at this.

    Comment


    • Originally posted by Volta View Post
      A feature Solaris lacks. Ping pong.
      https://docs.oracle.com/cd/E19683-01...-51/index.html
      On the bottom of that page you can find "© 2010, Oracle Corporation and/or its affiliates"

      Fine, but I can give you a lot of other Linux features Solaris doesn't have, so I don't see too much sense in this.
      Features like what?

      Comment


      • Originally posted by pal666 View Post
        disks can't checksum host memory contents, i.e. they can't catch all errors
        I can't read all responses, so not sure if this was addressed (my apologies if it was). No filesystem can catch host memory errors. You depend on ECC RAM for that. And pray the solar flares aren't that heavy this year (btw, there have been a few big ones this year, which were unusual given the solar cycle). If the bit-flip happens in L3 victim cache, then even with ECC RAM you're out of luck. When the sync happens, that error will be pushed into your storage.

        Comment


        • Originally posted by kloczek View Post
          https://docs.oracle.com/cd/E19683-01...-51/index.html
          On the bottom of that page you can find "© 2010, Oracle Corporation and/or its affiliates"
          Windows also has AI/O, but it doesn't even come close to io_uring.

          Features like what?
          RCU, RT scheduling, bcache, cgroups, KSM, KVM to name a few.

          Comment


          • Originally posted by Volta View Post
            RCU, RT scheduling, bcache, cgroups, KSM, KVM to name a few.
            Solaris has plugable scheduler since Solaris 8 (~20 years). You can change scheduler without reboot like it is on Linux.
            Things like cgropus never will be implemented because you can limit memory, cpu and other resources using processes, tasks, projects using FSS and other scheduler.
            Cgroups still does not provide even half functionalities of the Solaris.
            For example cgroups on Linux still does not provide full separation of memory stats (over /proc/meminfo you see physical system memory metrics). Cgroups still does not provide separation of kernel messages (dmesg inside cgroup still shows physical system kernel messages).
            Cgrops still does not provide proper separation on network layer and on top cgroup you must have organised bunch of bridges to provide proper/independent communications to for example LXCs. All those things on Solaris have been perfectly working since first day of Solaris 10GA (17 years ago).
            Something like RCU is on the Solaris +10 years (look for UTS).
            Equivalent of the bcache is on Solaris since Solaris 8 (look on cachefs). Currently cachefs is not used at all because now whole caching is done by ZFS ARC (Adaptive Reclaim Cache) which is faaaaar more sophisticated than what bcache provides
            KVM is ported to Solaris. It is possible to use it on Oracle Solaris but most of that type of needs provides kernel zones.
            Regular KVM and Xen are standard part of the OpenSolaris and derivatives like OmniOS. Xen development originally stared on Solaris than people started porting it to Linux
            KSM on Solaris is not needed at all

            Sorry dude what you just wrote says that you really knows nothing about Solaris
            As I wrote Solaris still is ahead of Linux at least 10 if not 15 years.

            Comment


            • There's a pretty serious bug in the block allocator accessing smp processor id in fully preemptible kernels so if you build in fully preemptible mode i suggest not pulling master

              Comment

              Working...
              X