Describe the bug
Over-provisioning dosen't work properly with values smaller than 200%

To Reproduce
Steps to reproduce the behavior:

1. Set over-provisioning to 150%
2. Create volume larger than available volume size
3. "Replica Scheduling Failure"
4. Delete volume
5. Change over-provisioning to 200%
6. Repeat
7. Works properly

Expected behavior
Volume should be scheduled

Log

time="2021-08-30T11:49:30Z" level=error msg="There's no available disk for replica testowyxd-r-bef22a18, size 214748364800"
time="2021-08-30T11:49:30Z" level=error msg="unable to schedule replica" accessMode=rwo controller=longhorn-volume frontend=blockdev migratable=false node=k8s01n03 owner=k8s01n03 replica=testowyxd-r-bef22a18 state=detached volume=testowyxd

Environment:

• Longhorn version: v1.1.2
• Installation method (e.g. Rancher Catalog App/Helm/Kubectl): Helm
• Kubernetes distro (e.g. RKE/K3s/EKS/OpenShift) and version: RKE v1.19.10
  • Number of management node in the cluster: 2
  • Number of worker node in the cluster: 4
• Node config
  • OS type and version: Ubuntu 20.04
  • CPU per node: 8-64
  • Memory per node: 64-128GB
  • Disk type(e.g. SSD/NVMe): HDD on node where I requested a volume
  • Network bandwidth between the nodes: Gbit
• Underlying Infrastructure (e.g. on AWS/GCE, EKS/GKE, VMWare/KVM, Baremetal): Baremetal
• Number of Longhorn volumes in the cluster: 25

150%

200% - volume schedules properly