aboutsummaryrefslogtreecommitdiffstats
path: root/storage/filesystem
diff options
context:
space:
mode:
authorzeripath <art27@cantab.net>2021-05-12 21:42:07 +0100
committerGitHub <noreply@github.com>2021-05-12 22:42:07 +0200
commit720c192831a890d0a36b4c6720b60411fa4a0159 (patch)
tree9f3020c074fe9b113e22d6f2c601e8a36bf0ac49 /storage/filesystem
parente6e23391e4d044cc85e09b4420a2533715e7312d (diff)
downloadgo-git-720c192831a890d0a36b4c6720b60411fa4a0159.tar.gz
plumbing: format/packfile, prevent large objects from being read into memory completely (#303)v5.4.0
This PR adds code to prevent large objects from being read into memory from packfiles or the filesystem. Objects greater than 1Mb are now no longer directly stored in the cache or read completely into memory. Signed-off-by: Andrew Thornton <art27@cantab.net>
Diffstat (limited to 'storage/filesystem')
-rw-r--r--storage/filesystem/dotgit/reader.go79
-rw-r--r--storage/filesystem/object.go9
2 files changed, 87 insertions, 1 deletions
diff --git a/storage/filesystem/dotgit/reader.go b/storage/filesystem/dotgit/reader.go
new file mode 100644
index 0000000..a82ac94
--- /dev/null
+++ b/storage/filesystem/dotgit/reader.go
@@ -0,0 +1,79 @@
+package dotgit
+
+import (
+ "fmt"
+ "io"
+ "os"
+
+ "github.com/go-git/go-git/v5/plumbing"
+ "github.com/go-git/go-git/v5/plumbing/format/objfile"
+ "github.com/go-git/go-git/v5/utils/ioutil"
+)
+
+var _ (plumbing.EncodedObject) = &EncodedObject{}
+
+type EncodedObject struct {
+ dir *DotGit
+ h plumbing.Hash
+ t plumbing.ObjectType
+ sz int64
+}
+
+func (e *EncodedObject) Hash() plumbing.Hash {
+ return e.h
+}
+
+func (e *EncodedObject) Reader() (io.ReadCloser, error) {
+ f, err := e.dir.Object(e.h)
+ if err != nil {
+ if os.IsNotExist(err) {
+ return nil, plumbing.ErrObjectNotFound
+ }
+
+ return nil, err
+ }
+ r, err := objfile.NewReader(f)
+ if err != nil {
+ return nil, err
+ }
+
+ t, size, err := r.Header()
+ if err != nil {
+ _ = r.Close()
+ return nil, err
+ }
+ if t != e.t {
+ _ = r.Close()
+ return nil, objfile.ErrHeader
+ }
+ if size != e.sz {
+ _ = r.Close()
+ return nil, objfile.ErrHeader
+ }
+ return ioutil.NewReadCloserWithCloser(r, f.Close), nil
+}
+
+func (e *EncodedObject) SetType(plumbing.ObjectType) {}
+
+func (e *EncodedObject) Type() plumbing.ObjectType {
+ return e.t
+}
+
+func (e *EncodedObject) Size() int64 {
+ return e.sz
+}
+
+func (e *EncodedObject) SetSize(int64) {}
+
+func (e *EncodedObject) Writer() (io.WriteCloser, error) {
+ return nil, fmt.Errorf("Not supported")
+}
+
+func NewEncodedObject(dir *DotGit, h plumbing.Hash, t plumbing.ObjectType, size int64) *EncodedObject {
+ return &EncodedObject{
+ dir: dir,
+ h: h,
+ t: t,
+ sz: size,
+ }
+}
diff --git a/storage/filesystem/object.go b/storage/filesystem/object.go
index 0c25dad..4862362 100644
--- a/storage/filesystem/object.go
+++ b/storage/filesystem/object.go
@@ -389,7 +389,6 @@ func (s *ObjectStorage) getFromUnpacked(h plumbing.Hash) (obj plumbing.EncodedOb
return cacheObj, nil
}
- obj = s.NewEncodedObject()
r, err := objfile.NewReader(f)
if err != nil {
return nil, err
@@ -402,6 +401,14 @@ func (s *ObjectStorage) getFromUnpacked(h plumbing.Hash) (obj plumbing.EncodedOb
return nil, err
}
+ if size > packfile.LargeObjectThreshold {
+ obj = dotgit.NewEncodedObject(s.dir, h, t, size)
+ s.objectCache.Put(obj)
+ return obj, nil
+ }
+
+ obj = s.NewEncodedObject()
+
obj.SetType(t)
obj.SetSize(size)
w, err := obj.Writer()