Skip to content
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

Jump to bottom

MGMT-19360: do not monitor hosts with status installed #7030

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

MGMT-19360: do not monitor hosts with status installed #7030

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2c9eb39
MGMT-19360: do not monitor hosts with status installed
adriengentil Nov 26, 2024
01dc47a
exclude cancelled and error hosts from SQL
adriengentil Nov 26, 2024
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
50 changes: 25 additions & 25 deletions internal/host/monitor.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,13 +14,6 @@ import (
"gorm.io/gorm"
)

func (m *Manager) SkipMonitoring(h *models.Host) bool {
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

nice !!!

skipMonitoringStates := []string{string(models.LogsStateCompleted), string(models.LogsStateTimeout), ""}
result := ((swag.StringValue(h.Status) == models.HostStatusError || swag.StringValue(h.Status) == models.HostStatusCancelled) &&
funk.Contains(skipMonitoringStates, h.LogsInfo))
return result
}

func (m *Manager) initMonitoringQueryGenerator() {
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks great , do we have a unit-test for it? if yes lets push

if m.monitorClusterQueryGenerator == nil {
buildInitialQuery := func(db *gorm.DB) *gorm.DB {
Expand All @@ -35,14 +28,22 @@ func (m *Manager) initMonitoringQueryGenerator() {
models.HostStatusPreparingSuccessful,
models.HostStatusInstalling,
models.HostStatusInstallingInProgress,
models.HostStatusInstalled,
models.HostStatusInstallingPendingUserAction,
models.HostStatusResettingPendingUserAction,
models.HostStatusCancelled, // for limited time, until log collection finished or timed-out
models.HostStatusError, // for limited time, until log collection finished or timed-out
}

dbWithCondition := common.LoadTableFromDB(db, common.HostsTable, "status in (?)", monitorStates)
// monitor following states for limited time, until log collection finished or timed-out
monitorStatesUntilLogCollection := []string{
models.HostStatusCancelled,
models.HostStatusError,
}
logCollectionEndStates := []string{
string(models.LogsStateCompleted),
string(models.LogsStateTimeout),
"",
}

dbWithCondition := common.LoadTableFromDB(db, common.HostsTable, "status in (?) or (status in (?) and logs_info not in (?))", monitorStates, monitorStatesUntilLogCollection, logCollectionEndStates)
dbWithCondition = common.LoadClusterTablesFromDB(dbWithCondition, common.HostsTable)
dbWithCondition = dbWithCondition.Where("exists (select 1 from hosts where clusters.id = hosts.cluster_id)")
return dbWithCondition
Expand Down Expand Up @@ -165,21 +166,20 @@ func (m *Manager) clusterHostMonitoring() int64 {
m.log.Debugf("Not a leader, exiting cluster HostMonitoring")
return monitored
}
if !m.SkipMonitoring(host) {
monitored += 1
err = m.refreshStatusInternal(ctx, host, c, nil, inventoryCache, m.db)

monitored += 1
err = m.refreshStatusInternal(ctx, host, c, nil, inventoryCache, m.db)
if err != nil {
log.WithError(err).Errorf("failed to refresh host %s state", *host.ID)
}
//the refreshed role will be taken into account in the validations
//on the next monitor cycle. The roles will not be calculated until
//all the hosts in the cluster has inventory to avoid race condition
//with the reset auto-assign mechanism.
if canRefreshRoles {
err = m.refreshRoleInternal(ctx, host, m.db, false, swag.Int(int(expectedMasterCount)))
if err != nil {
log.WithError(err).Errorf("failed to refresh host %s state", *host.ID)
}
//the refreshed role will be taken into account in the validations
//on the next monitor cycle. The roles will not be calculated until
//all the hosts in the cluster has inventory to avoid race condition
//with the reset auto-assign mechanism.
if canRefreshRoles {
err = m.refreshRoleInternal(ctx, host, m.db, false, swag.Int(int(expectedMasterCount)))
if err != nil {
log.WithError(err).Errorf("failed to refresh host %s role", *host.ID)
}
log.WithError(err).Errorf("failed to refresh host %s role", *host.ID)
}
}
}
Expand Down