Skip to content

Commit

Permalink
cmd/go: move GOCACHEPROG protocol types to their own package
Browse files Browse the repository at this point in the history 
This is a step toward making it easy to point to them in
documentation. The other option is that we copy-paste all of these
type definitions wholesale, which seems ridiculous.

Updates #71032
Updates #59719

Change-Id: I7117e03308ae0adc721ed7a57792c33ba68ce827
Reviewed-on: https://go-review.googlesource.com/c/go/+/638995
Auto-Submit: Austin Clements <austin@google.com>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
Reviewed-by: Michael Matloob <matloob@golang.org>
  • Loading branch information
@aclements @gopherbot
aclements authored and gopherbot committed Jan 2, 2025
1 parent 858a0e9 commit 20da34c
Show file tree
Hide file tree
Showing 2 changed files with 155 additions and 145 deletions.
163 changes: 18 additions & 145 deletions src/cmd/go/internal/cache/prog.go
View file
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@ package cache
import (
"bufio"
"cmd/go/internal/base"
"cmd/go/internal/cacheprog"
"cmd/internal/quoted"
"context"
"crypto/sha256"
Expand Down Expand Up @@ -38,7 +39,7 @@ type ProgCache struct {

// can are the commands that the child process declared that it supports.
// This is effectively the versioning mechanism.
can map[ProgCmd]bool
can map[cacheprog.ProgCmd]bool

// fuzzDirCache is another Cache implementation to use for the FuzzDir
// method. In practice this is the default GOCACHE disk-based
Expand All @@ -55,142 +56,14 @@ type ProgCache struct {

mu sync.Mutex // guards following fields
nextID int64
inFlight map[int64]chan<- *ProgResponse
inFlight map[int64]chan<- *cacheprog.ProgResponse
outputFile map[OutputID]string // object => abs path on disk

// writeMu serializes writing to the child process.
// It must never be held at the same time as mu.
writeMu sync.Mutex
}

// The following types define the protocol for a GOCACHEPROG program.
//
// By default, the go command manages a build cache stored in the file system
// itself. GOCACHEPROG can be set to the name of a command (with optional
// space-separated flags) that implements the go command build cache externally.
// This permits defining a different cache policy.
//
// The go command will start the GOCACHEPROG as a subprocess and communicate
// with it via JSON messages over stdin/stdout. The subprocess's stderr will be
// connected to the go command's stderr.
//
// The subprocess should immediately send a [ProgResponse] with its capabilities.
// After that, the go command will send a stream of [ProgRequest] messages and the
// subprocess should reply to each [ProgRequest] with a [ProgResponse] message.

// ProgCmd is a command that can be issued to a child process.
//
// If the interface needs to grow, the go command can add new commands or new
// versioned commands like "get2" in the future. The initial [ProgResponse] from
// the child process indicates which commands it supports.
type ProgCmd string

const (
// cmdPut tells the cache program to store an object in the cache.
//
// [ProgRequest.ActionID] is the cache key of this object. The cache should
// store [ProgRequest.OutputID] and [ProgRequest.Body] under this key for a
// later "get" request. It must also store the Body in a file in the local
// file system and return the path to that file in [ProgResponse.DiskPath],
// which must exist at least until a "close" request.
cmdPut = ProgCmd("put")

// cmdGet tells the cache program to retrieve an object from the cache.
//
// [ProgRequest.ActionID] specifies the key of the object to get. If the
// cache does not contain this object, it should set [ProgResponse.Miss] to
// true. Otherwise, it should populate the fields of [ProgResponse],
// including setting [ProgResponse.OutputID] to the OutputID of the original
// "put" request and [ProgResponse.DiskPath] to the path of a local file
// containing the Body of the original "put" request. That file must
// continue to exist at least until a "close" request.
cmdGet = ProgCmd("get")

// cmdClose requests that the cache program exit gracefully.
//
// The cache program should reply to this request and then exit
// (thus closing its stdout).
cmdClose = ProgCmd("close")
)

// ProgRequest is the JSON-encoded message that's sent from the go command to
// the GOCACHEPROG child process over stdin. Each JSON object is on its own
// line. A ProgRequest of Type "put" with BodySize > 0 will be followed by a
// line containing a base64-encoded JSON string literal of the body.
type ProgRequest struct {
// ID is a unique number per process across all requests.
// It must be echoed in the ProgResponse from the child.
ID int64

// Command is the type of request.
// The go command will only send commands that were declared
// as supported by the child.
Command ProgCmd

// ActionID is the cache key for "put" and "get" requests.
ActionID []byte `json:",omitempty"` // or nil if not used

// OutputID is stored with the body for "put" requests.
//
// Prior to Go 1.24, when GOCACHEPROG was still an experiment, this was
// accidentally named ObjectID. It was renamed to OutputID in Go 1.24.
OutputID []byte `json:",omitempty"` // or nil if not used

// Body is the body for "put" requests. It's sent after the JSON object
// as a base64-encoded JSON string when BodySize is non-zero.
// It's sent as a separate JSON value instead of being a struct field
// send in this JSON object so large values can be streamed in both directions.
// The base64 string body of a ProgRequest will always be written
// immediately after the JSON object and a newline.
Body io.Reader `json:"-"`

// BodySize is the number of bytes of Body. If zero, the body isn't written.
BodySize int64 `json:",omitempty"`

// ObjectID is the accidental spelling of OutputID that was used prior to Go
// 1.24.
//
// Deprecated: use OutputID. This field is only populated temporarily for
// backwards compatibility with Go 1.23 and earlier when
// GOEXPERIMENT=gocacheprog is set. It will be removed in Go 1.25.
ObjectID []byte `json:",omitempty"`
}

// ProgResponse is the JSON response from the child process to the go command.
//
// With the exception of the first protocol message that the child writes to its
// stdout with ID==0 and KnownCommands populated, these are only sent in
// response to a ProgRequest from the go command.
//
// ProgResponses can be sent in any order. The ID must match the request they're
// replying to.
type ProgResponse struct {
ID int64 // that corresponds to ProgRequest; they can be answered out of order
Err string `json:",omitempty"` // if non-empty, the error

// KnownCommands is included in the first message that cache helper program
// writes to stdout on startup (with ID==0). It includes the
// ProgRequest.Command types that are supported by the program.
//
// This lets the go command extend the protocol gracefully over time (adding
// "get2", etc), or fail gracefully when needed. It also lets the go command
// verify the program wants to be a cache helper.
KnownCommands []ProgCmd `json:",omitempty"`

// For "get" requests.

Miss bool `json:",omitempty"` // cache miss
OutputID []byte `json:",omitempty"` // the ObjectID stored with the body
Size int64 `json:",omitempty"` // body size in bytes
Time *time.Time `json:",omitempty"` // when the object was put in the cache (optional; used for cache expiration)

// For "get" and "put" requests.

// DiskPath is the absolute path on disk of the body corresponding to a
// "get" (on cache hit) or "put" request's ActionID.
DiskPath string `json:",omitempty"`
}

// startCacheProg starts the prog binary (with optional space-separated flags)
// and returns a Cache implementation that talks to it.
//
Expand Down Expand Up @@ -238,14 +111,14 @@ func startCacheProg(progAndArgs string, fuzzDirCache Cache) Cache {
stdout: out,
stdin: in,
bw: bufio.NewWriter(in),
inFlight: make(map[int64]chan<- *ProgResponse),
inFlight: make(map[int64]chan<- *cacheprog.ProgResponse),
outputFile: make(map[OutputID]string),
readLoopDone: make(chan struct{}),
}

// Register our interest in the initial protocol message from the child to
// us, saying what it can do.
capResc := make(chan *ProgResponse, 1)
capResc := make(chan *cacheprog.ProgResponse, 1)
pc.inFlight[0] = capResc

pc.jenc = json.NewEncoder(pc.bw)
Expand All @@ -260,7 +133,7 @@ func startCacheProg(progAndArgs string, fuzzDirCache Cache) Cache {
case <-timer.C:
log.Printf("# still waiting for GOCACHEPROG %v ...", prog)
case capRes := <-capResc:
can := map[ProgCmd]bool{}
can := map[cacheprog.ProgCmd]bool{}
for _, cmd := range capRes.KnownCommands {
can[cmd] = true
}
Expand All @@ -277,7 +150,7 @@ func (c *ProgCache) readLoop(readLoopDone chan<- struct{}) {
defer close(readLoopDone)
jd := json.NewDecoder(c.stdout)
for {
res := new(ProgResponse)
res := new(cacheprog.ProgResponse)
if err := jd.Decode(res); err != nil {
if c.closing.Load() {
return // quietly
Expand All @@ -302,8 +175,8 @@ func (c *ProgCache) readLoop(readLoopDone chan<- struct{}) {
}
}

func (c *ProgCache) send(ctx context.Context, req *ProgRequest) (*ProgResponse, error) {
resc := make(chan *ProgResponse, 1)
func (c *ProgCache) send(ctx context.Context, req *cacheprog.ProgRequest) (*cacheprog.ProgResponse, error) {
resc := make(chan *cacheprog.ProgResponse, 1)
if err := c.writeToChild(req, resc); err != nil {
return nil, err
}
Expand All @@ -318,7 +191,7 @@ func (c *ProgCache) send(ctx context.Context, req *ProgRequest) (*ProgResponse,
}
}

func (c *ProgCache) writeToChild(req *ProgRequest, resc chan<- *ProgResponse) (err error) {
func (c *ProgCache) writeToChild(req *cacheprog.ProgRequest, resc chan<- *cacheprog.ProgResponse) (err error) {
c.mu.Lock()
c.nextID++
req.ID = c.nextID
Expand Down Expand Up @@ -369,7 +242,7 @@ func (c *ProgCache) writeToChild(req *ProgRequest, resc chan<- *ProgResponse) (e
}

func (c *ProgCache) Get(a ActionID) (Entry, error) {
if !c.can[cmdGet] {
if !c.can[cacheprog.CmdGet] {
// They can't do a "get". Maybe they're a write-only cache.
//
// TODO(bradfitz,bcmills): figure out the proper error type here. Maybe
Expand All @@ -379,8 +252,8 @@ func (c *ProgCache) Get(a ActionID) (Entry, error) {
// error types on the Cache interface.
return Entry{}, &entryNotFoundError{}
}
res, err := c.send(c.ctx, &ProgRequest{
Command: cmdGet,
res, err := c.send(c.ctx, &cacheprog.ProgRequest{
Command: cacheprog.CmdGet,
ActionID: a[:],
})
if err != nil {
Expand Down Expand Up @@ -436,7 +309,7 @@ func (c *ProgCache) Put(a ActionID, file io.ReadSeeker) (_ OutputID, size int64,
return OutputID{}, 0, err
}

if !c.can[cmdPut] {
if !c.can[cacheprog.CmdPut] {
// Child is a read-only cache. Do nothing.
return out, size, nil
}
Expand All @@ -448,8 +321,8 @@ func (c *ProgCache) Put(a ActionID, file io.ReadSeeker) (_ OutputID, size int64,
deprecatedValue = out[:]
}

res, err := c.send(c.ctx, &ProgRequest{
Command: cmdPut,
res, err := c.send(c.ctx, &cacheprog.ProgRequest{
Command: cacheprog.CmdPut,
ActionID: a[:],
OutputID: out[:],
ObjectID: deprecatedValue, // TODO(bradfitz): remove in Go 1.25
Expand All @@ -473,8 +346,8 @@ func (c *ProgCache) Close() error {
// First write a "close" message to the child so it can exit nicely
// and clean up if it wants. Only after that exchange do we cancel
// the context that kills the process.
if c.can[cmdClose] {
_, err = c.send(c.ctx, &ProgRequest{Command: cmdClose})
if c.can[cacheprog.CmdClose] {
_, err = c.send(c.ctx, &cacheprog.ProgRequest{Command: cacheprog.CmdClose})
}
// Cancel the context, which will close the helper's stdin.
c.ctxCancel()
Expand Down
Loading

0 comments on commit 20da34c

Please sign in to comment.