Skip to content

ENG-19808 mlxfwreset before reboot in SR-IOV operator #8

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
punkerpunker merged 2 commits into from
Feb 20, 2025
Merged

ENG-19808 mlxfwreset before reboot in SR-IOV operator #8

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f9ba0d3
bring reboots back
punkerpunker Feb 14, 2025
d4acb26
bring reboots back
punkerpunker Feb 14, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
98 changes: 48 additions & 50 deletions pkg/plugins/mellanox/mellanox_plugin.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -92,56 +92,54 @@ func (p *MellanoxPlugin) OnNodeStateChange(new *sriovnetworkv1.SriovNetworkNodeS
return
}

// for _, ifaceSpec := range mellanoxNicsSpec {
// pciPrefix := mlx.GetPciAddressPrefix(ifaceSpec.PciAddress)
// // skip processed nics, help not running the same logic 2 times for dual port NICs
// if _, ok := processedNics[pciPrefix]; ok {
// continue
// }
// processedNics[pciPrefix] = true
// fwCurrent, fwNext, err := p.helpers.GetMlxNicFwData(ifaceSpec.PciAddress)
// if err != nil {
// return false, false, err
// }

// // isDualPort := mlx.IsDualPort(ifaceSpec.PciAddress, mellanoxNicsStatus)
// // Attributes to change
// attrs := &mlx.MlxNic{TotalVfs: -1}
// var changeWithoutReboot bool

// // totalVfs, totalVfsNeedReboot, totalVfsChangeWithoutReboot := mlx.HandleTotalVfs(fwCurrent, fwNext, attrs, ifaceSpec, isDualPort, mellanoxNicsSpec)
// // sriovEnNeedReboot, sriovEnChangeWithoutReboot := mlx.HandleEnableSriov(totalVfs, fwCurrent, fwNext, attrs)
// // needReboot = totalVfsNeedReboot || sriovEnNeedReboot
// // changeWithoutReboot = totalVfsChangeWithoutReboot || sriovEnChangeWithoutReboot
// needReboot = false
// changeWithoutReboot = false

// needLinkChange, err := mlx.HandleLinkType(pciPrefix, fwCurrent, attrs, mellanoxNicsSpec, mellanoxNicsStatus)
// if err != nil {
// return false, false, err
// }
// needReboot = needReboot || needLinkChange

// // no FW changes allowed when NIC is externally managed
// if ifaceSpec.ExternallyManaged {
// // if totalVfsNeedReboot || totalVfsChangeWithoutReboot {
// // return false, false, fmt.Errorf(
// // "interface %s required a change in the TotalVfs but the policy is externally managed failing: firmware TotalVf %d requested TotalVf %d",
// // ifaceSpec.PciAddress, fwCurrent.TotalVfs, totalVfs)
// // }
// if needLinkChange {
// return false, false, fmt.Errorf("change required for link type but the policy is externally managed, failing")
// }
// }

// if needReboot || changeWithoutReboot {
// attributesToChange[ifaceSpec.PciAddress] = *attrs
// }

// if needReboot {
// pciAddressesToReset = append(pciAddressesToReset, ifaceSpec.PciAddress)
// }
// }
for _, ifaceSpec := range mellanoxNicsSpec {
pciPrefix := mlx.GetPciAddressPrefix(ifaceSpec.PciAddress)
// skip processed nics, help not running the same logic 2 times for dual port NICs
if _, ok := processedNics[pciPrefix]; ok {
continue
}
processedNics[pciPrefix] = true
fwCurrent, fwNext, err := p.helpers.GetMlxNicFwData(ifaceSpec.PciAddress)
if err != nil {
return false, false, err
}

isDualPort := mlx.IsDualPort(ifaceSpec.PciAddress, mellanoxNicsStatus)
// Attributes to change
attrs := &mlx.MlxNic{TotalVfs: -1}
var changeWithoutReboot bool

totalVfs, totalVfsNeedReboot, totalVfsChangeWithoutReboot := mlx.HandleTotalVfs(fwCurrent, fwNext, attrs, ifaceSpec, isDualPort, mellanoxNicsSpec)
sriovEnNeedReboot, sriovEnChangeWithoutReboot := mlx.HandleEnableSriov(totalVfs, fwCurrent, fwNext, attrs)
needReboot = totalVfsNeedReboot || sriovEnNeedReboot
changeWithoutReboot = totalVfsChangeWithoutReboot || sriovEnChangeWithoutReboot

needLinkChange, err := mlx.HandleLinkType(pciPrefix, fwCurrent, attrs, mellanoxNicsSpec, mellanoxNicsStatus)
if err != nil {
return false, false, err
}
needReboot = needReboot || needLinkChange

// no FW changes allowed when NIC is externally managed
if ifaceSpec.ExternallyManaged {
if totalVfsNeedReboot || totalVfsChangeWithoutReboot {
return false, false, fmt.Errorf(
"interface %s required a change in the TotalVfs but the policy is externally managed failing: firmware TotalVf %d requested TotalVf %d",
ifaceSpec.PciAddress, fwCurrent.TotalVfs, totalVfs)
}
if needLinkChange {
return false, false, fmt.Errorf("change required for link type but the policy is externally managed, failing")
}
}

if needReboot || changeWithoutReboot {
attributesToChange[ifaceSpec.PciAddress] = *attrs
}

if needReboot {
pciAddressesToReset = append(pciAddressesToReset, ifaceSpec.PciAddress)
}
}

// Set total VFs to 0 for mellanox interfaces with no spec
for pciPrefix, portsMap := range mellanoxNicsStatus {
Expand Down
Loading