mirror of
https://github.com/replicatedhq/troubleshoot.git
synced 2026-04-15 07:16:34 +00:00
* Add collect command and remote host collectors
Adds the ability to run a host collector on a set of remote k8s nodes.
Target nodes can be filtered using the --selector flag, with the same
syntax as kubectl. Existing flags for --collector-image,
--collector-pullpolicy and --request-timeout are used. To run on a
specified node, --selector="kubernetes.io/hostname=kind-worker2" could
be used.
The collect command is used by the remote collector to output the
results using a "raw" format, which uses the filename as the key, and
the value the output as a escaped json string. When run manually it
defaults to fully decoded json. The existing block devices,
ipv4interfaces and services host collectors don't decode properly - the
fix is to convert their slice output to a map (fix not included as
unsure what depends on the existing format).
The collect command is also useful for troubleshooting preflight issues.
Examples are included to show remote collector usage.
```
bin/collect --collector-image=croomes/troubleshoot:latest examples/collect/remote/memory.yaml --namespace test
{
"kind-control-plane": {
"system/memory.json": {
"total": 1304207360
}
},
"kind-worker": {
"system/memory.json": {
"total": 1695780864
}
},
"kind-worker2": {
"system/memory.json": {
"total": 1726353408
}
}
}
```
The preflight command has been updated to run remote collectors. To run
a host collector remotely it must be specified in the spec as a
`remoteCollector`:
```
apiVersion: troubleshoot.sh/v1beta2
kind: HostPreflight
metadata:
name: memory
spec:
remoteCollectors:
- memory:
collectorName: memory
analyzers:
- memory:
outcomes:
- fail:
when: "< 8Gi"
message: At least 8Gi of memory is required
- warn:
when: "< 32Gi"
message: At least 32Gi of memory is recommended
- pass:
message: The system has as sufficient memory
```
Results for each node are analyzed separately, with the node name
appended to the title:
```
bin/preflight --interactive=false --collector-image=croomes/troubleshoot:latest examples/preflight/remote/memory.yaml --format=json
{memory running 0 1}
{memory completed 1 1}
{
"fail": [
{
"title": "Amount of Memory (kind-worker2)",
"message": "At least 8Gi of memory is required"
},
{
"title": "Amount of Memory (kind-worker)",
"message": "At least 8Gi of memory is required"
},
{
"title": "Amount of Memory (kind-control-plane)",
"message": "At least 8Gi of memory is required"
}
]
}
```
Also added a host collector to allow preflight checks of required kernel
modules, which is the main driver for this change.
167 lines
4.0 KiB
Go
167 lines
4.0 KiB
Go
package collect
|
|
|
|
import (
|
|
"reflect"
|
|
"testing"
|
|
|
|
"github.com/pkg/errors"
|
|
troubleshootv1beta2 "github.com/replicatedhq/troubleshoot/pkg/apis/troubleshoot/v1beta2"
|
|
)
|
|
|
|
type mockKernelModulesCollector struct {
|
|
result map[string]KernelModuleInfo
|
|
err error
|
|
}
|
|
|
|
func (m mockKernelModulesCollector) collect() (map[string]KernelModuleInfo, error) {
|
|
if m.err != nil {
|
|
return nil, m.err
|
|
}
|
|
return m.result, nil
|
|
}
|
|
|
|
var testKernelModuleErr = errors.New("error collecting modules")
|
|
|
|
func TestCollectHostKernelModules_Collect(t *testing.T) {
|
|
tests := []struct {
|
|
name string
|
|
hostCollector *troubleshootv1beta2.HostKernelModules
|
|
loadable kernelModuleCollector
|
|
loaded kernelModuleCollector
|
|
want map[string][]byte
|
|
wantErr bool
|
|
}{
|
|
{
|
|
name: "loadable",
|
|
loadable: mockKernelModulesCollector{
|
|
result: map[string]KernelModuleInfo{
|
|
"first": {
|
|
Status: KernelModuleLoadable,
|
|
},
|
|
"second": {
|
|
Status: KernelModuleLoadable,
|
|
},
|
|
},
|
|
},
|
|
loaded: mockKernelModulesCollector{},
|
|
want: map[string][]byte{
|
|
"system/kernel_modules.json": []byte("{\"first\":{\"size\":0,\"instances\":0,\"status\":\"loadable\"},\"second\":{\"size\":0,\"instances\":0,\"status\":\"loadable\"}}"),
|
|
},
|
|
},
|
|
{
|
|
name: "loaded",
|
|
loadable: mockKernelModulesCollector{},
|
|
loaded: mockKernelModulesCollector{
|
|
result: map[string]KernelModuleInfo{
|
|
"first": {
|
|
Status: KernelModuleLoaded,
|
|
Size: 10,
|
|
Instances: 2,
|
|
},
|
|
"second": {
|
|
Status: KernelModuleLoading,
|
|
},
|
|
},
|
|
},
|
|
want: map[string][]byte{
|
|
"system/kernel_modules.json": []byte("{\"first\":{\"size\":10,\"instances\":2,\"status\":\"loaded\"},\"second\":{\"size\":0,\"instances\":0,\"status\":\"loading\"}}"),
|
|
},
|
|
},
|
|
{
|
|
name: "loaded and unloaded",
|
|
loadable: mockKernelModulesCollector{
|
|
result: map[string]KernelModuleInfo{
|
|
"first": {
|
|
Status: KernelModuleLoadable,
|
|
},
|
|
"second": {
|
|
Status: KernelModuleLoadable,
|
|
},
|
|
},
|
|
},
|
|
loaded: mockKernelModulesCollector{
|
|
result: map[string]KernelModuleInfo{
|
|
"first": {
|
|
Status: KernelModuleLoaded,
|
|
Size: 10,
|
|
Instances: 2,
|
|
},
|
|
},
|
|
},
|
|
want: map[string][]byte{
|
|
"system/kernel_modules.json": []byte("{\"first\":{\"size\":10,\"instances\":2,\"status\":\"loaded\"},\"second\":{\"size\":0,\"instances\":0,\"status\":\"loadable\"}}"),
|
|
},
|
|
},
|
|
{
|
|
name: "loaded error",
|
|
loadable: mockKernelModulesCollector{
|
|
result: map[string]KernelModuleInfo{
|
|
"first": {
|
|
Status: KernelModuleLoadable,
|
|
},
|
|
"second": {
|
|
Status: KernelModuleLoadable,
|
|
},
|
|
},
|
|
},
|
|
loaded: mockKernelModulesCollector{
|
|
err: testKernelModuleErr,
|
|
},
|
|
wantErr: true,
|
|
},
|
|
{
|
|
name: "loadable error",
|
|
loadable: mockKernelModulesCollector{
|
|
err: testKernelModuleErr,
|
|
},
|
|
loaded: mockKernelModulesCollector{
|
|
result: map[string]KernelModuleInfo{
|
|
"first": {
|
|
Status: KernelModuleLoaded,
|
|
Size: 10,
|
|
Instances: 2,
|
|
},
|
|
"second": {
|
|
Status: KernelModuleLoading,
|
|
},
|
|
},
|
|
},
|
|
wantErr: true,
|
|
},
|
|
{
|
|
name: "both error",
|
|
loadable: mockKernelModulesCollector{
|
|
err: testKernelModuleErr,
|
|
},
|
|
loaded: mockKernelModulesCollector{
|
|
err: testKernelModuleErr,
|
|
},
|
|
wantErr: true,
|
|
},
|
|
}
|
|
for _, tt := range tests {
|
|
t.Run(tt.name, func(t *testing.T) {
|
|
c := &CollectHostKernelModules{
|
|
hostCollector: tt.hostCollector,
|
|
loadable: tt.loadable,
|
|
loaded: tt.loaded,
|
|
}
|
|
progressCh := make(chan interface{})
|
|
defer close(progressCh)
|
|
go func() {
|
|
for _ = range progressCh {
|
|
}
|
|
}()
|
|
|
|
got, err := c.Collect(progressCh)
|
|
if (err != nil) != tt.wantErr {
|
|
t.Errorf("CollectHostKernelModules.Collect() error = %v, wantErr %v", err, tt.wantErr)
|
|
return
|
|
}
|
|
if !reflect.DeepEqual(got, tt.want) {
|
|
t.Errorf("CollectHostKernelModules.Collect() = \n%v, want \n%v", got, tt.want)
|
|
}
|
|
})
|
|
}
|
|
}
|