Announcement

Collapse
No announcement yet.

Btrfs RAID 5/6 Sub-Page Support Readied For Linux 5.19

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

  • Btrfs RAID 5/6 Sub-Page Support Readied For Linux 5.19

    Phoronix: Btrfs RAID 5/6 Sub-Page Support Readied For Linux 5.19

    The latest Btrfs file-system work on its native RAID5/RAID6 mode is now supporting the file-system's sub-page functionality...

    Phoronix, Linux Hardware Reviews, Linux hardware benchmarks, Linux server benchmarks, Linux benchmarking, Desktop Linux, Linux performance, Open Source graphics, Linux How To, Ubuntu benchmarks, Ubuntu hardware, Phoronix Test Suite

  • #2
    That would be useful on systems with multiple page sizes like Power 9 **if** (and that's a big if) btrfs raid 5 would have been even remotely usable.
    ## VGA ##
    AMD: X1950XTX, HD3870, HD5870
    Intel: GMA45, HD3000 (Core i5 2500K)

    Comment


    • #3
      Originally posted by darkbasic View Post
      That would be useful on systems with multiple page sizes like Power 9 **if** (and that's a big if) btrfs raid 5 would have been even remotely usable.
      Raid 6 also has the same issue its just a lot less likely but your point still stands.

      Comment


      • #4
        Does this mean Raid5/6 won't melt your Btr?

        Comment


        • #5
          Originally posted by commodore256 View Post
          Does this mean Raid5/6 won't melt your Btr?
          From what I can tell no. Afaik fixing the RAID 5/6 write hole would require a change to the on disk format of BTRFs which is why it hasn't been done as of yet. Because of this I think its kind of evident that the creators of BTRFS never took RAID 5/6 seriously which is a shame (zfs for example doesn't have this issue).

          Comment


          • #6
            If Btrfs could ever get reliable RAID5/6 and native encryption, then I wouldn't have much need for ZFS anymore. Although still the Btrfs implementation of send/receive does make me a little nervous in that it seems to be working at the file level, whereas in ZFS it's working at the block level. That also makes me think that if Btrfs ever did get encryption, it wouldn't be as slick as the ZFS implementation. But as it stands they're two different tools with two different uses. Btrfs works great as a root filesystem in a single disk or mirrored scenario, and ZFS works great as a data storage filesystem.

            Comment


            • #7
              Originally posted by Chugworth View Post
              If Btrfs could ever get reliable RAID5/6 and native encryption, then I wouldn't have much need for ZFS anymore.
              I like to think so, too. But then again I increasingly rely on some differentiating features of ZFS, like combining drives of different sizes and makes into a single pool.

              I would be interested in a roadmap of Btrfs to production Raid5/6 support. The wiki refers to the following email from 2020 listing open issues which paints a scary picture (https://lore.kernel.org/linux-btrfs/...grycats.org/#r). Unfortunately, it doesn't contain links to a bug tracker ...

              Comment


              • #8
                As a long time btrfs user I can say we don't care about RAID5/6, but we are still waiting for the promised hot-relocation support (mixed SSD/HDD with hot data automatically being relocated to the SSD). I still have IBM's patches lying around for that, what happened to that effort?

                Comment


                • #9
                  Originally posted by ferry View Post
                  we are still waiting for the promised hot-relocation support (mixed SSD/HDD with hot data automatically being relocated to the SSD).
                  Yeah - good one. I keep taking that for granted in my ZFS pool.

                  Comment


                  • #10
                    Originally posted by ferry View Post
                    As a long time btrfs user I can say we don't care about RAID5/6, but we are still waiting for the promised hot-relocation support (mixed SSD/HDD with hot data automatically being relocated to the SSD). I still have IBM's patches lying around for that, what happened to that effort?
                    This exists on ZFS in the form of L2 ARC. The ability to expand ZFS RAIDs with additional disks is also nearing completion (final testing and review).

                    Comment

                    Working...
                    X