better error when peer selection fails (#3342)

* better error when peer selection fails

It is pretty hard to diagnose what went wrong when not enough peers for
an operation where found. This change now returns counts of reasons why
peers where discarded.

Changed the error to JSClusterNoPeers as it seems more appropriate
of an error for that operation. Not having enough resources is one of
the conditions for a peer not being considered. But so is having a non
matching tag. Which is why JSClusterNoPeers seems more appropriate
In addition, JSClusterNoPeers was already used as error after one call
to selectPeerGroup already.

example:
no suitable peers for placement: peer selection cluster 'C' with 3 peers
offline: 0
excludeTag: 1
noTagMatch: 2
noSpace: 0
uniqueTag: 0
misc: 0

Examle for mqtt:
mid:12 - "mqtt" - unable to connect: create sessions stream for account "$G":
no suitable peers for placement: peer selection cluster 'MQTT' with 3 peers
        offline: 0
        excludeTag: 0
        noTagMatch: 0
        noSpace: 0
        uniqueTag: 0
        misc: 0
         (10005)

Signed-off-by: Matthias Hanel <mh@synadia.com>

* review comment

Signed-off-by: Matthias Hanel <mh@synadia.com>
This commit is contained in:
Matthias Hanel
2022-08-06 00:17:01 +02:00
committed by GitHub
parent b927b228fc
commit 52c4872666
8 changed files with 148 additions and 67 deletions

View File

@@ -180,7 +180,7 @@ func TestJetStreamSuperClusterUniquePlacementTag(t *testing.T) {
si, err := js.AddStream(&nats.StreamConfig{Name: name, Replicas: test.replicas, Placement: test.placement})
if test.fail {
require_Error(t, err)
require_Equal(t, err.Error(), "insufficient resources")
require_Contains(t, err.Error(), "no suitable peers for placement")
return
}
require_NoError(t, err)
@@ -848,8 +848,8 @@ func TestJetStreamSuperClusterLeafNodesWithSharedSystemAccountAndDifferentDomain
Replicas: 2,
Placement: &nats.Placement{Cluster: pcn},
})
if err == nil || !strings.Contains(err.Error(), "insufficient resources") {
t.Fatalf("Expected insufficient resources, got: %v", err)
if err == nil || !strings.Contains(err.Error(), "no suitable peers for placement") {
t.Fatalf("Expected no suitable peers for placement, got: %v", err)
}
}
@@ -1380,8 +1380,7 @@ func TestJetStreamSuperClusterOverflowPlacement(t *testing.T) {
MaxBytes: 2 * 1024 * 1024 * 1024,
Placement: &nats.Placement{Cluster: pcn},
})
require_Error(t, err, NewJSInsufficientResourcesError(), NewJSStorageResourcesExceededError())
require_Contains(t, err.Error(), "no suitable peers for placement")
// Now test actual overflow placement. So try again with no placement designation.
// This will test the peer picker's logic since they are updated at this point and the meta leader
// knows it can not place it in C2.
@@ -1497,7 +1496,7 @@ func TestJetStreamSuperClusterStreamTagPlacement(t *testing.T) {
Subjects: []string{"foo"},
Placement: &nats.Placement{Tags: tags},
})
require_Error(t, err, NewJSInsufficientResourcesError())
require_Contains(t, err.Error(), "no suitable peers for placement")
}
placeErr("C1", []string{"cloud:GCP", "country:US"})
@@ -2381,7 +2380,8 @@ func TestJetStreamSuperClusterMaxHaAssets(t *testing.T) {
waitStatsz(3, 1)
_, err = js.AddStream(&nats.StreamConfig{Name: "S3", Replicas: 3, Placement: &nats.Placement{Cluster: "C1"}})
require_Error(t, err)
require_Equal(t, err.Error(), "insufficient resources")
require_Contains(t, err.Error(), "no suitable peers for placement")
require_Contains(t, err.Error(), "misc: 3")
require_NoError(t, js.DeleteStream("S1"))
waitStatsz(3, 2)
waitStatsz(3, 1)
@@ -2414,7 +2414,8 @@ func TestJetStreamSuperClusterMaxHaAssets(t *testing.T) {
require_Equal(t, err.Error(), "insufficient resources")
_, err = js.UpdateStream(&nats.StreamConfig{Name: "S2", Replicas: 3, Placement: &nats.Placement{Cluster: "C2"}})
require_Error(t, err)
require_Equal(t, err.Error(), "insufficient resources")
require_Contains(t, err.Error(), "no suitable peers for placement")
require_Contains(t, err.Error(), "misc: 3")
}
func TestJetStreamSuperClusterStreamAlternates(t *testing.T) {