Using Performance counters

Similar Questions

• How to call dll com APIs that range from the performance counters of less than 1 ms with CVI and always get less timer resolution of 1 ms

  Hello

  I've created a dll com in VC ++ using performance counters/timers to less than a millisecond.

  This is useful when you send a message to very high speed. (say 10 or more)

  This is done by the dll.

  When I use CVI to create a user interface, this dll runs at a fixed rate of 1ms.

  This slows down the application.

  I tried to use the same dll with VC ++ host and it works well.

  I need to check the registry setting to see if the useDefaultTimer is set to false or TRUE.

  (I'm not near the development PC) However, by default, it should be FALSE and I have no fidle with it.

  Veuileez post any suggestions you might have.

  Thank you!

  This problem is now solved for me.

  Just the highest thread priority in the dll.

  Thank you if you had the answer.

• vSphere networking performance counters - Teddy bear use of flow compared to its use

  I am responsible for a vSphere 5.1 environment that uses NFS data warehouses and I'm trying to collect metrics on how much bandwidth is used to access NFS data stores.  When I did it first a week ago, I ran esxtop and looked at network and sort by Mbps passed parameters and what he was able to indicate what vmnic NFS vmkernel was linked to.  I then took a look at the usage meter vmnic for a total of send/receive KB/s.  During my research, I ran across another counter: "use of flow rates for NFS Teddy."  Here's the problem, when we look at the use and Teddy flow using the counters from NFS on the same vmnic over the same period of time, the use of flow for meter NFS shows bandwidth much higher than that of the meter use (see image).  What gives?

  What I forgot to mention, is that measures to counter throughput.usage.nfs report a higher flow rate than the physical NETWORK adapter can handle.  The highest Summit on the graph shows about a flow of 13 GB/s on a network card 1 GB.  I spoke with a VMware engineer friend and he said it looks like the meter is mislabeled in vCenter.  I verified this by looking at the use of the NFS in vCenter Operations Manager metric and compared to the metric of its use on the same physical NETWORK adapter and the metric NFS for the NIC I was looking at showed approximately 23.8 MB/s (if I assume that the unit of measure of labelling was supposed to be B/s and not KB/s) and usage was about 24.2 MB / s.  The metric of higher use is due to the fact that the environment is badly designed by my predecessor and the NFS Sharing vmkernel rising with VM networks (something that I am trying to solve).

• Difference between vi3 and vc - sdk (visdk400) performance counters

  I found two links when searching for the CPU performance counters:

  1. http://www.vmware.com/support/developer/vc-sdk/visdk400pubs/ReferenceGuide/cpu_counters.html

  2 http://pubs.vmware.com/vi3/sdk/ReferenceGuide/cpu.html

  http://www.VMware.com/support/developer/VC-SDK/visdk400pubs/ReferenceGuide/cpu_counters.html [http://pubs.vmware.com/vi3/sdk/ReferenceGuide/cpu.html: http://pubs.vmware.com/vi3/sdk/ReferenceGuide/cpu.html]

  As I understand it, the first is for vSphere 4.0, ESX 4.0 and vCenter 4.0 and the second is for the previous version, when it was called VMWare Infrastructure 3. Is this good?

  I don't think you understand how to navigate the API reference page, the counter of 'performance' information available in each of the versions of the API, depending on the version, you'll see different counters, be they new or obsolete. You can also tell by looking at the URL

  for example

  visdk25pubs = VI 2.5

  visdk400pubs = vSphere 4.0

  visdk41pubs = vSphere 4.1

  The specific page that you are referring only lists the CPU performance counters, there is definitely more than that.

  Here's the exact URL to all 3 API listing the performance counters:

  VI 2.5 - http://www.vmware.com/support/developer/vc-sdk/visdk25pubs/ReferenceGuide/vim.PerformanceManager.html

  vSphere 4.0 - http://www.vmware.com/support/developer/vc-sdk/visdk400pubs/ReferenceGuide/vim.PerformanceManager.html

  vSphere 4.1 - http://www.vmware.com/support/developer/vc-sdk/visdk41pubs/ApiReference/index.html

  To access performance indicators (for example, I'll use vSphere 4.1) you will go through the following:

  1) go to this address - http://www.vmware.com/support/developer/vc-sdk/visdk41pubs/ApiReference/index.html

  2) click on managed object Types in the left pane

  3) click on the box in the middle that says "ServiceContent.

  4) scroll down and click on the link PerformanceManager

  (5) you should be taken to the page linked above with all perf counters performance

  It really helps to understand the object model of VI/vSphere to cross, here's a great blog by VMware used on the object model - http://www.doublecloud.org/2010/02/object-model-of-vmware-vsphere-api-a-big-picture-in-2-minutes/

  Hope it makes sense

  =========================================================================

  William Lam

  VMware vExpert 2009,2010

  VMware scripts and resources at: http://www.virtuallyghetto.com/

  Twitter: @lamw

  repository scripts vGhetto

  Introduction to the vMA (tips/tricks)

  Getting started with vSphere SDK for Perl

  VMware Code Central - Scripts/code samples for developers and administrators

  VMware developer community

  If you find this information useful, please give points to "correct" or "useful".

• Measurement of RPM without the use of counters

  I read several threads on how to measure the RPM of optical sensors, but they all involve the use of counters on the DAQ connector. My problem is that my project is to read and comparing four separate plans and my DAQ has only 2 terminals of counter. Ideally, I would just use the input channels of the analogue signal for all four sensors. I'm away to the extent of the counting of the edges of the analog signal using this code snippet.

  
  

• cDAQ-9174 cannot use the counters of 3 or 4

  Hello

  I try to display the entry of a potentiometer and 3 encoders of Quad.  I have a CDAQ-9174 with a 9215 OR (for the POT) in the slot 1, 9411 or in slot 2 and a NI 9401 in the Groove 3 (soon to another NOR 9411 when it happens).

  If I run the example 'Measure angular Position.vi' on each individual encoder (by selecting either modules on counter 0), I can see all three encoders work properly (exit count increments and decrements as expected)

  If I run the Test panels able and automation, I see all three encoders switch their respective 2 channels each.

  But when I change 'measurement Position.vi"to have all three separate entries (I copied the task of creating and all its entries twice, then expanded the while loop to have three different DaqMX Read vi, then 2 clearer spots on the right side (output) at all in a loop), I see only 2 encoders increment and decrement.

  I do not use Index Z entries, I changed the type of decoding to X 2 for all three.  I tried to change that, but I especially get the same result (2 encoders working, is not 1).

  I changed the encoders are the use of counters to 0, 1, and 2.  Only the assigned to counter 2 encoder does not work.

  I tried to use meter 3 - same problem.

  Is there a way to confirm that the cDAQ-9174 counters all work?  I tried all three in the test panels and they seem to be good?

  A cDAQ-9174 can manage 2 Quad encoders using 2 signals of each (A and B signals - A for metering, B for management)?

  I have something configured incorrectly?  If you use two Modules of entry at the same time, is it some additional configuration that must be done?

  Really appreciate some help here.

  Thank you

  Sam

  Yes, we use the 9.0.2 version drivers and no there is no error message.

  Turns out we had wired it incorrectly for Counter 2 use.  Being on the second module, I thought we had wire the same way the first module has been wired - not realizing that counters need a provision of the specific pins.

  Thank you for looking into this.

• Hardware performance counters are supported?

  It seems same issues remained in the past, but I thought I'd try again anyway. VMWare Workstation is-support material of performance counters? In other words, I'd be able to write code that triggers an interrupt on a performance counter overflow and run properly in the guest OS? If VMware Workstation does not support this, is there another VMware product that makes?

  I stumbled across a few validations dated around the net that seem to indicate that this feature is not available (see and below). However, because these are so old, it's quite possible the newer versions have since added support.

  Thank you

  devnull431

  http://oprofile.sourceforge.net/faq/, near the bottom, under "VMware".

  http://software.Intel.com/en-us/forums/Intel-VTune-Performance-Analyzer/topic/44195/

  No, the performance monitor counters are not virtualized in any VMware product.

• Get NFS via PowerCLI performance counters

  Hello

  I hope someone can help me or perhaps shed some light on my problem and I hope to propose a solution or a path to a solution.

  I need to be able to monitor the performance of e/s NFS (mainly the latency to read/write, but also the flow). I tried with the PowerCli using Get-Stat on ie. disk.deviceWriteLatency.average, but I get only for my stores of data non - NFS. I read in several places that there are some measures NFS deleted in an earlier version of vSphere, but also that some of them may actually be available again.

  I found that the statistics are available through the vSphere Client (go to an ESX host specific, Performance, advanced and click on build a graph with only my NFS data stores and only read/write latency counters.) This will produce a graph with also live-data and historical data. So I recon the ESX (or vSphere) actually knows NFS performance.

  I tried on 5.0.0 ESXi and ESXi 5.1.0 and with PowerCLI 5.1 Release 2.

  I've seen some proposals we should probe the VMs (and not the ESXi) for this information, but this seems an exaggeration of the probe of hundreds of virtual machines for more information the vSphere/ESXi server is apparently already?

  Does anyone have any suggestions or pointers to how I can get this information?

  Concerning

  Thomas

  If you want to use my Get-Stat2 function, you can do something like this

  $stat = "datastore.totalWriteLatency.average"$start = (Get-Date).AddDays(-5)
  
  Get-Datastore | where {$_.Type -eq "NFS"} | %{  $dsName = $_.Name  $uuid = $_.ExtensionData.Info.Url.Split('/')[-2]  $_.ExtensionData.Host | %{Get-View $_.Key |     Get-Stat2 -Stat $stat -Instance $uuid -Start $start -Interval HI2 |    Select Timestamp,CounterName,Interval,Instance,Value,Entity,@{N="Datastore";E={$dsName}}  }}
  

  You can do this with the ordinary Get-Stat

  $stat = "datastore.totalWriteLatency.average"$start = (Get-Date).AddDays(-5)
  
  Get-Datastore | where {$_.Type -eq "NFS"} | %{  $dsName = $_.Name  $uuid = $_.ExtensionData.Info.Url.Split('/')[-2]  Get-VMHost -Datastore $_ |    where {$_.Instance -eq $uuid} |     Select Timestamp,MetricId,IntervalSecs,Instance,Value,@{N="Entity";E={$_.Entity.Name}},@{N="Datastore";E={$dsName}}}
  

• How can I use two counters simultaneously to pulse width measurment

  Hello, everyone!

  I'm new to Labview. I currently have some cDAQ9171 and width measurment with 9401 impulses. My understanding is that the 9401 was 4 meters, which means that I can use these meter separately. However I have the following problem.

  1. I use ctr 0 and ctr 1 (PFI 1 and PFI5) to measure two different impulses. However, it seems that there is an interference between two counters. How can I make two counters working simultaneously and separately?

  2. I first try a pulse width measurment counter in Labview signalExpress. My pulse width is about 0.4ms. However, I can't get the right result, if I choose the starting edge is on the rise (the results always around 20ns. Only if I revise my pulse and pick the starting edge is down, I can get reliable results.

  I'm confused about these issues for about 3 weeks... Is there someone can help what can I do with that?

  I have attached a simple vi...

  Thank you very much!

  
  

• Physical connections using 4 counters with NI 9411 cDAQ chassis 9178

  Hello

  Currently I have a NI 9411 module in a 9178 cDAQ chassis.  I use 2 meter to read the frequency measures.

  The NI 9411 pinout diagram (see pdf file attached to this post), here are the links that I did:

  CTR 0 SRC, pin 1 ground COM

  DOOR of the CTR 0, pin 2 to the first signal of frequency

  CTR 1 CBC, PIN 6 COM/ground

  CTR 1 DOOR, pin 01:53 frequency signal

  The problem now is that I had like to use meters of 3rd and 4th in my 9178 cDAQ chassis, but I am confused how to wire

  frequency signals in 3rd and 4th, because CTR2 GATE is pin 1 and GATE CTR3 is pin 6.  Can I change the assignment of pins

  to use the other pins in the NI 9411 module for frequency counter measures?  I didn't understand how to do this in MAX

  Configuration.

  Thank you

  Anna

  Hi EETDer,

  Using 'C-Series Signal connections for counters that you found is a good resource.  One thing I want to point out, that's a measure of the frequency on a single meter, simply connect the source of the signal up to the door of the RTC.  Internally, the module will forward a database internal time appropriate to the source of counters, so DO NOT want to connect the Source CTR to the mass.  On your device, you will be just wire each signal to the source of the meter, so only utilizting pines 1,6,3,8 for your 4 frequency measurements.

• Available performance counters

  I'm looking for a list of all available performance perfmon and descriptions for windows server 2008r2 and 2012 counters.  Is there such a list or documentation available that I can view or download?

  Hi Jim,.

  The question you posted would be better suited in the Forum of the server. Please visit the link below to find a community that will provide the support you want.

  http://social.technet.Microsoft.com/forums/WindowsServer/en-us/home#Forum=winserver8gen&filter=AllTypes&sort=lastpostdesc&content=search

  Hope this information helps you.

• Performance counters are missing in .blg files

  Dear all,

  I installed the perfmon counter to collect the performance of my windows 2008 R2 server and I added the counter of our application to check its performance, but when I check the .blg file I see these application counters are missing. PerfMon counters for this has not saved.

  Interestingly, I added my application 10 counters and out of which 3 are missing. Can anyone explain me about this.

  Thank you

  Abhishek

  Hi Abhishek,

  Welcome to the Microsoft Community and thanks for posting your request.

  Since then, the issue is with windows 2008 server R2, it would be better suited by contacting Microsoft TechNet forum, we have a dedicated team with advanced tools and permissions to help you with such questions. Follow the link below to view the same query in the Microsoft TechNet forum for more help on this issue.

  https://social.technet.Microsoft.com/forums/Windows/en-us/home?category=w7itpro%2Cwindowsvistaitpro%2Cwindowsxpitpro%2Cwindowsserver%2CWindows10ITPro&filter=AllTypes&sort=lastpostdesc

  If you need help with Windows, let us know and will be happy to help you.

• New performance counters available in vCenter since ESXi 5?

  Hi guys,.

  Just noticed that the very useful counter co Stop seems to be available in the performance for a tab machine virtual hosts on an ESXi5.1 update 1 box. This is new since ESX(I) 4? Very convenient!

  According to this VMware vSphere 5.1 meter stop co vCenter introduced in v5.0... The meter is available in 4.1 but esxtop only... not in vCenter...

  / Rubeck

• Understanding Performance counters

  I am auditing a firm for the first time. I wish to see the performace of storage for a specific data store and virtual machines. The customer has 9 SQL servers on a single data store volume. (Talk about putting your eggs in the same basket) I can not connect via the CLI because I saw straight to GUI.

  First of all, read the data of a virtual machine or disc store in the Advanced section in the performance tab? What I was looking for in terms of poor performance outside the high I/O? What is the latency level determines the e/s, 15 high MS? They also have an iSCSI SAN.

  There are separate counters as a datastore. = disk.  A data store can be a single LUN, a combo of multiple LUNS (extensions) or connection (NFS) network.

• Performance counters to performance monitor for the Consolidation planning

  Hello

  I'm trying to understand what the servers are good canidates for the consolidation.  Spin the server VSphere 4 and a couple of hosts ESXi 4.  Rather than run the task "Analyze physical computers for consolidation" on the Vcenter server, I would rather go manual counters from perfmon on each server at least a week, so I can get a better picture of the resources needed for each server.

  I can't find any info on the vmware site which tells you counters set up and how to use them in the planning of peacebuilding.  Can someone point me to such a document and/or tell me counters are best to use?  Thank you.

  I agree with Dave - the big 4 are those to check.

  I have a blog entry on this http://communities.vmware.com/blogs/vmroyale/2008/12/22/creating-a-generic-baseline-for-windows that might help.

  Good luck!