1
0
mirror of https://github.com/golang/go synced 2024-10-01 05:18:33 -06:00
go/internal/lsp/cache/cache.go
Heschi Kreinick ecd3fc4348 internal/lsp: read files eagerly
We use file identities pervasively throughout gopls. Prior to this
change, the identity is the modification date of an unopened file, or
the hash of an opened file. That means that opening a file changes its
identity, which causes unnecessary churn in the cache.

Unfortunately, there isn't an easy way to fix this. Changing the
cache key to something else, such as the modification time, means that
we won't unify cache entries if a change is made and then undone. The
approach here is to read files eagerly in GetFile, so that we know their
hashes immediately. That resolves the churn, but means that we do a ton
of file IO at startup.

Incidental changes:

Remove the FileSystem interface; there was only one implementation and
it added a fair amount of cruft. We have many other places that assume
os.Stat and such work.

Add direct accessors to FileHandle for URI, Kind, and Version. Most uses
of (FileHandle).Identity were for stuff that we derive solely from the
URI, and this helped me disentangle them. It is a *ton* of churn,
though. I can revert it if you want.

Change-Id: Ia2133bc527f71daf81c9d674951726a232ca5bc9
Reviewed-on: https://go-review.googlesource.com/c/tools/+/237037
Run-TryBot: Heschi Kreinick <heschi@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Rebecca Stambler <rstambler@golang.org>
2020-06-11 22:11:59 +00:00

158 lines
3.4 KiB
Go

// Copyright 2019 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package cache
import (
"context"
"crypto/sha1"
"fmt"
"go/token"
"io/ioutil"
"os"
"reflect"
"strconv"
"sync/atomic"
"time"
"golang.org/x/tools/internal/event"
"golang.org/x/tools/internal/lsp/debug/tag"
"golang.org/x/tools/internal/lsp/source"
"golang.org/x/tools/internal/memoize"
"golang.org/x/tools/internal/span"
errors "golang.org/x/xerrors"
)
func New(ctx context.Context, options func(*source.Options)) *Cache {
index := atomic.AddInt64(&cacheIndex, 1)
c := &Cache{
id: strconv.FormatInt(index, 10),
fset: token.NewFileSet(),
options: options,
}
return c
}
type Cache struct {
id string
fset *token.FileSet
options func(*source.Options)
store memoize.Store
}
type fileKey struct {
uri span.URI
modTime time.Time
}
type fileHandle struct {
uri span.URI
memoize.NoCopy
bytes []byte
hash string
err error
}
func (c *Cache) GetFile(ctx context.Context, uri span.URI) (source.FileHandle, error) {
var modTime time.Time
if fi, err := os.Stat(uri.Filename()); err == nil {
modTime = fi.ModTime()
}
key := fileKey{
uri: uri,
modTime: modTime,
}
h := c.store.Bind(key, func(ctx context.Context) interface{} {
return readFile(ctx, uri, modTime)
})
v := h.Get(ctx)
if v == nil {
return nil, ctx.Err()
}
return v.(*fileHandle), nil
}
// ioLimit limits the number of parallel file reads per process.
var ioLimit = make(chan struct{}, 128)
func readFile(ctx context.Context, uri span.URI, origTime time.Time) *fileHandle {
ctx, done := event.Start(ctx, "cache.getFile", tag.File.Of(uri.Filename()))
_ = ctx
defer done()
ioLimit <- struct{}{}
defer func() { <-ioLimit }()
var modTime time.Time
if fi, err := os.Stat(uri.Filename()); err == nil {
modTime = fi.ModTime()
}
if modTime != origTime {
return &fileHandle{err: errors.Errorf("%s: file has been modified", uri.Filename())}
}
data, err := ioutil.ReadFile(uri.Filename())
if err != nil {
return &fileHandle{err: err}
}
return &fileHandle{
uri: uri,
bytes: data,
hash: hashContents(data),
}
}
func (c *Cache) NewSession(ctx context.Context) *Session {
index := atomic.AddInt64(&sessionIndex, 1)
s := &Session{
cache: c,
id: strconv.FormatInt(index, 10),
options: source.DefaultOptions(),
overlays: make(map[span.URI]*overlay),
}
event.Log(ctx, "New session", KeyCreateSession.Of(s))
return s
}
func (c *Cache) FileSet() *token.FileSet {
return c.fset
}
func (h *fileHandle) URI() span.URI {
return h.uri
}
func (h *fileHandle) Kind() source.FileKind {
return source.DetectLanguage("", h.uri.Filename())
}
func (h *fileHandle) Version() float64 {
return 0
}
func (h *fileHandle) Identity() source.FileIdentity {
return source.FileIdentity{
URI: h.uri,
Identifier: h.hash,
Kind: h.Kind(),
}
}
func (h *fileHandle) Read() ([]byte, error) {
return h.bytes, h.err
}
func hashContents(contents []byte) string {
// TODO: consider whether sha1 is the best choice here
// This hash is used for internal identity detection only
return fmt.Sprintf("%x", sha1.Sum(contents))
}
var cacheIndex, sessionIndex, viewIndex int64
func (c *Cache) ID() string { return c.id }
func (c *Cache) MemStats() map[reflect.Type]int { return c.store.Stats() }