Announcement

Collapse
No announcement yet.

Samsung 840 EVO 120GB SSD

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

  • #16
    Originally posted by ricequackers View Post
    Honestly, you bought the wrong drive. The 128GB is slower than its siblings as not all NAND channels are populated. Step up to the 256GB or the 512GB (I own the latter) and it's a super speedy drive that's much cheaper than its direct competitors.
    Yes, because everyone needs more than 120GB. Most people doing nothing but surfing the web, watching videos and using Office etc. don't need more space, and buying a bigger version would be a waste of money for them.

    Originally posted by devonwarren View Post
    Did you update to the latest firmware? http://www.samsung.com/global/busine...downloads.html

    I am surprised by these benchmarks, I was going to swap out my current vertex 3 for an evo (mostly because I am running out of storage) but now I am doubting that decision..
    How often do you copy huge files? Because in day-to-day tasks, it performs amazing. Who cares about sequential write.

    Originally posted by zanny View Post
    Good luck with that, considering Samsung dosen't provide any means to update their firmware through Linux.

    I know Sandforce models do, though. Their update utilities are even in the AUR.
    No problem at all. Use unetbootin or something on Linux and install FreeDOS on an USB drive with one click. Then put the firmware update files on it and boot from the USB drive. It works, I did it this way.



    I switched from a 2010 120GB Intel Postville SSD to a 2013 250GB Samsung 840 EVO SSD and don't notice any differences in day-to-day scenarios like opening applications etc., it was fast before and it is still fast. Tbh., SSD benchmarks are really uninteresting at this point as 99% of the people don't copy huge files all the time and just use their applications/games. The Intel SSD is now sitting in my Thinkpad X121e with an old AMD E-350 APU and it runs great there.

    Comment


    • #17
      The OCZ drives can be upgraded "live" on linux.
      (I.e.: without taking down your server).
      Just extract the right tools from their rescue CD (you must mount -o loop the squashfs packages of the firmware to cp them), cp them to your server and remove the SSD from the raid, upgrade, and put it back in the raid.

      For hobby I use 2 samsung 840's (not EVO), and I won't upgrade them because I can't. I wouldn't know how... Bike to the datacenter, then remove them. Then go with the SSD's to a place where I can upgrade them (still don't know where and how), then bike back to the datacenter, screw them back in, and turn it on. Because It's raid, I have to do it for each SSD, and in the mean time the server is down.

      From a professional point of view, the OCZ's are the least hassles to upgrade.

      Comment


      • #18
        Originally posted by stiiixy View Post
        I got stuck with a Samsung 830. Apparently they're even crappier than rotating disc-a-mathings. After seeing people with these rotor things load games faster on shittier spec'd systems that I, I tend to agree.

        *shrug*

        200GB of SSD that still loads 70% of tasks faster than any rotunda-drive can offer is good enough for me. Just not for the price premium SSD demands =D Lucky I got it on spesh!
        Umm, what? The 830 uses MLC vs the 840 EVO using TLC, making the 830 actually better than the 840 Evo (the 840 Evo Pro is an entirely different beast). The 830 has also consistently been rated in the top tier of all SSD drivers, and, when new, was generally one of the fastest out there, too. So, either your drive, bios/system config, or another piece of hardware in your system is fubar'd.

        Comment


        • #19
          Huh, that's very interesting. I was looking at the 120GB version, so it's probably good that I went with Toshiba after all. Since I don't have it installed yet, I'll probably take the opportunity to run a benchmark on my end to see how it fares.

          I'm also a bit unsure of I/O schedulers at the moment. I always thought you're supposed to use deadline or noop with SSDs, but it seems that CFQ got updates and now works fine on SSDs as well. Hmm... Of course, deadline is good for benchmarks, but probably it's best to stay with cfq on desktops, then?

          Comment


          • #20
            These results looks pretty odd. Did the test have trim enabled? Which scheduler was used? Was SATA set to IDE or AHCI? noatime set?

            Comment


            • #21
              Wasn't there some big slowdown found in kernel 3.13? Was that ever fixed?

              Comment


              • #22
                Originally posted by zanny View Post
                I wonder how much btrfs transparent compression helps here.
                on a i7-4770 i found btrfs transparent compression couldn't keep up with raid 10 3xsamsung 840 evo. zfs and lz4 compression could though.

                all these tests are write-heavy though, and they go past the turbowrite theshold.

                Comment


                • #23
                  Originally posted by bakgwailo View Post
                  These results looks pretty odd. Did the test have trim enabled? Which scheduler was used? Was SATA set to IDE or AHCI? noatime set?
                  i got some odd results with my raidz zfs 3xsamsung 840 evo on these tests too, i didn't upload my results in the end, as i don't think it's a proper way to benchmark real world usage at the same time.

                  the samsung 840 evo's only do about 135mb/sec write speed when you write more than 3gb of data, that these tests do.

                  that said, i still haven't figure out best way to benchmark real world usage. i found something to test read iops in parallel, but all ssd's i've come across seem to such at sequential 4k read iop's, and that's more like what most linux systems are actually doing.

                  curiously, i also foudn when using md that there was a difference in performance between direct and buffer cache speeds, but there was a much bigger difference in cpu usage - to the tune of an order of magnitude difference in dd cpu usage with using buffered i/o versus direct, and a much smaller difference with raw speeds.
                  Last edited by mercutio; 01-24-2014, 05:54 PM.

                  Comment


                  • #24
                    Guys, as an owner of 250GB version of Samsung 840 EVO, I did quite thorough research of my drive on the web before I bought it and the result is that is is one of the fastest SSD on the marked. This is clearly visible from numerous benchmarks all over the web, so I am afraid there is some serious problem with your tests. Are your filesystems alligned? Is 6Gb SATA really working? Do you have AHCI enabled and working? Do you have latest FW in all drives? there is no way that Samsung 840 EVO is so much slower than OCZ Vertex 3, actualy it is usually faster, sometimes significantly:

                    http://www.bit-tech.net/hardware/sto...gb-1tb-revie/6
                    http://www.anandtech.com/bench/SSD/260
                    http://ssd.userbenchmark.com/SpeedTe...-840-EVO-120GB

                    and most importantly:
                    http://www.anandtech.com/show/7173/s...dels-tested/10

                    please, check what is wrong with your setup, fix it and rerun the test, this is really shame on your side!

                    Comment


                    • #25
                      Originally posted by walkeer View Post
                      Guys, as an owner of 250GB version of Samsung 840 EVO, I did quite thorough research of my drive on the web before I bought it and the result is that is is one of the fastest SSD on the marked. This is clearly visible from numerous benchmarks all over the web, so I am afraid there is some serious problem with your tests.
                      I own an Evo 250GB version as well, and yes, it flys on Linux despite the inability to use the software enhancements. I have also owned both the Vertex II 60GB and Vertex III 90GB respectively (as well as a Crucial M4 128GB and a Mushkin Chronos Enhanced 60GB) and have a collection of synthetic benchmarks for all (Using the benchmark feature in Gnome Disk Utility). The Samsung rates the best overall of the bunch although I have not had it long enough to know if performance degrades over time (Both Vertex drives had to be Secure Erased every couple of months to restore full performance as they would drop by 20% with regular use). Interestingly, the benchmark differences are essentially insignificant for read speeds (varying test to test between 545MB and 559MB, excepting of course the Vertex 2 which is SATA II if I recall correctly). The write speeds vary more widely.

                      All that being said, having looked at the scores in this article, I come to two possible conclusions.
                      Either the performance difference between the 120GB and 250GB is staggeringly different* and the 120GB Evo is a complete piece of garbage or something in the Phoronix benchmark process is horribly askew.


                      * As mentioned earlier in this thread, the 120GB is clearly lacking compared to its larger kin but I am hard pressed to believe that it is only slightly faster then spinning platters.

                      Comment


                      • #26
                        Here are the results of my Toshiba Q Series Pro:
                        http://openbenchmarking.org/result/1...hm=y&obr_sgm=y
                        Note that my processor is not as strong as the one Michael used, and it's not a clean install (with programs running during tests), so any processor-bound tests will show poorer performance in comparison.
                        But overall it seems it beats the Samsung 840 EVO 120 GB and the Kingston drive as well. For the price (same as the Samsung drive) that's really not bad at all.

                        Comment


                        • #27
                          Well crap. I was going to get that drive. I guess I will have to keep looking.

                          Comment


                          • #28
                            So what SSD do you guys recommend? I'm looking for an affordable 120/8GB model. Was looking at the Samsung EVO but this review is turning me away from it.

                            Comment


                            • #29
                              Originally posted by Melcar View Post
                              So what SSD do you guys recommend? I'm looking for an affordable 120/8GB model. Was looking at the Samsung EVO but this review is turning me away from it.
                              *points towards my last post*

                              Comment


                              • #30
                                Originally posted by Laslow View Post
                                I own an Evo 250GB version as well, and yes, it flys on Linux despite the inability to use the software enhancements. I have also owned both the Vertex II 60GB and Vertex III 90GB respectively (as well as a Crucial M4 128GB and a Mushkin Chronos Enhanced 60GB) and have a collection of synthetic benchmarks for all (Using the benchmark feature in Gnome Disk Utility). The Samsung rates the best overall of the bunch although I have not had it long enough to know if performance degrades over time (Both Vertex drives had to be Secure Erased every couple of months to restore full performance as they would drop by 20% with regular use). Interestingly, the benchmark differences are essentially insignificant for read speeds (varying test to test between 545MB and 559MB, excepting of course the Vertex 2 which is SATA II if I recall correctly). The write speeds vary more widely.

                                All that being said, having looked at the scores in this article, I come to two possible conclusions.
                                Either the performance difference between the 120GB and 250GB is staggeringly different* and the 120GB Evo is a complete piece of garbage or something in the Phoronix benchmark process is horribly askew.


                                * As mentioned earlier in this thread, the 120GB is clearly lacking compared to its larger kin but I am hard pressed to believe that it is only slightly faster then spinning platters.
                                Tom's Hardware has an extensive write up but basically the 120 has a slightly different chip configuration than the 250 for the 840 EVO. That said i read this review and headed over to the comments to see if anyone else thought the authors results were way off target. I have a 250 EVO 840 on a SATA II bus pushing read/writes above 200 MB/sec with a confirmed 3gbps sata link. Tom's hardware goes into detail when you'll hit the cache limit and will be slowed to the maximum writes of the TLC flash (on their SATA III rig about 300+ MB/sec). I don't think the test in this article is representative of the 840 EVO.

                                Comment

                                Working...
                                X