Single Client Performance - CIFS & NFS on Linux

A CentOS 6.2 virtual machine was used to evaluate NFS and CIFS performance of the NAS when accessed from a Linux client. We chose IOZone as the benchmark for this case. In order to standardize the testing across multiple NAS units, we mount the CIFS and NFS shares during startup with the following /etc/fstab entries.

//<NAS_IP>/PATH_TO_SMB_SHARE /PATH_TO_LOCAL_MOUNT_FOLDER cifs rw,username=guest,password= 0 0

<NAS_IP>:/PATH_TO_NFS_SHARE /PATH_TO_LOCAL_MOUNT_FOLDER nfs rw,relatime,vers=3,rsize=32768,wsize=32768,namlen=255,hard,proto=tcp,timeo=600,retrans=2, sec=sys,mountaddr <NAS_IP>,mountvers=3,mountproto=udp,local_lock=none,addr=<NAS_IP> 0 0

The following IOZone command was used to benchmark the CIFS share:

IOZone -aczR -g 2097152 -U /PATH_TO_LOCAL_CIFS_MOUNT -f /PATH_TO_LOCAL_CIFS_MOUNT/testfile -b <NAS_NAME>_CIFS_EXCEL_BIN.xls > <NAS_NAME>_CIFS_CSV.csv

IOZone provides benchmark numbers for a multitude of access scenarios with varying file sizes and record lengths. Some of these are very susceptible to caching effects on the client side. This is evident in some of the graphs in the gallery below.

Readers interested in the hard numbers can refer to the CSV program output here.

The NFS share was also benchmarked in a similar manner with the following command:

IOZone -aczR -g 2097152 -U /nfs_test_mount/ -f /nfs_test_mount/testfile -b <NAS_NAME>_NFS_EXCEL_BIN.xls > <NAS_NAME>_NFS_CSV.csv

The IOZone CSV output can be found here for those interested in the exact numbers.

A summary of the bandwidth numbers for various tests averaged across all file and record sizes is provided in the table below. As noted previously, some of these numbers are skewed by caching effects. A reference to the actual CSV outputs linked above make the entries affected by this effect obvious.

ioSafe 1513+ - Linux Client Performance (MBps)
IOZone Test CIFS NFS
Init Write 68 66
Re-Write 68 73
Read 34 123
Re-Read 35 123
Random Read 20 59
Random Write 62 73
Backward Read 19 46
Record Re-Write 38 1300*
Stride Read 31 105
File Write 68 77
File Re-Write 68 78
File Read 24 92
File Re-Read 24 92
*: Number skewed due to caching effect

 

Single Client Performance - CIFS & iSCSI On Windows Multi-Client Performance - CIFS
Comments Locked

43 Comments

View All Comments

  • ddriver - Saturday, August 16, 2014 - link

    Thanks for the input. BTW, where I come from, "cellar" does not imply "basement" - our cellars are usually on floor levels, tiny room, around 1 m^2 for general storage purposes, no water mains no nothing. Closer to what you may call "pantry" in the US. Cultural differences... me'h. Nothing to burn and nothing to flood in there. Plus noise in the cellar bothers nobody.

    Never failed a demo - which exactly proves the point I make earlier about being careful with controlled fires. That would create the illusion your products are flawless and someone's gonna buy one expecting it to survive his fancy wooden and lacquer soaked cottage burning to the ground which I am willing to bet it will not. You should really draw the line between "office fire accidents" and "fire disasters" just for the sake of being more realistic and not deceiving consumers, deliberately or not. People are impressed by big numbers, and could easily be impressed by the 1700 F number, absent the realization most flammable materials burn at significantly higher temperatures. Every engineer knows - there is no such thing as a flawless product, the fact you never had a failed demo only goes to show you never really pushed your products. With those zero failed demos you will very easily give consumers the wrong idea and unrealistic expectations, especially ones who are not educated on the subject. You SHOULD fail a few demos, because it will be beneficial for people to know what your products CAN'T HANDLE. A few failures in extreme cases will not degrade consumer trust as your PR folks might be prone to believing, it will actually make you look more honest and therefore more trustworthy.
  • ddriver - Saturday, August 16, 2014 - link

    I mean better you cross that line with a test unit than some outraged consumer going viral over the internet how your product failed and he lost his life work ;)
  • robb.moore - Monday, August 18, 2014 - link

    Hi ddriver-
    As mentioned, our fireproof tech relies on proven methods that are over 100 years old. Appreciate the heated skepticism though. As an engineer myself, I agree that no product is flawless and everything (including our own products) have their limits. I take back the "never failed a demo" comment. We did some gun demos with shotguns (passed) - got a bunch of flack for ONLY using shotguns so we redid the demo with fully auto AR-15's - blew holes completely through the product and of course failed...sometimes. Fun demo though.
    -Robb
  • Phil Stephen - Monday, August 18, 2014 - link

    ddriver: I'm a firefighter and can confirm that, based on the specs, these units would indeed withstand a typical structure fire.
  • zlobster - Sunday, August 17, 2014 - link

    Dear Mr. Moore,

    I'm really glad that you actually follow up with the public opinion.

    I'll try to use the opportunity and use it to ask you whether you are planning to build a unit with non-Intel CPU, rather with AMD/ARM/Marvell/etc.? A unit that can handle the latest industry standards for on-the-fly encryption without sacrificing the performance even a bit?

    Also, besides the physical integrity and resiliency tests that you are conducting, do you do similar penetration-testing for data integrity? I mean, with well-known independent hacker/pen-testing communities? With all the fuzz around govt. agencies putting backdoors virtually everywhere, it's of extreme importance for the piece of mind of extreme paranoics (like me), to know how hack-proof your devices are.

    Regards,
    Zlob
  • robb.moore - Monday, August 18, 2014 - link

    Hi Zlop-
    We're constantly working on new products. The 1513+ does use an Intel chip but our other NAS (2 bay), ioSafe 214 uses a Marvell chip. We realize that encryption can be important in many situations and we're always interested in balancing features, cost and speed for our products. Can't make direct comments though on what we have in the pipeline except stay tuned! :)

    In regards to "hack-proof", the most "hack-proof" systems (aka CIA, etc.) don't exist on the internet at all. They're fully contained offline in secured facilities. In fact, ioSafe systems are used in situations like this where offsite backup (online or physical relocation) is not allowed or impractical but the end user still wants a disaster plan.

    Obviously, there's a balance between security, accessibility, cost and speed. If you put an ioSafe system online, no firewall, never update OS/firmware, all ports open with standard admin passwords - expect mayhem. If you put an ioSafe system in a bank vault, offline and turned off it's obviously pretty secure but inaccessible - not very useful. Security can be complicated. Striking the right balance is different for every situation. Our NAS systems are based on the Synology platform which in turn is a custom Linux kernel so it's as safe as you make it generally (like all connected systems) and is susceptible to hackers if setup incorrectly. We're very happy to help you with configuring your device if you have any questions at all about the tradeoffs.

    Ultimately though its under your control. You're in charge of opening or closing doors.

    Robb Moore, CEO
    ioSafe Inc.
  • PEJUman - Saturday, August 16, 2014 - link

    I second that, for this price... I really want to know it it would last the rated time under fire. Should try it under propane {bbq tank 2300+ C} and and Nat. Gas/wood based flame {1900+ C} To simulate household/industry gas line.
  • bsd228 - Thursday, August 14, 2014 - link

    Well for the $1000 extra, one could buy a 30"x72" inch gun safe that can also be used to store the regular Synology (or a DIY NAS) plus guns, camera gear, and any other valuables. Harder to steal as well- they weight 500-1000lbs.
  • DanNeely - Thursday, August 14, 2014 - link

    Maybe; but good luck using the NAS with the door shut...
  • smorebuds - Thursday, August 14, 2014 - link

    l0l

Log in

Don't have an account? Sign up now