Can OS X Server solve tcp/ip timeouts choking a Mac Pro now on 10.6.4?

Discussion in 'Mac OS X Server, Xserve, and Networking' started by abbott.bill, Sep 19, 2010.

  1. abbott.bill macrumors newbie

    Sep 17, 2010
    (Moderators: This is a work related problem and we have Mac-users as customers but the question is technical and not product related. I've removed all commercial info and feel the question has merit in this forum as is. I've read the faq and user rules and I believe this is a fair use, but if you require it I'm happy to annotate my company and product names. But what I'm asking is really an OS X 10.6 vs OS X Server AND tcp/ip question, without reference to particular applications. This note needn't accompany the posting.)

    I'm testing a multi-platform app that uses tcp/ip for client/server communications. To simulate a typical environment, a script calls a script... to start a number of parallel operations through tcp/ip. The data is the same for all instances but can be anything the discs will hold. For testing, both clients and server are actually running on the same computer.

    Our baseline Linux server runs fine, with 100 simultaneous "users" and
    8 files each- 6 text and binary files up to 1M, a 4.5Mb bitmap photo
    image and a 17Mb bitmap photo image. (yes we chose the bitmaps to load
    the system. The clients compress and decompress them before and after they go through the network.

    With OS X 10.5 Server, our very lightly configured Intel XServe blade
    can handle it too- it has four cores, 2.* GHz (just under 3) and 4 Gb
    of physical memory. We had it configured as a lightweight to support
    testing client software, mostly.

    With OS X 10.6.4, my desk Mac Pro chokes at something over 60 'users',
    although it has 8 cores (two quads at 2.66Ghz, 1066 bus speed) and
    16Gb of physical memory. With only the 6 little files and the smaller (4.5Mb)
    photo. Take out the photo and I can get 100 'users' running, files
    size up to 1Mb spreadsheet, without a problem.

    When it chokes, I get tcp/ip timeout errors, leading to broken pipe
    errors, all from deep in the stack.

    I copied all the sysctl parameters relating to networks from the XServe/OS X
    Server 1.5 to my Mac Pro/ OS X 1.6.4. Number of processes per UID, number of files, etc etc. There were fewer failures but no complete success.

    One of our frighteningly smart, but not very Mac knowledgeable,
    resources believes that its the OS getting in the way and we should buy
    Server for the Mac Pro. They also believe that having the same
    parameters in OS X and OS X Server is as good as we can get.

    I suspect that the Mac Pro, good though it is, with twice the cores and four times the memory, is still less powerful than the XServe, in terms of tcp/ip throughput. I am certainly willing to hope, however. If there were a software change that allowed me to make this work, I'd be on it.

    The next step is dual booting with Linux, and hoping that tcp/ip support is better there.

    Does anyone have experience using OS X Server on a Mac Pro (mid 2009
    production) as a way to get better tcp/ip performance? vs OS X 10.6.4?

    I think copying the sysctl parameters may be less than a complete effort, not only are 10.5 Server and 10.6.4 different, the hardware is different and built for different tasks. There may be different parameters to set and different parameter values needed to get the max throughput without timeouts.

    Second question, does anyone have experience tuning Mac OS X 10.6 for maximum tcp/ip throughput, in particular, tuning-out the timeouts/broken pipes?

    Of course,researching all these settings is my next step- RTFM.

    If someone's been down this path and has experience I'd love to
    hear from them. Particularly whether spending $499 for Server will
    solve the problem, or if the bandwidth problem is something I can tune out. Anyone? This is too long as it is but I can supply blow by blow sysctl values, etc, if anyone needs them.

    Many thanks

  2. foidulus macrumors 6502a

    Jan 15, 2007
    Sorry not a whole lot experience with this

    but the first thing I would recommend is checking your DNS setup. OS X gets very particular with how it does lookups and a misconfigured DNS can cause all sorts of TCP/IP havoc(I've seen it, it's not pretty).

    Secondly I would recommend you try to isolate one variable at a time here, you are trying on 10.5 server and 10.6 client. I'd be curious if you have tried your code on a 10.5 client machine(unfortunately you cannot install 10.5 on your mac pro, you may have to dig up an older machine)

    I doubt the difference is really between the client/server versions of the operating system. The "Server" doesn't actually go very deep into the OS itself, certainly wouldn't affect anything at the TCP/IP level. (IIRC the kernel itself is IDENTICAL). It's really just a amalgam of services running on top of OS X.
  3. jerry333 macrumors regular


    Nov 4, 2005
    What foidulus said. Plus make sure you're running in 64 bit mode. OS X Server is always 64bit mode, but OS X may not be. (Activity monitor will show 64 bit processes running if it's running in 64 bit mode).
  4. assembled macrumors regular

    Jan 12, 2009
    The stack is the same on desktop and server, there are numerous small changes to the rest of the os/app stack, but the core tcp/ip stack is the same. 10.5 and 10.6 do not have the same stack.

    I'd guess that your code is the problem. did you recompile for 10.6 ?

    It sounds like your application accepts a files, then processes it, have you tried just doing the process part on a large number of files, and just tried just accepting large number of files.

    If you want to check network performance of each computer, run iperf, but I'n guessing that you've already done this... You could also try running one of the many FTP servers and seeing what throughput you can achieve...

    Unless you need something that is only available on OS X IMHO I wouldn't use it for server applications as Apple servers simply don't scale the way that HP/Dell/IBM ones do. Before people think this is flaming, I run a server that has 4 quad core processors, 128gb of memory 4 disk in a RAID10 for boot, and another 4 in RAID10 for swap with 4 gigabit NICS and two dual port FC-AL cards, and this server runs at ~75% utilisation most of the time...

    We also run Apple servers for OD logins (via AD) for some legacy Apple only software, but migrated everything else to Windows or Linux a long time ago.

Share This Page