[pbs-devel] [PATCH v7 proxmox-backup 59/69] test-suite: add detection mode change benchmark

[Christian Ebner <c.ebner@proxmox.com>]

Introduces the proxmox-backup-test-suite create intended for
benchmarking and high level user facing testing.

The initial code includes a benchmark intended for regression testing of
the proxmox-backup-client when using different file detection modes
during backup.

Signed-off-by: Christian Ebner <c.ebner@proxmox.com>
---
changes since version 6:
- no changes

 Cargo.toml                                    |   1 +
 proxmox-backup-test-suite/Cargo.toml          |  18 ++
 .../src/detection_mode_bench.rs               | 294 ++++++++++++++++++
 proxmox-backup-test-suite/src/main.rs         |  17 +
 4 files changed, 330 insertions(+)
 create mode 100644 proxmox-backup-test-suite/Cargo.toml
 create mode 100644 proxmox-backup-test-suite/src/detection_mode_bench.rs
 create mode 100644 proxmox-backup-test-suite/src/main.rs

diff --git a/Cargo.toml b/Cargo.toml
index 4119b3cac..e83c65b60 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -45,6 +45,7 @@ members = [
     "proxmox-restore-daemon",
 
     "pxar-bin",
+    "proxmox-backup-test-suite",
 ]
 
 [lib]
diff --git a/proxmox-backup-test-suite/Cargo.toml b/proxmox-backup-test-suite/Cargo.toml
new file mode 100644
index 000000000..3f899e9bc
--- /dev/null
+++ b/proxmox-backup-test-suite/Cargo.toml
@@ -0,0 +1,18 @@
+[package]
+name = "proxmox-backup-test-suite"
+version = "0.1.0"
+authors.workspace = true
+edition.workspace = true
+
+[dependencies]
+anyhow.workspace = true
+futures.workspace = true
+serde.workspace = true
+serde_json.workspace = true
+
+pbs-client.workspace = true
+pbs-key-config.workspace = true
+pbs-tools.workspace = true
+proxmox-async.workspace = true
+proxmox-router = { workspace = true, features = ["cli"] }
+proxmox-schema = { workspace = true, features = [ "api-macro" ] }
diff --git a/proxmox-backup-test-suite/src/detection_mode_bench.rs b/proxmox-backup-test-suite/src/detection_mode_bench.rs
new file mode 100644
index 000000000..9a3c76802
--- /dev/null
+++ b/proxmox-backup-test-suite/src/detection_mode_bench.rs
@@ -0,0 +1,294 @@
+use std::path::Path;
+use std::process::Command;
+use std::{thread, time};
+
+use anyhow::{bail, format_err, Error};
+use serde_json::Value;
+
+use pbs_client::{
+    tools::{complete_repository, key_source::KEYFILE_SCHEMA, REPO_URL_SCHEMA},
+    BACKUP_SOURCE_SCHEMA,
+};
+use pbs_tools::json;
+use proxmox_router::cli::*;
+use proxmox_schema::api;
+
+const DEFAULT_NUMBER_OF_RUNS: u64 = 5;
+// Homepage https://cocodataset.org/
+const COCO_DATASET_SRC_URL: &'static str = "http://images.cocodataset.org/zips/unlabeled2017.zip";
+// Homepage https://kernel.org/
+const LINUX_GIT_REPOSITORY: &'static str =
+    "git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git";
+const LINUX_GIT_TAG: &'static str = "v6.5.5";
+
+pub(crate) fn detection_mode_bench_mgtm_cli() -> CliCommandMap {
+    let run_cmd_def = CliCommand::new(&API_METHOD_DETECTION_MODE_BENCH_RUN)
+        .arg_param(&["backupspec"])
+        .completion_cb("repository", complete_repository)
+        .completion_cb("keyfile", complete_file_name);
+
+    let prepare_cmd_def = CliCommand::new(&API_METHOD_DETECTION_MODE_BENCH_PREPARE);
+    CliCommandMap::new()
+        .insert("prepare", prepare_cmd_def)
+        .insert("run", run_cmd_def)
+}
+
+#[api(
+   input: {
+       properties: {
+           backupspec: {
+               type: Array,
+               description: "List of backup source specifications ([<label.ext>:<path>] ...)",
+               items: {
+                   schema: BACKUP_SOURCE_SCHEMA,
+               }
+           },
+           repository: {
+               schema: REPO_URL_SCHEMA,
+               optional: true,
+           },
+           keyfile: {
+               schema: KEYFILE_SCHEMA,
+               optional: true,
+           },
+           "number-of-runs": {
+               description: "Number of times to repeat the run",
+               type: Integer,
+               optional: true,
+           },
+       }
+   }
+)]
+/// Run benchmark to compare performance for backups using different change detection modes.
+fn detection_mode_bench_run(param: Value) -> Result<(), Error> {
+    let mut pbc = Command::new("proxmox-backup-client");
+    pbc.arg("backup");
+
+    let backupspec_list = json::required_array_param(&param, "backupspec")?;
+    for backupspec in backupspec_list {
+        let arg = backupspec
+            .as_str()
+            .ok_or_else(|| format_err!("failed to parse backupspec"))?;
+        pbc.arg(arg);
+    }
+
+    if let Some(repo) = param["repository"].as_str() {
+        pbc.arg("--repository");
+        pbc.arg::<&str>(repo);
+    }
+
+    if let Some(keyfile) = param["keyfile"].as_str() {
+        pbc.arg("--keyfile");
+        pbc.arg::<&str>(keyfile);
+    }
+
+    let number_of_runs = match param["number_of_runs"].as_u64() {
+        Some(n) => n,
+        None => DEFAULT_NUMBER_OF_RUNS,
+    };
+    if number_of_runs < 1 {
+        bail!("Number of runs must be greater than 1, aborting.");
+    }
+
+    // First run is an initial run to make sure all chunks are present already, reduce side effects
+    // by filesystem caches ecc.
+    let _stats_initial = do_run(&mut pbc, 1)?;
+
+    println!("\nStarting benchmarking backups with regular detection mode...\n");
+    let stats_reg = do_run(&mut pbc, number_of_runs)?;
+
+    // Make sure to have a valid reference with catalog fromat version 2
+    pbc.arg("--change-detection-mode=metadata");
+    let _stats_initial = do_run(&mut pbc, 1)?;
+
+    println!("\nStarting benchmarking backups with metadata detection mode...\n");
+    let stats_meta = do_run(&mut pbc, number_of_runs)?;
+
+    println!("\nCompleted benchmark with {number_of_runs} runs for each tested mode.");
+    println!("\nCompleted regular backup with:");
+    println!("Total runtime: {:.2} s", stats_reg.total);
+    println!("Average: {:.2} ± {:.2} s", stats_reg.avg, stats_reg.stddev);
+    println!("Min: {:.2} s", stats_reg.min);
+    println!("Max: {:.2} s", stats_reg.max);
+
+    println!("\nCompleted metadata detection mode backup with:");
+    println!("Total runtime: {:.2} s", stats_meta.total);
+    println!(
+        "Average: {:.2} ± {:.2} s",
+        stats_meta.avg, stats_meta.stddev
+    );
+    println!("Min: {:.2} s", stats_meta.min);
+    println!("Max: {:.2} s", stats_meta.max);
+
+    let diff_stddev =
+        ((stats_meta.stddev * stats_meta.stddev) + (stats_reg.stddev * stats_reg.stddev)).sqrt();
+    println!("\nDifferences (metadata based - regular):");
+    println!(
+        "Delta total runtime: {:.2} s ({:.2} %)",
+        stats_meta.total - stats_reg.total,
+        100.0 * (stats_meta.total / stats_reg.total - 1.0),
+    );
+    println!(
+        "Delta average: {:.2} ± {:.2} s ({:.2} %)",
+        stats_meta.avg - stats_reg.avg,
+        diff_stddev,
+        100.0 * (stats_meta.avg / stats_reg.avg - 1.0),
+    );
+    println!(
+        "Delta min: {:.2} s ({:.2} %)",
+        stats_meta.min - stats_reg.min,
+        100.0 * (stats_meta.min / stats_reg.min - 1.0),
+    );
+    println!(
+        "Delta max: {:.2} s ({:.2} %)",
+        stats_meta.max - stats_reg.max,
+        100.0 * (stats_meta.max / stats_reg.max - 1.0),
+    );
+
+    Ok(())
+}
+
+fn do_run(cmd: &mut Command, n_runs: u64) -> Result<Statistics, Error> {
+    // Avoid consecutive snapshot timestamps collision
+    thread::sleep(time::Duration::from_millis(1000));
+    let mut timings = Vec::with_capacity(n_runs as usize);
+    for iteration in 1..n_runs + 1 {
+        let start = std::time::SystemTime::now();
+        let mut child = cmd.spawn()?;
+        let exit_code = child.wait()?;
+        let elapsed = start.elapsed()?;
+        timings.push(elapsed);
+        if !exit_code.success() {
+            bail!("Run number {iteration} of {n_runs} failed, aborting.");
+        }
+    }
+
+    Ok(statistics(timings))
+}
+
+struct Statistics {
+    total: f64,
+    avg: f64,
+    stddev: f64,
+    min: f64,
+    max: f64,
+}
+
+fn statistics(timings: Vec<std::time::Duration>) -> Statistics {
+    let total = timings
+        .iter()
+        .fold(0f64, |sum, time| sum + time.as_secs_f64());
+    let avg = total / timings.len() as f64;
+    let var = 1f64 / (timings.len() - 1) as f64
+        * timings.iter().fold(0f64, |sq_sum, time| {
+            let diff = time.as_secs_f64() - avg;
+            sq_sum + diff * diff
+        });
+    let stddev = var.sqrt();
+    let min = timings.iter().min().unwrap().as_secs_f64();
+    let max = timings.iter().max().unwrap().as_secs_f64();
+
+    Statistics {
+        total,
+        avg,
+        stddev,
+        min,
+        max,
+    }
+}
+
+#[api(
+    input: {
+        properties: {
+            target: {
+                description: "target path to prepare test data.",
+            },
+        },
+    },
+)]
+/// Prepare files required for detection mode backup benchmarks.
+fn detection_mode_bench_prepare(target: String) -> Result<(), Error> {
+    let linux_repo_target = format!("{target}/linux");
+    let coco_dataset_target = format!("{target}/coco");
+    git_clone(LINUX_GIT_REPOSITORY, linux_repo_target.as_str())?;
+    git_checkout(LINUX_GIT_TAG, linux_repo_target.as_str())?;
+    wget_download(COCO_DATASET_SRC_URL, coco_dataset_target.as_str())?;
+
+    Ok(())
+}
+
+fn git_clone(repo: &str, target: &str) -> Result<(), Error> {
+    println!("Calling git clone for '{repo}'.");
+    let target_git = format!("{target}/.git");
+    let path = Path::new(&target_git);
+    if let Ok(true) = path.try_exists() {
+        println!("Target '{target}' already contains a git repository, skip.");
+        return Ok(());
+    }
+
+    let mut git = Command::new("git");
+    git.args(["clone", repo, target]);
+
+    let mut child = git.spawn()?;
+    let exit_code = child.wait()?;
+    if exit_code.success() {
+        println!("git clone finished with success.");
+    } else {
+        bail!("git clone failed for '{target}'.");
+    }
+
+    Ok(())
+}
+
+fn git_checkout(checkout_target: &str, target: &str) -> Result<(), Error> {
+    println!("Calling git checkout '{checkout_target}'.");
+    let mut git = Command::new("git");
+    git.args(["-C", target, "checkout", checkout_target]);
+
+    let mut child = git.spawn()?;
+    let exit_code = child.wait()?;
+    if exit_code.success() {
+        println!("git checkout finished with success.");
+    } else {
+        bail!("git checkout '{checkout_target}' failed for '{target}'.");
+    }
+    Ok(())
+}
+
+fn wget_download(source_url: &str, target: &str) -> Result<(), Error> {
+    let path = Path::new(&target);
+    if let Ok(true) = path.try_exists() {
+        println!("Target '{target}' already exists, skip.");
+        return Ok(());
+    }
+    let zip = format!("{}/unlabeled2017.zip", target);
+    let path = Path::new(&zip);
+    if !path.try_exists()? {
+        println!("Download archive using wget from '{source_url}' to '{target}'.");
+        let mut wget = Command::new("wget");
+        wget.args(["-P", target, source_url]);
+
+        let mut child = wget.spawn()?;
+        let exit_code = child.wait()?;
+        if exit_code.success() {
+            println!("Download finished with success.");
+        } else {
+            bail!("Failed to download '{source_url}' to '{target}'.");
+        }
+        return Ok(());
+    } else {
+        println!("Target '{target}' already contains download, skip download.");
+    }
+
+    let mut unzip = Command::new("unzip");
+    unzip.args([&zip, "-d", target]);
+
+    let mut child = unzip.spawn()?;
+    let exit_code = child.wait()?;
+    if exit_code.success() {
+        println!("Extracting zip archive finished with success.");
+    } else {
+        bail!("Failed to extract zip archive '{zip}' to '{target}'.");
+    }
+    Ok(())
+}
diff --git a/proxmox-backup-test-suite/src/main.rs b/proxmox-backup-test-suite/src/main.rs
new file mode 100644
index 000000000..0a5b436a8
--- /dev/null
+++ b/proxmox-backup-test-suite/src/main.rs
@@ -0,0 +1,17 @@
+use proxmox_router::cli::*;
+
+mod detection_mode_bench;
+
+fn main() {
+    let cmd_def = CliCommandMap::new().insert(
+        "detection-mode-bench",
+        detection_mode_bench::detection_mode_bench_mgtm_cli(),
+    );
+
+    let rpcenv = CliEnvironment::new();
+    run_cli_command(
+        cmd_def,
+        rpcenv,
+        Some(|future| proxmox_async::runtime::main(future)),
+    );
+}
-- 
2.39.2



_______________________________________________
pbs-devel mailing list
pbs-devel@lists.proxmox.com
https://lists.proxmox.com/cgi-bin/mailman/listinfo/pbs-devel