Merge remote-tracking branch 'origin/master' into fix/ceph_remove_osd

Reviewed-on: #121
Reviewed-by: johnride <jg@nationtech.io>

Cargo.lock

@@ -4255,6 +4255,15 @@ version = "0.8.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2b15c43186be67a4fd63bee50d0303afffcef381492ebe2c5d87f324e1b8815c"
 
+[[package]]
+name = "remove_rook_osd"
+version = "0.1.0"
+dependencies = [
+ "harmony",
+ "harmony_cli",
+ "tokio",
+]
+
 [[package]]
 name = "reqwest"
 version = "0.11.27"

examples/remove_rook_osd/Cargo.toml

@@ -0,0 +1,11 @@
+[package]
+name = "example-remove-rook-osd"
+edition = "2024"
+version.workspace = true
+readme.workspace = true
+license.workspace = true
+
+[dependencies]
+harmony = { version = "0.1.0", path = "../../harmony" }
+harmony_cli = { version = "0.1.0", path = "../../harmony_cli" }
+tokio.workspace = true

examples/remove_rook_osd/src/main.rs

@@ -0,0 +1,18 @@
+use harmony::{
+    inventory::Inventory, modules::storage::ceph::ceph_remove_osd_score::CephRemoveOsd,
+    topology::K8sAnywhereTopology,
+};
+
+#[tokio::main]
+async fn main() {
+    let ceph_score = CephRemoveOsd {
+        osd_deployment_name: "rook-ceph-osd-2".to_string(),
+        rook_ceph_namespace: "rook-ceph".to_string(),
+    };
+
+    let topology = K8sAnywhereTopology::from_env();
+    let inventory = Inventory::autoload();
+    harmony_cli::run(inventory, topology, vec![Box::new(ceph_score)], None)
+        .await
+        .unwrap();
+}

examples/validate_ceph_cluster_health/Cargo.toml

@@ -0,0 +1,11 @@
+[package]
+name = "example_validate_ceph_cluster_health"
+edition = "2024"
+version.workspace = true
+readme.workspace = true
+license.workspace = true
+
+[dependencies]
+harmony = { version = "0.1.0", path = "../../harmony" }
+harmony_cli = { version = "0.1.0", path = "../../harmony_cli" }
+tokio.workspace = true

examples/validate_ceph_cluster_health/src/main.rs

@@ -0,0 +1,18 @@
+use harmony::{
+    inventory::Inventory,
+    modules::storage::ceph::ceph_validate_health_score::CephVerifyClusterHealth,
+    topology::K8sAnywhereTopology,
+};
+
+#[tokio::main]
+async fn main() {
+    let ceph_health_score = CephVerifyClusterHealth {
+        rook_ceph_namespace: "rook-ceph".to_string(),
+    };
+
+    let topology = K8sAnywhereTopology::from_env();
+    let inventory = Inventory::autoload();
+    harmony_cli::run(inventory, topology, vec![Box::new(ceph_health_score)], None)
+        .await
+        .unwrap();
+}

harmony/src/domain/interpret/mod.rs

@@ -32,6 +32,8 @@ pub enum InterpretName {
     Lamp,
     ApplicationMonitoring,
     K8sPrometheusCrdAlerting,
+    CephRemoveOsd,
+    CephClusterHealth,
 }
 
 impl std::fmt::Display for InterpretName {
@@ -58,6 +60,8 @@ impl std::fmt::Display for InterpretName {
             InterpretName::Lamp => f.write_str("LAMP"),
             InterpretName::ApplicationMonitoring => f.write_str("ApplicationMonitoring"),
             InterpretName::K8sPrometheusCrdAlerting => f.write_str("K8sPrometheusCrdAlerting"),
+            InterpretName::CephRemoveOsd => f.write_str("CephRemoveOsd"),
+            InterpretName::CephClusterHealth => f.write_str("CephClusterHealth"),
         }
     }
 }

harmony/src/domain/topology/k8s.rs

@@ -15,7 +15,7 @@ use kube::{
     api::{ApiResource, GroupVersionKind},
     runtime::wait::await_condition,
 };
-use log::{debug, error, trace};
+use log::{debug, error, info, trace};
 use serde::{Serialize, de::DeserializeOwned};
 use serde_json::json;
 use similar::TextDiff;
@@ -59,10 +59,13 @@ impl K8sClient {
         namespace: Option<&str>,
     ) -> Result<Option<Deployment>, Error> {
         let deps: Api<Deployment> = if let Some(ns) = namespace {
+            debug!("getting namespaced deployment");
             Api::namespaced(self.client.clone(), ns)
         } else {
+            debug!("getting default namespace deployment");
             Api::default_namespaced(self.client.clone())
         };
+        debug!("getting deployment {} in ns {}", name, namespace.unwrap());
         Ok(deps.get_opt(name).await?)
     }
 
@@ -93,7 +96,7 @@ impl K8sClient {
             }
         });
         let pp = PatchParams::default();
-        let scale = Patch::Apply(&patch);
+        let scale = Patch::Merge(&patch);
         deployments.patch_scale(name, &pp, &scale).await?;
         Ok(())
     }

harmony/src/modules/storage/ceph/ceph_remove_osd_score.rs

@@ -1,11 +1,10 @@
 use std::{
-    process::Command,
     sync::Arc,
     time::{Duration, Instant},
 };
 
 use async_trait::async_trait;
-use log::{info, warn};
+use log::{debug, warn};
 use serde::{Deserialize, Serialize};
 use tokio::time::sleep;
 
@@ -19,8 +18,8 @@ use crate::{
 
 #[derive(Debug, Clone, Serialize)]
 pub struct CephRemoveOsd {
-    osd_deployment_name: String,
-    rook_ceph_namespace: String,
+    pub osd_deployment_name: String,
+    pub rook_ceph_namespace: String,
 }
 
 impl<T: Topology + K8sclient> Score<T> for CephRemoveOsd {
@@ -54,18 +53,17 @@ impl<T: Topology + K8sclient> Interpret<T> for CephRemoveOsdInterpret {
         self.verify_deployment_scaled(client.clone()).await?;
         self.delete_deployment(client.clone()).await?;
         self.verify_deployment_deleted(client.clone()).await?;
-        let osd_id_full = self.get_ceph_osd_id().unwrap();
-        self.purge_ceph_osd(client.clone(), &osd_id_full).await?;
-        self.verify_ceph_osd_removal(client.clone(), &osd_id_full)
-            .await?;
+        self.purge_ceph_osd(client.clone()).await?;
+        self.verify_ceph_osd_removal(client.clone()).await?;
 
+        let osd_id_full = self.get_ceph_osd_id().unwrap();
         Ok(Outcome::success(format!(
             "Successfully removed OSD {} from rook-ceph cluster by deleting deployment {}",
             osd_id_full, self.score.osd_deployment_name
         )))
     }
     fn get_name(&self) -> InterpretName {
-        todo!()
+        InterpretName::CephRemoveOsd
     }
 
     fn get_version(&self) -> Version {
@@ -82,7 +80,7 @@ impl<T: Topology + K8sclient> Interpret<T> for CephRemoveOsdInterpret {
 }
 
 impl CephRemoveOsdInterpret {
-    pub fn get_ceph_osd_id(&self) -> Result<String, InterpretError> {
+    pub fn get_ceph_osd_id_numeric(&self) -> Result<String, InterpretError> {
         let osd_id_numeric = self
             .score
             .osd_deployment_name
@@ -94,9 +92,14 @@ impl CephRemoveOsdInterpret {
                     self.score.osd_deployment_name
                 ))
             })?;
+        Ok(osd_id_numeric.to_string())
+    }
+
+    pub fn get_ceph_osd_id(&self) -> Result<String, InterpretError> {
+        let osd_id_numeric = self.get_ceph_osd_id_numeric().unwrap();
         let osd_id_full = format!("osd.{}", osd_id_numeric);
 
-        info!(
+        debug!(
             "Targeting Ceph OSD: {} (parsed from deployment {})",
             osd_id_full, self.score.osd_deployment_name
         );
@@ -108,6 +111,7 @@ impl CephRemoveOsdInterpret {
         &self,
         client: Arc<K8sClient>,
     ) -> Result<Outcome, InterpretError> {
+        debug!("verifying toolbox exists");
         let toolbox_dep = "rook-ceph-tools".to_string();
 
         match client
@@ -149,7 +153,7 @@ impl CephRemoveOsdInterpret {
         &self,
         client: Arc<K8sClient>,
     ) -> Result<Outcome, InterpretError> {
-        info!(
+        debug!(
             "Scaling down OSD deployment: {}",
             self.score.osd_deployment_name
         );
@@ -172,7 +176,7 @@ impl CephRemoveOsdInterpret {
     ) -> Result<Outcome, InterpretError> {
         let (timeout, interval, start) = self.build_timer();
 
-        info!("Waiting for OSD deployment to scale down to 0 replicas");
+        debug!("Waiting for OSD deployment to scale down to 0 replicas");
         loop {
             let dep = client
                 .get_deployment(
@@ -180,11 +184,9 @@ impl CephRemoveOsdInterpret {
                     Some(&self.score.rook_ceph_namespace),
                 )
                 .await?;
-
             if let Some(deployment) = dep {
                 if let Some(status) = deployment.status {
-                    if status.replicas.unwrap_or(1) == 0 && status.ready_replicas.unwrap_or(1) == 0
-                    {
+                    if status.replicas == None && status.ready_replicas == None {
                         return Ok(Outcome::success(
                             "Deployment successfully scaled down.".to_string(),
                         ));
@@ -212,7 +214,7 @@ impl CephRemoveOsdInterpret {
         &self,
         client: Arc<K8sClient>,
     ) -> Result<Outcome, InterpretError> {
-        info!(
+        debug!(
             "Deleting OSD deployment: {}",
             self.score.osd_deployment_name
         );
@@ -234,7 +236,7 @@ impl CephRemoveOsdInterpret {
     ) -> Result<Outcome, InterpretError> {
         let (timeout, interval, start) = self.build_timer();
 
-        info!("Waiting for OSD deployment to scale down to 0 replicas");
+        debug!("Verifying OSD deployment deleted");
         loop {
             let dep = client
                 .get_deployment(
@@ -244,7 +246,7 @@ impl CephRemoveOsdInterpret {
                 .await?;
 
             if dep.is_none() {
-                info!(
+                debug!(
                     "Deployment {} successfully deleted.",
                     self.score.osd_deployment_name
                 );
@@ -276,12 +278,10 @@ impl CephRemoveOsdInterpret {
         Ok(tree)
     }
 
-    pub async fn purge_ceph_osd(
-        &self,
-        client: Arc<K8sClient>,
-        osd_id_full: &str,
-    ) -> Result<Outcome, InterpretError> {
-        info!(
+    pub async fn purge_ceph_osd(&self, client: Arc<K8sClient>) -> Result<Outcome, InterpretError> {
+        let osd_id_numeric = self.get_ceph_osd_id_numeric().unwrap();
+        let osd_id_full = self.get_ceph_osd_id().unwrap();
+        debug!(
             "Purging OSD {} from Ceph cluster and removing its auth key",
             osd_id_full
         );
@@ -291,8 +291,9 @@ impl CephRemoveOsdInterpret {
                 "app".to_string(),
                 Some(&self.score.rook_ceph_namespace),
                 vec![
-                    format!("ceph osd purge {osd_id_full} --yes-i-really-mean-it").as_str(),
-                    format!("ceph auth del osd.{osd_id_full}").as_str(),
+                    "sh",
+                    "-c",
+                    format!("ceph osd purge {osd_id_numeric} --yes-i-really-mean-it && ceph auth del {osd_id_full}").as_str(),
                 ],
             )
             .await?;
@@ -305,10 +306,10 @@ impl CephRemoveOsdInterpret {
     pub async fn verify_ceph_osd_removal(
         &self,
         client: Arc<K8sClient>,
-        osd_id_full: &str,
     ) -> Result<Outcome, InterpretError> {
         let (timeout, interval, start) = self.build_timer();
-        info!(
+        let osd_id_full = self.get_ceph_osd_id().unwrap();
+        debug!(
             "Verifying OSD {} has been removed from the Ceph tree...",
             osd_id_full
         );
@@ -318,7 +319,7 @@ impl CephRemoveOsdInterpret {
                     "rook-ceph-tools".to_string(),
                     "app".to_string(),
                     Some(&self.score.rook_ceph_namespace),
-                    vec!["ceph osd tree -f json"],
+                    vec!["sh", "-c", "ceph osd tree -f json"],
                 )
                 .await?;
             let tree =

harmony/src/modules/storage/ceph/ceph_validate_health_score.rs

@@ -0,0 +1,136 @@
+use std::{sync::Arc, time::Duration};
+
+use async_trait::async_trait;
+use log::debug;
+use serde::Serialize;
+use tokio::time::Instant;
+
+use crate::{
+    data::{Id, Version},
+    interpret::{Interpret, InterpretError, InterpretName, InterpretStatus, Outcome},
+    inventory::Inventory,
+    score::Score,
+    topology::{K8sclient, Topology, k8s::K8sClient},
+};
+
+#[derive(Clone, Debug, Serialize)]
+pub struct CephVerifyClusterHealth {
+    pub rook_ceph_namespace: String,
+}
+
+impl<T: Topology + K8sclient> Score<T> for CephVerifyClusterHealth {
+    fn name(&self) -> String {
+        format!("CephValidateClusterHealth")
+    }
+
+    fn create_interpret(&self) -> Box<dyn Interpret<T>> {
+        Box::new(CephVerifyClusterHealthInterpret {
+            score: self.clone(),
+        })
+    }
+}
+
+#[derive(Clone, Debug)]
+pub struct CephVerifyClusterHealthInterpret {
+    score: CephVerifyClusterHealth,
+}
+
+#[async_trait]
+impl<T: Topology + K8sclient> Interpret<T> for CephVerifyClusterHealthInterpret {
+    async fn execute(
+        &self,
+        _inventory: &Inventory,
+        topology: &T,
+    ) -> Result<Outcome, InterpretError> {
+        let client = topology.k8s_client().await.unwrap();
+        self.verify_ceph_toolbox_exists(client.clone()).await?;
+        self.validate_ceph_cluster_health(client.clone()).await?;
+        Ok(Outcome::success("Ceph cluster healthy".to_string()))
+    }
+
+    fn get_name(&self) -> InterpretName {
+        InterpretName::CephClusterHealth
+    }
+
+    fn get_version(&self) -> Version {
+        todo!()
+    }
+
+    fn get_status(&self) -> InterpretStatus {
+        todo!()
+    }
+
+    fn get_children(&self) -> Vec<Id> {
+        todo!()
+    }
+}
+
+impl CephVerifyClusterHealthInterpret {
+    pub async fn verify_ceph_toolbox_exists(
+        &self,
+        client: Arc<K8sClient>,
+    ) -> Result<Outcome, InterpretError> {
+        let toolbox_dep = "rook-ceph-tools".to_string();
+
+        match client
+            .get_deployment(&toolbox_dep, Some(&self.score.rook_ceph_namespace))
+            .await
+        {
+            Ok(Some(deployment)) => {
+                if let Some(status) = deployment.status {
+                    let ready_count = status.ready_replicas.unwrap_or(0);
+                    if ready_count >= 1 {
+                        return Ok(Outcome::success(format!(
+                            "'{}' is ready with {} replica(s).",
+                            &toolbox_dep, ready_count
+                        )));
+                    } else {
+                        return Err(InterpretError::new(
+                            "ceph-tool-box not ready in cluster".to_string(),
+                        ));
+                    }
+                } else {
+                    Err(InterpretError::new(format!(
+                        "failed to get deployment status {}",
+                        &toolbox_dep
+                    )))
+                }
+            }
+            Ok(None) => Err(InterpretError::new(format!(
+                "Deployment '{}' not found in namespace '{}'.",
+                &toolbox_dep, self.score.rook_ceph_namespace
+            ))),
+            Err(e) => Err(InterpretError::new(format!(
+                "Failed to query for deployment '{}': {}",
+                &toolbox_dep, e
+            ))),
+        }
+    }
+
+    pub async fn validate_ceph_cluster_health(
+        &self,
+        client: Arc<K8sClient>,
+    ) -> Result<Outcome, InterpretError> {
+        debug!("Verifying ceph cluster is in healthy state");
+
+        let health = client
+            .exec_app_capture_output(
+                "rook-ceph-tools".to_string(),
+                "app".to_string(),
+                Some(&self.score.rook_ceph_namespace),
+                vec!["sh", "-c", "ceph health"],
+            )
+            .await?;
+
+        if health.contains("HEALTH_OK") {
+            return Ok(Outcome::success(
+                "Ceph Cluster in healthy state".to_string(),
+            ));
+        } else {
+            Err(InterpretError::new(format!(
+                "Ceph cluster unhealthy {}",
+                health
+            )))
+        }
+    }
+}

harmony/src/modules/storage/ceph/mod.rs

@@ -1 +1,2 @@
-pub mod ceph_osd_replacement_score;
+pub mod ceph_remove_osd_score;
+pub mod ceph_validate_health_score;