[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
This commit is contained in:
kim 2025-04-26 09:56:15 +00:00 committed by GitHub
commit 6a6a499333
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
108 changed files with 2935 additions and 5213 deletions

View file

@ -22,155 +22,93 @@ import (
"errors"
apimodel "github.com/superseriousbusiness/gotosocial/internal/api/model"
apiutil "github.com/superseriousbusiness/gotosocial/internal/api/util"
"github.com/superseriousbusiness/gotosocial/internal/db"
statusfilter "github.com/superseriousbusiness/gotosocial/internal/filter/status"
"github.com/superseriousbusiness/gotosocial/internal/filter/usermute"
"github.com/superseriousbusiness/gotosocial/internal/filter/visibility"
"github.com/superseriousbusiness/gotosocial/internal/gtscontext"
"github.com/superseriousbusiness/gotosocial/internal/gtserror"
"github.com/superseriousbusiness/gotosocial/internal/gtsmodel"
"github.com/superseriousbusiness/gotosocial/internal/state"
"github.com/superseriousbusiness/gotosocial/internal/timeline"
"github.com/superseriousbusiness/gotosocial/internal/typeutils"
"github.com/superseriousbusiness/gotosocial/internal/util"
"github.com/superseriousbusiness/gotosocial/internal/log"
"github.com/superseriousbusiness/gotosocial/internal/paging"
)
// ListTimelineGrab returns a function that satisfies GrabFunction for list timelines.
func ListTimelineGrab(state *state.State) timeline.GrabFunction {
return func(ctx context.Context, listID string, maxID string, sinceID string, minID string, limit int) ([]timeline.Timelineable, bool, error) {
statuses, err := state.DB.GetListTimeline(ctx, listID, maxID, sinceID, minID, limit)
if err != nil && !errors.Is(err, db.ErrNoEntries) {
err = gtserror.Newf("error getting statuses from db: %w", err)
return nil, false, err
}
count := len(statuses)
if count == 0 {
// We just don't have enough statuses
// left in the db so return stop = true.
return nil, true, nil
}
items := make([]timeline.Timelineable, count)
for i, s := range statuses {
items[i] = s
}
return items, false, nil
}
}
// ListTimelineFilter returns a function that satisfies FilterFunction for list timelines.
func ListTimelineFilter(state *state.State, visFilter *visibility.Filter) timeline.FilterFunction {
return func(ctx context.Context, listID string, item timeline.Timelineable) (shouldIndex bool, err error) {
status, ok := item.(*gtsmodel.Status)
if !ok {
err = gtserror.New("could not convert item to *gtsmodel.Status")
return false, err
}
list, err := state.DB.GetListByID(ctx, listID)
if err != nil {
err = gtserror.Newf("error getting list with id %s: %w", listID, err)
return false, err
}
requestingAccount, err := state.DB.GetAccountByID(ctx, list.AccountID)
if err != nil {
err = gtserror.Newf("error getting account with id %s: %w", list.AccountID, err)
return false, err
}
timelineable, err := visFilter.StatusHomeTimelineable(ctx, requestingAccount, status)
if err != nil {
err = gtserror.Newf("error checking hometimelineability of status %s for account %s: %w", status.ID, list.AccountID, err)
return false, err
}
return timelineable, nil
}
}
// ListTimelineStatusPrepare returns a function that satisfies PrepareFunction for list timelines.
func ListTimelineStatusPrepare(state *state.State, converter *typeutils.Converter) timeline.PrepareFunction {
return func(ctx context.Context, listID string, itemID string) (timeline.Preparable, error) {
status, err := state.DB.GetStatusByID(ctx, itemID)
if err != nil {
err = gtserror.Newf("error getting status with id %s: %w", itemID, err)
return nil, err
}
list, err := state.DB.GetListByID(ctx, listID)
if err != nil {
err = gtserror.Newf("error getting list with id %s: %w", listID, err)
return nil, err
}
requestingAccount, err := state.DB.GetAccountByID(ctx, list.AccountID)
if err != nil {
err = gtserror.Newf("error getting account with id %s: %w", list.AccountID, err)
return nil, err
}
filters, err := state.DB.GetFiltersForAccountID(ctx, requestingAccount.ID)
if err != nil {
err = gtserror.Newf("couldn't retrieve filters for account %s: %w", requestingAccount.ID, err)
return nil, err
}
mutes, err := state.DB.GetAccountMutes(gtscontext.SetBarebones(ctx), requestingAccount.ID, nil)
if err != nil {
err = gtserror.Newf("couldn't retrieve mutes for account %s: %w", requestingAccount.ID, err)
return nil, err
}
compiledMutes := usermute.NewCompiledUserMuteList(mutes)
return converter.StatusToAPIStatus(ctx, status, requestingAccount, statusfilter.FilterContextHome, filters, compiledMutes)
}
}
func (p *Processor) ListTimelineGet(ctx context.Context, authed *apiutil.Auth, listID string, maxID string, sinceID string, minID string, limit int) (*apimodel.PageableResponse, gtserror.WithCode) {
// Ensure list exists + is owned by this account.
list, err := p.state.DB.GetListByID(ctx, listID)
if err != nil {
if errors.Is(err, db.ErrNoEntries) {
return nil, gtserror.NewErrorNotFound(err)
}
// ListTimelineGet gets a pageable timeline of statuses
// in the list timeline of ID by the requesting account.
func (p *Processor) ListTimelineGet(
ctx context.Context,
requester *gtsmodel.Account,
listID string,
page *paging.Page,
) (
*apimodel.PageableResponse,
gtserror.WithCode,
) {
// Fetch the requested list with ID.
list, err := p.state.DB.GetListByID(
gtscontext.SetBarebones(ctx),
listID,
)
if err != nil && !errors.Is(err, db.ErrNoEntries) {
return nil, gtserror.NewErrorInternalError(err)
}
if list.AccountID != authed.Account.ID {
err = gtserror.Newf("list with id %s does not belong to account %s", list.ID, authed.Account.ID)
// Check exists.
if list == nil {
const text = "list not found"
return nil, gtserror.NewErrorNotFound(
errors.New(text),
text,
)
}
// Check list owned by auth'd account.
if list.AccountID != requester.ID {
err := gtserror.New("list does not belong to account")
return nil, gtserror.NewErrorNotFound(err)
}
statuses, err := p.state.Timelines.List.GetTimeline(ctx, listID, maxID, sinceID, minID, limit, false)
if err != nil && !errors.Is(err, db.ErrNoEntries) {
err = gtserror.Newf("error getting statuses: %w", err)
return nil, gtserror.NewErrorInternalError(err)
}
// Fetch status timeline for list.
return p.getStatusTimeline(ctx,
count := len(statuses)
if count == 0 {
return util.EmptyPageableResponse(), nil
}
// Auth'd
// account.
requester,
var (
items = make([]interface{}, count)
nextMaxIDValue = statuses[count-1].GetID()
prevMinIDValue = statuses[0].GetID()
// Keyed-by-list-ID, list timeline cache.
p.state.Caches.Timelines.List.MustGet(listID),
// Current
// page.
page,
// List timeline ID's endpoint.
"/api/v1/timelines/list/"+listID,
// No page
// query.
nil,
// Status filter context.
statusfilter.FilterContextHome,
// Database load function.
func(pg *paging.Page) (statuses []*gtsmodel.Status, err error) {
return p.state.DB.GetListTimeline(ctx, listID, pg)
},
// Filtering function,
// i.e. filter before caching.
func(s *gtsmodel.Status) bool {
// Check the visibility of passed status to requesting user.
ok, err := p.visFilter.StatusHomeTimelineable(ctx, requester, s)
if err != nil {
log.Errorf(ctx, "error filtering status %s: %v", s.URI, err)
}
return !ok
},
// Post filtering funtion,
// i.e. filter after caching.
nil,
)
for i := range statuses {
items[i] = statuses[i]
}
return util.PackagePageableResponse(util.PageableResponseParams{
Items: items,
Path: "/api/v1/timelines/list/" + listID,
NextMaxIDValue: nextMaxIDValue,
PrevMinIDValue: prevMinIDValue,
Limit: limit,
})
}