Announcement

Collapse
No announcement yet.

Benchmarks Of The New ZFS On Linux: EXT4 Wins

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

  • #11
    wow, what posts... one bullshit post after the other. even kindergarden would have a higher educated level than what i read here.

    Comment


    • #12
      asdx, as always inconsistent with his own opinion:
      Originally posted by asdx
      I really don't care if BSD or Linux shares ideas between them, in fact, I believe that's a good thing.
      So actually you think that ZFS on Linux is a good thing? So why do you now state it the other way around? By the way, the same thing that is done by the antiBSD troll, in his previous incarnations as "systemd anals BSD", as you can see here (the original post was deleted): http://phoronix.com/forums/showthrea...280#post309280

      Grow up, start to contribute instead of bitching around on forums and maybe start to be consistent with your own opinion, then people will start to take you seriously.

      Comment


      • #13
        Jesus, don't feed the trolls, people. Seriously, the Phoronix forums are disgraceful. Spamming the forums with crap like this really should get you banned.

        I will say though that I would expect ZFS to be slower that EXT4, but there are no details here on how either filesystem was configured, and unless ashift for ZFS was set correctly these results are invalid. With that said, you can expect performance for SSD-backed ZFS to suck pretty hard after a full disk of writes, since there's still no vdev TRIM support. For closer apples to apples you could also configure both filesystems to have more comparable features enabled, but whatever.

        Multi-disk comparisons should be interesting, though I don't know how you decide which pool topologies you test, and what you do about ZFS support for SSD-backed ZIL and L2ARC.
        Last edited by pdffs; 18 April 2013, 08:59 PM.

        Comment


        • #14
          Originally posted by pdffs View Post
          Multi-disk comparisons should be interesting, though I don't know how you decide which pool topologies you test, and what you do about ZFS support for SSD-backed ZIL and L2ARC.
          An interesting test, and the only one that really matters in the real world, would be which one loses data quicker. Ext4 seems to have the lead there.

          Comment


          • #15
            I love reading comments from grown men acting like prebubescent punks on the tech sites. It reminds me of 3rd grade when the fat kid beat up on the smallest kid in school. Later on as they both matured the fat kid became the runt and ostracised from progress. The same will be with filesystems.

            Comment


            • #16
              Originally posted by crapI3SD
              He does contribute to open source, he contributes to proprietary software via BSD. That's worse that not contributing at all.
              Flawed argument is flawed. He contributes to both proprietary software and open source software. Just because you contribute to BSD doesnt mean your code is automatically closed so no one but some arbitrary company can see it. The code itself is open, their copy of the code is closed and therefore benefits BOTH open and closed source programs.
              All opinions are my own not those of my employer if you know who they are.

              Comment


              • #17
                Did ext4 win the reliability tests?

                Comment


                • #18
                  Originally posted by johnc View Post
                  Did ext4 win the reliability tests?
                  If both tie for, "i've never lost anything under this file system", does it even matter which one is technically more reliable?

                  For big data centers, sure, but not for a desktop system.

                  Comment


                  • #19
                    Originally posted by smitty3268 View Post
                    If both tie for, "i've never lost anything under this file system"
                    That statement is totally true until it's not. Which is the only time you care.

                    Comment


                    • #20
                      Originally posted by pdffs View Post
                      That statement is totally true until it's not. Which is the only time you care.
                      Which is equally true of zfs. Nothing replaces a real backup.

                      Comment

                      Working...
                      X