M-Series read + Write, threading or async , performance issues

I have a slightly unusual issue: Using 2 USB-6251 and 2 USB-6015 within the same application.
1 of the USB-6251s reads data on a 50 msec look (Driven by an async timer).
Depending on the input the code decides to output a 40 Hz, 300 usec  waveform  of varying amplitude  - the output goes one until there is  a user event that might make it stop.
Now , here is the problem.  I have implemented the output function using a sepereate high priority thread and the delay( delay_in_sec) command.
I find that while the data acquisition timer is NOT running the frequency of the output is very close to 40 Hz. When the data acquisition IS running , the frequency of the output varies considerably - most likely reflecting USB delays.
I was able to see the output 40Hz, 300 usec waveform using a seperate app using a single async timer w/o any data acq and the timing was immaculate.
My questions are:
1. Could I use 2 different async timers in the same app - I tried to do this and the output was still wacky when I turned data acquisition on
2. Is there any way outside the delay() command that could improve the timing accuracy of the analog output thread?
3. I measured the time to create a 300 usec pulse of a certain amplitude, write it to the USB-6251 and start the task and it was ~ 13 msec. This is way too slow for 300 samples at 1 MHz - is it a USB bus limitation, or I should look at my design to see what is going on?
4. Any NI hardware that would allow me to handle 4 analog outputs more gracefuly? (FYI, 2 of my outputs are at 1 MHz and 2 of them at 50 Hz).
Thanks
AP

THanks for taking the time to look at my message.
I am using 4 DAQs. First one, USB-6251 is used to collect data (4 analog inputs @ 20Hz) and also occasionally provide analog output @ 1 MHz.
Second DAQ is a USB-6251 occasionally provide analog output @ 1 MHz.
Third and Fourth DAQ  areUSB-6015 occasionally providing analog output @ 50 Hz.
All devices are connected via USB to a Dell Dual Core notebook.
THis is how I create & configure the analog output channels - using 1 task per device.
                    DAQmxErrChk(DAQmxCreateAOVoltageChan(TaskAnalogX,channelstring , "Ramp 1",0 , 10, DAQmx_Val_Volts, ""));
                    DAQmxErrChk(DAQmxCfgSampClkTiming(TaskAnalogX, "",1MHz OR 50Hz, DAQmx_Val_Rising, DAQmx_Val_FiniteSamps     , SECONDS*1MHz));
                    DAQmxErrChk(DAQmxWriteAnalogF64 (TaskAnalog1, ( int32 )SECONDS*1MHz OR 50Hz ), 0, DAQmx_Val_WaitInfinitely, DAQmx_Val_GroupByChannel , PHAOarr, &sampsPerChanWritten, NULL));
THe design/architecture is pretty complex but on a very high level whenever I need to deliver analog output I configure the output waveforms and then write it to the DAQs and then use some timers/logic to deliver the waveform from the DAQ as needed.
Now the challenge has been that in one specific case I need to deliver analog output of uknown duration (whereas everything else is deterministic). In that case i  created a seperate thread and write each 300 usec pulse individually to the analog output (using USB 6251)using the following tASK:
                    DAQmxErrChk(DAQmxCreateTask("Tonic Output Task", &TaskTonic));  
                    DAQmxErrChk(DAQmxCreateAOVoltageChan(TaskTonic, channelstring , "PulseToPulse",0 , 10, DAQmx_Val_Volts, ""));    
                    DAQmxErrChk(DAQmxCfgSampClkTiming(TaskTonic, "",1.0E+06, DAQmx_Val_Rising, DAQmx_Val_FiniteSamps , 301));
As described in my first message this is very sensitive to timing and it takes 13 msec to stop the task , write the array to the DAQcard and then start the task again.
On the hardware timing recommendation. I tried to configure the DAQ  using the DAQmx_Val_HWTimedSinglePoint samplemode but it seems not to be supported by the hardware I am using.  Is there a CVI example of using hardware timing that I can take a look at?
THanks
AP
Hi AP,
My first impression is that you would want to use hardware timing
rather than software timing.  Try using a DAQmx Timing command and
specify the rate there.  Aside from that, could you be more specific
about your application?  How do you have your hardware set up and which
devices are handling each part of the task?  How are you generating the
output?
Regards,
Joe S.

Similar Messages

  • Reader writer thread

    I don't know how to start to implement a reader writer thread. I have a vector, and multiple threads. I would like to allow mulitple threads to read and one to modify. Does anyone where I should start? I know that I can't use
    synchronize(object) {
    since this will only allow one thread to acess the code.
    Thanks.

    It doesn't sound like you have a good background in concurrency yet. Take a look at this book.
    http://java.sun.com/docs/books/cp/
    Great book, great guy. Let me know if you need any help after you start.

  • Reader/writer threads

    I have a program with three threads running at the same time. One thread writes integers to a shared store and two identical reader threads read from the store. Is there any way to specify which specific reader reads the integer depending on (for example) if the integer in the store is an odd or even number?
    Any help much appreciated.
    Meg

    Why ? What practical application would it have.
    Not sure about practical applications - I am just learning about threads so it is a made up example to help me understand... - any pointers?

  • Multithreaded problem in read and write thread

    This is a producer consumer problem in a multi-threaded environment.
    Assume that i have multiple consumer (Multiple read threads) and a
    single producer(write thread).
    I have a common data structure (say an int variable), being read and written into.
    The write to the data sturcture happens occasionally (say at every 2 secs) but read happens contineously.
    Since the read operation is contineous and done by multiple threads, making the read method synchronized will add
    overhead(i.e read operation by one thread should not block the other read threads). But when ever write happens by
    the write thread, that time the read operations should not be allowed.
    Any ideas how to achive this ??

    If all you're doing is reading an int, then just use regular Java synchronization. You'll actually get a performance hit if you're doing simple read operations, as stated in the ReadWriteLock documentation:
    Whether or not a read-write lock will improve performance over the use of a mutual exclusion lock depends on the frequency that the data is read compared to being modified, the duration of the read and write operations, and the contention for the data - that is, the number of threads that will try to read or write the data at the same time. For example, a collection that is initially populated with data and thereafter infrequently modified, while being frequently searched (such as a directory of some kind) is an ideal candidate for the use of a read-write lock. However, if updates become frequent then the data spends most of its time being exclusively locked and there is little, if any increase in concurrency. Further, if the read operations are too short the overhead of the read-write lock implementation (which is inherently more complex than a mutual exclusion lock) can dominate the execution cost, particularly as many read-write lock implementations still serialize all threads through a small section of code. Ultimately, only profiling and measurement will establish whether the use of a read-write lock is suitable for your application.

  • How should I report forum performance issues?

    The forums rely heavily on the caching features of browsers to improve the speed of page rendering. Performance of these forums should greatly improve after a few pages because more and more of the images, css and javascript is cached in the browser. As a consequence, when reporting forums performance issues the report should include some information on the state of the browser cache to determine whether the issue is a browser issue or a server issue. Such detailed information is generally not available from just watching the browser screen, but needs to come from specialized tools such as performance monitor plugins and recording proxies.
    The preferred report method for performance issues is to use the speed reporting features build into or available as a plugin for a browser for both the page you want to report a problem with and several refence pages in the site. Detailed instructions are listed below separated out for different browsers. If possible, please use Firefox for submitting the report because it provides an export format that can be read back electronically.
    Known performance issues
    The performance issues with any screen with a Rich Text Editor, such as the Reply window and the compose Private Message window have been acknowleged and improvements are being implemented.
    Mozilla Firefox (preferred)
    Warning: it is currently not recommended to generate a speed report when logged in. The speed report has enough detail for somebody else to hijack your session and impersonate you on the forums. If you really must report while logged in, make sure you log out your browser after generating the speed report and wait at least 4 hours before posting.
    Install the Firebug plugin
    Install the NetExport 0.6 extension for Firebug
    Enable all Firebug panels
    Switch to the "Net" panel in Firebug
    Click on this link
    Export the data from the Firebug Net panel
    Click on this link
    Export the data from the Firebug Net panel
    Browse to the page where you are experiencing the performance problem.
    Export the data from the Firebug Net panel
    Click on this link
    Export the data from the Firebug Net panel
    Click on this link
    Export the data from the Firebug Net panel
    Browse to the page where you are experiencing the performance problem.
    Export the data from the Firebug Net panel
    When you report a performance problem please attach the 6 exports from the Firebug Net panel and an explanation of how you are experiencing the issues (for instance how much slower it is then normal) and include a description of your internet connection (dial-up, dsl, cable etc.) and the country from where you are connecting. If you have non-standard tweaks to your Firefox configuration (such as pipelining enabled) or are running any plugins please include that information in your report as well.
    Google Chrome
    Open the Developer Tools (Ctrl-Shift-J)
    Navigate to the resources tab
    Enable resource tracking.
    Click on this link
    Export the resource loading data.
    Reset the data by disabling and enabling resource tracking
    Click on this link
    Export the data
    Reset the data by disabling and enabling resource tracking
    Navigate to the page where you experience the performance problem
    Export the data
    Reset the data by disabling and enabling resource tracking
    Click on this link
    Export the data
    Reset the data by disabling and enabling resource tracking
    Click on this link
    Export the data
    Reset the data by disabling and enabling resource tracking
    Navigate to the page where you experience the performance problem
    Export the data
    Since Google Chrome does not have an export format for the Resource Tracking information best current practice is to take a screenshot and note the hover details for any resource with a tail that is longer then 25% of the total load time. When you report a performance problem please attach the screenshots and an explanation of how you are experiencing the issues (for instance how much slower it is then normal)  and include a description of your internet connection (dial-up, dsl, cable etc.) and the country from where you are connecting.
    Apple Safari
    The Apple Safari Web Inspector has a Resources panel similar to the Resources panel in the Google Chrome developer tools.To get there, follow these steps:
    Show the menu bar.
    Go to preferences
    Go to the Advanced Tab
    Check “Show  Develop menu in menu bar”.
    From the Develop menu select “Show Web  Inspector”. 
    Collecting the performance information and exporting works exactly the same as in Google Chrome. Please refer to the instructions for Google Chrome.
    Microsoft Internet Explorer
    IE does not have native features to analyze web traffic. No plugins have been found that produce the required information (please let us know if we missed any). For now, please reproduce the issue with Firefox, Chrome or Safari.
    Please note that due to the reliance on Javascript for the interactive effects the performance of these forums will be much better on MS IE 8 then on previous versions of MS IE.

    Hi
    It works, check once again...
    regards
    Swami

  • Performance issue with Jdeveloper

    Hi Guys,
    I am experiencing strange performance issue with Jdeveloper 10.1.3.3.0.4157. There are many other threads regarding the performance issue in this forum, but the problem I have is a little bit different.
    I have two computers: one is Athlon 3200+ with Vista and another one is P4 dual core 6400 with XP (service pack 2). Both of them have 2GB memory.
    I am running the same simple project on both computer, but only the one with Vista has the problem. The problem is very similar to the problem mentioned in the thread:
    Re: IDE has become extremely slow?
    But it's much worse. It only happens only on JSF pages. Basically, any operations on the JSF pages are very slow. Loading the page, changing the attributes of a button in source editor, or even clicking the items in the design view take forever to run.
    The first weird thing is that it may use 100% CPU, but it never recover, which means the 100% CPU usage never stops or when it stops, the Jdeveloper stops responding.
    The second weird thing is that the project is not big. Actually, it's very small. The problem started to happen since last week. There are not big changes during the period. The only thing I can say is that we created two more JSF pages.
    The third weird thing is that the same project never happened on the P4+XP box. When I open the project on the P4+XP box, it’s always fast and no CPU spike.
    Any advises are welcome!
    Thanks,
    Steven

    Hi Guys,
    I re-made a simple test project for this problem and now I now always reproduce the problem in JDeveloper on both system (XP & Vista). Everytime I open this jspx file in the source editor and try to scroll up/down the source file, or manually delete an attribute, JDeveloepr will hang and the CPU usage is 0%.
    Here is the content of the test file:
    <?xml version='1.0' encoding='windows-1252'?>
    <jsp:root xmlns:jsp="http://java.sun.com/JSP/Page" version="2.0"
    xmlns:h="http://java.sun.com/jsf/html"
    xmlns:f="http://java.sun.com/jsf/core"
    xmlns:af="http://xmlns.oracle.com/adf/faces"
    xmlns:afh="http://xmlns.oracle.com/adf/faces/html">
    <jsp:output omit-xml-declaration="true" doctype-root-element="HTML"
    doctype-system="http://www.w3.org/TR/html4/loose.dtd"
    doctype-public="-//W3C//DTD HTML 4.01 Transitional//EN"/>
    <jsp:directive.page contentType="text/html;charset=windows-1252"/>
    <f:view>
    <afh:html binding="#{backing_streettypedetail.html1}" id="html1">
    <afh:head title="streettypedetail"
    binding="#{backing_streettypedetail.head1}" id="head1">
    <meta http-equiv="Content-Type"
    content="text/html; charset=windows-1252"/>
    </afh:head>
    <afh:body binding="#{backing_streettypedetail.body1}" id="body1">
    <af:messages binding="#{backing_streettypedetail.messages1}"
    id="messages1"/>
    <h:form binding="#{backing_streettypedetail.form1}" id="form1">
    <af:panelForm binding="#{backing_streettypedetail.panelForm1}"
    id="panelForm1">
    <af:inputText value="#{bindings.streetTypeID.inputValue}"
    label="#{bindings.streetTypeID.label}"
    required="#{bindings.streetTypeID.mandatory}"
    columns="#{bindings.streetTypeID.displayWidth}"
    binding="#{backing_streettypedetail.inputText1}"
    id="inputText1">
    <af:validator binding="#{bindings.streetTypeID.validator}"/>
    </af:inputText>
    <af:inputText value="#{bindings.description.inputValue}"
    label="#{bindings.description.label}"
    required="#{bindings.description.mandatory}"
    columns="#{bindings.description.displayWidth}"
    binding="#{backing_streettypedetail.inputText2}"
    id="inputText2">
    <af:validator binding="#{bindings.description.validator}"/>
    </af:inputText>
    <af:inputText value="#{bindings.abbr.inputValue}"
    label="#{bindings.abbr.label}"
    required="#{bindings.abbr.mandatory}"
    columns="#{bindings.abbr.displayWidth}"
    binding="#{backing_streettypedetail.inputText3}"
    id="inputText3">
    <af:validator binding="#{bindings.abbr.validator}"/>
    </af:inputText>
    <f:facet name="footer">
    <h:panelGroup binding="#{backing_streettypedetail.panelGroup1}"
    id="panelGroup1">
    <af:commandButton text="Save"
    binding="#{backing_streettypedetail.saveButton}"
    id="saveButton"
    actionListener="#{bindings.mergeEntity.execute}"
    action="#{userState.retrieveReturnNavigationRule}"
    disabled="#{!bindings.mergeEntity.enabled}"
    partialSubmit="false">
    <af:setActionListener from="#{true}"
    to="#{userState.refresh}"/>
    </af:commandButton>
    <af:commandButton text="Cancel"
    binding="#{backing_streettypedetail.cancelButton}"
    action="#{userState.retrieveReturnNavigationRule}"
    id="cancelButton">
    <af:setActionListener from="#{false}"
    to="#{userState.refresh}"/>
    </af:commandButton>
    </h:panelGroup>
    </f:facet>
    </af:panelForm>
    </h:form>
    </afh:body>
    </afh:html>
    </f:view>
    <!--oracle-jdev-comment:auto-binding-backing-bean-name:backing_streettypedetail-->
    </jsp:root>
    Can anybody take a look at the file and let me know what's wrong with it?
    Thanks in advance.
    Steven

  • Synchronizing many reader threads with one writer thread?

    Hi
    I was wondering if there is a way in java to allow different threads to read an object simultaneously however to block them all only when the object is being updated. Here is an example:
    I have the following object which is shared between many Servlet instances:
    public class ActiveFlights
         private final HashMap<String,Flight> flights;
         private final Object lock;
         public ActiveFlights()
              flights = new HashMap<String, Flight>();
              lock = new Object();
         public void updateFlights(ArrayList<FlightData> newFlights)
              synchronized (lock)
                   //some code which updates the HashMap
         public ArrayList<Flight> getSomeFlights()
              ArrayList<Flight> wantedFlights = new ArrayList<Flight>();
              synchronized (lock)
                   //some code which selects flights from the HashMap
              return wantedFlights;
    }Now all the Servlet doGet() functions call the getSomeFlights() method. There is also a Timer object which calls the updateFlights() method once every few minutes.
    I need the synchronized blocks in order that the Timer doesn't try to update my object while it is being read by a Servlet however this is not optimal since it also causes each Servlet doGet() to block the others even though it would be possible for to doGet()'s to read the object simultaneously.
    Is there a better way of doing this?
    Thanks
    Aharon

    It is highly unlikely this is a real performance issue for you. Unless you know this is a bottle neck, you don't need to change your code.
    However, as an exercise, you can just use ConcurentHashMap for lockless Map access. However, there is still a risk of getting a read in the middle of a write.
    Instead you can take a snapshot copy of the Map and use this snapshot for reads. See below.
    In term of coding style;
    - I suggest you use the Map and List interfaces where ever possible.
    - You don't need to create a seperate lock object, the Map will do the same job.
    - Use can create the HashMap on the same line as it is declared removing the need to define a constructor.
    public class ActiveFlights {
         private final Map<String, Flight> flights = new HashMap<String, Flight>();
         private volatile Map<String, Flight> flightCopy = new HashMap<String, Flight>();
         public void updateFlights(List<FlightData> newFlights) {
              //some code which updates the HashMap
              // this takes a snapshot copy of the flights.  Use the copy for reads.
              flightCopy = new HashMap<String, Flight>(flights);
         public List<Flight> getSomeFlights() {
              // take a copy of the reference, neither the reference, nor the map it refers to will change over the life of this method call.
              final Map<String, Flight> flightCopy = this.flightCopy;
              final List<Flight> wantedFlights = new ArrayList<Flight>();
              //some code which selects flightCopy from the HashMap
              return wantedFlights;
    }

  • ORA-27070: async read/write failed

    Hi,
    We have a 2 node RAC on AIX 5.3 TL10 with CRS & ASM on 11.1.0.7
    The DB is running on 10.2.0.4
    The servers use VIO-server connection to SAN & LAN
    This morning the flashbackrecovery diskgroup got unmounted because of a
    ORA-27070: async read/write failed
    WARNING: IO Failed. subsys:System dg:2, diskname:/dev/asmreco3 disk:0x2.0x93e51c34 au:895
    iop:0x110b7bbc0 bufp:0x700000006190000 offset(bytes):938913792 iosz:4096 operation:2(Write) synchronous:0
    result: 4 osderr:0x0 osderr1:0x0 pid:11739286
    NOTE: cache initiating offline of disk 2 group 2
    WARNING: initiating offline of disk 2.2481265716 (FB01_0002) with mask 0x7e
    NOTE: initiating PST update: grp = 2, dsk = 2, mode = 0x15
    kfdp_updateDsk(): 7
    Thu Dec 31 08:58:13 2009
    kfdp_updateDskBg(): 7
    ERROR: too many offline disks in PST (grp 2)
    NOTE: halting all I/Os to diskgroup FB01
    Thu Dec 31 08:58:13 2009
    SQL> alter diskgroup FB01 dismount force
    NOTE: active pin found: 0x70000000ddfe530
    NOTE: active pin found: 0x70000000ddfe110
    NOTE: active pin found: 0x70000000ddfe428
    NOTE: active pin found: 0x70000000ddfe320
    NOTE: active pin found: 0x70000000ddfe740
    NOTE: active pin found: 0x70000000ddfe218
    NOTE: active pin found: 0x70000000ddfe638
    NOTE: active pin found: 0x70000000ddfe530
    NOTE: active pin found: 0x70000000ddfe110
    NOTE: active pin found: 0x70000000ddfe428
    NOTE: active pin found: 0x70000000ddfe320
    NOTE: active pin found: 0x70000000ddfe740
    NOTE: active pin found: 0x70000000ddfe218
    NOTE: active pin found: 0x70000000ddfe638
    NOTE: cache dismounting group 2/0xCD55ECD5 (FB01)
    Thu Dec 31 08:58:14 2009
    kjbdomdet send to node 1
    detach from dom 2, sending detach message to node 1
    Thu Dec 31 08:58:14 2009
    Dirty detach reconfiguration started (old inc 24, new inc 24)
    List of nodes:
    0 1
    Global Resource Directory partially frozen for dirty detach
    * dirty detach - domain 2 invalid = TRUE
    2617 GCS resources traversed, 1 cancelled
    Dirty Detach Reconfiguration complete
    Thu Dec 31 08:58:15 2009
    WARNING: dirty detached from domain 2
    NOTE: cache dismounted group 2/0xCD55ECD5 (FB01)
    kfdp_dismount(): 8
    kfdp_dismountBg(): 8
    NOTE: De-assigning number (2,0) from disk (/dev/asmreco1)
    NOTE: De-assigning number (2,1) from disk (/dev/asmreco2)
    NOTE: De-assigning number (2,2) from disk (/dev/asmreco3)
    SUCCESS: diskgroup FB01 was dismounted
    There are however no errors on the OS level
    Any hints are welcome

    All has been checked, and rechecked.
    We now have a very strange situation:
    We testen failover by manually turning of one LPAR at a time.
    After this reboot, the Async I/O error seem to have gone.
    That is, they haven't appeared now for two days
    Why they occurred and why they don't occur anymore is not found/explained
    There I'll close this thread.

  • Async read/write

    Hi all,
    I am developing a device driver for a custom PCI card on 64 bit Sparc
    Solaris 8 which is going to replace another card. We already have
    applications running, so I'm supposed to give the same interface as the
    original one.
    The application with the original driver/card makes asynchronous
    reads/writes as follows:
    - open(device, O_RDWR | O_NONBLOCK)
    - call write
    - for (;;) {
    call ioctl to get device status
    break on completion or error.
    - call write second time (same buffer, same size)
    So, in the driver, I should implement async writes in the 'write'
    entry, not 'awrite'.
    I was thinking of creating an aio_req structure and calling aphysio
    inside 'write', but this is not documented. Another problem in this
    approach is the second call to 'write' in the application.
    So my questions are:
    1) How should I implement this? Create a thread and provide async
    functionality inside this thread? But this doesn't make much sense to
    me because there's already an async functionality provided by Solaris.
    2) What could the purpose of the second 'write' call be in the user app.
    Thanks in advance

    All has been checked, and rechecked.
    We now have a very strange situation:
    We testen failover by manually turning of one LPAR at a time.
    After this reboot, the Async I/O error seem to have gone.
    That is, they haven't appeared now for two days
    Why they occurred and why they don't occur anymore is not found/explained
    There I'll close this thread.

  • MAX and Async Read/Write

    Didn't MAX use to have an option to perform async read and write in the "Communicate with Instrument" window? I'm presently using Measurement & Automation Explorer 5.4.0f0. Please explain how I can use MAX to start and terminate async read and write calls.

    VISAIC did use to support Async. See figures 7 and 8 on this link. It appears this was silently removed in later versions. When doing a Read or Write with Async checked, I believe it then showed a terminate button while it was executing. The benefit was this let you cancel the operation rather than waiting for a timeout error. Plus it was a quick sanity check of the instruments ability to perform and terminate async I/O.
    NI does have a good async read/write Measurement Studio VB.NET sample project called SimpleAsynchronousReadWrite.

  • To have great read/write performance, do you have to save all programs onto the SSD or can you save programs onto the HDD?

    if I want to use the fast read/write speeds of my SSD, do I have to save the programs (Final Cut Pro X, Adobe After Effects, Microsoft Powerpoint, Steam, Counter-Strike, etc)  onto the SSD? Or can I save all programs onto a 2nd drive which would be a HDD  and still have fast speeds WITHOUT storing those programs onto the SSD? My 2012 mid Macbook Pro has a SSD as its main bootup drive and will be getting a 2tb HDD to replace the optical drive.
    Any advice or comments is greatly appreciated,
    Thank you!

    Sorry for my late reply.
    Techinspace I'm with the latest Yosemite 10.10.2 and everything always up to date.
    babowa My login Items are two: ColorNavigator 6 and cDock Agent. One is for the color calibration the other is Dock customization app.
    Have AdwareMedic but it is not auto starting program. Also have Kaspersky Internet Security because my system is dual boot and need to keep the Windows drive clean. Nothing else.
    Verifyed and checked the disks permissions and found one problem there:
    Warning: SUID file "System/Library/CoreServices/RemoteManegement/ARDAgent.app/Content/MacOS/ARDAge nt" has been modified and will not be repaired.
    Apple advise for this message to be ignored: Mac OS X: Disk Utility's Repair Disk Permissions messages that you can safely ignore - Apple Support
    EtreCheck version: 2.1.8 (121)
    Hardware Information: ℹ️
        MacBook Pro (Retina, 15-inch, Mid 2014) (Technical Specifications)
        MacBook Pro - model: MacBookPro11,3
        1 2.8 GHz Intel Core i7 CPU: 4-core
        16 GB RAM Not upgradeable
            BANK 0/DIMM0
                8 GB DDR3 1600 MHz ok
            BANK 1/DIMM0
                8 GB DDR3 1600 MHz ok
        Bluetooth: Good - Handoff/Airdrop2 supported
        Wireless:  en0: 802.11 a/b/g/n/ac
        Battery Health: Normal - Cycle count 138
    Video Information: ℹ️
        Intel Iris Pro
        NVIDIA GeForce GT 750M - VRAM: 2048 MB
            Color LCD spdisplays_2880x1800Retina
            CX240 1920 x 1200
    System Software: ℹ️
        OS X 10.10.2 (14C1514) - Time since boot: 0:34:49
    Disk Information: ℹ️
        APPLE SSD SM1024F disk0 : (1 TB)
            EFI (disk0s1) <not mounted> : 210 MB
            Macintosh HD (disk0s2) / : 698.70 GB (224.98 GB free)
            Recovery HD (disk0s3) <not mounted>  [Recovery]: 650 MB
            BOOTCAMP (disk0s4) /Volumes/BOOTCAMP : 301.00 GB (122.94 GB free)
    USB Information: ℹ️
        Apple Internal Memory Card Reader
        VIA Labs, Inc. USB3.0 Hub
            VIA Labs, Inc. USB3.0 Hub
                Western Digital Elements 1048 2 TB
            HFS (disk1s1) /Volumes/HFS : 1.32 TB (488.20 GB free)
            XFat (disk1s2) /Volumes/XFat : 679.86 GB (178.77 GB free)
            VIA Labs, Inc. USB3.0 Hub
        Apple Inc. BRCM20702 Hub
            Apple Inc. Bluetooth USB Host Controller
        Apple Inc. Apple Internal Keyboard / Trackpad
        VIA Labs, Inc. USB2.0 Hub
            Logitech USB Keyboard
            VIA Labs, Inc. USB2.0 Hub
                EIZO EIZO USB HID Monitor
            VIA Labs, Inc. USB2.0 Hub
                Datacolor Datacolor Spyder4
                ©Microsoft Corporation Controller
                Tablet PTK-440
    Thunderbolt Information: ℹ️
        Apple Inc. thunderbolt_bus
    Configuration files: ℹ️
        /etc/hosts - Count: 22
    Gatekeeper: ℹ️
        Mac App Store and identified developers
    Kernel Extensions: ℹ️
            /Applications/VMware Fusion.app
        [not loaded]    com.vmware.kext.vmci (90.5.7) [Click for support]
        [not loaded]    com.vmware.kext.vmioplug.12.1.17 (12.1.17) [Click for support]
        [not loaded]    com.vmware.kext.vmnet (0188.79.83) [Click for support]
        [not loaded]    com.vmware.kext.vmx86 (0188.79.83) [Click for support]
        [not loaded]    com.vmware.kext.vsockets (90.5.7) [Click for support]
            /Library/Application Support/Kaspersky Lab/KAV/Bases/Cache
        [loaded]    com.kaspersky.kext.kimul.44 (44) [Click for support]
        [loaded]    com.kaspersky.kext.mark.1.0.5 (1.0.5) [Click for support]
            /Library/Extensions
        [not loaded]    com.Logitech.Control Center.HID Driver (3.9.1 - SDK 10.8) [Click for support]
        [loaded]    com.kaspersky.kext.klif (3.0.5a45) [Click for support]
        [loaded]    com.kaspersky.nke (2.0.0a12) [Click for support]
            /System/Library/Extensions
        [not loaded]    com.Logitech.Unifying.HID Driver (1.3.0 - SDK 10.6) [Click for support]
        [not loaded]    com.basICColor.driver.basICColorDISCUS (1.0.0 - SDK 10.4) [Click for support]
        [loaded]    com.mice.driver.Xbox360Controller (1.0.0d13 - SDK 10.8) [Click for support]
        [loaded]    com.nvidia.CUDA (1.1.0) [Click for support]
        [not loaded]    com.wacom.kext.wacomtablet (6.3.8 - SDK 10.9) [Click for support]
            /System/Library/Extensions/360Controller.kext/Contents/PlugIns
        [not loaded]    com.mice.driver.Wireless360Controller (1.0.0d13 - SDK 10.8) [Click for support]
        [not loaded]    com.mice.driver.WirelessGamingReceiver (1.0.0d13 - SDK 10.8) [Click for support]
    Startup Items: ℹ️
        TuxeraNTFSUnmountHelper: Path: /Library/StartupItems/TuxeraNTFSUnmountHelper
        Startup items are obsolete in OS X Yosemite
    Launch Agents: ℹ️
        [not loaded]    com.adobe.AAM.Updater-1.0.plist [Click for support]
        [loaded]    com.adobe.AD4ServiceManager.plist [Click for support]
        [running]    com.kaspersky.kav.gui.plist [Click for support]
        [loaded]    com.nvidia.CUDASoftwareUpdate.plist [Click for support]
        [running]    com.wacom.wacomtablet.plist [Click for support]
    Launch Daemons: ℹ️
        [loaded]    com.adobe.fpsaud.plist [Click for support]
        [running]    com.bombich.ccchelper.plist [Click for support]
        [running]    com.kaspersky.kav.plist [Click for support]
        [running]    com.mice.360Daemon.plist [Click for support]
        [loaded]    com.nvidia.cuda.launcher.plist [Click for support]
    User Launch Agents: ℹ️
        [loaded]    com.adobe.AAM.Updater-1.0.plist [Click for support]
        [loaded]    com.google.keystone.agent.plist [Click for support]
    User Login Items: ℹ️
        ColorNavigator 6    Application  (/Applications/ColorNavigator 6.app)
        cDock Agent    Application  (/Applications/cDock.app/Contents/Resources/helpers/cDock Agent.app)
    Internet Plug-ins: ℹ️
        AdobeAAMDetect: Version: AdobeAAMDetect 1.0.0.0 - SDK 10.6 [Click for support]
        FlashPlayer-10.6: Version: 16.0.0.305 - SDK 10.6 [Click for support]
        QuickTime Plugin: Version: 7.7.3
        Flash Player: Version: 16.0.0.305 - SDK 10.6 Outdated! Update
        Default Browser: Version: 600 - SDK 10.10
        Silverlight: Version: 5.1.30514.0 - SDK 10.6 [Click for support]
        WacomTabletPlugin: Version: WacomTabletPlugin 2.1.0.6 - SDK 10.9 [Click for support]
        JavaAppletPlugin: Version: 15.0.0 - SDK 10.10 Check version
    Safari Extensions: ℹ️
        Virtual Keyboard
        URL Advisor
    3rd Party Preference Panes: ℹ️
        CUDA Preferences  [Click for support]
        Flash Player  [Click for support]
        Tuxera NTFS  [Click for support]
        WacomTablet  [Click for support]
        XBox 360 Controllers  [Click for support]
    Time Machine: ℹ️
        Skip System Files: NO
        Mobile backups: ON
        Auto backup: YES
        Volumes being backed up:
            Macintosh HD: Disk size: 698.70 GB Disk used: 473.72 GB
        Destinations:
            Os X [Local]
            Total size: 1.32 TB
            Total number of backups: 39
            Oldest backup: 2015-01-27 20:51:11 +0000
            Last backup: 2015-03-31 01:29:52 +0000
            Size of backup disk: Too small
                Backup size 1.32 TB < (Disk used 473.72 GB X 3)
    Top Processes by CPU: ℹ️
             4%    backupd
             4%    firefox
             4%    WindowServer
             2%    VLC
             1%    coreaudiod
    Top Processes by Memory: ℹ️
        464 MB    firefox
        344 MB    kav
        223 MB    Dock
        172 MB    mds_stores
        155 MB    WindowServer
    Virtual Memory Information: ℹ️
        10.93 GB    Free RAM
        3.24 GB    Active RAM
        1.20 GB    Inactive RAM
        1.79 GB    Wired RAM
        3.46 GB    Page-ins
        0 B    Page-outs
    Diagnostics Information: ℹ️
        Mar 31, 2015, 11:33:40 PM    Self test - passed

  • Performance issue showing read by other session Event

    Hi All,
    we are having a severe performance issue in my database when we are running batch jobs.
    This was a new database(11.2.0.2) and we are testing the performance by running some batch jobs. These batch jobs included some inserts and updates.
    I am seeing read by other session in top 5 timed events and cache buffers chains in Latch Miss Sources section.
    Please help me to solve this out.
    Inst Num Startup Time    Release     RAC
    1 27-Feb-12 09:03 11.2.0.2.0  NO
    Platform                         CPUs Cores Sockets Memory(GB)
    Linux x86 64-bit                    8     8       8      48.00           
    Snap Id      Snap Time      Sessions Curs/Sess
    Begin Snap:      5605 29-Feb-12 03:00:27        63       4.5
      End Snap:      5614 29-Feb-12 12:00:47        63       4.3
       Elapsed:              540.32 (mins)
       DB Time:            1,774.23 (mins)
    Cache Sizes                       Begin        End
    ~~~~~~~~~~~                  ---------- ----------
                   Buffer Cache:     1,952M     1,952M  Std Block Size:        16K
               Shared Pool Size:     1,024M     1,024M      Log Buffer:    18,868K
    Load Profile              Per Second    Per Transaction   Per Exec   Per Call
    ~~~~~~~~~~~~         ---------------    --------------- ---------- ----------
          DB Time(s):                3.3                0.8       0.02       0.05
           DB CPU(s):                1.1                0.3       0.01       0.02
           Redo size:           55,763.8           13,849.3
       Logical reads:           23,906.6            5,937.4
       Block changes:              325.7               80.9
      Physical reads:              665.6              165.3
    Physical writes:               40.4               10.0
          User calls:               60.7               15.1
              Parses:               10.6                2.6
         Hard parses:                1.1                0.3
    W/A MB processed:                0.6                0.2
              Logons:                0.1                0.0
            Executes:              151.2               37.6
           Rollbacks:                0.0                0.0
        Transactions:                4.0
    Instance Efficiency Percentages (Target 100%)
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
                Buffer Nowait %:   99.94       Redo NoWait %:  100.00
                Buffer  Hit   %:   97.90    In-memory Sort %:  100.00
                Library Hit   %:   98.06        Soft Parse %:   90.16
             Execute to Parse %:   92.96         Latch Hit %:  100.00
    Parse CPU to Parse Elapsd %:   76.71     % Non-Parse CPU:   98.57
    Shared Pool Statistics        Begin    End
                 Memory Usage %:   89.38   87.96
        % SQL with executions>1:   97.14   95.15
      % Memory for SQL w/exec>1:   96.05   92.46
    Top 5 Timed Foreground Events
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
                                                               Avg
                                                              wait   % DB
    Event                                 Waits     Time(s)   (ms)   time Wait Class
    db file sequential read          14,092,706      65,613      5   61.6 User I/O
    DB CPU                                           34,819          32.7
    read by other session               308,534       1,260      4    1.2 User I/O
    direct path read                     97,454         987     10     .9 User I/O
    db file scattered read               71,870         910     13     .9 User I/O
    Host CPU (CPUs:    8 Cores:    8 Sockets:    8)
    ~~~~~~~~         Load Average
                   Begin       End     %User   %System      %WIO     %Idle
                    0.43      0.36      13.7       0.6       9.7      85.7
    Instance CPU
    ~~~~~~~~~~~~
                  % of total CPU for Instance:      13.5
                  % of busy  CPU for Instance:      94.2
      %DB time waiting for CPU - Resource Mgr:       0.0
    Memory Statistics
    ~~~~~~~~~~~~~~~~~                       Begin          End
                      Host Mem (MB):     49,152.0     49,152.0
                       SGA use (MB):      3,072.0      3,072.0
                       PGA use (MB):        506.5        629.1
        % Host Mem used for SGA+PGA:         7.28         7.53
    Time Model Statistics             
    -> Total time in database user-calls (DB Time): 106453.8s
    -> Statistics including the word "background" measure background process
       time, and so do not contribute to the DB time statistic
    -> Ordered by % or DB time desc, Statistic name
    Statistic Name                                       Time (s) % of DB Time
    sql execute elapsed time                            105,531.1         99.1
    DB CPU                                               34,818.8         32.7
    parse time elapsed                                      714.7           .7
    hard parse elapsed time                                 684.8           .6
    PL/SQL execution elapsed time                           161.9           .2
    PL/SQL compilation elapsed time                          44.2           .0
    connection management call elapsed time                  16.9           .0
    hard parse (sharing criteria) elapsed time               10.2           .0
    hard parse (bind mismatch) elapsed time                   9.4           .0
    sequence load elapsed time                                2.9           .0
    repeated bind elapsed time                                0.5           .0
    failed parse elapsed time                                 0.0           .0
    DB time                                             106,453.8
    background elapsed time                               1,753.9
    background cpu time                                      61.7
    Operating System Statistics        
    -> *TIME statistic values are diffed.
       All others display actual values.  End Value is displayed if different
    -> ordered by statistic type (CPU Use, Virtual Memory, Hardware Config), Name
    Statistic                                  Value        End Value
    BUSY_TIME                              3,704,415
    IDLE_TIME                             22,203,740
    IOWAIT_TIME                            2,517,864
    NICE_TIME                                      3
    SYS_TIME                                 145,696
    USER_TIME                              3,557,758
    LOAD                                           0                0
    RSRC_MGR_CPU_WAIT_TIME                         0
    VM_IN_BYTES                      358,813,045,760
    VM_OUT_BYTES                      29,514,830,848
    PHYSICAL_MEMORY_BYTES             51,539,607,552
    NUM_CPUS                                       8
    NUM_CPU_CORES                                  8
    NUM_CPU_SOCKETS                                8
    GLOBAL_RECEIVE_SIZE_MAX                4,194,304
    GLOBAL_SEND_SIZE_MAX                   1,048,586
    TCP_RECEIVE_SIZE_DEFAULT                  87,380
    TCP_RECEIVE_SIZE_MAX                   4,194,304
    TCP_RECEIVE_SIZE_MIN                       4,096
    TCP_SEND_SIZE_DEFAULT                     16,384
    TCP_SEND_SIZE_MAX                      4,194,304
    TCP_SEND_SIZE_MIN                          4,096
    Operating System Statistics -
    Snap Time           Load    %busy    %user     %sys    %idle  %iowait
    29-Feb 03:00:27      0.4      N/A      N/A      N/A      N/A      N/A
    29-Feb 04:00:35      1.4     11.9     11.2      0.6     88.1     14.3
    29-Feb 05:00:41      1.7     13.8     13.2      0.6     86.2     15.8
    29-Feb 06:00:48      1.5     14.0     13.5      0.6     86.0     12.3
    29-Feb 07:01:00      1.8     16.3     15.8      0.5     83.7     10.4
    29-Feb 08:00:12      2.6     23.2     22.5      0.6     76.8     12.6
    29-Feb 09:00:26      1.3     16.6     16.0      0.5     83.4      5.7
    29-Feb 10:00:33      1.2     13.8     13.3      0.5     86.2      2.0
    29-Feb 11:00:43      1.3     14.5     14.0      0.5     85.5      3.8
    29-Feb 12:00:47      0.4      4.9      4.2      0.7     95.1     10.6
    Foreground Wait Class              
    -> s  - second, ms - millisecond -    1000th of a second
    -> ordered by wait time desc, waits desc
    -> %Timeouts: value of 0 indicates value was < .5%.  Value of null is truly 0
    -> Captured Time accounts for         97.9%  of Total DB time     106,453.79 (s)
    -> Total FG Wait Time:            69,415.64 (s)  DB CPU time:      34,818.79 (s)
                                                                      Avg
                                          %Time       Total Wait     wait
    Wait Class                      Waits -outs         Time (s)     (ms)  %DB time
    User I/O                   14,693,843     0           69,222        5      65.0
    DB CPU                                                34,819               32.7
    Commit                         40,629     0              119        3       0.1
    System I/O                     26,504     0               57        2       0.1
    Network                     1,945,010     0               11        0       0.0
    Other                         125,200    99                4        0       0.0
    Application                     2,673     0                2        1       0.0
    Concurrency                     3,059     0                1        0       0.0
    Configuration                      31    19                0       15       0.0
    Foreground Wait Events            
    -> s  - second, ms - millisecond -    1000th of a second
    -> Only events with Total Wait Time (s) >= .001 are shown
    -> ordered by wait time desc, waits desc (idle events last)
    -> %Timeouts: value of 0 indicates value was < .5%.  Value of null is truly 0
                                                                 Avg
                                            %Time Total Wait    wait    Waits   % DB
    Event                             Waits -outs   Time (s)    (ms)     /txn   time
    db file sequential read      14,092,706     0     65,613       5    108.0   61.6
    read by other session           308,534     0      1,260       4      2.4    1.2
    direct path read                 97,454     0        987      10      0.7     .9
    db file scattered read           71,870     0        910      13      0.6     .9
    db file parallel read            35,001     0        372      11      0.3     .3
    log file sync                    40,629     0        119       3      0.3     .1
    control file sequential re       26,504     0         57       2      0.2     .1
    direct path read temp            14,499     0         49       3      0.1     .0
    direct path write temp            9,186     0         28       3      0.1     .0
    SQL*Net message to client     1,923,973     0          5       0     14.7     .0
    SQL*Net message from dblin        1,056     0          5       5      0.0     .0
    Disk file operations I/O          8,848     0          2       0      0.1     .0
    ASM file metadata operatio           36     0          2      54      0.0     .0
    SQL*Net break/reset to cli        2,636     0          1       1      0.0     .0
    ADR block file read                 472     0          1       1      0.0     .0
    os thread startup                     8     0          1      74      0.0     .0
    SQL*Net more data to clien       17,656     0          1       0      0.1     .0
    asynch descriptor resize        123,852   100          0       0      0.9     .0
    local write wait                    110     0          0       4      0.0     .0
    utl_file I/O                     55,635     0          0       0      0.4     .0
    log file switch (private s            8     0          0      52      0.0     .0
    cursor: pin S wait on X               2     0          0     142      0.0     .0
    enq: KO - fast object chec           13     0          0      20      0.0     .0
    PX Deq: Slave Session Stat          248     0          0       1      0.0     .0
    enq: RO - fast object reus           18     0          0      11      0.0     .0
    latch: cache buffers chain        2,511     0          0       0      0.0     .0
    latch: shared pool                  195     0          0       1      0.0     .0
    CSS initialization                   12     0          0       8      0.0     .0
    PX qref latch                        54   100          0       2      0.0     .0
    SQL*Net more data from cli          995     0          0       0      0.0     .0
    SQL*Net more data from dbl          300     0          0       0      0.0     .0
    kksfbc child completion               1   100          0      56      0.0     .0
    library cache: mutex X              244     0          0       0      0.0     .0
    PX Deq: Signal ACK RSG              124     0          0       0      0.0     .0
    undo segment extension                6   100          0       7      0.0     .0
    PX Deq: Signal ACK EXT              124     0          0       0      0.0     .0
    library cache load lock               3     0          0       9      0.0     .0
    ADR block file write                 45     0          0       1      0.0     .0
    CSS operation: action                12     0          0       2      0.0     .0
    reliable message                     28     0          0       1      0.0     .0
    CSS operation: query                 72     0          0       0      0.0     .0
    latch: row cache objects             14     0          0       1      0.0     .0
    enq: SQ - contention                 17     0          0       0      0.0     .0
    latch free                           32     0          0       0      0.0     .0
    buffer busy waits                    52     0          0       0      0.0     .0
    enq: PS - contention                 16     0          0       0      0.0     .0
    enq: TX - row lock content            6     0          0       1      0.0     .0
    SQL*Net message to dblink         1,018     0          0       0      0.0     .0
    cursor: pin S                        23     0          0       0      0.0     .0
    latch: cache buffers lru c            8     0          0       0      0.0     .0
    SQL*Net message from clien    1,923,970     0    944,508     491     14.7
    jobq slave wait                  66,732   100     33,334     500      0.5
    Streams AQ: waiting for me        6,481   100     32,412    5001      0.0
    wait for unread message on       32,858    98     32,411     986      0.3
    PX Deq: Execution Msg             1,448     0        190     131      0.0
    PX Deq: Execute Reply             1,196     0         74      62      0.0
    HS message to agent                 228     0          4      19      0.0
    single-task message                  42     0          4      97      0.0
    PX Deq Credit: send blkd            904     0          2       3      0.0
    PX Deq Credit: need buffer          205     0          1       3      0.0
    Foreground Wait Events            
    -> s  - second, ms - millisecond -    1000th of a second
    -> Only events with Total Wait Time (s) >= .001 are shown
    -> ordered by wait time desc, waits desc (idle events last)
    -> %Timeouts: value of 0 indicates value was < .5%.  Value of null is truly 0
                                                                 Avg
                                            %Time Total Wait    wait    Waits   % DB
    Event                             Waits -outs   Time (s)    (ms)     /txn   time
    PX Deq: Table Q Normal            4,291     0          1       0      0.0
    PX Deq: Join ACK                    124     0          0       1      0.0
    PX Deq: Parse Reply                 124     0          0       0      0.0
    KSV master wait                     256     0          0       0      0.0
    Latch Miss Sources                
    -> only latches with sleeps are shown
    -> ordered by name, sleeps desc
                                                         NoWait              Waiter
    Latch Name               Where                       Misses     Sleeps   Sleeps
    ASM map operation freeli kffmTranslate2                   0          2        0
    DML lock allocation      ktadmc                           0          2        0
    FOB s.o list latch       ksfd_allfob                      0          2        2
    In memory undo latch     ktiFlushMe                       0          5        0
    In memory undo latch     ktichg: child                    0          3        0
    PC and Classifier lists  No latch                         0          6        0
    Real-time plan statistic keswxAddNewPlanEntry             0         20       20
    SQL memory manager worka qesmmIRegisterWorkArea:1         0          1        1
    active service list      kswslogon: session logout        0         23       12
    active service list      kswssetsvc: PX session swi       0          6        1
    active service list      kswsite: service iterator        0          1        0
    archive process latch    kcrrgpll                         0          3        3
    cache buffers chains     kcbgtcr_2                        0      1,746      573
    cache buffers chains     kcbgtcr: fast path (cr pin       0      1,024    2,126
    cache buffers chains     kcbgcur_2                        0         60        8
    cache buffers chains     kcbchg1: kslbegin: bufs no       0         16        3
    cache buffers chains     kcbgtcr: fast path               0         14       20
    cache buffers chains     kcbzibmlt: multi-block rea       0         10        0
    cache buffers chains     kcbrls_2                         0          9       53
    cache buffers chains     kcbgtcr: kslbegin shared         0          8        1
    cache buffers chains     kcbrls_1                         0          7       84
    cache buffers chains     kcbgtcr: kslbegin excl           0          6       14
    cache buffers chains     kcbnew: new latch again          0          6        0
    cache buffers chains     kcbzgb: scan from tail. no       0          6        0
    cache buffers chains     kcbzwb                           0          5        8
    cache buffers chains     kcbgcur: fast path (shr)         0          3        0
    cache buffers chains     kcbget: pin buffer               0          3        0
    cache buffers chains     kcbzhngcbk2_1                    0          1        0
    cache buffers lru chain  kcbzgws                          0         19        0
    cache buffers lru chain  kcbo_link_q                      0          3        0
    call allocation          ksuxds                           0         14       10
    call allocation          ksudlp: top call                 0          2        3
    enqueue hash chains      ksqgtl3                          0          2        1
    enqueue hash chains      ksqrcl                           0          1        2
    enqueues                 ksqgel: create enqueue           0          1        0
    object queue header oper kcbo_unlink_q                    0          5        2
    object queue header oper kcbo_sw_buf                      0          2        0
    object queue header oper kcbo_link_q                      0          1        2
    object queue header oper kcbo_switch_cq                   0          1        2
    object queue header oper kcbo_switch_mq_bg                0          1        4
    parallel query alloc buf kxfpbalo                         0          1        1
    process allocation       ksucrp:1                         0          2        0
    process queue reference  kxfpqrsnd                        0          1        0
    qmn task queue latch     kwqmnmvtsks: delay to read       0          1        0
    redo allocation          kcrfw_redo_gen: redo alloc       0         17        0
    row cache objects        kqreqd: reget                    0          6        0
    row cache objects        kqrpre: find obj                 0          6       13
    row cache objects        kqrso                            0          2        0
    row cache objects        kqreqd                           0          1        2
    row cache objects        kqrpre: init complete            0          1        1
    shared pool              kghalo                           0        199      106
    shared pool              kghupr1                          0         39      109
    shared pool              kghfre                           0         18       19
    shared pool              kghalp                           0          7       29
    space background task la ktsj_grab_task                   0         21       27
    Mutex Sleep Summary                
    -> ordered by number of sleeps desc
                                                                             Wait
    Mutex Type            Location                               Sleeps    Time (ms)
    Library Cache         kglhdgn2 106                              338           12
    Library Cache         kgllkc1   57                              259           10
    Library Cache         kgllkdl1  85                              123           21
    Cursor Pin            kkslce [KKSCHLPIN2]                        70          286
    Library Cache         kglget2   2                                31            1
    Library Cache         kglhdgn1  62                               31            2
    Library Cache         kglpin1   4                                26            1
    Library Cache         kglpnal1  90                               18            0
    Library Cache         kglpndl1  95                               15            2
    Library Cache         kgllldl2 112                                6            0
    Library Cache         kglini1   32                                1            0
              -------------------------------------------------------------Thanks in advance.

    Hi,
    Thanks for reply.
    I provided one hour report.
    Inst Num Startup Time    Release     RAC
    1 27-Feb-12 09:03 11.2.0.2.0  NO
      Platform                         CPUs Cores Sockets Memory(GB)
    Linux x86 64-bit                    8     8       8      48.00
                  Snap Id      Snap Time      Sessions Curs/Sess
    Begin Snap:      5606 29-Feb-12 04:00:35        63       3.7
      End Snap:      5607 29-Feb-12 05:00:41        63       3.6
       Elapsed:               60.11 (mins)
       DB Time:              382.67 (mins)
    Cache Sizes                       Begin        End
    ~~~~~~~~~~~                  ---------- ----------
                   Buffer Cache:     1,952M     1,952M  Std Block Size:        16K
               Shared Pool Size:     1,024M     1,024M      Log Buffer:    18,868K
    Load Profile              Per Second    Per Transaction   Per Exec   Per Call
    ~~~~~~~~~~~~         ---------------    --------------- ---------- ----------
          DB Time(s):                6.4                0.8       0.03       0.03
           DB CPU(s):                1.0                0.1       0.00       0.00
           Redo size:           84,539.3           10,425.6
       Logical reads:           23,345.6            2,879.1
       Block changes:              386.5               47.7
      Physical reads:            1,605.0              197.9
    Physical writes:                7.1                0.9
          User calls:              233.9               28.9
              Parses:                4.0                0.5
         Hard parses:                0.1                0.0
    W/A MB processed:                0.1                0.0
              Logons:                0.1                0.0
            Executes:              210.9               26.0
           Rollbacks:                0.0                0.0
        Transactions:                8.1
    Instance Efficiency Percentages (Target 100%)
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
                Buffer Nowait %:   99.62       Redo NoWait %:  100.00
                Buffer  Hit   %:   95.57    In-memory Sort %:  100.00
                Library Hit   %:   99.90        Soft Parse %:   98.68
             Execute to Parse %:   98.10         Latch Hit %:   99.99
    Parse CPU to Parse Elapsd %:   32.08     % Non-Parse CPU:   99.90
    Shared Pool Statistics        Begin    End
                 Memory Usage %:   89.25   89.45
        % SQL with executions>1:   96.79   97.52
      % Memory for SQL w/exec>1:   95.67   96.56
    Top 5 Timed Foreground Events
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
                                                               Avg
                                                              wait   % DB
    Event                                 Waits     Time(s)   (ms)   time Wait Class
    db file sequential read           3,054,464      17,002      6   74.0 User I/O
    DB CPU                                            3,748          16.3
    read by other session               199,603         796      4    3.5 User I/O
    direct path read                     46,301         439      9    1.9 User I/O
    db file scattered read               21,113         269     13    1.2 User I/O
    Host CPU (CPUs:    8 Cores:    8 Sockets:    8)
    ~~~~~~~~         Load Average
                   Begin       End     %User   %System      %WIO     %Idle
                    1.45      1.67      13.2       0.6      15.8      86.2
    Instance CPU
    ~~~~~~~~~~~~
                  % of total CPU for Instance:      13.0
                  % of busy  CPU for Instance:      94.7
      %DB time waiting for CPU - Resource Mgr:       0.0
    Memory Statistics
    ~~~~~~~~~~~~~~~~~                       Begin          End
                      Host Mem (MB):     49,152.0     49,152.0
                       SGA use (MB):      3,072.0      3,072.0
                       PGA use (MB):        513.5        467.7
        % Host Mem used for SGA+PGA:         7.29         7.20
    Time Model Statistics            
    -> Total time in database user-calls (DB Time): 22960.5s
    -> Statistics including the word "background" measure background process
       time, and so do not contribute to the DB time statistic
    -> Ordered by % or DB time desc, Statistic name
    Statistic Name                                       Time (s) % of DB Time
    sql execute elapsed time                             22,835.9         99.5
    DB CPU                                                3,748.4         16.3
    parse time elapsed                                       15.4           .1
    hard parse elapsed time                                  14.3           .1
    PL/SQL execution elapsed time                             7.5           .0
    PL/SQL compilation elapsed time                           6.0           .0
    connection management call elapsed time                   1.6           .0
    sequence load elapsed time                                0.4           .0
    hard parse (sharing criteria) elapsed time                0.0           .0
    repeated bind elapsed time                                0.0           .0
    failed parse elapsed time                                 0.0           .0
    DB time                                              22,960.5
    background elapsed time                                 238.1
    background cpu time                                       4.9
    Operating System Statistics        
    -> *TIME statistic values are diffed.
       All others display actual values.  End Value is displayed if different
    -> ordered by statistic type (CPU Use, Virtual Memory, Hardware Config), Name
    Statistic                                  Value        End Value
    BUSY_TIME                                396,506
    IDLE_TIME                              2,483,725
    IOWAIT_TIME                              455,495
    NICE_TIME                                      0
    SYS_TIME                                  16,163
    USER_TIME                                380,052
    LOAD                                           1                2
    RSRC_MGR_CPU_WAIT_TIME                         0
    VM_IN_BYTES                       95,646,943,232
    VM_OUT_BYTES                       1,686,059,008
    PHYSICAL_MEMORY_BYTES             51,539,607,552
    NUM_CPUS                                       8
    NUM_CPU_CORES                                  8
    NUM_CPU_SOCKETS                                8
    GLOBAL_RECEIVE_SIZE_MAX                4,194,304
    GLOBAL_SEND_SIZE_MAX                   1,048,586
    TCP_RECEIVE_SIZE_DEFAULT                  87,380
    TCP_RECEIVE_SIZE_MAX                   4,194,304
    TCP_RECEIVE_SIZE_MIN                       4,096
    TCP_SEND_SIZE_DEFAULT                     16,384
    TCP_SEND_SIZE_MAX                      4,194,304
    TCP_SEND_SIZE_MIN                          4,096
    Operating System Statistics -
    Snap Time           Load    %busy    %user     %sys    %idle  %iowait
    29-Feb 04:00:35      1.4      N/A      N/A      N/A      N/A      N/A
    29-Feb 05:00:41      1.7     13.8     13.2      0.6     86.2     15.8
    Foreground Wait Class              
    -> s  - second, ms - millisecond -    1000th of a second
    -> ordered by wait time desc, waits desc
    -> %Timeouts: value of 0 indicates value was < .5%.  Value of null is truly 0
    -> Captured Time accounts for         97.6%  of Total DB time      22,960.46 (s)
    -> Total FG Wait Time:            18,651.75 (s)  DB CPU time:       3,748.35 (s)
                                                                      Avg
                                          %Time       Total Wait     wait
    Wait Class                      Waits -outs         Time (s)     (ms)  %DB time
    User I/O                    3,327,253     0           18,576        6      80.9
    DB CPU                                                 3,748               16.3
    Commit                         23,882     0               69        3       0.3
    System I/O                      1,035     0                3        3       0.0
    Network                       842,393     0                2        0       0.0
    Other                          10,120    99                0        0       0.0
    Configuration                       3     0                0       58       0.0
    Application                       264     0                0        1       0.0
    Concurrency                     1,482     0                0        0       0.0
    Foreground Wait Events            
    -> s  - second, ms - millisecond -    1000th of a second
    -> Only events with Total Wait Time (s) >= .001 are shown
    -> ordered by wait time desc, waits desc (idle events last)
    -> %Timeouts: value of 0 indicates value was < .5%.  Value of null is truly 0
                                                                 Avg
                                            %Time Total Wait    wait    Waits   % DB
    Event                             Waits -outs   Time (s)    (ms)     /txn   time
    db file sequential read       3,054,464     0     17,002       6    104.5   74.0
    read by other session           199,603     0        796       4      6.8    3.5
    direct path read                 46,301     0        439       9      1.6    1.9
    db file scattered read           21,113     0        269      13      0.7    1.2
    log file sync                    23,882     0         69       3      0.8     .3
    db file parallel read             4,727     0         68      14      0.2     .3
    control file sequential re        1,035     0          3       3      0.0     .0
    SQL*Net message to client       840,792     0          2       0     28.8     .0
    direct path read temp                95     0          2      18      0.0     .0
    local write wait                     79     0          0       4      0.0     .0
    Disk file operations I/O            870     0          0       0      0.0     .0
    ASM file metadata operatio            4     0          0      50      0.0     .0
    log file switch (private s            3     0          0      58      0.0     .0
    ADR block file read                  36     0          0       3      0.0     .0
    enq: RO - fast object reus            5     0          0      16      0.0     .0
    latch: cache buffers chain        1,465     0          0       0      0.1     .0
    SQL*Net break/reset to cli          256     0          0       0      0.0     .0
    asynch descriptor resize         10,059   100          0       0      0.3     .0
    SQL*Net more data to clien        1,510     0          0       0      0.1     .0
    enq: KO - fast object chec            3     0          0       8      0.0     .0
    SQL*Net more data from cli           91     0          0       0      0.0     .0
    latch: shared pool                   14     0          0       0      0.0     .0
    ADR block file write                  5     0          0       1      0.0     .0
    reliable message                      8     0          0       0      0.0     .0
    direct path write temp                1     0          0       2      0.0     .0
    SQL*Net message from clien      840,794     0     68,885      82     28.8
    jobq slave wait                   7,365   100      3,679     499      0.3
    Streams AQ: waiting for me          721   100      3,605    5000      0.0
    wait for unread message on        3,648    98      3,603     988      0.1
    KSV master wait                      20     0          0       0      0.0
    Background Wait Events            
    -> ordered by wait time desc, waits desc (idle events last)
    -> Only events with Total Wait Time (s) >= .001 are shown
    -> %Timeouts: value of 0 indicates value was < .5%.  Value of null is truly 0
                                                                 Avg
                                            %Time Total Wait    wait    Waits   % bg
    Event                             Waits -outs   Time (s)    (ms)     /txn   time
    log file parallel write          29,353     0         83       3      1.0   34.8
    db file parallel write            5,753     0         17       3      0.2    6.9
    db file sequential read           1,638     0         15       9      0.1    6.1
    control file sequential re        5,142     0         13       2      0.2    5.4
    os thread startup                   140     0          8      58      0.0    3.4
    control file parallel writ        1,440     0          8       6      0.0    3.4
    log file sequential read            304     0          8      26      0.0    3.3
    db file scattered read              214     0          2       9      0.0     .8
    ASM file metadata operatio        1,199     0          1       1      0.0     .3
    direct path write                    35     0          0       6      0.0     .1
    direct path read                     41     0          0       5      0.0     .1
    kfk: async disk IO                    6     0          0       9      0.0     .0
    Disk file operations I/O          1,266     0          0       0      0.0     .0
    ADR block file read                  16     0          0       2      0.0     .0
    read by other session                 3     0          0       8      0.0     .0
    Log archive I/O                       2     0          0      10      0.0     .0
    log file sync                         3     0          0       5      0.0     .0
    asynch descriptor resize            341   100          0       0      0.0     .0
    CSS initialization                    1     0          0       6      0.0     .0
    log file single write                 4     0          0       1      0.0     .0
    latch: redo allocation                3     0          0       1      0.0     .0
    ADR block file write                  5     0          0       1      0.0     .0
    LGWR wait for redo copy              45     0          0       0      0.0     .0
    CSS operation: query                  6     0          0       0      0.0     .0
    CSS operation: action                 1     0          0       1      0.0     .0
    SQL*Net message to client           420     0          0       0      0.0     .0
    rdbms ipc message                47,816    39     61,046    1277      1.6
    DIAG idle wait                    7,200   100      7,200    1000      0.2
    Space Manager: slave idle         1,146    98      5,674    4951      0.0
    class slave wait                    284     0      3,983   14026      0.0
    dispatcher timer                     61   100      3,660   60006      0.0
    Streams AQ: qmn coordinato          258    50      3,613   14003      0.0
    Streams AQ: qmn slave idle          130     0      3,613   27789      0.0
    Streams AQ: waiting for ti            7    71      3,608  515430      0.0
    wait for unread message on        3,605   100      3,606    1000      0.1
    pmon timer                        1,201   100      3,604    3001      0.0
    smon timer                           15    73      3,603  240207      0.0
    ASM background timer                754     0      3,602    4777      0.0
    shared server idle wait             120   100      3,601   30006      0.0
    SQL*Net message from clien          554     0          4       7      0.0
    KSV master wait                     101     0          0       2      0.0
    Wait Event Histogram              
    -> Units for Total Waits column: K is 1000, M is 1000000, G is 1000000000
    -> % of Waits: value of .0 indicates value was <.05%; value of null is truly 0
    -> % of Waits: column heading of <=1s is truly <1024ms, >1s is truly >=1024ms
    -> Ordered by Event (idle events last)
                                                        % of Waits
                               Total
    Event                      Waits  <1ms  <2ms  <4ms  <8ms <16ms <32ms  <=1s   >1s
    ADR block file read           52  73.1   1.9   9.6  13.5               1.9
    ADR block file write          10 100.0
    ADR file lock                 12 100.0
    ARCH wait for archivelog l     3 100.0
    ASM file metadata operatio  1203  97.3    .5    .7    .3    .2          .9
    CSS initialization             1                   100.0
    CSS operation: action          1       100.0
    CSS operation: query           6  83.3  16.7
    Disk file operations I/O    2118  95.4   4.5    .1
    LGWR wait for redo copy       45 100.0
    Log archive I/O                2                         100.0
    SQL*Net break/reset to cli   256  99.6    .4
    SQL*Net message to client  839.9 100.0    .0
    SQL*Net more data from cli    91 100.0
    SQL*Net more data to clien  1503 100.0
    asynch descriptor resize   10.4K 100.0
    buffer busy waits              2 100.0
    control file parallel writ  1440   5.7  35.1  24.0  16.3  12.0   5.5   1.5
    control file sequential re  6177  69.4   7.5   5.9   8.1   7.1   1.7    .3
    db file parallel read       4727   1.7   3.2   3.2  10.1  46.6  33.3   1.8
    db file parallel write      5755  42.3  21.3  18.6  11.2   4.6   1.4    .5
    db file scattered read     21.5K   8.4   4.3  11.9  18.9  26.3  25.3   4.9
    db file sequential read    3053.  28.7  15.1  11.1  17.9  21.5   5.4    .3    .0
    direct path read           46.3K   9.9   8.8  18.5  21.7  22.8  15.7   2.7
    direct path read temp         95               9.5   9.5  23.2  49.5   8.4
    direct path write             35  11.4  31.4  17.1  22.9  11.4   2.9   2.9
    direct path write temp         1       100.0
    enq: KO - fast object chec     3                    66.7  33.3
    enq: RO - fast object reus     5  20.0              20.0  20.0  20.0  20.0
    kfk: async disk IO             6  50.0  16.7              16.7        16.7
    latch free                     3 100.0
    latch: cache buffers chain  1465 100.0
    latch: cache buffers lru c     1 100.0
    latch: object queue header     2 100.0
    latch: redo allocation         3  33.3  33.3  33.3
    latch: row cache objects       2 100.0
    latch: shared pool            15  93.3   6.7
    local write wait              79        35.4  34.2  21.5   8.9
    log file parallel write    29.4K  47.8  21.7  11.9   9.9   6.8   1.6    .3
    log file sequential read     304   6.3   3.0   3.6  10.2  23.4  24.3  29.3
    log file single write          4  25.0  75.0
    log file switch (private s     3                                     100.0
    log file sync              23.9K  40.9  28.0  12.9   9.7   6.7   1.5    .3
    os thread startup            140                                     100.0
    read by other session      199.6  37.1  19.9  12.9  13.1  13.8   3.1    .2
    reliable message               8 100.0
    ASM background timer         755   2.9    .4    .1    .1    .3    .1    .3  95.8
    DIAG idle wait              7196                                     100.0
    KSV master wait              121  88.4   2.5   3.3   2.5    .8    .8   1.7
    SQL*Net message from clien 840.1  97.1   1.8    .5    .2    .2    .1    .0    .1
    Space Manager: slave idle   1147    .1                                  .5  99.4
    Streams AQ: qmn coordinato   258  49.6                .4                    50.0
    Streams AQ: qmn slave idle   130    .8                                      99.2
    Streams AQ: waiting for me   721                                           100.0
    Streams AQ: waiting for ti     7  28.6                                42.9  28.6
    class slave wait             283  39.9   2.5   2.5   3.5   4.9   9.2  15.2  22.3
    dispatcher timer              60                                           100.0
    jobq slave wait             7360    .0    .0    .0                    99.9
    pmon timer                  1201                                           100.0
    rdbms ipc message          47.8K   2.7  31.6  17.4   1.1   1.1    .9  20.9  24.3
    Wait Event Histogram               DB/Inst: I2KPROD/I2KPROD  Snaps: 5606-5607
    -> Units for Total Waits column: K is 1000, M is 1000000, G is 1000000000
    -> % of Waits: value of .0 indicates value was <.05%; value of null is truly 0
    -> % of Waits: column heading of <=1s is truly <1024ms, >1s is truly >=1024ms
    -> Ordered by Event (idle events last)
                                                        % of Waits
                               Total
    Event                      Waits  <1ms  <2ms  <4ms  <8ms <16ms <32ms  <=1s   >1s
    shared server idle wait      120                                           100.0
    smon timer                    16                                       6.3  93.8
    wait for unread message on  7250                                  .1  99.9
    Latch Miss Sources                
    -> only latches with sleeps are shown
    -> ordered by name, sleeps desc
                                                         NoWait              Waiter
    Latch Name               Where                       Misses     Sleeps   Sleeps
    In memory undo latch     ktichg: child                    0          1        0
    active service list      kswslogon: session logout        0          2        0
    cache buffers chains     kcbgtcr_2                        0      1,123      483
    cache buffers chains     kcbgtcr: fast path (cr pin       0        496    1,131
    cache buffers chains     kcbrls_2                         0          5        6
    cache buffers chains     kcbgcur_2                        0          4        0
    cache buffers chains     kcbgtcr: fast path               0          3        1
    cache buffers chains     kcbzwb                           0          2        4
    cache buffers chains     kcbchg1: kslbegin: bufs no       0          1        0
    cache buffers chains     kcbnew: new latch again          0          1        0
    cache buffers chains     kcbrls_1                         0          1        6
    cache buffers chains     kcbzgb: scan from tail. no       0          1        0
    cache buffers lru chain  kcbzgws                          0          1        0
    object queue header oper kcbo_switch_cq                   0          1        0
    object queue header oper kcbo_switch_mq_bg                0          1        2
    redo allocation          kcrfw_redo_gen: redo alloc       0          3        0
    row cache objects        kqrpre: find obj                 0          1        1
    row cache objects        kqrso                            0          1        0
    shared pool              kghalo                           0         13        3
    shared pool              kghupr1                          0          4       15
    shared pool              kghalp                           0          1        0
    space background task la ktsj_grab_task                   0          2        2
              -------------------------------------------------------------

  • Interested by performance issue ?  Read this !  If you can explain, you're a master Jedi !

    This is the question we will try to answer...
    What si the bottle neck (hardware) of Adobe Premiere Pro CS6
    I used PPBM5 as a benchmark testing template.
    All the data and log as been collected using performance counter
    First of all, describe my computer...
    Operating System
    Microsoft Windows 8 Pro 64-bit
    CPU
    Intel Xeon E5 2687W @ 3.10GHz
    Sandy Bridge-EP/EX 32nm Technology
    RAM
    Corsair Dominator Platinum 64.0 GB DDR3
    Motherboard
    EVGA Corporation Classified SR-X
    Graphics
    PNY Nvidia Quadro 6000
    EVGA Nvidia GTX 680   // Yes, I created bench stats for both card
    Hard Drives
    16.0GB Romex RAMDISK (RAID)
    556GB LSI MegaRAID 9260-8i SATA3 6GB/s 5 disks with Fastpath Chip Installed (RAID 0)
    I have other RAID installed, but not relevant for the present post...
    PSU
    Cosair 1000 Watts
    After many days of tests, I wanna share my results with community and comment them.
    CPU Introduction
    I tested my cpu and pushed it at maximum speed to understand where is the limit, can I reach this limit and I've logged precisely all result in graph (See pictures 1).
    Intro : I tested my E5-XEON 2687W (8 Cores Hyperthread - 16 threads) to know if programs can use the maximum of it.  I used Prime 95 to get the result.  // I know this seem to be ordinary, but you will understand soon...
    The result : Yes, I can get 100% of my CPU with 1 program using 20 threads in parallel.  The CPU gives everything it can !
    Comment : I put 3 IO (cpu, disk, ram) on the graph of my computer during the test...
    (picture 1)
    Disk Introduction
    I tested my disk and pushed it at maximum speed to understand where is the limit and I've logged precisely all result in graph (See pictures 2).
    Intro : I tested my RAID 0 556GB (LSI MegaRAID 9260-8i SATA3 6GB/s 5 disks with Fastpath Chip Installed) to know if I can reach the maximum % disk usage (0% idle Time)
    The result : As you can see in picture 2, yes, I can get the max of my drive at ~ 1.2 Gb/sec read/write steady !
    Comment : I put 3 IO (cpu, disk, ram) on the graph of my computer during the test to see the impact of transfering many Go of data during ~10 sec...
    (picture 2)
    Now, I know my limits !  It's time to enter deeper in the subject !
    PPBM5 (H.264) Result
    I rendered the sequence (H.264) using Adobe Media Encoder.
    The result :
    My CPU is not used at 100%, the turn around 50%
    My Disk is totally idle !
    All the process usage are idle except process of (Adobe Media Encoder)
    The transfert rate seem to be a wave (up and down).  Probably caused by (Encrypt time....  write.... Encrypt time.... write...)  // It's ok, ~5Mb/sec during transfert rate !
    CPU Power management give 100% of clock to CPU during the encoding process (it's ok, the clock is stable during process).
    RAM, more than enough !  39 Go RAM free after the test !  // Excellent
    ~65 thread opened by Adobe Media Encoder (Good, thread is the sign that program try to using many cores !)
    GPU Load on card seem to be a wave also ! (up and down)  ~40% usage of GPU during the process of encoding.
    GPU Ram get 1.2Go of RAM (But with GTX 680, no problem and Quadro 6000 with 6 GB RAM, no problem !)
    Comment/Question : CPU is free (50%), disks are free (99%), GPU is free (60%), RAM is free (62%), my computer is not pushed at limit during the encoding process.  Why ????  Is there some time delay in the encoding process ?
    Other : Quadro 6000 & GTX 680 gives the same result !
    (picture 3)
    PPBM5 (Disk Test) Result (RAID LSI)
    I rendered the sequence (Disk Test) using Adobe Media Encoder on my RAID 0 LSI disk.
    The result :
    My CPU is not used at 100%
    My Disk wave and wave again, but far far from the limit !
    All the process usage are idle except process of (Adobe Media Encoder)
    The transfert rate wave and wave again (up and down).  Probably caused by (Buffering time....  write.... Buffering time.... write...)  // It's ok, ~375Mb/sec peak during transfert rate !  Easy !
    CPU Power management give 100% of clock to CPU during the encoding process (it's ok, the clock is stable during process).
    RAM, more than enough !  40.5 Go RAM free after the test !  // Excellent
    ~48 thread opened by Adobe Media Encoder (Good, thread is the sign that program try to using many cores !)
    GPU Load on card = 0 (This kind of encoding is GPU irrelevant)
    GPU Ram get 400Mb of RAM (No usage for encoding)
    Comment/Question : CPU is free (65%), disks are free (60%), GPU is free (100%), RAM is free (63%), my computer is not pushed at limit during the encoding process.  Why ????  Is there some time delay in the encoding process ?
    (picture 4)
    PPBM5 (Disk Test) Result (Direct in RAMDrive)
    I rendered the same sequence (Disk Test) using Adobe Media Encoder directly in my RamDrive
    Comment/Question : Look at the transfert rate under (picture 5).  It's exactly the same speed than with my RAID 0 LSI controller.  Impossible !  Look in the same picture the transfert rate I can reach with the ramdrive (> 3.0 Gb/sec steady) and I don't go under 30% of disk usage.  CPU is idle (70%), Disk is idle (100%), GPU is idle (100%) and RAM is free (63%).  // This kind of results let me REALLY confused.  It's smell bug and big problem with hardware and IO usage in CS6 !
    (picture 5)
    PPBM5 (MPEG-DVD) Result
    I rendered the sequence (MPEG-DVD) using Adobe Media Encoder.
    The result :
    My CPU is not used at 100%
    My Disk is totally idle !
    All the process usage are idle except process of (Adobe Media Encoder)
    The transfert rate wave and wave again (up and down).  Probably caused by (Encoding time....  write.... Encoding time.... write...)  // It's ok, ~2Mb/sec during transfert rate !  Real Joke !
    CPU Power management give 100% of clock to CPU during the encoding process (it's ok, the clock is stable during process).
    RAM, more than enough !  40 Go RAM free after the test !  // Excellent
    ~80 thread opened by Adobe Media Encoder (Lot of thread, but it's ok in multi-thread apps!)
    GPU Load on card = 100 (This use the maximum of my GPU)
    GPU Ram get 1Gb of RAM
    Comment/Question : CPU is free (70%), disks are free (98%), GPU is loaded (MAX), RAM is free (63%), my computer is pushed at limit during the encoding process for GPU only.  Now, for this kind of encoding, the speed limit is affected by the slower IO (Video Card GPU)
    Other : Quadro 6000 is slower than GTX 680 for this kind of encoding (~20 s slower than GTX).
    (picture 6)
    Encoding single clip FULL HD AVCHD to H.264 Result (Premiere Pro CS6)
    You can look the result in the picture.
    Comment/Question : CPU is free (55%), disks are free (99%), GPU is free (90%), RAM is free (65%), my computer is not pushed at limit during the encoding process.  Why ????   Adobe Premiere seem to have some bug with thread management.  My hardware is idle !  I understand AVCHD can be very difficult to decode, but where is the waste ?  My computer want, but the software not !
    (picture 7)
    Render composition using 3D Raytracer in After Effects CS6
    You can look the result in the picture.
    Comment : GPU seems to be the bottle neck when using After Effects.  CPU is free (99%), Disks are free (98%), Memory is free (60%) and it depend of the setting and type of project.
    Other : Quadro 6000 & GTX 680 gives the same result in time for rendering the composition.
    (picture 8)
    Conclusion
    There is nothing you can do (I thing) with CS6 to get better performance actually.  GTX 680 is the best (Consumer grade card) and the Quadro 6000 is the best (Profressional card).  Both of card give really similar result (I will probably return my GTX 680 since I not really get any better performance).  I not used Tesla card with my Quadro, but actually, both, Premiere Pro & After Effects doesn't use multi GPU.  I tried to used both card together (GTX & Quadro), but After Effects gives priority to the slower card (In this case, the GTX 680)
    Premiere Pro, I'm speechless !  Premiere Pro is not able to get max performance of my computer.  Not just 10% or 20%, but average 60%.  I'm a programmor, multi-threadling apps are difficult to manage and I can understand Adobe's programmor.  But actually, if anybody have comment about this post, tricks or any kind of solution, you can comment this post.  It's seem to be a bug...
    Thank you.

    Patrick,
    I can't explain everything, but let me give you some background as I understand it.
    The first issue is that CS6 has a far less efficient internal buffering or caching system than CS5/5.5. That is why the MPEG encoding in CS6 is roughly 2-3 times slower than the same test with CS5. There is some 'under-the-hood' processing going on that causes this significant performance loss.
    The second issue is that AME does not handle regular memory and inter-process memory very well. I have described this here: Latest News
    As to your test results, there are some other noteworthy things to mention. 3D Ray tracing in AE is not very good in using all CUDA cores. In fact it is lousy, it only uses very few cores and the threading is pretty bad and does not use the video card's capabilities effectively. Whether that is a driver issue with nVidia or an Adobe issue, I don't know, but whichever way you turn it, the end result is disappointing.
    The overhead AME carries in our tests is something we are looking into and the next test will only use direct export and no longer the AME queue, to avoid some of the problems you saw. That entails other problems for us, since we lose the capability to check encoding logs, but a solution is in the works.
    You see very low GPU usage during the H.264 test, since there are only very few accelerated parts in the timeline, in contrast to the MPEG2-DVD test, where there is rescaling going on and that is CUDA accelerated. The disk I/O test suffers from the problems mentioned above and is the reason that my own Disk I/O results are only 33 seconds with the current test, but when I extend the duration of that timeline to 3 hours, the direct export method gives me 22 seconds, although the amount of data to be written, 37,092 MB has increased threefold. An effective write speed of 1,686 MB/s.
    There are a number of performance issues with CS6 that Adobe is aware of, but whether they can be solved and in what time, I haven't the faintest idea.
    Just my $ 0.02

  • Performance issues - Log file parallel write

    Hi there,
    Since a few months I have big performance issues with my Oracle 11.2.0.1.0.
    If I look in the Enterprise manager (in blocking sessions) I see al lot of "log file paralles writes" and a lot of "log file sync" .
    We have configured an active data guard environment and are using ASM.
    We are not stressing out the database with heavy queries or commits or something, but sometimes during the day this happens on non specific times...
    We've investigated everything (performance to SAN / heavy queries / oracle problems etc etc) and we really don't know what to do anymore so i thought.. let's try a post on the Forum.....
    Perhaps someone had similar things?
    Thanks,
    BR
    Mark

    mwevromans wrote:
    See blow a tail of alertlog.
    Tue Apr 24 15:12:17 2012
    Thread 1 cannot allocate new log, sequence 194085
    Checkpoint not complete
    Current log# 1 seq# 194084 mem# 0: +DATA/kewillprd/onlinelog/group_1.262.712516155
    Current log# 1 seq# 194084 mem# 1: +FRA/kewillprd/onlinelog/group_1.438.756466165
    LGWR: Standby redo logfile selected to archive thread 1 sequence 194085
    LGWR: Standby redo logfile selected for thread 1 sequence 194085 for destination LOG_ARCHIVE_DEST_2
    Thread 1 advanced to log sequence 194085 (LGWR switch)
    Current log# 2 seq# 194085 mem# 0: +DATA/kewillprd/onlinelog/group_2.264.712516155
    Current log# 2 seq# 194085 mem# 1: +FRA/kewillprd/onlinelog/group_2.418.756466215
    Tue Apr 24 15:12:21 2012
    Archived Log entry 388061 added for thread 1 sequence 194084 ID 0x90d7aa62 dest 1:
    Tue Apr 24 15:14:09 2012
    Thread 1 cannot allocate new log, sequence 194086
    Checkpoint not complete
    Current log# 2 seq# 194085 mem# 0: +DATA/kewillprd/onlinelog/group_2.264.712516155
    Current log# 2 seq# 194085 mem# 1: +FRA/kewillprd/onlinelog/group_2.418.756466215
    LGWR: Standby redo logfile selected to archive thread 1 sequence 194086
    LGWR: Standby redo logfile selected for thread 1 sequence 194086 for destination LOG_ARCHIVE_DEST_2
    Thread 1 advanced to log sequence 194086 (LGWR switch)
    Current log# 3 seq# 194086 mem# 0: +DATA/kewillprd/onlinelog/group_3.266.712516155
    Current log# 3 seq# 194086 mem# 1: +FRA/kewillprd/onlinelog/group_3.435.756466241
    Tue Apr 24 15:14:14 2012
    Archived Log entry 388063 added for thread 1 sequence 194085 ID 0x90d7aa62 dest 1:
    Tue Apr 24 15:16:46 2012
    Thread 1 cannot allocate new log, sequence 194087
    Checkpoint not complete
    Current log# 3 seq# 194086 mem# 0: +DATA/kewillprd/onlinelog/group_3.266.712516155
    Current log# 3 seq# 194086 mem# 1: +FRA/kewillprd/onlinelog/group_3.435.756466241
    Thread 1 cannot allocate new log, sequence 194087
    Private strand flush not complete
    Current log# 3 seq# 194086 mem# 0: +DATA/kewillprd/onlinelog/group_3.266.712516155
    Current log# 3 seq# 194086 mem# 1: +FRA/kewillprd/onlinelog/group_3.435.756466241
    LGWR: Standby redo logfile selected to archive thread 1 sequence 194087
    LGWR: Standby redo logfile selected for thread 1 sequence 194087 for destination LOG_ARCHIVE_DEST_2
    Thread 1 advanced to log sequence 194087 (LGWR switch)
    Current log# 1 seq# 194087 mem# 0: +DATA/kewillprd/onlinelog/group_1.262.712516155
    Current log# 1 seq# 194087 mem# 1: +FRA/kewillprd/onlinelog/group_1.438.756466165
    Tue Apr 24 15:16:54 2012
    Archived Log entry 388065 added for thread 1 sequence 194086 ID 0x90d7aa62 dest 1:
    Tue Apr 24 15:18:59 2012
    Thread 1 cannot allocate new log, sequence 194088
    Checkpoint not complete
    Current log# 1 seq# 194087 mem# 0: +DATA/kewillprd/onlinelog/group_1.262.712516155
    Current log# 1 seq# 194087 mem# 1: +FRA/kewillprd/onlinelog/group_1.438.756466165
    Thread 1 cannot allocate new log, sequence 194088
    Private strand flush not complete
    Current log# 1 seq# 194087 mem# 0: +DATA/kewillprd/onlinelog/group_1.262.712516155
    Current log# 1 seq# 194087 mem# 1: +FRA/kewillprd/onlinelog/group_1.438.756466165
    LGWR: Standby redo logfile selected to archive thread 1 sequence 194088
    LGWR: Standby redo logfile selected for thread 1 sequence 194088 for destination LOG_ARCHIVE_DEST_2
    Thread 1 advanced to log sequence 194088 (LGWR switch)
    Current log# 2 seq# 194088 mem# 0: +DATA/kewillprd/onlinelog/group_2.264.712516155
    Current log# 2 seq# 194088 mem# 1: +FRA/kewillprd/onlinelog/group_2.418.756466215
    Tue Apr 24 15:19:06 2012
    Archived Log entry 388067 added for thread 1 sequence 194087 ID 0x90d7aa62 dest 1:
    Tue Apr 24 15:22:00 2012
    Thread 1 cannot allocate new log, sequence 194089
    Checkpoint not complete
    Current log# 2 seq# 194088 mem# 0: +DATA/kewillprd/onlinelog/group_2.264.712516155
    Current log# 2 seq# 194088 mem# 1: +FRA/kewillprd/onlinelog/group_2.418.756466215
    Thread 1 cannot allocate new log, sequence 194089
    Private strand flush not complete
    Current log# 2 seq# 194088 mem# 0: +DATA/kewillprd/onlinelog/group_2.264.712516155
    Current log# 2 seq# 194088 mem# 1: +FRA/kewillprd/onlinelog/group_2.418.756466215
    LGWR: Standby redo logfile selected to archive thread 1 sequence 194089
    LGWR: Standby redo logfile selected for thread 1 sequence 194089 for destination LOG_ARCHIVE_DEST_2
    Thread 1 advanced to log sequence 194089 (LGWR switch)
    Current log# 3 seq# 194089 mem# 0: +DATA/kewillprd/onlinelog/group_3.266.712516155
    Current log# 3 seq# 194089 mem# 1: +FRA/kewillprd/onlinelog/group_3.435.756466241
    Tue Apr 24 15:19:06 2012
    Archived Log entry 388069 added for thread 1 sequence 194088 ID 0x90d7aa62 dest 1:Hi
    1st switch time ==> Tue Apr 24 15:18:59 2012
    2nd switch time ==> Tue Apr 24 15:19:06 2012
    3rd switch time ==> Tue Apr 24 15:19:06 2012
    Redo log file switch has good impact on the performance of the database. Frequent log switches may lead to the slowness of the database . Oracle documents suggests to resize the redolog files so that log switches happen more like every 15-30 min (roughly depending on the architecture and recovery requirements).
    AS i check the alertlog file and find that the log are switchinh very fequent which is one of the reason that you are getting checkpoint  not complete message . i have face this issue many times and i generally increase the size of the logfile and set the archive_lag_time parameter as i have suggested above . If you further want to go root cause and more details then above guys will help you more because i don't have much experience in database tunning . If you looking for aworkarounf then you must go through it .
    Good Luck
    --neeraj                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       

  • Reader/Writer.close() is slow

    I've written a multi-threaded application that does a lot of disk I/O using Buffered and File Reader/Writers. Each thread is reading and writing it's OWN file. Everything works great except the performance of the Reader/Writer.close() method. When I'm running say 10 threads at a time and my code calls close() it can take anywhere from 1 - 3 seconds for the call to return. If I only run 5 threads then close() returns in a respectable timeframe.
    Can someone please explain what could be causing close() to take so long to return?
    Thanks!

    Each thread has to vie for CPU time with other processes on your system. More threads means more scheduling of processes, the threads do not run at the same time--it's just an illusion created by scheduling. When you have 10 threads, you have more scheduling going on--hence more wait when you want to close out: you have wait for each to gain enough active CPU time to flush and close, but there can only be up to as many threads running at one time as your system has CPUs*Threads/CPU. Just because you have more Java threads, does not mean that you're processing faster--it just means there is seperate processing going on as the system can schedule resources for your threads to work in with the rest of the system processes all of them essentially competing for many of the same resources.

Maybe you are looking for