[pve-devel] [PATCH proxmox-resource-scheduling 2/3] add pve_static module

[Fiona Ebner]

Models usage of guests and nodes, and allows scoring nodes on which to
start a new service via TOPSIS. For this scoring, each node in turn is
considered as if the service was already running on it.

CPU and memory usage are used as criteria, with memory being weighted
much more, because it's a truly limited resource. For both, CPU and
memory, highest usage among nodes (weighted more, as ideally no node
should be overcommited) and average usage of all nodes (to still be
able to distinguish in case there already is a more highly commited
node) are considered.

Signed-off-by: Fiona Ebner <f.ebner at proxmox.com>
---
 Cargo.toml        |   2 +
 src/lib.rs        |   1 +
 src/pve_static.rs | 143 ++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 146 insertions(+)
 create mode 100644 src/pve_static.rs

diff --git a/Cargo.toml b/Cargo.toml
index ec8e12f..85d0ec1 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -18,3 +18,5 @@ path = "src/lib.rs"
 
 [dependencies]
 anyhow = "1.0"
+lazy_static = "1.4"
+serde = { version = "1.0", features = ["derive"] }
diff --git a/src/lib.rs b/src/lib.rs
index dda0563..c82bd40 100644
--- a/src/lib.rs
+++ b/src/lib.rs
@@ -1 +1,2 @@
+pub mod pve_static;
 pub mod topsis;
diff --git a/src/pve_static.rs b/src/pve_static.rs
new file mode 100644
index 0000000..cb8a823
--- /dev/null
+++ b/src/pve_static.rs
@@ -0,0 +1,143 @@
+use anyhow::Error;
+use lazy_static::lazy_static;
+use serde::{Deserialize, Serialize};
+
+use crate::topsis::{TopsisCriteria, TopsisCriterion, TopsisMatrix};
+
+#[derive(Serialize, Deserialize)]
+#[serde(rename_all = "kebab-case")]
+/// Static usage information of a node.
+pub struct StaticNodeUsage {
+    /// Hostname of the node.
+    pub name: String,
+    /// CPU utilization. Can be more than `maxcpu` if overcommited.
+    pub cpu: f64,
+    /// Total number of CPUs.
+    pub maxcpu: usize,
+    /// Used memory in bytes. Can be more than `maxmem` if overcommited.
+    pub mem: usize,
+    /// Total memory in bytes.
+    pub maxmem: usize,
+}
+
+#[derive(Serialize, Deserialize)]
+#[serde(rename_all = "kebab-case")]
+/// Static usage information of an HA resource.
+pub struct StaticServiceUsage {
+    /// Number of assigned CPUs or CPU limit.
+    pub maxcpu: f64,
+    /// Maximum assigned memory in bytes.
+    pub maxmem: usize,
+}
+
+/// Calculate new CPU usage in percent.
+/// `add` being `0.0` means "unlimited" and results in `max` being added.
+fn add_cpu_usage(old: f64, max: f64, add: f64) -> f64 {
+    if add == 0.0 {
+        old + max
+    } else {
+        old + add
+    }
+}
+
+impl StaticNodeUsage {
+    /// Add usage of `service` to the node's usage.
+    pub fn add_service_usage(&mut self, service: &StaticServiceUsage) {
+        self.cpu = add_cpu_usage(self.cpu, self.maxcpu as f64, service.maxcpu);
+        self.mem += service.maxmem;
+    }
+}
+
+/// A given alternative.
+struct PveTopsisAlternative {
+    average_cpu: f64,
+    highest_cpu: f64,
+    average_memory: f64,
+    highest_memory: f64,
+}
+
+const N_CRITERIA: usize = 4;
+
+// NOTE It is essenital that the order of the criteria definition and the order in the
+// From<PveTopsisAlternative> implementation match up.
+
+lazy_static! {
+    static ref PVE_HA_TOPSIS_CRITERIA: TopsisCriteria<N_CRITERIA> = TopsisCriteria::new([
+        TopsisCriterion::new("average CPU".to_string(), -1.0),
+        TopsisCriterion::new("highest CPU".to_string(), -2.0),
+        TopsisCriterion::new("average memory".to_string(), -5.0),
+        TopsisCriterion::new("highest memory".to_string(), -10.0),
+    ])
+    .unwrap();
+}
+
+impl From<PveTopsisAlternative> for [f64; N_CRITERIA] {
+    fn from(alternative: PveTopsisAlternative) -> Self {
+        [
+            alternative.average_cpu,
+            alternative.highest_cpu,
+            alternative.average_memory,
+            alternative.highest_memory,
+        ]
+    }
+}
+
+/// Scores candidate `nodes` to start a `service` on. Scoring is done according to the static memory
+/// and CPU usages of the nodes as if the service would already be running on each.
+///
+/// Returns a vector of (nodename, score) pairs. Scores are between 0.0 and 1.0 and a higher score
+/// is better.
+pub fn score_nodes_to_start_service(
+    nodes: &[&StaticNodeUsage],
+    service: &StaticServiceUsage,
+) -> Result<Vec<(String, f64)>, Error> {
+    let len = nodes.len();
+
+    let matrix = nodes
+        .iter()
+        .enumerate()
+        .map(|(target_index, _)| {
+            // all of these are as percentages to be comparable across nodes
+            let mut highest_cpu = 0.0;
+            let mut sum_cpu = 0.0;
+            let mut highest_mem = 0.0;
+            let mut sum_mem = 0.0;
+
+            for (index, node) in nodes.iter().enumerate() {
+                let new_cpu = if index == target_index {
+                    add_cpu_usage(node.cpu, node.maxcpu as f64, service.maxcpu)
+                } else {
+                    node.cpu
+                } / (node.maxcpu as f64);
+                highest_cpu = f64::max(highest_cpu, new_cpu);
+                sum_cpu += new_cpu;
+
+                let new_mem = if index == target_index {
+                    node.mem + service.maxmem
+                } else {
+                    node.mem
+                } as f64
+                    / node.maxmem as f64;
+                highest_mem = f64::max(highest_mem, new_mem);
+                sum_mem += new_mem;
+            }
+
+            PveTopsisAlternative {
+                average_cpu: sum_cpu / len as f64,
+                highest_cpu,
+                average_memory: sum_mem / len as f64,
+                highest_memory: highest_mem,
+            }
+            .into()
+        })
+        .collect::<Vec<_>>();
+
+    let scores =
+        crate::topsis::score_alternatives(&TopsisMatrix::new(matrix)?, &PVE_HA_TOPSIS_CRITERIA)?;
+
+    Ok(scores
+        .into_iter()
+        .enumerate()
+        .map(|(n, score)| (nodes[n].name.clone(), score))
+        .collect())
+}
-- 
2.30.2