gotosocial/internal/db/bundb/list.go
kim 6a6a499333
[performance] rewrite timelines to rely on new timeline cache type (#3941)
* start work rewriting timeline cache type

* further work rewriting timeline caching

* more work integration new timeline code

* remove old code

* add local timeline, fix up merge conflicts

* remove old use of go-bytes

* implement new timeline code into more areas of codebase, pull in latest go-mangler, go-mutexes, go-structr

* remove old timeline package, add local timeline cache

* remove references to old timeline types that needed starting up in tests

* start adding page validation

* fix test-identified timeline cache package issues

* fix up more tests, fix missing required changes, etc

* add exclusion for test.out in gitignore

* clarify some things better in code comments

* tweak cache size limits

* fix list timeline cache fetching

* further list timeline fixes

* linter, ssssssssshhhhhhhhhhhh please

* fix linter hints

* reslice the output if it's beyond length of 'lim'

* remove old timeline initialization code, bump go-structr to v0.9.4

* continued from previous commit

* improved code comments

* don't allow multiple entries for BoostOfID values to prevent repeated boosts of same boosts

* finish writing more code comments

* some variable renaming, for ease of following

* change the way we update lo,hi paging values during timeline load

* improved code comments for updated / returned lo , hi paging values

* finish writing code comments for the StatusTimeline{} type itself

* fill in more code comments

* update go-structr version to latest with changed timeline unique indexing logic

* have a local and public timeline *per user*

* rewrite calls to public / local timeline calls

* remove the zero length check, as lo, hi values might still be set

* simplify timeline cache loading, fix lo/hi returns, fix timeline invalidation side-effects missing for some federated actions

* swap the lo, hi values 🤦

* add (now) missing slice reverse of tag timeline statuses when paging ASC

* remove local / public caches (is out of scope for this work), share more timeline code

* remove unnecessary change

* again, remove more unused code

* remove unused function to appease the linter

* move boost checking to prepare function

* fix use of timeline.lastOrder, fix incorrect range functions used

* remove comments for repeat code

* remove the boost logic from prepare function

* do a maximum of 5 loads, not 10

* add repeat boost filtering logic, update go-structr, general improvements

* more code comments

* add important note

* fix timeline tests now that timelines are returned in page order

* remove unused field

* add StatusTimeline{} tests

* add more status timeline tests

* start adding preloading support

* ensure repeat boosts are marked in preloaded entries

* share a bunch of the database load code in timeline cache, don't clear timelines on relationship change

* add logic to allow dynamic clear / preloading of timelines

* comment-out unused functions, but leave in place as we might end-up using them

* fix timeline preload state check

* much improved status timeline code comments

* more code comments, don't bother inserting statuses if timeline not preloaded

* shift around some logic to make sure things aren't accidentally left set

* finish writing code comments

* remove trim-after-insert behaviour

* fix-up some comments referring to old logic

* remove unsetting of lo, hi

* fix preload repeatBoost checking logic

* don't return on status filter errors, these are usually transient

* better concurrency safety in Clear() and Done()

* fix test broken due to addition of preloader

* fix repeatBoost logic that doesn't account for already-hidden repeatBoosts

* ensure edit submodels are dropped on cache insertion

* update code-comment to expand CAS accronym

* use a plus1hULID() instead of 24h

* remove unused functions

* add note that public / local timeline requester can be nil

* fix incorrect visibility filtering of tag timeline statuses

* ensure we filter home timeline statuses on local only

* some small re-orderings to confirm query params in correct places

* fix the local only home timeline filter func
2025-04-26 09:56:15 +00:00

480 lines
13 KiB
Go

// GoToSocial
// Copyright (C) GoToSocial Authors admin@gotosocial.org
// SPDX-License-Identifier: AGPL-3.0-or-later
//
// This program is free software: you can redistribute it and/or modify
// it under the terms of the GNU Affero General Public License as published by
// the Free Software Foundation, either version 3 of the License, or
// (at your option) any later version.
//
// This program is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU Affero General Public License for more details.
//
// You should have received a copy of the GNU Affero General Public License
// along with this program. If not, see <http://www.gnu.org/licenses/>.
package bundb
import (
"context"
"errors"
"fmt"
"slices"
"time"
"github.com/superseriousbusiness/gotosocial/internal/db"
"github.com/superseriousbusiness/gotosocial/internal/gtscontext"
"github.com/superseriousbusiness/gotosocial/internal/gtserror"
"github.com/superseriousbusiness/gotosocial/internal/gtsmodel"
"github.com/superseriousbusiness/gotosocial/internal/log"
"github.com/superseriousbusiness/gotosocial/internal/paging"
"github.com/superseriousbusiness/gotosocial/internal/state"
"github.com/superseriousbusiness/gotosocial/internal/util/xslices"
"github.com/uptrace/bun"
)
type listDB struct {
db *bun.DB
state *state.State
}
/*
LIST FUNCTIONS
*/
func (l *listDB) GetListByID(ctx context.Context, id string) (*gtsmodel.List, error) {
return l.getList(
ctx,
"ID",
func(list *gtsmodel.List) error {
return l.db.NewSelect().
Model(list).
Where("? = ?", bun.Ident("list.id"), id).
Scan(ctx)
},
id,
)
}
func (l *listDB) getList(ctx context.Context, lookup string, dbQuery func(*gtsmodel.List) error, keyParts ...any) (*gtsmodel.List, error) {
list, err := l.state.Caches.DB.List.LoadOne(lookup, func() (*gtsmodel.List, error) {
var list gtsmodel.List
// Not cached! Perform database query.
if err := dbQuery(&list); err != nil {
return nil, err
}
return &list, nil
}, keyParts...)
if err != nil {
// already processed
return nil, err
}
if gtscontext.Barebones(ctx) {
// Only a barebones model was requested.
return list, nil
}
if err := l.state.DB.PopulateList(ctx, list); err != nil {
return nil, err
}
return list, nil
}
func (l *listDB) GetListsByAccountID(ctx context.Context, accountID string) ([]*gtsmodel.List, error) {
listIDs, err := l.GetListIDsByAccountID(ctx, accountID)
if err != nil {
return nil, err
}
return l.GetListsByIDs(ctx, listIDs)
}
func (l *listDB) CountListsByAccountID(ctx context.Context, accountID string) (int, error) {
listIDs, err := l.GetListIDsByAccountID(ctx, accountID)
return len(listIDs), err
}
func (l *listDB) GetListsContainingFollowID(ctx context.Context, followID string) ([]*gtsmodel.List, error) {
listIDs, err := l.getListIDsWithFollowID(ctx, followID)
if err != nil {
return nil, err
}
return l.GetListsByIDs(ctx, listIDs)
}
func (l *listDB) GetFollowsInList(ctx context.Context, listID string, page *paging.Page) ([]*gtsmodel.Follow, error) {
followIDs, err := l.GetFollowIDsInList(ctx, listID, page)
if err != nil {
return nil, err
}
return l.state.DB.GetFollowsByIDs(ctx, followIDs)
}
func (l *listDB) GetAccountsInList(ctx context.Context, listID string, page *paging.Page) ([]*gtsmodel.Account, error) {
accountIDs, err := l.GetAccountIDsInList(ctx, listID, page)
if err != nil {
return nil, err
}
return l.state.DB.GetAccountsByIDs(ctx, accountIDs)
}
func (l *listDB) IsAccountInList(ctx context.Context, listID string, accountID string) (bool, error) {
accountIDs, err := l.GetAccountIDsInList(ctx, listID, nil)
return slices.Contains(accountIDs, accountID), err
}
func (l *listDB) PopulateList(ctx context.Context, list *gtsmodel.List) error {
var (
err error
errs gtserror.MultiError
)
if list.Account == nil {
// List account is not set, fetch from the database.
list.Account, err = l.state.DB.GetAccountByID(
gtscontext.SetBarebones(ctx),
list.AccountID,
)
if err != nil {
errs.Appendf("error populating list account: %w", err)
}
}
return errs.Combine()
}
func (l *listDB) PutList(ctx context.Context, list *gtsmodel.List) error {
// note that inserting list will call OnInvalidateList()
// which will handle clearing caches other than List cache.
return l.state.Caches.DB.List.Store(list, func() error {
_, err := l.db.NewInsert().Model(list).Exec(ctx)
return err
})
}
func (l *listDB) UpdateList(ctx context.Context, list *gtsmodel.List, columns ...string) error {
list.UpdatedAt = time.Now()
if len(columns) > 0 {
// If we're updating by column, ensure "updated_at" is included.
columns = append(columns, "updated_at")
}
// Update list in the database, invalidating main list cache.
if err := l.state.Caches.DB.List.Store(list, func() error {
_, err := l.db.NewUpdate().
Model(list).
Where("? = ?", bun.Ident("list.id"), list.ID).
Column(columns...).
Exec(ctx)
return err
}); err != nil {
return err
}
// Clear cached timeline associated with list ID.
l.state.Caches.Timelines.List.Clear(list.ID)
return nil
}
func (l *listDB) DeleteListByID(ctx context.Context, id string) error {
// Acquire list owner ID.
var accountID string
// Gather follow IDs of all
// entries contained in list.
var followIDs []string
// Delete all list entries associated with list, and list itself in transaction.
if err := l.db.RunInTx(ctx, nil, func(ctx context.Context, tx bun.Tx) error {
if _, err := tx.NewDelete().
Table("list_entries").
Where("? = ?", bun.Ident("list_id"), id).
Returning("?", bun.Ident("follow_id")).
Exec(ctx, &followIDs); err != nil {
return err
}
_, err := tx.NewDelete().
Table("lists").
Where("? = ?", bun.Ident("id"), id).
Returning("?", bun.Ident("account_id")).
Exec(ctx, &accountID)
return err
}); err != nil {
return err
}
// Invalidate the main list database cache.
l.state.Caches.DB.List.Invalidate("ID", id)
// Invalidate cache of list IDs owned by account.
l.state.Caches.DB.ListIDs.Invalidate("a" + accountID)
// Invalidate all related entry caches for this list.
l.invalidateEntryCaches(ctx, []string{id}, followIDs)
// Delete the cached timeline of list.
l.state.Caches.Timelines.List.Delete(id)
return nil
}
func (l *listDB) GetListIDsByAccountID(ctx context.Context, accountID string) ([]string, error) {
return l.state.Caches.DB.ListIDs.Load("a"+accountID, func() ([]string, error) {
var listIDs []string
// List IDs not in cache.
// Perform the DB query.
if _, err := l.db.NewSelect().
Table("lists").
Column("id").
Where("? = ?", bun.Ident("account_id"), accountID).
OrderExpr("? DESC", bun.Ident("created_at")).
Exec(ctx, &listIDs); err != nil &&
!errors.Is(err, db.ErrNoEntries) {
return nil, err
}
return listIDs, nil
})
}
func (l *listDB) getListIDsWithFollowID(ctx context.Context, followID string) ([]string, error) {
return l.state.Caches.DB.ListIDs.Load("f"+followID, func() ([]string, error) {
var listIDs []string
// List IDs not in cache.
// Perform the DB query.
if _, err := l.db.NewSelect().
Table("list_entries").
Column("list_id").
Where("? = ?", bun.Ident("follow_id"), followID).
OrderExpr("? DESC", bun.Ident("created_at")).
Exec(ctx, &listIDs); err != nil &&
!errors.Is(err, db.ErrNoEntries) {
return nil, err
}
return listIDs, nil
})
}
func (l *listDB) GetFollowIDsInList(ctx context.Context, listID string, page *paging.Page) ([]string, error) {
return loadPagedIDs(&l.state.Caches.DB.ListedIDs, "f"+listID, page, func() ([]string, error) {
var followIDs []string
// Follow IDs not in cache.
// Perform the DB query.
_, err := l.db.NewSelect().
Table("list_entries").
Column("follow_id").
Where("? = ?", bun.Ident("list_id"), listID).
OrderExpr("? DESC", bun.Ident("created_at")).
Exec(ctx, &followIDs)
if err != nil && !errors.Is(err, db.ErrNoEntries) {
return nil, err
}
return followIDs, nil
})
}
func (l *listDB) GetAccountIDsInList(ctx context.Context, listID string, page *paging.Page) ([]string, error) {
return loadPagedIDs(&l.state.Caches.DB.ListedIDs, "a"+listID, page, func() ([]string, error) {
var accountIDs []string
// Account IDs not in cache.
// Perform the DB query.
_, err := l.db.NewSelect().
Table("follows").
Column("follows.target_account_id").
Join("INNER JOIN ?", bun.Ident("list_entries")).
JoinOn("? = ?", bun.Ident("follows.id"), bun.Ident("list_entries.follow_id")).
Where("? = ?", bun.Ident("list_entries.list_id"), listID).
OrderExpr("? DESC", bun.Ident("list_entries.id")).
Exec(ctx, &accountIDs)
if err != nil && !errors.Is(err, db.ErrNoEntries) {
return nil, err
}
return accountIDs, nil
})
}
func (l *listDB) GetListsByIDs(ctx context.Context, ids []string) ([]*gtsmodel.List, error) {
// Load all list IDs via cache loader callbacks.
lists, err := l.state.Caches.DB.List.LoadIDs("ID",
ids,
func(uncached []string) ([]*gtsmodel.List, error) {
// Preallocate expected length of uncached lists.
lists := make([]*gtsmodel.List, 0, len(uncached))
// Perform database query scanning
// the remaining (uncached) IDs.
if err := l.db.NewSelect().
Model(&lists).
Where("? IN (?)", bun.Ident("id"), bun.In(uncached)).
Scan(ctx); err != nil {
return nil, err
}
return lists, nil
},
)
if err != nil {
return nil, err
}
// Reorder the lists by their
// IDs to ensure in correct order.
getID := func(l *gtsmodel.List) string { return l.ID }
xslices.OrderBy(lists, ids, getID)
if gtscontext.Barebones(ctx) {
// no need to fully populate.
return lists, nil
}
// Populate all loaded lists, removing those we fail to
// populate (removes needing so many nil checks everywhere).
lists = slices.DeleteFunc(lists, func(list *gtsmodel.List) bool {
if err := l.PopulateList(ctx, list); err != nil {
log.Errorf(ctx, "error populating list %s: %v", list.ID, err)
return true
}
return false
})
return lists, nil
}
func (l *listDB) PopulateListEntry(ctx context.Context, listEntry *gtsmodel.ListEntry) error {
var err error
if listEntry.Follow == nil {
// ListEntry follow is not set, fetch from the database.
listEntry.Follow, err = l.state.DB.GetFollowByID(
gtscontext.SetBarebones(ctx),
listEntry.FollowID,
)
if err != nil {
return fmt.Errorf("error populating listEntry follow: %w", err)
}
}
return nil
}
func (l *listDB) PutListEntries(ctx context.Context, entries []*gtsmodel.ListEntry) error {
// Insert all entries into the database in a single transaction (all or nothing!).
if err := l.db.RunInTx(ctx, nil, func(ctx context.Context, tx bun.Tx) error {
for _, entry := range entries {
if _, err := tx.
NewInsert().
Model(entry).
Exec(ctx); err != nil {
return err
}
}
return nil
}); err != nil {
return err
}
// Collect unique list IDs from the provided list entries.
listIDs := xslices.Collate(entries, func(e *gtsmodel.ListEntry) string {
return e.ListID
})
// Collect unique follow IDs from the provided list entries.
followIDs := xslices.Collate(entries, func(e *gtsmodel.ListEntry) string {
return e.FollowID
})
// Invalidate all related list entry caches.
l.invalidateEntryCaches(ctx, listIDs, followIDs)
return nil
}
func (l *listDB) DeleteListEntry(ctx context.Context, listID string, followID string) error {
// Delete list entry with given
// ID, returning its list ID.
if _, err := l.db.NewDelete().
Table("list_entries").
Where("? = ?", bun.Ident("list_id"), listID).
Where("? = ?", bun.Ident("follow_id"), followID).
Exec(ctx, &listID); err != nil &&
!errors.Is(err, db.ErrNoEntries) {
return err
}
// Invalidate all related list entry caches.
l.invalidateEntryCaches(ctx, []string{listID},
[]string{followID})
return nil
}
func (l *listDB) DeleteAllListEntriesByFollows(ctx context.Context, followIDs ...string) error {
var listIDs []string
// Check for empty list.
if len(followIDs) == 0 {
return nil
}
// Delete all entries with follow
// ID, returning IDs and list IDs.
if _, err := l.db.NewDelete().
Table("list_entries").
Where("? IN (?)", bun.Ident("follow_id"), bun.In(followIDs)).
Returning("?", bun.Ident("list_id")).
Exec(ctx, &listIDs); err != nil &&
!errors.Is(err, db.ErrNoEntries) {
return err
}
// Deduplicate IDs before invalidate.
listIDs = xslices.Deduplicate(listIDs)
// Invalidate all related list entry caches.
l.invalidateEntryCaches(ctx, listIDs, followIDs)
return nil
}
// invalidateEntryCaches will invalidate all related ListEntry caches for given list IDs and follow IDs, including timelines.
func (l *listDB) invalidateEntryCaches(ctx context.Context, listIDs, followIDs []string) {
var keys []string
// Generate ListedID keys to invalidate.
keys = slices.Grow(keys[:0], 2*len(listIDs))
for _, listID := range listIDs {
keys = append(keys,
"a"+listID,
"f"+listID,
)
// Invalidate list timeline cache by ID.
l.state.Caches.Timelines.List.Clear(listID)
}
// Invalidate ListedID slice cache entries.
l.state.Caches.DB.ListedIDs.Invalidate(keys...)
// Generate ListID keys to invalidate.
keys = slices.Grow(keys[:0], len(followIDs))
for _, followID := range followIDs {
keys = append(keys, "f"+followID)
}
// Invalidate ListID slice cache entries.
l.state.Caches.DB.ListIDs.Invalidate(keys...)
}