A few SK changes (#12577)

# TLDR 
This PR is a no-op. 

## Problem
When a SK loses a disk, it must recover all WALs from the very
beginning. This may take days/weeks to catch up to the latest WALs for
all timelines it owns.

## Summary of changes
When SK starts up,
if it finds that it has 0 timelines,
- it will ask SC for the timeline it owns.
- Then, pulls the timeline from its peer safekeepers to restore the WAL
redundancy right away.

After pulling timeline is complete, it will become active and accepts
new WALs.

The current impl is a prototype. We can optimize the impl further, e.g.,
parallel pull timelines.

---------

Co-authored-by: Haoyu Huang <haoyu.huang@databricks.com>

libs/pageserver_api/src/controller_api.rs

@@ -1,5 +1,6 @@
 use std::collections::{HashMap, HashSet};
 use std::fmt::Display;
+use std::net::IpAddr;
 use std::str::FromStr;
 use std::time::{Duration, Instant};
 
@@ -60,6 +61,11 @@ pub struct NodeRegisterRequest {
     pub listen_https_port: Option<u16>,
 
     pub availability_zone_id: AvailabilityZone,
+
+    // Reachable IP address of the PS/SK registering, if known.
+    // Hadron Cluster Coordiantor will update the DNS record of the registering node
+    // with this IP address.
+    pub node_ip_addr: Option<IpAddr>,
 }
 
 #[derive(Serialize, Deserialize)]
@@ -545,6 +551,39 @@ pub struct SafekeeperDescribeResponse {
     pub scheduling_policy: SkSchedulingPolicy,
 }
 
+#[derive(Serialize, Deserialize, Clone, Debug)]
+pub struct TimelineSafekeeperPeer {
+    pub node_id: NodeId,
+    pub listen_http_addr: String,
+    pub http_port: i32,
+}
+
+#[derive(Serialize, Deserialize, Clone, Debug)]
+pub struct SCSafekeeperTimeline {
+    // SC does not know the tenant id.
+    pub timeline_id: TimelineId,
+    pub peers: Vec<NodeId>,
+}
+
+#[derive(Serialize, Deserialize, Clone, Debug)]
+pub struct SCSafekeeperTimelinesResponse {
+    pub timelines: Vec<SCSafekeeperTimeline>,
+    pub safekeeper_peers: Vec<TimelineSafekeeperPeer>,
+}
+
+#[derive(Serialize, Deserialize, Clone, Debug)]
+pub struct SafekeeperTimeline {
+    pub tenant_id: TenantId,
+    pub timeline_id: TimelineId,
+    pub peers: Vec<NodeId>,
+}
+
+#[derive(Serialize, Deserialize, Clone, Debug)]
+pub struct SafekeeperTimelinesResponse {
+    pub timelines: Vec<SafekeeperTimeline>,
+    pub safekeeper_peers: Vec<TimelineSafekeeperPeer>,
+}
+
 #[derive(Serialize, Deserialize, Clone)]
 pub struct SafekeeperSchedulingPolicyRequest {
     pub scheduling_policy: SkSchedulingPolicy,

libs/utils/src/ip_address.rs

@@ -0,0 +1,73 @@
+use std::env::{VarError, var};
+use std::error::Error;
+use std::net::IpAddr;
+use std::str::FromStr;
+
+/// Name of the environment variable containing the reachable IP address of the node. If set, the IP address contained in this
+/// environment variable is used as the reachable IP address of the pageserver or safekeeper node during node registration.
+/// In a Kubernetes environment, this environment variable should be set by Kubernetes to the Pod IP (specified in the Pod
+/// template).
+pub const HADRON_NODE_IP_ADDRESS: &str = "HADRON_NODE_IP_ADDRESS";
+
+/// Read the reachable IP address of this page server from env var HADRON_NODE_IP_ADDRESS.
+/// In Kubernetes this environment variable is set to the Pod IP (specified in the Pod template).
+pub fn read_node_ip_addr_from_env() -> Result<Option<IpAddr>, Box<dyn Error>> {
+    match var(HADRON_NODE_IP_ADDRESS) {
+        Ok(v) => {
+            if let Ok(addr) = IpAddr::from_str(&v) {
+                Ok(Some(addr))
+            } else {
+                Err(format!("Invalid IP address string: {v}. Cannot be parsed as either an IPv4 or an IPv6 address.").into())
+            }
+        }
+        Err(VarError::NotPresent) => Ok(None),
+        Err(e) => Err(e.into()),
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use std::env;
+    use std::net::{Ipv4Addr, Ipv6Addr};
+
+    #[test]
+    fn test_read_node_ip_addr_from_env() {
+        // SAFETY: test code
+        unsafe {
+            // Test with a valid IPv4 address
+            env::set_var(HADRON_NODE_IP_ADDRESS, "192.168.1.1");
+            let result = read_node_ip_addr_from_env().unwrap();
+            assert_eq!(result, Some(IpAddr::V4(Ipv4Addr::new(192, 168, 1, 1))));
+
+            // Test with a valid IPv6 address
+            env::set_var(
+                HADRON_NODE_IP_ADDRESS,
+                "2001:0db8:85a3:0000:0000:8a2e:0370:7334",
+            );
+        }
+        let result = read_node_ip_addr_from_env().unwrap();
+        assert_eq!(
+            result,
+            Some(IpAddr::V6(
+                Ipv6Addr::from_str("2001:0db8:85a3:0000:0000:8a2e:0370:7334").unwrap()
+            ))
+        );
+
+        // Test with an invalid IP address
+        // SAFETY: test code
+        unsafe {
+            env::set_var(HADRON_NODE_IP_ADDRESS, "invalid_ip");
+        }
+        let result = read_node_ip_addr_from_env();
+        assert!(result.is_err());
+
+        // Test with no environment variable set
+        // SAFETY: test code
+        unsafe {
+            env::remove_var(HADRON_NODE_IP_ADDRESS);
+        }
+        let result = read_node_ip_addr_from_env().unwrap();
+        assert_eq!(result, None);
+    }
+}

libs/utils/src/lib.rs

@@ -26,6 +26,9 @@ pub mod auth;
 // utility functions and helper traits for unified unique id generation/serialization etc.
 pub mod id;
 
+// utility functions to obtain reachable IP addresses in PS/SK nodes.
+pub mod ip_address;
+
 pub mod shard;
 
 mod hex;