The CPU suddenly very high low host CPU

Hi all

I was struggling with a particular host for awhile and am unable to access the root of the cause. What we have so far:

Physics:

1 host, 2 quadcores with HT technology (total 8 cores, 16 logic due to HT), 24 GB of ram

HP Proliant DL380 G6

Virtual:

1 x Windows 2008R2 DC/FS 2vcpu

1 x Windows 2008R2 SQL 4vcpu

1 x Windows 2008R2 Exchange 2010 1vcpu

1 x Windows 2012R2 RDS currently 8vcpu

Recently, the old 2008R2 RDS has been replaced by the new 2012R2 RDS. This went well, nothing special, no complaints, that rent because it was quite a bit of snappyier than the last.

Then, (and I did not understand what happened yet, could have been power failure) after about a week the Esxi host froze and we had to restart. Servers began and everything was fine, until the problems started.

The 2012R2 virtual machine currently maxing out at 100% cpu usage in Windows Task Manager, between all the virtual cores. This can be achieved by something as simple as the launch of chrome and Outlook at the same time. Performance on this virtual machine is terrible. All other virtual machines are affected also, extremely high CPU usage in Windows, maxing out even with simple tasks. If I open vSphere and check the CPU usage, it's nowhere near capacity. The RDS virtual machine did not exceed 3000 mhz maximum.

What we have tried so far:

-Reboot the host

-Restart the virtual machine

-The power management has changed compared to the High Performance HP OS Control setting, and the powersetting to high performance in vsphere. I can see through esxtop that all hearts are at c0 permanently. (Could not verify this before because of ILO2 failing to display this when HP high performance mode is activated)

-J' tried all sorts of Vcpu assignments, until 1 vcpu/1core 8 sockets on the 2012RDS. There is no pool of resources, there is no reserves (I tried those who, unfortunately, no effect)

-Close all VM except one (to check if there is some sort of contention cpu), always the same.

I think something is gone belly up when the host rebooted, simply unable to understand why, and apart from the crazy CPU usage, the server running now stable.

Any input is greatly appreciated.

21:03:46 until 01:52, 344 worlds, 4 VMS, vCPUs 15; CPU load average: 0.19, 0.26, 0.22

PCPU USED (%): 2.6 2.5 2.5 3.0 4.1 2.1 2.7 1.9 2.9 5.7 2.2 2.4 1.9 1.7 2.3 2.4 AVG: 2.7

PCPU UTIL (%): 19 19 19 21 28 18 20 16 17 28 16 16 13 14 14 16 AVG: 19

UTIL (%) BASE: 33 35 40 31 40 27 23 26 AVG: 32

ID NAME NWLD % USED GID % PERFORMANCE SYS % WAITING % VMWAIT % % IDLE % OVRLP % % MLMTD % SWPWT CSTP RDY

3785 3785 XXXXX 14 24.00 153,48 0.13 1243,64 11.57 2.75 633.36 0.81 0.00 0.00 0.00

10167 10167 XXXX01 10 6.87 54,83 0.11 944,21 3.31 341.84 0.95 0.21 0.00 0.00 0.00

3361 3361 XXXXX01 7 3.21 13.37 0.05 686,25 0.23 87.04 0.35 0.00 0.00 0.00 0.00

3349 3349 XXXXe01 10 1.64 8,89 0.06 990,63 0.28 191.21 0.50 0.02 0.00 0.00 0.00

This has been fixed!

Have us shut completely the host, took off all power physically and reconnected. After that, CPU returned to normal. Upgrade to ESXi for good measure.

Apparently restart with the ILO is not enough.

Tags: VMware

Similar Questions

  • Display of Windows Vista, the icons and all THE GRAPHICS suddenly pixelated, appear low quality at the highest resolution and colors

    Please help, out of nowhere on my screen - background, all icons, all graphics (including the Explorer and other programs) have become rough and pixelated and seem very low qualty even if my display is set to the highest resolution management settings and color. I've not been able to find a way to restore and have no idea why it is doing this in the first place. It's really bothering me, it's hard to read (text appears fuzzy and broken up, not smooth and sharp, icons have white or another pixelation around them and do not have the 'look of glass'.) I was wondering if one of the old games my children changed my settings somewhere but I've lived every control panel I find and have not been able to correct the problem.  Even the buttons (back, forward, refresh, etc.) in Explorer have bad pixelation. That's happened? Help! :) Thank you

    I would also update the drivers, firmware or software for your monitor at the same time.  Also, if you have another monitor, swap them to see if the problem goes away or moves - then we can pretty much reduce the question to the screen and not the video card (and if the updated drivers do not resolve this problem, then it's a hardware problem and you can either take a workshop of computer service repair or simply a replacement of purchase screen.)

    I hope this helps.

    Good luck!

    Lorien - MCSA/MCSE/network + / has + - if this post solves your problem, please click the 'Mark as answer' or 'Useful' button at the top of this message. Marking a post as answer, or relatively useful, you help others find the answer more quickly.

  • Get the parts with very high level in a tree by using Connect by

    I have the following table:

    CREATE TABLE (Z_BOM2)has VARCHAR2(4 CHAR), B VARCHAR2(4 CHAR));

    Insert into Z_BOM2 (A, B) values ('A', 'B');

    Insert into Z_BOM2 (A, B) values ('A', 'C');

    Insert into Z_BOM2 (A, B) values ('C' ' d ' ");

    Insert into Z_BOM2 (A, B) values ('C', 'F');

    Insert into Z_BOM2 (A, B) values (', 'E');

    COMMIT;

    SELECT * FROM Z_BOM2;

    AB
    AC
    CD
    CF
    DE

    A is basically a Parent and B is a child.

    I would like to input not valid 'E' and 'F' in a query and get only the parents of high-level both those who should be 'A' for both of them. Here's the query I use:

    Select SYS_CONNECT_BY_PATH (, "/") as a path, a, CONNECT_BY_ISLEAF AS worksheet b, level, CONNECT_BY_ROOT b top_level

    of Z_BOM2

    connect by prior a = b

    Start with b IN ('E', 'F');


    Which returns the following:

    / DDE10E
    / D/CCD20E
    / C/D/A.AC31E
    / CCF10F
    / C/AAC21F

    Why it not return the appropriate top-level parent?

    This isn't my request.

    It is:

    select cbr the_parent, a the_child_you_started_with
    from (select a, b, level, connect_by_isleaf cbil, connect_by_root b cbr
    from z_bom2
    connect by prior a = b
    start with b in ('D'))
    where cbil = 1
    

    She returns B and has

  • In this improved version, the tabs went to the task bar very high, so erase my: I have no "file", "edit", "view","tools. "How to make a comeback?

    The area to open new tabs is now all up, thus doing away with the taskbar. "I have no"file","edit","view"," tools, "etc. How to make a comeback? Where did they go?

    With the orange Firefox button displays the menu bar is hidden, you can get the menu bar back quite easily. Right-click on a toolbar, and then click on the entrance to the "Menu bar" to view it.

  • How to acquire the signal to very high sampling frequency

    Hello world

    My name is Luke Ho. I am trying to acquire the signal with Labview (Sthelescope). The signal comes from sensor acoustics, then filters and amplifiers to adapt to ADC rank (0 - 5V). Thus, the maximum frequency of the signal is 40 kHz.

    According to the Nyquist theorem, I sampled at least 80 Khz signal.

    Is there a sampling frequency devices like that? or y at - it another way of better? I used the Arduino before, but it was about 10 kHz.

    I need your advice.
    Thank you all and have a nice day.

    holucbme wrote:

    Thanks for your recommendation

    But is it possible without USB Data Acquisition, it is quite expensive for me.

    This is the cheapest option to NEITHER. I tried to look for options to other companies, but more I found in the same price range, or not answering is not your condition of sample rate.

  • SG200 - 26 [FW - 1.1.2.0]-very high response time: > 1000 ms!

    Hello

    Problem: New SG - 200 26 Smart Switch with the latest Firmware - very high response time 500-800 ms

    We have a router of EdgeMarc 4500 with 10 VPN tunnels at 10 locations of brach. SG-200 26 Smart Switch is connected to 7 servers (Terminal 2, SQL and others), all locations have 50 MB download and download 20 MB of Verizon FiOS Internet service speed.

    Depending on the tool Kulvik, the response time of this switch is around 500ms. At the same time, the response time of the EdgeMarc 4500 router is around 40ms and less.

    We have 60 remote desktop computers connected to our SQL Server database and 40 users of RDP via Remote Desktop. The configuration is the same for 3 years. But we change the switch HP 1800 - 24G of Cisco because of some failures of connection. For connection failures, we first think the old switch from HP, but it looks like problem with router EdgeMarc.

    This response time is normal? I have attached two screenshots of Switch Cisco and response time for the past 24 hours EdgeMarc router according to the tool Kulvik. Any other advice would be greatly appreciated. Thank you.

    Hello Srinath,

    Thank you for your participation in the community of support to small businesses. My name is Nico Muselle of Cisco Sofia HWC.

    The response time of the switch can be considered quite normal. Reason for this is that the switch gives CPU priority to its actual tasks that would be sure to pass, lists of access, VLANs, QoS, multicast, and DHCP snooping etc etc. As a result, the switch itself ping response time does not show in any way the good operation of the switch.

    I invite to try the rattling customers connected to the switch, you should be able to notice that the response time to customers are much lower than the response time of the switch itself.

    I hope that answers your question!

    Best regards

    Nico glacier

    Senior Network Engineer - CCNA - CCNA security

  • Very high readings of temperature CPU of the Mac Pro 8-core 2007

    I have a Mac Pro 1.1 updated to level with two Intel Xeon X 5365 CPU and firmware 2.1. The system has worked very well for months. However, I'm worried about CPU temperature readings. Assuming that the readings are correct, I have no explanation for the difference in typical 30 degree Celsius between the processor and the heat sink.

    Is it possible, that the CPU exceeds their life expectancy?

    During a stress test, I can see the following typical readings:

    CPU core 87 C / 189 F

    CPU a heatsink 58 C / 136 F

    B processor 91 c/196 F

    CPU radiator B C 59/138 F

    I use new thermal paste Arctic MX-2 and tried various measures, including polishing of the surface of the CPU and the heatsink using sandpaper grain 1000. Nothing has so far had no effect on temperature readings. There should be enough good contact between the heatsink and processor during the installation, because they stick well enough to remove the heatsink again.

    Max TCASE. According to the operating temperature -1333 http://ark.intel.com/products/30702/Intel-Xeon-Processor-X5365-8M-Cache-3_00-GHz-MHz-FSB is 63 degrees Celsius.

    According to http://www.intel.com/content/dam/doc/design-guide/5400-chipset-memory-controller-moyeu-guidelines.pdf the Quad-Core Intel® Xeon® 5300 series include a function of on-chip temperature sensor. The heat sink provided by Apple has a temperature sensor, which seems to be fixed directly on the coper plate that touches the CPU head spreader.

    Given the following quote from the same document:

    TIM's performance is sensitive to degradation (e.g. breakdown of fat) over the life of the processor because of the temperature of the phenomena of cycling. For this reason, measuring of the processor given TCASE value can decrease over time according to the type of material of TIM.

    Anyone know if the IHS on the CPU is soldered or whether they used the thermal paste between the IHS and the die of a CPU? In the case, perhaps it could explain the current temperature readings.

    Any ideas? Thank you!

    Your temperatures look a bit high, but not outrageous. The temperature measured on the Silicon of heat will be always higher than the temperature measured on the radiator. That's what the radiator is supposed to do, leads away from the heat to the fins, which would measure even more cool.

    Your Mac allows to adjust speed of the fans to the top in a loop of feedback, founded the temperature of these measures. You can place a floor under your minimum speeds of fans. This can be done with the tool similar to some tool you already use, like the SMC fan control.

    If the processors to exceed their safe operation temperature, your Mac will perform a sudden uncontrolled power off.

  • Satellite L50 - B fan works even if the CPU load is very low

    I recently bought a Satellite L50 - B and I made a Windows 10 updated. The problem is that the fan works even if the CPU load is very low and the noise bothers me a lot.
    I ordered the video card driver and the system tells methat driver is updated to the latest version.
    I don't know what I can do to change this sad situation.
    Please, please, could you help me solve the problem?
    Thank you very much for your support and understanding.
    I await your quick response.
    Thank you.
    Giovanni Spina

    What CPU temp? Probably overheating?
    Try to replace the thermal interface on the CPU. ;-)

  • Very high CPU usage in svchost during playback of an event in a major newspaper of the events using WMI

    Hello

    I have a very high utilization of the processor in the process 'svchost.exe LocalServiceNetworkRestricted' during playback of an event in an event log in Windows 2008 64 SP02 using local or remote WMI.  The same happens using Wbemtest or C++ WMI code.  The use of WbemTest, "Open forum" (identical to one the GetObject of WMI API) read just one of recent events in the event log:

    Win32_NTLogEvent.logfile = "application", recordNumber = 2615657 (in this case, it was the id since the last event in the very large to the Application event log)

    takes 3/4 seconds consuming thant plus 50% of the monitored computer CPU.  This only occurs when the event log is very large (in my case 1 million records), the event log contains about 10000 events just fine.

    The problem is that I read the complete paper in a remote program and this product CPU usage charge too much CPU to the monitored computer.  I do not read the newspaper of the events one by one, but I'm using WQL queries but I do some GetObjects and the peformance is really terrible.

    Any idea what to change or search?

    Best regards

    Jordi

    Hi jordil,.

    Your question is more complex than what is generally answered in the Microsoft Answers forums. It is better suited for the IT Pro TechNet public.

    TechNet Windows Server general Forum

  • Port Replicator III + very high CPU when you move the usb mouse only in W2k

    Tecra M2 with a port replicator III +.

    It is set to dual boot XP and Windows 2000 (yes I know it is well a bit but I have a bunch of stuff installed in win2k it is difficult to find these days).

    XP is very good at 100%, but with win 2000 if I use my * USB mouse * on the * ports port replicator and waggle the mouse around - the * CPU * jumps from 0 to * 70 + % * use (System process that seems indicatates like IRQ problem). If I plug the mouse into the ports of the laptop (when the laptop is connected) - it's fine, no more than 5% cpu usage. It's a microsoft basic mouse. I really believe that this is a problem of usb any, because the cpu jumps a little if I type quickly on my usb keyboard (only a few %). It comes with the usb ports on all the Replicator.

    Any ideas? I don't really want to plug my mouse in the morning because it beats a little interest to have a docking station in the first place! I have installed mobile extensions. All other aspects of the replicator are fine

    Martin

    Huh it will not be easy to find the right explanation for this.
    At the moment when Tecra M2 has been offered on the market as Replicator port compatible Toshiba offered Toshiba Advanced Port Replicator III (no +) and at that time both supported in operating system has been tested with it.

    Toshiba later designed Toshiba Advanced Port Replicator III + and confirmed the compatibility with Tecra M2, but obviously with more recent WXP (at this time).
    So now, you've been following situation: you use most recent Replicator port, but with much older operating system so I assume that there may be a compatibility issue with W2K.

    I can't imagine use you so often with W2K and if so, may not be so problematic to connect the mouse directly on the cell s USB port.

    Sorry, but I don't think that there is nothing you can do about it.

  • Very low host CPU consumption

    Hi all.

    I have ESXi installed for the test on HP DC 7800 2x2.6 GHz C2D E6750, Im trying to install Windows Server 2008 x 64 on the Virtual Machine, and it takes a long time. IM wondering why during this installation the CPU use is if low, because his equal to about 300 MHz. I made a reservation about 1, 8 GHz, but it does not help...

    What wrong with my VMWare?

    Thamks for any help

    concerning

    Michal

    As I see, you have set up the 8 GB of RAM for VM and in fact, you only have 2 GB physical.

    Pwoer VM, change the settings of the virtual machine and allocates no more than 1 GB for VM.

    ---

    VMware vExpert 2009

    http://blog.vadmin.ru

  • CPU becomes very high - OS restart automatically - viruses?

    for 3 months, I have a problem with my cpu...
    the use of the cpu suddenly become very high and that's when I have access to the internet...
    the computer is just after this release out of control and the operating system automatically restarts from scratch, why is this?

    Hi Ryad,

    This behavior soiunds looks a lot like the Sasser worm that causes very heavy use of the CPU and causes also the PC restart regularly.

    You need start your computer in safe mode, and then run your antivirus software (I would also like to run your Malware software as well) to try to remove the virus. However, Sasser is not so easy to remove so please also consult the following URL: -.
    http://securityresponse.Symantec.com/avcenter/venc/data/W32.Sasser.removal.tool.html

    Kind regards

  • How high does the CPU for my system idle process?

    So far, my SIP is dragged through the years ninety superior. My CPU usage is very low, but the process window lists the CPU SIP between 93 and 99, and it is causing my PC just trolling. I know that the SIP is necessary for my system, but I don't know if there is something wrong or if it's just the time to invest in more RAM (I currently have 512MB). I am running Windows XP Home Edition with Service Pack 3.

    I also have a cooling fan which is the power of attraction of a USB connection. Not sure if this has something to do with it.

    the high SIP is NOT causing the lag. SIP in 90 s is normal. Upper SIP simply indicates that your CPU is idle. Its not to consume all the resources also made her by saying that it is a little too lazy, to do something :)

    The offset of the PC can be attributed to the lack of RAM or another software that is at the origin of the problem. I suggest you look at the column 'Memory' to see what process/app is devours RAM. To let us know. :)

    -L' learner, who sometimes writes about Microsoft & other stuff randomly http://beingmanan.com :)

  • Unique guest VM uses 100% of CPU Guest, but only 7% of the CPU host (includes screenshots)

    We have a Dell T420 ESXi 5.5 server.  The host has to a single UC E5-2407 (4 Core 2.2 GHz without Hyperthreading), 16 GB of RAM and RAID storage.

    The host runs a single VM Windows Server 2008, which was a P2V conversion.  The virtual machine is currently assigned 1 Plug and 4 Cores, corresponding to the host CPU.

    Since implementing this server about a year ago, he had a problem recurring pop up every few months.  When the problem occurs, the Server 2008 VM suddenly max use of the processor and the terrible performance, but CPU is be contributed to the maximum, not by a single program, but several normal processes.  For example, WMI, explorer.exe and the Task Manager may show all 30% CPU usage.  In the meantime, even if the guest virtual computer has 100% CPU usage, the host will show only using 300 to 500 MHz of CPU, or about 7% of available.  It comes despite the fact that it is the unique virtual machine and has full reign of all the resources of the host.  If the problem seems to be not with an abnormal load on the Guest VM, but less than the resources of the host.

    Restart the virtual machine does not correct the problem, and restart, which normally takes only a few minutes, lasts 30 minutes.  In the past, restart the ESXi host temporarily solved the problem, however it popup until today and persists even after several reboots of ESXi host.  See the attached screenshots for parameters and symptoms:

    ESXi CPU Problem 1.png

    It's the performance monitor virtual machine, whereas the problem that happens.  Notes on the virtual machine, Windows 2008 reports 100% of a core 2.2 GHz CPU 4 CPU usage, while the side host, the CPU usage never goes 626 MHz.

    ESXi CPU Problem 4.png

    Here are the counters of the State whereas the problem that happens.  When you start the virtual machine, the WAIT and SLOW counters were quite high, but they finally dip down when startup is complete.

    ESXi CPU Problem 2.png

    Here are the parameters and the stats of the ESXi host.

    ESXi CPU Problem 3.png

    Here are the parameters and the stats of the guest VM so that the problem that happens.

    Other troubleshooting steps:

    We changed number of vCPU on the VM from 4 to 1, without change.

    We put the CPU reserve for the VM to 50% and 100%, no change.

    The machine virtual was version 8 and we have updated to version 9, no change.

    Has anyone ever experience this problem?  Any help towards a solution would be appreciated.

    Hello

    I would say that it is somehow related to the fact that the VM was converted from physical server. Here are a few questions you should ask yourself:

    Type of CPU on the computer old physical host and VM match? At least seller of CPU? It goes the same for the chipset: are there different chipset vendor on the two hosts?

    What type of card NETWORK VM uses?

    Has uninstalled the drivers card mother/CPU specific converted VM? The VM tools are installed?

    Uninstall the old drivers of VM, currently they are not visible in the Device Manager here some is read: http://itknowledgeexchange.techtarget.com/virtualization-pro/removing-old-hardware-after-a-p2v-conversion/

    I would also check the BIOS of the server - maybe there is some sort of option for active energy that interfere with the VM?

  • Low utilization of the CPU, system hot, noisy fans

    My 2011 27 iMac mid has worked well. Here are the basics.

    The system has an SSD instead of a hard drive (therefore less heat than normal). I use the development system: it is not and has never had a lot of junk on it. About four weeks ago, the system started to run hot and the fan was strong while the CPU is about 99% vacuum. I have download the trial of TG Pro and the CPU seems

    "Load" in the photo below, which is less than 3%, is high normal baseline because I'm running TG Pro and activity monitor.

    The noise is very annoying and seems out of line for the load of the system.

    Someone has any practical suggestions or see obvious problems? (Until you point out 24 GB RAM and other fundamental issues, keep in mind that this system has been stable and performing normally in the current configuration for about nine months, save El Capitan updates).

    Resetting the SMC often with these problems reset management system (SCM) controller on your Mac - Apple Support

Maybe you are looking for