Announcement

Collapse
No announcement yet.

Btrfs Gets More RAID 5/6 Fixes In Linux 4.16

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

  • #31
    Originally posted by gbcox View Post
    I believe the answer may be bcachefs.
    ok, list here bcachefs patches which went into 4.16

    Comment


    • #32
      Originally posted by duby229 View Post
      Yeah, it's definitely past time for linux filesystem developers to get over BTRFS and start something new. Redhat may not be on the right track, so the kernels filesystem devs need to get crackin'. And soon.
      so, are you going to show how to do it properly, or you will limit yourself to issuing orders to linux filesystem developers?

      Comment


      • #33
        Originally posted by pal666 View Post
        so, are you going to show how to do it properly, or you will limit yourself to issuing orders to linux filesystem developers?
        Well, I suppose you can consider common sense an order I guess.

        Comment


        • #34
          Originally posted by duby229 View Post
          Of course, because that's where it's already proven to be perpetually stuck.
          what fs with comparable featureset was developed faster? though nobody is going to stop you, you can start developing your magic fs right now. or join bcachefs circus

          Comment


          • #35
            Originally posted by duby229 View Post
            Well, I suppose you can consider common sense an order I guess.
            since your sense is common, right now most linux fs devs are busy executing your suggestion, right?

            Comment


            • #36
              Originally posted by pal666 View Post
              since your sense is common, right now most linux fs devs are busy executing your suggestion, right?
              I sure do hope so.

              Comment


              • #37
                Originally posted by caligula View Post
                Faster at rebuilding perhaps? OTOH raid5/6 has significantly faster RW speed. You can easily achieve throughput such as 500 MB/s with spinning disks and RAID5. It's because you can do independent reads and writes of different blocks using multiple disks. On RAID-1 read speed has a theoretical max of 2x disk speed (assuming the file system can do checksums for blocks independently). On RAID-5 it's N-1, where N is the number of disks.
                your math is wrong. raid1 can read all N disks in parallel. though btrfs didn't do that in the past, it was supposed to be fixed. but write on raid5 is read-modify-write

                Comment


                • #38
                  Originally posted by duby229 View Post
                  I sure do hope so.
                  oh, you were right, here is evidence https://www.youtube.com/watch?v=3wbyRTW8fNQ

                  Comment


                  • #39
                    Originally posted by caligula View Post
                    Having 10 disks in RAID-1 is just dumb.
                    disks are cheap and it brings both redundancy and speed compared to 5 disk raid0

                    Comment


                    • #40
                      Originally posted by starshipeleven View Post
                      What's the status of bcachefs? Is that just faith or you actually saw/tested something promising beyond some words on a Patreon page?
                      Do a quick Google search - or simply go back and review previous Phoronix articles concerning bcachefs and btrfs.

                      Comment

                      Working...
                      X