[pbs-devel] [PATCH proxmox-backup v2 1/2] partial fix #3701: sync/pull: add transfer-last parameter

[Stefan Hanreich <s.hanreich@proxmox.com>]

Specifying the transfer-last parameter limits the amount of backups
that get synced via the pull command/sync job. The parameter specifies
how many of the N latest backups should get pulled/synced. All other
backups will get skipped.

This is particularly useful in situations where the sync target has
less disk space than the source. Syncing all backups from the source
is not possible if there is not enough disk space on the target.
Additionally this can be used for limiting the amount of data
transferred, reducing load on the network.

Signed-off-by: Stefan Hanreich <s.hanreich@proxmox.com>
---
I had to make slight adjustments to Wolfgang's proposed condition because it
wouldn't work in cases where transfer-last was greater than the total amount of
backups available.
Nevertheless, the condition should now be a lot less obtuse and easier to read.

 pbs-api-types/src/jobs.rs         | 11 +++++++++++
 src/api2/config/sync.rs           |  9 +++++++++
 src/api2/pull.rs                  | 10 +++++++++-
 src/bin/proxmox-backup-manager.rs | 11 ++++++++++-
 src/server/pull.rs                | 17 ++++++++++++++++-
 5 files changed, 55 insertions(+), 3 deletions(-)

diff --git a/pbs-api-types/src/jobs.rs b/pbs-api-types/src/jobs.rs
index cf7618c4..b9f57719 100644
--- a/pbs-api-types/src/jobs.rs
+++ b/pbs-api-types/src/jobs.rs
@@ -444,6 +444,11 @@ pub const GROUP_FILTER_SCHEMA: Schema = StringSchema::new(
 pub const GROUP_FILTER_LIST_SCHEMA: Schema =
     ArraySchema::new("List of group filters.", &GROUP_FILTER_SCHEMA).schema();
 
+pub const TRANSFER_LAST_SCHEMA: Schema =
+    IntegerSchema::new("The maximum amount of snapshots to be transferred (per group).")
+        .minimum(1)
+        .schema();
+
 #[api(
     properties: {
         id: {
@@ -493,6 +498,10 @@ pub const GROUP_FILTER_LIST_SCHEMA: Schema =
             schema: GROUP_FILTER_LIST_SCHEMA,
             optional: true,
         },
+        "transfer-last": {
+            schema: TRANSFER_LAST_SCHEMA,
+            optional: true,
+        },
     }
 )]
 #[derive(Serialize, Deserialize, Clone, Updater, PartialEq)]
@@ -522,6 +531,8 @@ pub struct SyncJobConfig {
     pub group_filter: Option<Vec<GroupFilter>>,
     #[serde(flatten)]
     pub limit: RateLimitConfig,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub transfer_last: Option<usize>,
 }
 
 impl SyncJobConfig {
diff --git a/src/api2/config/sync.rs b/src/api2/config/sync.rs
index bd7373df..01e5f2ce 100644
--- a/src/api2/config/sync.rs
+++ b/src/api2/config/sync.rs
@@ -215,6 +215,8 @@ pub enum DeletableProperty {
     RemoteNs,
     /// Delete the max_depth property,
     MaxDepth,
+    /// Delete the transfer_last property,
+    TransferLast,
 }
 
 #[api(
@@ -309,6 +311,9 @@ pub fn update_sync_job(
                 DeletableProperty::MaxDepth => {
                     data.max_depth = None;
                 }
+                DeletableProperty::TransferLast => {
+                    data.transfer_last = None;
+                }
             }
         }
     }
@@ -343,6 +348,9 @@ pub fn update_sync_job(
     if let Some(group_filter) = update.group_filter {
         data.group_filter = Some(group_filter);
     }
+    if let Some(transfer_last) = update.transfer_last {
+        data.transfer_last = Some(transfer_last);
+    }
 
     if update.limit.rate_in.is_some() {
         data.limit.rate_in = update.limit.rate_in;
@@ -507,6 +515,7 @@ acl:1:/remote/remote1/remotestore1:write@pbs:RemoteSyncOperator
         group_filter: None,
         schedule: None,
         limit: pbs_api_types::RateLimitConfig::default(), // no limit
+        transfer_last: None,
     };
 
     // should work without ACLs
diff --git a/src/api2/pull.rs b/src/api2/pull.rs
index b2473ec8..daeba7cf 100644
--- a/src/api2/pull.rs
+++ b/src/api2/pull.rs
@@ -10,6 +10,7 @@ use pbs_api_types::{
     Authid, BackupNamespace, GroupFilter, RateLimitConfig, SyncJobConfig, DATASTORE_SCHEMA,
     GROUP_FILTER_LIST_SCHEMA, NS_MAX_DEPTH_REDUCED_SCHEMA, PRIV_DATASTORE_BACKUP,
     PRIV_DATASTORE_PRUNE, PRIV_REMOTE_READ, REMOTE_ID_SCHEMA, REMOVE_VANISHED_BACKUPS_SCHEMA,
+    TRANSFER_LAST_SCHEMA,
 };
 use pbs_config::CachedUserInfo;
 use proxmox_rest_server::WorkerTask;
@@ -76,6 +77,7 @@ impl TryFrom<&SyncJobConfig> for PullParameters {
             sync_job.max_depth,
             sync_job.group_filter.clone(),
             sync_job.limit.clone(),
+            sync_job.transfer_last,
         )
     }
 }
@@ -201,7 +203,11 @@ pub fn do_sync_job(
             limit: {
                 type: RateLimitConfig,
                 flatten: true,
-            }
+            },
+            "transfer-last": {
+                schema: TRANSFER_LAST_SCHEMA,
+                optional: true,
+            },
         },
     },
     access: {
@@ -225,6 +231,7 @@ async fn pull(
     max_depth: Option<usize>,
     group_filter: Option<Vec<GroupFilter>>,
     limit: RateLimitConfig,
+    transfer_last: Option<usize>,
     rpcenv: &mut dyn RpcEnvironment,
 ) -> Result<String, Error> {
     let auth_id: Authid = rpcenv.get_auth_id().unwrap().parse()?;
@@ -257,6 +264,7 @@ async fn pull(
         max_depth,
         group_filter,
         limit,
+        transfer_last,
     )?;
     let client = pull_params.client().await?;
 
diff --git a/src/bin/proxmox-backup-manager.rs b/src/bin/proxmox-backup-manager.rs
index 06330c78..9ea5830c 100644
--- a/src/bin/proxmox-backup-manager.rs
+++ b/src/bin/proxmox-backup-manager.rs
@@ -13,7 +13,7 @@ use pbs_api_types::percent_encoding::percent_encode_component;
 use pbs_api_types::{
     BackupNamespace, GroupFilter, RateLimitConfig, SyncJobConfig, DATASTORE_SCHEMA,
     GROUP_FILTER_LIST_SCHEMA, IGNORE_VERIFIED_BACKUPS_SCHEMA, NS_MAX_DEPTH_SCHEMA,
-    REMOTE_ID_SCHEMA, REMOVE_VANISHED_BACKUPS_SCHEMA, UPID_SCHEMA,
+    REMOTE_ID_SCHEMA, REMOVE_VANISHED_BACKUPS_SCHEMA, TRANSFER_LAST_SCHEMA, UPID_SCHEMA,
     VERIFICATION_OUTDATED_AFTER_SCHEMA,
 };
 use pbs_client::{display_task_log, view_task_result};
@@ -272,6 +272,10 @@ fn task_mgmt_cli() -> CommandLineInterface {
                 schema: OUTPUT_FORMAT,
                 optional: true,
             },
+            "transfer-last": {
+                schema: TRANSFER_LAST_SCHEMA,
+                optional: true,
+            },
         }
    }
 )]
@@ -287,6 +291,7 @@ async fn pull_datastore(
     max_depth: Option<usize>,
     group_filter: Option<Vec<GroupFilter>>,
     limit: RateLimitConfig,
+    transfer_last: Option<usize>,
     param: Value,
 ) -> Result<Value, Error> {
     let output_format = get_output_format(&param);
@@ -319,6 +324,10 @@ async fn pull_datastore(
         args["remove-vanished"] = Value::from(remove_vanished);
     }
 
+    if transfer_last.is_some() {
+        args["transfer-last"] = json!(transfer_last)
+    }
+
     let mut limit_json = json!(limit);
     let limit_map = limit_json
         .as_object_mut()
diff --git a/src/server/pull.rs b/src/server/pull.rs
index 65eedf2c..81f4faf3 100644
--- a/src/server/pull.rs
+++ b/src/server/pull.rs
@@ -1,5 +1,6 @@
 //! Sync datastore from remote server
 
+use std::cmp::min;
 use std::collections::{HashMap, HashSet};
 use std::io::{Seek, SeekFrom};
 use std::sync::atomic::{AtomicUsize, Ordering};
@@ -59,6 +60,8 @@ pub(crate) struct PullParameters {
     group_filter: Option<Vec<GroupFilter>>,
     /// Rate limits for all transfers from `remote`
     limit: RateLimitConfig,
+    /// How many snapshots should be transferred at most (taking the newest N snapshots)
+    transfer_last: Option<usize>,
 }
 
 impl PullParameters {
@@ -78,6 +81,7 @@ impl PullParameters {
         max_depth: Option<usize>,
         group_filter: Option<Vec<GroupFilter>>,
         limit: RateLimitConfig,
+        transfer_last: Option<usize>,
     ) -> Result<Self, Error> {
         let store = DataStore::lookup_datastore(store, Some(Operation::Write))?;
 
@@ -109,6 +113,7 @@ impl PullParameters {
             max_depth,
             group_filter,
             limit,
+            transfer_last,
         })
     }
 
@@ -573,7 +578,7 @@ impl std::fmt::Display for SkipInfo {
     fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
         write!(
             f,
-            "skipped: {} snapshot(s) ({}) older than the newest local snapshot",
+            "skipped: {} snapshot(s) ({}) - older than the newest local snapshot or excluded by transfer-last",
             self.count,
             self.affected().map_err(|_| std::fmt::Error)?
         )
@@ -646,6 +651,11 @@ async fn pull_group(
         count: 0,
     };
 
+    let total_amount = list.len();
+
+    let mut transfer_amount = params.transfer_last.unwrap_or(total_amount);
+    transfer_amount = min(transfer_amount, total_amount);
+
     for (pos, item) in list.into_iter().enumerate() {
         let snapshot = item.backup;
 
@@ -668,6 +678,11 @@ async fn pull_group(
             }
         }
 
+        if pos < (total_amount - transfer_amount) {
+            skip_info.update(snapshot.time);
+            continue;
+        }
+
         // get updated auth_info (new tickets)
         let auth_info = client.login().await?;
 
-- 
2.30.2