This browser is no longer supported.
Upgrade to Microsoft Edge to take advantage of the latest features, security updates, and technical support.
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(198.4, 33%, 29%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EC%3C/text%3E%3C/svg%3E)
We have a 5 node Windows Server 2016 Failover Cluster setup using an HPE Nimble as shared storage. We're using the cluster for Hyper-V. All virtual machine VHDXs are stored on the cluster shared volume (CSV).
We're having a problems with disk performance within VMs when the VM is running on a node which does not own the CSV storage.
Transferring files via SMB between VMs when they are both running on a node which owns the CSV speeds are between 1.5GB/s and 2GB/s. If you take the storage ownership away from that node, speeds drop to ~100MB/s.
This seems like the storage traffic is going via the 1GB network, through the owner node then into the SAN. From what I understand this shouldn't be the case unless the CSV has been set to redirected mode. (I've not confirmed this with Wireshark or anything yet, working on that)
I've run the command Get-ClusterSharedVolumeState which returned the following:
BlockRedirectedIOReason : NotBlockRedirected
FileSystemRedirectedIOReason : NotFileSystemRedirected
Name : Cluster Disk 1
Node : HyperV03
StateInfo : Direct
VolumeFriendlyName : VM-CSV
VolumeName : \?\Volume{9323278e-8374-474c-b9e7-1097305c0d1f}\BlockRedirectedIOReason : NotBlockRedirected
FileSystemRedirectedIOReason : NotFileSystemRedirected
Name : Cluster Disk 1
Node : Hyperv06
StateInfo : Direct
VolumeFriendlyName : VM-CSV
VolumeName : \?\Volume{9323278e-8374-474c-b9e7-1097305c0d1f}\BlockRedirectedIOReason : NotBlockRedirected
FileSystemRedirectedIOReason : NotFileSystemRedirected
Name : Cluster Disk 1
Node : hyperv05
StateInfo : Direct
VolumeFriendlyName : VM-CSV
VolumeName : \?\Volume{9323278e-8374-474c-b9e7-1097305c0d1f}\BlockRedirectedIOReason : NotBlockRedirected
FileSystemRedirectedIOReason : NotFileSystemRedirected
Name : Cluster Disk 1
Node : Hyperv04
StateInfo : Direct
VolumeFriendlyName : VM-CSV
VolumeName : \?\Volume{9323278e-8374-474c-b9e7-1097305c0d1f}\BlockRedirectedIOReason : NotBlockRedirected
FileSystemRedirectedIOReason : NotFileSystemRedirected
Name : Cluster Disk 1
Node : Hyperv02
StateInfo : Direct
VolumeFriendlyName : VM-CSV
VolumeName : \?\Volume{9323278e-8374-474c-b9e7-1097305c0d1f}\
According to this output redirection isn't the cause of the issue.
Can anyone think of a reason why else this might be happening?
Connections to the SAN have all been setup using HPE Windows Toolkit which configures the MPIO settings and various other bits for you. We've confirmed all nodes are able to hit transfers speeds of the expected 1GB/s+ but only when that node takes ownership of the CSV.
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(208, 40%, 30%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ERM%3C/text%3E%3C/svg%3E)
it's 11/2024 and I have this same issue on Datacenter 2022. All the money I spent on fast hardware, the flash based SAN that can do 25GB on each of its 4 ports at the same time, 100GB!!! and my 25GB Cisco switches, and everything else and my crappy MS cluster can only hit the speed of 125MB per NIC if it's a CSV (250/MB). If I mount as a regular drive I reach close to 2GB/s speeds and now I am adding 2 more NICs so I can try to reach 500MB when I should be hitting 4GB. This is terrible!
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(188.79999999999998, 96%, 28%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3ECL%3C/text%3E%3C/svg%3E)
I have the same issue and we are using windows 2019 DC version with 5 nodes clustering.
I ask the vendors to request Microsoft to provide the patch/fix but they replied it's by design and expected behaviour which i do not agreed with that. I still want the vendor to pursue this fix/patch with Microsoft
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(182.40000000000003, 82%, 27%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EGV%3C/text%3E%3C/svg%3E)
Hi there! I am also needing that answer. DId you got any feedback from MS and vendors?
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(147.20000000000002, 31%, 24%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EKT%3C/text%3E%3C/svg%3E)
Hi, I have an comparable issue.
We have 5 node cluster (Windows Server 2022 ) and while copying data to LUNs that are used as CSV we hit 480 MB/s (max output SSD). But when copying the same testdata to a LUN on same SAN which is connected as iSCSI target without being a CSV, the copyrates are twice as fast.
Any ideas why this happens, or how to fix this?
Best regards
KT
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(265.6, 15%, 35%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EJ%3C/text%3E%3C/svg%3E)
KT,
Are you running CrowdStrike or other security software on your clusters that watch your CSVs?
Jared
it's 11/2024 and I have this same issue on Datacenter 2022. All the money I spent on fast hardware, the flash based SAN that can do 25GB on each of its 4 ports at the same time, 100GB!!! and my 25GB Cisco switches, and everything else and my crappy MS cluster can only hit the speed of 125MB per NIC if it's a CSV (250/MB). If I mount as a regular drive I reach close to 2GB/s speeds and now I am adding 2 more NICs so I can try to reach 500MB when I should be hitting 4GB. This is terrible!