mirror of
https://github.com/aptly-dev/aptly.git
synced 2026-02-15 09:01:30 +00:00
In current aptly, each repository and snapshot has its own reflist in the database. This brings a few problems with it: - Given a sufficiently large repositories and snapshots, these lists can get enormous, reaching >1MB. This is a problem for LevelDB's overall performance, as it tends to prefer values around the confiruged block size (defaults to just 4KiB). - When you take these large repositories and snapshot them, you have a full, new copy of the reflist, even if only a few packages changed. This means that having a lot of snapshots with a few changes causes the database to basically be full of largely duplicate reflists. - All the duplication also means that many of the same refs are being loaded repeatedly, which can cause some slowdown but, more notably, eats up huge amounts of memory. - Adding on more and more new repositories and snapshots will cause the time and memory spent on things like cleanup and publishing to grow roughly linearly. At the core, there are two problems here: - Reflists get very big because there are just a lot of packages. - Different reflists can tend to duplicate much of the same contents. *Split reflists* aim at solving this by separating reflists into 64 *buckets*. Package refs are sorted into individual buckets according to the following system: - Take the first 3 letters of the package name, after dropping a `lib` prefix. (Using only the first 3 letters will cause packages with similar prefixes to end up in the same bucket, under the assumption that packages with similar names tend to be updated together.) - Take the 64-bit xxhash of these letters. (xxhash was chosen because it relatively good distribution across the individual bits, which is important for the next step.) - Use the first 6 bits of the hash (range [0:63]) as an index into the buckets. Once refs are placed in buckets, a sha256 digest of all the refs in the bucket is taken. These buckets are then stored in the database, split into roughly block-sized segments, and all the repositories and snapshots simply store an array of bucket digests. This approach means that *repositories and snapshots can share their reflist buckets*. If a snapshot is taken of a repository, it will have the same contents, so its split reflist will point to the same buckets as the base repository, and only one copy of each bucket is stored in the database. When some packages in the repository change, only the buckets containing those packages will be modified; all the other buckets will remain unchanged, and thus their contents will still be shared. Later on, when these reflists are loaded, each bucket is only loaded once, short-cutting loaded many megabytes of data. In effect, split reflists are essentially copy-on-write, with only the changed buckets stored individually. Changing the disk format means that a migration needs to take place, so that task is moved into the database cleanup step, which will migrate reflists over to split reflists, as well as delete any unused reflist buckets. All the reflist tests are also changed to additionally test out split reflists; although the internal logic is all shared (since buckets are, themselves, just normal reflists), some special additions are needed to have native versions of the various reflist helper methods. In our tests, we've observed the following improvements: - Memory usage during publish and database cleanup, with `GOMEMLIMIT=2GiB`, goes down from ~3.2GiB (larger than the memory limit!) to ~0.7GiB, a decrease of ~4.5x. - Database size decreases from 1.3GB to 367MB. *In my local tests*, publish times had also decreased down to mere seconds but the same effect wasn't observed on the server, with the times staying around the same. My suspicions are that this is due to I/O performance: my local system is an M1 MBP, which almost certainly has much faster disk speeds than our DigitalOcean block volumes. Split reflists include a side effect of requiring more random accesses from reading all the buckets by their keys, so if your random I/O performance is slower, it might cancel out the benefits. That being said, even in that case, the memory usage and database size advantages still persist. Signed-off-by: Ryan Gonzalez <ryan.gonzalez@collabora.com>
230 lines
6.8 KiB
Go
230 lines
6.8 KiB
Go
package api
|
||
|
||
import (
|
||
"fmt"
|
||
"sort"
|
||
|
||
"github.com/aptly-dev/aptly/aptly"
|
||
"github.com/aptly-dev/aptly/database"
|
||
"github.com/aptly-dev/aptly/deb"
|
||
"github.com/aptly-dev/aptly/task"
|
||
"github.com/aptly-dev/aptly/utils"
|
||
"github.com/gin-gonic/gin"
|
||
)
|
||
|
||
// @Summary DB Cleanup
|
||
// @Description **Cleanup Aptly DB**
|
||
// @Description Database cleanup removes information about unreferenced packages and deletes files in the package pool that aren’t used by packages anymore.
|
||
// @Description It is a good idea to run this command after massive deletion of mirrors, snapshots or local repos.
|
||
// @Tags Database
|
||
// @Produce json
|
||
// @Param _async query bool false "Run in background and return task object"
|
||
// @Success 200 {object} string "Output"
|
||
// @Failure 404 {object} Error "Not Found"
|
||
// @Router /api/db/cleanup [post]
|
||
func apiDbCleanup(c *gin.Context) {
|
||
resources := []string{string(task.AllResourcesKey)}
|
||
maybeRunTaskInBackground(c, "Clean up db", resources, func(out aptly.Progress, detail *task.Detail) (*task.ProcessReturnValue, error) {
|
||
var err error
|
||
|
||
collectionFactory := context.NewCollectionFactory()
|
||
|
||
// collect information about referenced packages and their reflist buckets...
|
||
existingPackageRefs := deb.NewSplitRefList()
|
||
existingBuckets := deb.NewRefListDigestSet()
|
||
|
||
reflistMigration := collectionFactory.RefListCollection().NewMigration()
|
||
|
||
out.Printf("Loading mirrors, local repos, snapshots and published repos...")
|
||
err = collectionFactory.RemoteRepoCollection().ForEach(func(repo *deb.RemoteRepo) error {
|
||
sl := deb.NewSplitRefList()
|
||
e := collectionFactory.RefListCollection().LoadCompleteAndMigrate(sl, repo.RefKey(), reflistMigration)
|
||
if e != nil && e != database.ErrNotFound {
|
||
return e
|
||
}
|
||
|
||
existingPackageRefs = existingPackageRefs.Merge(sl, false, true)
|
||
existingBuckets.AddAllInRefList(sl)
|
||
|
||
return nil
|
||
})
|
||
if err != nil {
|
||
return nil, err
|
||
}
|
||
|
||
err = collectionFactory.LocalRepoCollection().ForEach(func(repo *deb.LocalRepo) error {
|
||
sl := deb.NewSplitRefList()
|
||
e := collectionFactory.RefListCollection().LoadCompleteAndMigrate(sl, repo.RefKey(), reflistMigration)
|
||
if e != nil && e != database.ErrNotFound {
|
||
return e
|
||
}
|
||
|
||
existingPackageRefs = existingPackageRefs.Merge(sl, false, true)
|
||
existingBuckets.AddAllInRefList(sl)
|
||
|
||
return nil
|
||
})
|
||
if err != nil {
|
||
return nil, err
|
||
}
|
||
|
||
err = collectionFactory.SnapshotCollection().ForEach(func(snapshot *deb.Snapshot) error {
|
||
sl := deb.NewSplitRefList()
|
||
e := collectionFactory.RefListCollection().LoadCompleteAndMigrate(sl, snapshot.RefKey(), reflistMigration)
|
||
if e != nil {
|
||
return e
|
||
}
|
||
|
||
existingPackageRefs = existingPackageRefs.Merge(sl, false, true)
|
||
existingBuckets.AddAllInRefList(sl)
|
||
|
||
return nil
|
||
})
|
||
if err != nil {
|
||
return nil, err
|
||
}
|
||
|
||
err = collectionFactory.PublishedRepoCollection().ForEach(func(published *deb.PublishedRepo) error {
|
||
if published.SourceKind != deb.SourceLocalRepo {
|
||
return nil
|
||
}
|
||
|
||
for _, component := range published.Components() {
|
||
sl := deb.NewSplitRefList()
|
||
e := collectionFactory.RefListCollection().LoadCompleteAndMigrate(sl, published.RefKey(component), reflistMigration)
|
||
if e != nil {
|
||
return e
|
||
}
|
||
|
||
existingPackageRefs = existingPackageRefs.Merge(sl, false, true)
|
||
existingBuckets.AddAllInRefList(sl)
|
||
}
|
||
return nil
|
||
})
|
||
if err != nil {
|
||
return nil, err
|
||
}
|
||
|
||
err = reflistMigration.Flush()
|
||
if err != nil {
|
||
return nil, err
|
||
}
|
||
if stats := reflistMigration.Stats(); stats.Reflists > 0 {
|
||
out.Printf("Split %d reflist(s) into %d bucket(s) (%d segment(s))",
|
||
stats.Reflists, stats.Buckets, stats.Segments)
|
||
}
|
||
|
||
// ... and compare it to the list of all packages
|
||
out.Printf("Loading list of all packages...")
|
||
allPackageRefs := collectionFactory.PackageCollection().AllPackageRefs()
|
||
|
||
toDelete := allPackageRefs.Subtract(existingPackageRefs.Flatten())
|
||
|
||
// delete packages that are no longer referenced
|
||
out.Printf("Deleting unreferenced packages (%d)...", toDelete.Len())
|
||
|
||
// database can't err as collection factory already constructed
|
||
db, _ := context.Database()
|
||
|
||
if toDelete.Len() > 0 {
|
||
batch := db.CreateBatch()
|
||
toDelete.ForEach(func(ref []byte) error {
|
||
collectionFactory.PackageCollection().DeleteByKey(ref, batch)
|
||
return nil
|
||
})
|
||
|
||
err = batch.Write()
|
||
if err != nil {
|
||
return nil, fmt.Errorf("unable to write to DB: %s", err)
|
||
}
|
||
}
|
||
|
||
bucketsToDelete, err := collectionFactory.RefListCollection().AllBucketDigests()
|
||
if err != nil {
|
||
return nil, err
|
||
}
|
||
|
||
bucketsToDelete.RemoveAll(existingBuckets)
|
||
|
||
out.Printf("Deleting unreferenced reflist buckets (%d)...", bucketsToDelete.Len())
|
||
if bucketsToDelete.Len() > 0 {
|
||
batch := db.CreateBatch()
|
||
err := bucketsToDelete.ForEach(func(digest []byte) error {
|
||
return collectionFactory.RefListCollection().UnsafeDropBucket(digest, batch)
|
||
})
|
||
if err != nil {
|
||
return nil, err
|
||
}
|
||
|
||
if err := batch.Write(); err != nil {
|
||
return nil, err
|
||
}
|
||
}
|
||
|
||
// now, build a list of files that should be present in Repository (package pool)
|
||
out.Printf("Building list of files referenced by packages...")
|
||
referencedFiles := make([]string, 0, existingPackageRefs.Len())
|
||
|
||
err = existingPackageRefs.ForEach(func(key []byte) error {
|
||
pkg, err2 := collectionFactory.PackageCollection().ByKey(key)
|
||
if err2 != nil {
|
||
tail := ""
|
||
return fmt.Errorf("unable to load package %s: %s%s", string(key), err2, tail)
|
||
}
|
||
paths, err2 := pkg.FilepathList(context.PackagePool())
|
||
if err2 != nil {
|
||
return err2
|
||
}
|
||
referencedFiles = append(referencedFiles, paths...)
|
||
|
||
return nil
|
||
})
|
||
if err != nil {
|
||
return nil, err
|
||
}
|
||
|
||
sort.Strings(referencedFiles)
|
||
|
||
// build a list of files in the package pool
|
||
out.Printf("Building list of files in package pool...")
|
||
existingFiles, err := context.PackagePool().FilepathList(out)
|
||
if err != nil {
|
||
return nil, fmt.Errorf("unable to collect file paths: %s", err)
|
||
}
|
||
|
||
// find files which are in the pool but not referenced by packages
|
||
filesToDelete := utils.StrSlicesSubstract(existingFiles, referencedFiles)
|
||
|
||
// delete files that are no longer referenced
|
||
out.Printf("Deleting unreferenced files (%d)...", len(filesToDelete))
|
||
|
||
countFilesToDelete := len(filesToDelete)
|
||
taskDetail := struct {
|
||
TotalNumberOfPackagesToDelete int
|
||
RemainingNumberOfPackagesToDelete int
|
||
}{
|
||
countFilesToDelete, countFilesToDelete,
|
||
}
|
||
detail.Store(taskDetail)
|
||
|
||
if countFilesToDelete > 0 {
|
||
var size, totalSize int64
|
||
for _, file := range filesToDelete {
|
||
size, err = context.PackagePool().Remove(file)
|
||
if err != nil {
|
||
return nil, err
|
||
}
|
||
|
||
taskDetail.RemainingNumberOfPackagesToDelete--
|
||
detail.Store(taskDetail)
|
||
totalSize += size
|
||
}
|
||
|
||
out.Printf("Disk space freed: %s...", utils.HumanBytes(totalSize))
|
||
}
|
||
|
||
out.Printf("Compacting database...")
|
||
return nil, db.CompactDB()
|
||
})
|
||
}
|