How many and how large VMs we are talking about here ?
What troubleshooting steps /analysis have you performed till now ?
6x VMs - varying no. of CPUs from 6 to 14, varying memory from 64GB to 128GB, i.e. large VMs.
I've tinkered with NTP till the cows come home, I've increased CPU shares to HIGH for all of these VMs.
I've not tried to reserve CPU yet, or disabled NTP and tried sync'ing through Tools.
Need some more insight into the affected VMs as my initial guess is that your issue maybe due to snapshot since only 6 VMs are facing the issue.
1. Since when you are facing the NTP issue ?
2. Around the time as per ques 1, any changes in VMs/backup/storage infrastructure made ?
3. Total size of each VM w.r.t disk?
4. Any active or manual snapshot on VMs before backup snapshot process starts ?
5. What is the stun time for each VM when snapshot process occurs (when VM is not accessible over network) ?
6. What's the underlying storage type for these VMs? HDD or SSD ?
Think I'm gonna try this option....only problem is it's a power off of VM.
Maintenance window here I come!