| 1 |
On Sun, Jul 26, 2020, at 11:21 PM, Adam Carter wrote: |
| 2 |
> On Mon, Jul 27, 2020 at 1:35 PM Ashley Dixon <ash@××××××××××.uk> wrote: |
| 3 |
> > On Mon, Jul 27, 2020 at 01:23:46PM +1000, Adam Carter wrote: |
| 4 |
> > > Having performance issues on a linux vmware guest that doesnt run vmtools |
| 5 |
> > > because its an 'appliance', but it does allow shell access. I assume CPU |
| 6 |
> > > utilisation shown by top etc is the utilisation of the vCPUs. Is there any |
| 7 |
> > > way to discover or infer host CPU issues? |
| 8 |
> > |
| 9 |
> > Do you mean that you want to monitor the host system from the guest? Can you not |
| 10 |
> > just SSH into the host from the guest? You can also infer CPU usage from the |
| 11 |
> > /proc/stat file on the host system, if you can share files over NFS or some |
| 12 |
> > other file-sharing means. |
| 13 |
> |
| 14 |
> I have ssh access (including root) to the guest but no access to the host. |
| 15 |
|
| 16 |
Compare realtime it to measured CPU time. If one realtime second is shorter than a |
| 17 |
CPU second then you know the host is pausing your VM. There are other ways to |
| 18 |
check, but this should always work if you can contact an asynchronous time standard. |
| 19 |
You may need to average the time over tens of seconds or a minute. |
| 20 |
|
| 21 |
This method will allow you to figure out that AWS spot instances are |
| 22 |
oversubscribed ~1.5x. |
Archives