Artifact [705b9bcc12]

Artifact 705b9bcc12c25fa6a0cea3e19692b08c082719a408142465a87fe024acc5879a:

• File internal/shun/purge.go — part of check-in [0fd2a507b8] at 2026-07-24 15:27:03 on branch trunk — perf: route history-walking expansions through content.Cache (#151) (#153)

  The buffer-reuse fix in #145/#150 cut the cost of expanding one delta chain once. It did nothing for callers that expand many versions of the same artifact in a single operation: each bare content.Expand still replayed the whole O(depth) chain, so a walk over N overlapping revisions cost O(N^2) blob reads even though content.Cache already existed for exactly this pattern.

  Audited every non-test content.Expand caller. Two access patterns genuinely repeat over overlapping delta chains and are now routed through a per-operation content.Cache:

  - annotate walks every revision of one file along the parent chain. content_deltify stores each older file blob as a delta against its successor, so the per-revision expansions are all walks of the same few chains. One cache threaded through the walk (file blob + manifest listing via new manifest.ListFilesCached/GetManifestCached, both nil-passthrough so existing callers are unchanged) turns it linear. Measured on a deltified 150-revision file: 1.60s -> 0.65s (2.5x), 764k -> 308k allocs; the win grows with history depth.

  - verify.Verify and verify.Rebuild sweep every blob more than once (Rebuild: checkBlobs + rebuildManifests + rebuildTags x2). A single cache shared across the pass walks each chain once instead of once per sweep and amortizes overlap within each sweep. Measured on a 150-revision two-file repo: Rebuild 3.34s -> 0.068s (48x), 4.59M -> 98k allocs.

  Callers that only ever touch the tip or make a single pass over distinct blobs (branch create, merge-config load, R-card / delta manifest build, MergeParentFiles, crosslinkSingle, shun undelta, pairwise Diff) are left on bare Expand, each with a comment stating why a cache cannot amortize their access.

  No behavior change: expansion output is byte-identical, verified across the modernc and ncruces drivers with REQUIRE_FOSSIL_BIN=1 cross-checks and the DST suite. (user: [email protected], size: 3270) [annotate] [blame] [check-ins using]

package shun

import (
	"fmt"

	"github.com/danmestas/go-libfossil/db"
	"github.com/danmestas/go-libfossil/internal/blob"
	"github.com/danmestas/go-libfossil/internal/content"
	libfossil "github.com/danmestas/go-libfossil/internal/fsltype"
)

// PurgeResult summarizes what Purge deleted.
type PurgeResult struct {
	BlobsDeleted   int
	DeltasExpanded int
	PrivateCleaned int
}

// Purge physically removes all shunned blobs from the repo.
// Follows Fossil's shun_artifacts() algorithm from shun.c.
// Requires *db.DB (not Querier) because it runs in a transaction.
func Purge(d *db.DB) (PurgeResult, error) {
	if d == nil {
		panic("shun.Purge: d must not be nil")
	}
	var result PurgeResult

	err := d.WithTx(func(tx *db.Tx) error {
		// Step 1: Find rids to delete.
		_, err := tx.Exec(`CREATE TEMP TABLE toshun(rid INTEGER PRIMARY KEY)`)
		if err != nil {
			return fmt.Errorf("create toshun: %w", err)
		}

		_, err = tx.Exec(`INSERT INTO toshun SELECT rid FROM blob WHERE uuid IN (SELECT uuid FROM shun)`)
		if err != nil {
			return fmt.Errorf("populate toshun: %w", err)
		}

		// Step 2: Undelta dependents — expand blobs whose delta source is being shunned.
		rows, err := tx.Query(`SELECT rid FROM delta WHERE srcid IN (SELECT rid FROM toshun)`)
		if err != nil {
			return fmt.Errorf("query dependents: %w", err)
		}
		var dependents []libfossil.FslID
		for rows.Next() {
			var rid libfossil.FslID
			if err := rows.Scan(&rid); err != nil {
				rows.Close()
				return fmt.Errorf("scan dependent: %w", err)
			}
			dependents = append(dependents, rid)
		}
		rows.Close()

		// Bare Expand: each dependent of a shunned base is expanded once to be
		// rewritten as whole content. Distinct rids, single pass -- and the
		// deltas are being deleted, so there is no chain left to cache against.
		for _, rid := range dependents {
			expanded, err := content.Expand(tx, rid)
			if err != nil {
				return fmt.Errorf("expand rid %d: %w", rid, err)
			}
			compressed, err := blob.Compress(expanded)
			if err != nil {
				return fmt.Errorf("compress rid %d: %w", rid, err)
			}
			_, err = tx.Exec("UPDATE blob SET content=?, size=? WHERE rid=?",
				compressed, len(expanded), rid)
			if err != nil {
				return fmt.Errorf("update blob rid %d: %w", rid, err)
			}
			_, err = tx.Exec("DELETE FROM delta WHERE rid=?", rid)
			if err != nil {
				return fmt.Errorf("delete delta rid %d: %w", rid, err)
			}
			result.DeltasExpanded++
		}

		// Step 3: Delete shunned blobs.
		_, err = tx.Exec("DELETE FROM delta WHERE rid IN (SELECT rid FROM toshun)")
		if err != nil {
			return fmt.Errorf("delete shunned deltas: %w", err)
		}

		res, err := tx.Exec("DELETE FROM blob WHERE rid IN (SELECT rid FROM toshun)")
		if err != nil {
			return fmt.Errorf("delete shunned blobs: %w", err)
		}
		n, _ := res.RowsAffected()
		result.BlobsDeleted = int(n)

		_, err = tx.Exec("DROP TABLE toshun")
		if err != nil {
			return fmt.Errorf("drop toshun: %w", err)
		}

		// Step 4: Orphan cleanup.
		res, err = tx.Exec("DELETE FROM private WHERE NOT EXISTS (SELECT 1 FROM blob WHERE rid=private.rid)")
		if err != nil {
			return fmt.Errorf("cleanup private: %w", err)
		}
		n, _ = res.RowsAffected()
		result.PrivateCleaned = int(n)

		return nil
	})

	return result, err
}