Announcement

Collapse
No announcement yet.

Btrfs vs. EXT4 vs. XFS vs. F2FS On Linux 3.10

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

  • Btrfs vs. EXT4 vs. XFS vs. F2FS On Linux 3.10

    Phoronix: Btrfs vs. EXT4 vs. XFS vs. F2FS On Linux 3.10

    Building upon our F2FS file-system benchmarks from earlier in this week is a large comparison of four of the leading Linux file-systems at the moment: Btrfs, EXT4, XFS, and F2FS. With the four Linux kernel file-systems, each was benchmarked on the Linux 3.8, 3.9, and 3.10-rc1 kernels. The results from this large file-system comparison when backed by a solid-state drive are now published on Phoronix.

    http://www.phoronix.com/vr.php?view=18720

  • #2
    The next set of benchmarks better have btrfs told to compress with lzo, otherwise you're not really testing btrfs in a way that would be used real world.

    Comment


    • #3
      For btrfs, are you turning off COW for database file(s) for the database-driven tests?

      Comment


      • #4
        Originally posted by Ericg View Post
        The next set of benchmarks better have btrfs told to compress with lzo, otherwise you're not really testing btrfs in a way that would be used real world.
        That would break many benchmarks. Notice that test files are often full of zeroes, yielding unrealistic benefits. Real world data isn't anything like that.

        Comment


        • #5
          Originally posted by rvalles View Post
          That would break many benchmarks. Notice that test files are often full of zeroes, yielding unrealistic benefits. Real world data isn't anything like that.
          True, wasn't thinking about the fact that he just does zero-filled files instead of random-filled

          Comment


          • #6
            Other OS tests

            It would be interesting to get an idea of what that hardware can do under NTFS or OSX, for comparison. For example, btrfs looks pretty bad compared to ext4, but i wonder if it's competitive with what you'd see on other OS's. In other words, is btrfs really struggling, or is ext4 just really good?

            Comment


            • #7
              With ZFS finally being declared stable on linux, it should really be included in these benchmarks. It is an excellent comparison for btrfs, since they are both COW, modern filesystems, which can lead to performance penalties compared to conventional filesystems like ext4 or XFS.

              Comment


              • #8
                Originally posted by smitty3268 View Post
                It would be interesting to get an idea of what that hardware can do under NTFS or OSX, for comparison. For example, btrfs looks pretty bad compared to ext4, but i wonder if it's competitive with what you'd see on other OS's. In other words, is btrfs really struggling, or is ext4 just really good?
                Btrfs has different features. But what would be worthwhile is to test NTFS (as a counterpart to EXT4) and ResFS (as a counterpart to Btrfs) on Windows.

                Comment


                • #9
                  btrfstune

                  Michael, in 3.10, btrfs has gained skinny metadata support. It'd be interesting to benchmark btrfs with that feature turned on (needs btrfstune).

                  Comment


                  • #10
                    If you choose your filesystem based on a bunch of artificial benchmarks that show how "fast" it is, you are an idiot!

                    Choose a filesystem based on requirements and testing. If you have only the requirement for it go really fast, then sure, these could inform your decision, but you should still test with your own workloads. This is however a very specialized subset of people (pros doing video editing, photoshop artists, CERN etc.) that need outrageous speed when editing or during experiments. For long term storage these people will still be using one of the "slow" filesystems that actually protect their data.

                    Everyone else should pick the filesystem with the best data integrity and resiliance. You will likely never notice loss of "speed" what with continuous improvements in hardware, caching and prefetch of data.

                    Comment


                    • #11
                      ext4 forever

                      ext4 forever! Seriously, do we really need so many filesystems ? Benchmark after benchmark, I fail to see any advantage of all those filesystems compared to ext4.
                      Last edited by wargames; 05-18-2013, 07:47 AM.

                      Comment


                      • #12
                        Originally posted by kiwi_kid_aka_bod View Post
                        For long term storage these people will still be using one of the "slow" filesystems that actually protect their data.
                        It's not like ext4 isn't stable at all. The only upside of btrfs about stability is snapshots; it is usually less stable than ext4.

                        Originally posted by kiwi_kid_aka_bod View Post
                        Everyone else should pick the filesystem with the best data integrity and resiliance. You will likely never notice loss of "speed" what with continuous improvements in hardware, caching and prefetch of data.
                        Everyone else should encrypt their multiplayer game packets in AES, too, because you don't want other players to know your location on the map, but we can afford our ping times going from 50 ms to 150 ms. Amirite?

                        Ontopic : it's quite funny, but even on a SSD, ext4 tends to be better than F2FS. I'm using it on a SSD and it works fine.
                        Last edited by Calinou; 05-18-2013, 08:16 AM.

                        Comment


                        • #13
                          what about HUMMER, reFS and tux3?

                          I think if you are very bored you should try to make a grand filesystem speed comparison.

                          Comment


                          • #14
                            Still don't get it...

                            I still fail to get the point of these apples-vs-oranges benchmarks...

                            Comment


                            • #15
                              Originally posted by wargames View Post
                              ext4 forever! Seriously, do we really need so many filesystems ? Benchmark after benchmark, I fail to see any advantage of all those filesystems compared to ext4.
                              Ext4's architecture and design is 20years old, its boilerplate code atop ext1. Thats about as much of a "hackjob" as you can get. So tell me.. do you like the thought of your entire filesystem being a hack job?

                              Besides, every filesystem has its own place and own goal. F2F2 is designed or flash media like phones and tablets. Btrfs is a pretty good general filesystem, especially if have limited space (compression) or multiple disks (built in volume management), it also has functions specifically built in for ssd's which is very relevent in the future, something that ext4 doesn't have.

                              XFS, JFS, Reiser, those..I honestly couldn't tell you what they are good for. From what I hear, XFS is very prone to complete failures and even one dirty shutdown can hose the entire system. JFS was an IBM filesystem from forever ago, Reiser was a proof-of-concept filesystem who's reputation got trashed after its head developer (and the person it was named after) murdered his wife.

                              What I am looking forward to though is Tux3, It will be very interesting to see the results of Tux3 vs Btrfs in the next few years.

                              --A happy btrfs user--

                              Comment

                              Working...
                              X