Compare commits

...

3 Commits

Author SHA1 Message Date
Gabriel José Mouallem Rodrigues
8e4470317c
Merge eefb45ca5a into 25d72ce0a3 2026-03-18 09:12:43 +01:00
Marco Nenciarini
25d72ce0a3
fix(restore): race condition in parallel WAL restore spool (#812)
Some checks failed
release-please / release-please (push) Failing after 3s
Update github.com/cloudnative-pg/barman-cloud from the pre-release pin
(ced266c) to the official v0.5.0 release.

This update fixes a race condition in parallel WAL restore where
prefetched files could be read while still being downloaded, causing
PostgreSQL recovery to fail with "invalid checkpoint record" errors. It
also fixes a misleading "missing Azure credentials" error message when
no object store credentials are defined at all.

Signed-off-by: Marco Nenciarini <marco.nenciarini@enterprisedb.com>
2026-03-17 15:50:02 +01:00
Gabriel Jose Mouallem Rodrigues
eefb45ca5a fix: add retry logic to updateRecoveryWindow for concurrent status updates
When backup completion and retention policy enforcement run concurrently,
both call updateRecoveryWindow to update the ObjectStore status. This can
cause "object has been modified" errors due to Kubernetes optimistic
concurrency control.

This change wraps the status update in retry.RetryOnConflict, matching
the pattern already used in setLastFailedBackupTime in the same file.
The retry logic fetches a fresh copy of the ObjectStore before each
update attempt, ensuring the resourceVersion is current.

Fixes #758

Signed-off-by: Gabriel Mouallem <gabriel@latitude.sh>
2026-02-03 15:01:30 -03:00
3 changed files with 31 additions and 21 deletions

4
go.mod
View File

@ -7,7 +7,7 @@ toolchain go1.26.1
require (
github.com/cert-manager/cert-manager v1.19.4
github.com/cloudnative-pg/api v1.28.1
github.com/cloudnative-pg/barman-cloud v0.4.1-0.20260302035520-53b8620f1bd6
github.com/cloudnative-pg/barman-cloud v0.5.0
github.com/cloudnative-pg/cloudnative-pg v1.28.1
github.com/cloudnative-pg/cnpg-i v0.3.1
github.com/cloudnative-pg/cnpg-i-machinery v0.4.2
@ -117,7 +117,7 @@ require (
golang.org/x/net v0.49.0 // indirect
golang.org/x/oauth2 v0.34.0 // indirect
golang.org/x/sync v0.19.0 // indirect
golang.org/x/sys v0.41.0 // indirect
golang.org/x/sys v0.42.0 // indirect
golang.org/x/term v0.39.0 // indirect
golang.org/x/text v0.33.0 // indirect
golang.org/x/time v0.14.0 // indirect

8
go.sum
View File

@ -18,8 +18,8 @@ github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UF
github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
github.com/cloudnative-pg/api v1.28.1 h1:hp/TDgR+RrTa4EMp/pAKZia+kZ52i8ZPLG+JG10eeVU=
github.com/cloudnative-pg/api v1.28.1/go.mod h1:J0RTwrOYxQP17N1YMrDxcUmr/0wPYHQW179P7ibkVsM=
github.com/cloudnative-pg/barman-cloud v0.4.1-0.20260302035520-53b8620f1bd6 h1:BpKKrciaTMC01jMgwWOosC/S8pvDFCxZdJx2ahzksIQ=
github.com/cloudnative-pg/barman-cloud v0.4.1-0.20260302035520-53b8620f1bd6/go.mod h1:N/ax2XSnj67scfJ9iFXKxCRMLFghD9B2XX5/SrRsPys=
github.com/cloudnative-pg/barman-cloud v0.5.0 h1:DykSaX4o7ee2vyu5FQoG1RJsntHd+EIttIKZbJPlB1Q=
github.com/cloudnative-pg/barman-cloud v0.5.0/go.mod h1:SO2HzLa+GWlSIpGyxnISoJAFPIcaa/qDa33Bb3jefac=
github.com/cloudnative-pg/cloudnative-pg v1.28.1 h1:HdOUWgFhta558uHfXeO/199qCApxaj5yi05x6nWNmgs=
github.com/cloudnative-pg/cloudnative-pg v1.28.1/go.mod h1:yhRa4GqJAjNd0tT9AiRgk1KdqLhMjo/JmGGoASRl2CU=
github.com/cloudnative-pg/cnpg-i v0.3.1 h1:fKj8NoToWI11HUL2UWYJBpkVzmaTvbs3kDMo7wQF8RU=
@ -277,8 +277,8 @@ golang.org/x/oauth2 v0.34.0 h1:hqK/t4AKgbqWkdkcAeI8XLmbK+4m4G5YeQRrmiotGlw=
golang.org/x/oauth2 v0.34.0/go.mod h1:lzm5WQJQwKZ3nwavOZ3IS5Aulzxi68dUSgRHujetwEA=
golang.org/x/sync v0.19.0 h1:vV+1eWNmZ5geRlYjzm2adRgW2/mcpevXNg50YZtPCE4=
golang.org/x/sync v0.19.0/go.mod h1:9KTHXmSnoGruLpwFjVSX0lNNA75CykiMECbovNTZqGI=
golang.org/x/sys v0.41.0 h1:Ivj+2Cp/ylzLiEU89QhWblYnOE9zerudt9Ftecq2C6k=
golang.org/x/sys v0.41.0/go.mod h1:OgkHotnGiDImocRcuBABYBEXf8A9a87e/uXjp9XT3ks=
golang.org/x/sys v0.42.0 h1:omrd2nAlyT5ESRdCLYdm3+fMfNFE/+Rf4bDIQImRJeo=
golang.org/x/sys v0.42.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw=
golang.org/x/term v0.39.0 h1:RclSuaJf32jOqZz74CkPA9qFuVTX7vhLlpfj/IGWlqY=
golang.org/x/term v0.39.0/go.mod h1:yxzUCTP/U+FzoxfdKmLaA0RV1WgE0VY7hXBwKtY/4ww=
golang.org/x/text v0.33.0 h1:B3njUFyqtHDUI5jMn1YIr5B0IE2U0qck04r6d4KPAxE=

View File

@ -33,7 +33,8 @@ import (
)
// updateRecoveryWindow updates the recovery window inside the object
// store status subresource
// store status subresource. It uses retry logic to handle concurrent
// updates from backup completion and retention policy enforcement.
func updateRecoveryWindow(
ctx context.Context,
c client.Client,
@ -41,6 +42,14 @@ func updateRecoveryWindow(
objectStore *barmancloudv1.ObjectStore,
serverName string,
) error {
objectStoreKey := client.ObjectKeyFromObject(objectStore)
return retry.RetryOnConflict(retry.DefaultBackoff, func() error {
var freshObjectStore barmancloudv1.ObjectStore
if err := c.Get(ctx, objectStoreKey, &freshObjectStore); err != nil {
return err
}
// Set the recovery window inside the barman object store object
convertTime := func(t *time.Time) *metav1.Time {
if t == nil {
@ -49,16 +58,17 @@ func updateRecoveryWindow(
return ptr.To(metav1.NewTime(*t))
}
recoveryWindow := objectStore.Status.ServerRecoveryWindow[serverName]
recoveryWindow := freshObjectStore.Status.ServerRecoveryWindow[serverName]
recoveryWindow.FirstRecoverabilityPoint = convertTime(backupList.GetFirstRecoverabilityPoint())
recoveryWindow.LastSuccessfulBackupTime = convertTime(backupList.GetLastSuccessfulBackupTime())
if objectStore.Status.ServerRecoveryWindow == nil {
objectStore.Status.ServerRecoveryWindow = make(map[string]barmancloudv1.RecoveryWindow)
if freshObjectStore.Status.ServerRecoveryWindow == nil {
freshObjectStore.Status.ServerRecoveryWindow = make(map[string]barmancloudv1.RecoveryWindow)
}
objectStore.Status.ServerRecoveryWindow[serverName] = recoveryWindow
freshObjectStore.Status.ServerRecoveryWindow[serverName] = recoveryWindow
return c.Status().Update(ctx, objectStore)
return c.Status().Update(ctx, &freshObjectStore)
})
}
// setLastFailedBackupTime sets the last failed backup time in the