scripts: vsql certificate script recovery paths from the second review
ci / frontend (push) Successful in 41s
ci / server (push) Successful in 11m2s
ci / image (push) Successful in 57s
ci / e2e (push) Failing after 4m25s

- A rollback record now says which restarts succeeded. A snapshot stays open
  while an instance is unrestored or its restart failed (or was declined), so
  -Rollback -RestartInstances retries exactly those instead of reporting done
  or stepping back to an older deployment.
- Running dependents (SQL Server Agent) are written to dependents-<service>.json
  before the stop and removed once they run again, so a failed restart does not
  leave Agent stopped for good.
- GetRegValue returns $null only for a value confirmed absent; a missing key or
  read error throws, so it is never snapshotted or verified as absent.
- Instances come from the value names of Instance Names\SQL; the 'PS*' filter
  dropped names such as PSREPORTING.

Tests for each, including the real registry operations on an HKCU test key.
Pester green on PowerShell 7.6 (63) and Windows PowerShell 5.1 (62, 1 skipped).

Co-Authored-By: Claude Opus 5.5 <[email protected]>
This commit is contained in:
2026-10-18 21:50:34 -06:00
co-authored by Claude Opus 5.5
parent 90adcebc44
commit b7c22e1988
4 changed files with 204 additions and 39 deletions
@@ -84,6 +84,10 @@ BeforeAll {
IcaclsFail = $false
SetFails = @{} # regKey -> $true: Set-ItemProperty throws
SetIgnored = @{} # regKey -> $true: the write does not stick
ReadFails = @{} # regKey -> $true: reading throws (access denied)
Dependents = @{ 'MSSQLSERVER' = @('SQLSERVERAGENT'); 'MSSQL$DEV' = @('SQLAgent$DEV') }
Running = New-Object 'System.Collections.Generic.HashSet[string]' ([StringComparer]::OrdinalIgnoreCase)
RestartFails = @{} # service -> $true: stops it and its dependents, then fails to start
KeyFile = Join-Path $Work 'machinekey.bin'
ShouldProcess = $null
}
@@ -97,7 +101,11 @@ BeforeAll {
GetInstanceMap = { param($r) $fake.Instances }.GetNewClosure()
GetService = { param($n) [void]$fake.Calls.Add("GetService $n"); $fake.Services[$n] }.GetNewClosure()
TestRegKey = { param($k) $fake.Registry.ContainsKey($k) }.GetNewClosure()
GetRegValue = { param($k, $n) $v = $fake.Registry[$k]; if ($v.ContainsKey($n)) { [string]$v[$n] } else { $null } }.GetNewClosure()
GetRegValue = {
param($k, $n)
if ($fake.ReadFails[$k]) { throw "Requested registry access is not allowed: $k" }
$v = $fake.Registry[$k]; if ($v.ContainsKey($n)) { [string]$v[$n] } else { $null }
}.GetNewClosure()
SetRegValue = {
param($k, $n, $v)
[void]$fake.Calls.Add("SetReg $k $n=$v")
@@ -139,11 +147,21 @@ BeforeAll {
GetKeyInfo = { param($c) $k = & $realKeyInfo $c; if ($k) { $k.Machine = $true }; $k }.GetNewClosure()
KeyFilePath = { param($k) $fake.KeyFile }.GetNewClosure()
TestFile = { param($f) Test-Path -LiteralPath $f -PathType Leaf }
RestartService = { param($n) [void]$fake.Calls.Add("Restart $n"); @() }.GetNewClosure()
GetRunningDependents = { param($n) @($fake.Dependents[$n] | Where-Object { $fake.Running.Contains($_) }) }.GetNewClosure()
RestartService = {
param($n)
[void]$fake.Calls.Add("Restart $n")
foreach ($d in $fake.Dependents[$n]) { [void]$fake.Running.Remove($d) }
[void]$fake.Running.Remove($n)
if ($fake.RestartFails[$n]) { throw "Service '$n' cannot be started" }
[void]$fake.Running.Add($n)
}.GetNewClosure()
StartService = { param($n) [void]$fake.Calls.Add("Start $n"); [void]$fake.Running.Add($n) }.GetNewClosure()
Now = { Get-Date }
Log = { param($m) [void]$fake.Log.Add("$m") }.GetNewClosure()
ShouldProcess = $null
}
foreach ($svc in 'MSSQLSERVER', 'MSSQL$DEV', 'SQLSERVERAGENT', 'SQLAgent$DEV') { [void]$fake.Running.Add($svc) }
$fake.Provider = $p
return $fake
}
@@ -547,6 +565,106 @@ Describe 'Finding 6: rollback restores each instance on its own and verifies' {
}
}
Describe 'Second review: recovery paths' {
BeforeEach {
$f = New-FakeHost (Join-Path $TestDrive ([guid]::NewGuid()))
Add-ToStore $f $Good
$f.Registry[$KeyDefault].Certificate = 'aaaa'; $f.Registry[$KeyDev].Certificate = 'bbbb'
Invoke-VsqlCertificateDeployment -Provider $f.Provider -Thumbprint $Good.Thumbprint | Out-Null
$f.Calls.Clear()
}
It 'a rollback whose restart failed is retried, not skipped and not stepped past' {
$f.RestartFails['MSSQL$DEV'] = $true
{ Invoke-VsqlCertificateDeployment -Provider $f.Provider -Rollback -RestartInstances } | Should -Throw '*Rollback incomplete*MSSQL$DEV*'
$f.Registry[$KeyDev].Certificate | Should -Be 'bbbb'
$f.RestartFails.Clear()
$f.Calls.Clear()
$r = Invoke-VsqlCertificateDeployment -Provider $f.Provider -Rollback -RestartInstances
$r.Snapshot | Should -Not -BeNullOrEmpty
$r.Restarted | Should -Be @('DEV')
$f.Calls | Should -Contain 'Restart MSSQL$DEV'
$f.Calls | Should -Not -Contain 'Restart MSSQLSERVER'
$f.Registry[$KeyDev].Certificate | Should -Be 'bbbb'
# Now complete: nothing left to do.
(Invoke-VsqlCertificateDeployment -Provider $f.Provider -Rollback -RestartInstances).Snapshot | Should -BeNullOrEmpty
}
It 'a declined restart under -Confirm also stays open' {
$f.Provider.ShouldProcess = { param($t, $a) $a -notlike 'restart service*' -or $t -ne 'MSSQL$DEV' }
Invoke-VsqlCertificateDeployment -Provider $f.Provider -Rollback -RestartInstances | Out-Null
$f.Provider.ShouldProcess = $null
$r = Invoke-VsqlCertificateDeployment -Provider $f.Provider -Rollback -RestartInstances
$r.Restarted | Should -Be @('DEV')
}
It 'SQL Server Agent is started again after a failed restart is retried' {
$f.RestartFails['MSSQL$DEV'] = $true
{ Invoke-VsqlCertificateDeployment -Provider $f.Provider -Rollback -RestartInstances } | Should -Throw
$f.Running.Contains('SQLAgent$DEV') | Should -BeFalse
$depFile = Join-Path $f.Provider.WorkDir 'dependents-MSSQL_DEV.json'
(Get-Content $depFile -Raw | ConvertFrom-Json).services | Should -Be @('SQLAgent$DEV')
$f.RestartFails.Clear()
Invoke-VsqlCertificateDeployment -Provider $f.Provider -Rollback -RestartInstances | Out-Null
$f.Calls | Should -Contain 'Start SQLAgent$DEV'
$f.Running.Contains('SQLAgent$DEV') | Should -BeTrue
Test-Path $depFile | Should -BeFalse
}
It 'a successful restart starts the agent that ran and leaves no dependents file' {
Invoke-VsqlCertificateDeployment -Provider $f.Provider -Thumbprint $Good.Thumbprint -Instances MSSQLSERVER -RestartInstances | Out-Null
$f.Calls | Should -Contain 'Start SQLSERVERAGENT'
$f.Running.Contains('SQLSERVERAGENT') | Should -BeTrue
@(Get-ChildItem $f.Provider.WorkDir -Filter 'dependents-*.json') | Should -BeNullOrEmpty
}
It 'a registry read failure stops a deployment before any snapshot or change' {
Add-ToStore $f $Good2
$before = @(Get-Snapshots $f).Count
$f.ReadFails[$KeyDev] = $true
{ Invoke-VsqlCertificateDeployment -Provider $f.Provider -Thumbprint $Good2.Thumbprint } | Should -Throw '*not allowed*'
@($f.Calls | Where-Object { $_ -match '^(SetReg|RemoveReg)' }) | Should -BeNullOrEmpty
@(Get-Snapshots $f).Count | Should -Be $before
}
It 'a registry read failure during rollback is a failure, never verified as absent' {
$f.ReadFails[$KeyDev] = $true
{ Invoke-VsqlCertificateDeployment -Provider $f.Provider -Rollback } | Should -Throw '*Rollback incomplete*DEV*not allowed*'
$f.Log | Should -Not -Contain 'Restored DEV to bbbb (verified)'
}
}
Describe 'Real registry operations (HKCU test key)' {
BeforeAll {
$script:TestRoot = "HKCU:\Software\PS2-VSQL-CERT-TEST-$([guid]::NewGuid())"
New-Item -Path "$TestRoot\Instance Names\SQL" -Force | Out-Null
New-ItemProperty -Path "$TestRoot\Instance Names\SQL" -Name 'PSREPORTING' -Value 'MSSQL16.PSREPORTING' | Out-Null
New-ItemProperty -Path "$TestRoot\Instance Names\SQL" -Name 'DEV' -Value 'MSSQL16.DEV' | Out-Null
New-Item -Path "$TestRoot\Empty" -Force | Out-Null
New-ItemProperty -Path "$TestRoot\Empty" -Name 'Certificate' -Value '' | Out-Null
New-Item -Path "$TestRoot\Absent" -Force | Out-Null
$script:Real = Get-VsqlDefaultProvider
}
AfterAll { Remove-Item -LiteralPath $TestRoot -Recurse -Force }
It 'lists every instance, including one whose name starts with PS' {
$map = & $Real.GetInstanceMap $TestRoot
@($map.Keys) | Should -Be @('PSREPORTING', 'DEV')
$map['PSREPORTING'] | Should -Be 'MSSQL16.PSREPORTING'
}
It 'returns an empty map when no instance is registered' {
(& $Real.GetInstanceMap "$TestRoot\Absent").Count | Should -Be 0
}
It 'tells an empty value from an absent one' {
& $Real.GetRegValue "$TestRoot\Empty" 'Certificate' | Should -BeExactly ''
$null -eq (& $Real.GetRegValue "$TestRoot\Absent" 'Certificate') | Should -BeTrue
}
It 'throws, rather than reporting absent, when the key cannot be read' {
{ & $Real.GetRegValue "$TestRoot\Missing" 'Certificate' } | Should -Throw
}
It 'writes, reads back and removes through the real operations' {
& $Real.SetRegValue "$TestRoot\Absent" 'Certificate' 'abcd'
& $Real.GetRegValue "$TestRoot\Absent" 'Certificate' | Should -Be 'abcd'
& $Real.RemoveRegValue "$TestRoot\Absent" 'Certificate'
$null -eq (& $Real.GetRegValue "$TestRoot\Absent" 'Certificate') | Should -BeTrue
}
}
Describe '-WhatIf' {
It 'changes nothing on the real ShouldProcess path' {
$f = New-FakeHost (Join-Path $TestDrive 'whatif-real')