Announcement

Collapse
No announcement yet.

Running The Flash-Friendly File-System On A Hard Drive? Benchmarks Of F2FS On An HDD

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

  • Running The Flash-Friendly File-System On A Hard Drive? Benchmarks Of F2FS On An HDD

    Phoronix: Running The Flash-Friendly File-System On A Hard Drive? Benchmarks Of F2FS On An HDD

    While I have benchmarked the F2FS file-system a lot since it was mainlined back in 2013, it's all been on solid-state drives or even other forms of flash storage like USB drives. After all, F2FS is short for the Flash-Friendly File-System. But a Phoronix reader recently suggested that F2FS also works out well for traditional, rotating hard drives so I decided to run some benchmarks.

    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
    PostgreSQL: Hard-Drive-Friendly File System (HDFFS)

    Typo:

    Originally posted by phoronix View Post
    On the the SATA 3.0 SSD meanwhile F2FS was right in line with EXT4 and XFS.

    Comment


    • #3
      Originally posted by phoronix View Post
      If you are going to those extents to try to maximize your Linux system's storage performance, it may be time to consider switching to SSDs considering the falling prices.
      Lol. Nice line.

      Those tests make me glad I chose XFS for my current Manjaro desktop on a HDD...and reminded me that I forgot to set the cp reflink alias...

      Comment


      • #4
        Wow, WD VelociRaptor. That's a name I haven't heard in quite a long time. Surprisingly you can still buy them on Amazon, though they seem to be new old stock since WD doesn't list them on their site outside of the support section.

        Comment


        • #5
          an age old question of mine has been answered, f2fs works on hdds, and not bad at it

          Comment


          • #6
            That's somewhat surprising.

            Comment


            • #7
              Also worth noting that f2fs is good for pro-longing the life of your drive. It is designed to spread reads and writes more evenly across the sectors. One way it achieves this is by storing the file system meta data (file names, file lengths etc) all across the drive. It intermingles that meta data with the actual data. I think most file systems don't do that; they store all the meta data in one location, usually at the beginning of the partition, resulting in that part of the drive being read/written to more frequently.

              I expect f2fs is a good fit for memory constrained embedded devices that use a micro SD card or some other small flash storage device. The constrained memory means you can't necessarily store the file system meta data in memory which will result in more frequent flash drive reads/writes.

              Comment


              • #8
                Originally posted by cybertraveler View Post
                Also worth noting that f2fs is good for pro-longing the life of your drive. It is designed to spread reads and writes more evenly across the sectors. One way it achieves this is by storing the file system meta data (file names, file lengths etc) all across the drive. It intermingles that meta data with the actual data. I think most file systems don't do that; they store all the meta data in one location, usually at the beginning of the partition, resulting in that part of the drive being read/written to more frequently.
                SSDs will spread writes all right, what you see in the partitioning /defrag software is actually a lie for flash-based media (Flash Translation Layer). The data can be written all over the drive even if your OS thinks it is writing in sector X all the time.

                F2FS has any relevance only for eMMC and USB/Sdcards. And even then the controllers do have some form of wear leveling too, all devices where you could physically kill the cells by overwriting the same "sectors" many times are long obsolete.

                Comment


                • #9
                  Originally posted by starshipeleven View Post
                  The data can be written all over the drive even if your OS thinks it is writing in sector X all the time.
                  I added bold.

                  f2fs is part of the OS and it writes data all over the drive (or rather the part of the drive where the partition is).

                  I think the f2fs design is useful. It's another layer that helps to reduce the chance of uneven reads writes. If the controller lacks wear leveling or the controllers wear leveling design is poor, f2fs will improve the situation.

                  Comment


                  • #10
                    Just benchmarking it on a clean drive is rather useless. The question is more how it behaves when the drive is more fragmented or more used. Since F2FS is a log-based filesystem it fragments quite heavily. Using it in a long run on a HDD could lead to rather bad performance overall.

                    Comment

                    Working...
                    X