2018-07-23 21:05:02 +01:00
|
|
|
// Copyright (C) 2018 Storj Labs, Inc.
|
|
|
|
// See LICENSE for copying information.
|
|
|
|
|
|
|
|
package segment
|
|
|
|
|
|
|
|
import (
|
|
|
|
"context"
|
|
|
|
"io"
|
|
|
|
"time"
|
|
|
|
|
|
|
|
monkit "gopkg.in/spacemonkeygo/monkit.v2"
|
|
|
|
|
|
|
|
"storj.io/storj/pkg/eestream"
|
|
|
|
"storj.io/storj/pkg/kademlia"
|
|
|
|
"storj.io/storj/pkg/overlay"
|
|
|
|
"storj.io/storj/pkg/paths"
|
|
|
|
"storj.io/storj/pkg/piecestore/rpc/client"
|
|
|
|
"storj.io/storj/pkg/pointerdb"
|
|
|
|
"storj.io/storj/pkg/ranger"
|
|
|
|
"storj.io/storj/pkg/storage"
|
|
|
|
"storj.io/storj/pkg/storage/ec"
|
|
|
|
opb "storj.io/storj/protos/overlay"
|
|
|
|
ppb "storj.io/storj/protos/pointerdb"
|
|
|
|
)
|
|
|
|
|
|
|
|
var (
|
|
|
|
mon = monkit.Package()
|
|
|
|
)
|
|
|
|
|
|
|
|
// Meta will contain encryption and stream information
|
|
|
|
type Meta struct {
|
|
|
|
Data []byte
|
|
|
|
}
|
|
|
|
|
|
|
|
// Store for segments
|
|
|
|
type Store interface {
|
|
|
|
Meta(ctx context.Context, path paths.Path) (meta Meta, err error)
|
|
|
|
Get(ctx context.Context, path paths.Path) (rr ranger.RangeCloser,
|
|
|
|
meta Meta, err error)
|
|
|
|
Put(ctx context.Context, path paths.Path, data io.Reader, metadata []byte,
|
|
|
|
expiration time.Time) (meta Meta, err error)
|
|
|
|
Delete(ctx context.Context, path paths.Path) (err error)
|
|
|
|
List(ctx context.Context, prefix, startAfter, endBefore paths.Path,
|
|
|
|
recursive bool, limit int, metaFlags uint64) (items []storage.ListItem,
|
|
|
|
more bool, err error)
|
|
|
|
}
|
|
|
|
|
|
|
|
type segmentStore struct {
|
|
|
|
oc overlay.Client
|
|
|
|
ec ecclient.Client
|
|
|
|
pdb pointerdb.Client
|
|
|
|
rs eestream.RedundancyStrategy
|
|
|
|
}
|
|
|
|
|
|
|
|
// NewSegmentStore creates a new instance of segmentStore
|
|
|
|
func NewSegmentStore(oc overlay.Client, ec ecclient.Client,
|
|
|
|
pdb pointerdb.Client, rs eestream.RedundancyStrategy) Store {
|
|
|
|
return &segmentStore{oc: oc, ec: ec, pdb: pdb, rs: rs}
|
|
|
|
}
|
|
|
|
|
|
|
|
// Meta retrieves the metadata of the segment
|
|
|
|
func (s *segmentStore) Meta(ctx context.Context, path paths.Path) (meta Meta,
|
|
|
|
err error) {
|
|
|
|
defer mon.Task()(&ctx)(&err)
|
|
|
|
|
|
|
|
pr, err := s.pdb.Get(ctx, path, nil)
|
|
|
|
if err != nil {
|
|
|
|
return Meta{}, Error.Wrap(err)
|
|
|
|
}
|
|
|
|
|
|
|
|
return Meta{Data: pr.GetMetadata()}, nil
|
|
|
|
}
|
|
|
|
|
|
|
|
// Put uploads a segment to an erasure code client
|
|
|
|
func (s *segmentStore) Put(ctx context.Context, path paths.Path, data io.Reader,
|
|
|
|
metadata []byte, expiration time.Time) (meta Meta, err error) {
|
|
|
|
defer mon.Task()(&ctx)(&err)
|
|
|
|
|
|
|
|
// uses overlay client to request a list of nodes
|
|
|
|
nodes, err := s.oc.Choose(ctx, s.rs.TotalCount(), 0)
|
|
|
|
if err != nil {
|
|
|
|
return Meta{}, Error.Wrap(err)
|
|
|
|
}
|
|
|
|
|
|
|
|
pieceID := client.NewPieceID()
|
|
|
|
|
|
|
|
// puts file to ecclient
|
|
|
|
err = s.ec.Put(ctx, nodes, s.rs, pieceID, data, expiration)
|
|
|
|
if err != nil {
|
|
|
|
return Meta{}, Error.Wrap(err)
|
|
|
|
}
|
|
|
|
|
|
|
|
var remotePieces []*ppb.RemotePiece
|
|
|
|
for i := range nodes {
|
|
|
|
remotePieces = append(remotePieces, &ppb.RemotePiece{
|
|
|
|
PieceNum: int64(i),
|
|
|
|
NodeId: nodes[i].Id,
|
|
|
|
})
|
|
|
|
}
|
|
|
|
|
|
|
|
// creates pointer
|
|
|
|
pr := &ppb.Pointer{
|
|
|
|
Type: ppb.Pointer_REMOTE,
|
|
|
|
Remote: &ppb.RemoteSegment{
|
|
|
|
Redundancy: &ppb.RedundancyScheme{
|
|
|
|
Type: ppb.RedundancyScheme_RS,
|
|
|
|
MinReq: int64(s.rs.RequiredCount()),
|
|
|
|
Total: int64(s.rs.TotalCount()),
|
|
|
|
RepairThreshold: int64(s.rs.Min),
|
|
|
|
SuccessThreshold: int64(s.rs.Opt),
|
|
|
|
},
|
|
|
|
PieceId: string(pieceID),
|
|
|
|
RemotePieces: remotePieces,
|
|
|
|
},
|
|
|
|
Metadata: metadata,
|
|
|
|
}
|
|
|
|
|
|
|
|
// puts pointer to pointerDB
|
|
|
|
err = s.pdb.Put(ctx, path, pr, nil)
|
|
|
|
if err != nil {
|
|
|
|
return Meta{}, Error.Wrap(err)
|
|
|
|
}
|
|
|
|
|
|
|
|
// get the metadata for the newly uploaded segment
|
|
|
|
m, err := s.Meta(ctx, path)
|
|
|
|
if err != nil {
|
|
|
|
return Meta{}, Error.Wrap(err)
|
|
|
|
}
|
|
|
|
return m, nil
|
|
|
|
}
|
|
|
|
|
|
|
|
// Get retrieves a segment using erasure code, overlay, and pointerdb clients
|
|
|
|
func (s *segmentStore) Get(ctx context.Context, path paths.Path) (
|
|
|
|
rr ranger.RangeCloser, meta Meta, err error) {
|
|
|
|
defer mon.Task()(&ctx)(&err)
|
|
|
|
|
|
|
|
pr, err := s.pdb.Get(ctx, path, nil)
|
|
|
|
if err != nil {
|
|
|
|
return nil, Meta{}, Error.Wrap(err)
|
|
|
|
}
|
|
|
|
|
|
|
|
if pr.GetType() != ppb.Pointer_REMOTE {
|
|
|
|
return nil, Meta{}, Error.New("TODO: only getting remote pointers supported")
|
|
|
|
}
|
|
|
|
|
|
|
|
seg := pr.GetRemote()
|
|
|
|
pid := client.PieceID(seg.PieceId)
|
|
|
|
nodes, err := s.lookupNodes(ctx, seg)
|
|
|
|
if err != nil {
|
|
|
|
return nil, Meta{}, Error.Wrap(err)
|
|
|
|
}
|
|
|
|
|
|
|
|
rr, err = s.ec.Get(ctx, nodes, s.rs, pid, pr.GetSize())
|
|
|
|
if err != nil {
|
|
|
|
return nil, Meta{}, Error.Wrap(err)
|
|
|
|
}
|
|
|
|
|
|
|
|
return rr, Meta{Data: pr.GetMetadata()}, nil
|
|
|
|
}
|
|
|
|
|
|
|
|
// Delete tells piece stores to delete a segment and deletes pointer from pointerdb
|
|
|
|
func (s *segmentStore) Delete(ctx context.Context, path paths.Path) (err error) {
|
|
|
|
defer mon.Task()(&ctx)(&err)
|
|
|
|
|
|
|
|
pr, err := s.pdb.Get(ctx, path, nil)
|
|
|
|
if err != nil {
|
|
|
|
return Error.Wrap(err)
|
|
|
|
}
|
|
|
|
|
|
|
|
if pr.GetType() != ppb.Pointer_REMOTE {
|
|
|
|
return Error.New("TODO: only getting remote pointers supported")
|
|
|
|
}
|
|
|
|
|
|
|
|
seg := pr.GetRemote()
|
|
|
|
pid := client.PieceID(seg.PieceId)
|
|
|
|
nodes, err := s.lookupNodes(ctx, seg)
|
|
|
|
if err != nil {
|
|
|
|
return Error.Wrap(err)
|
|
|
|
}
|
|
|
|
|
|
|
|
// ecclient sends delete request
|
|
|
|
err = s.ec.Delete(ctx, nodes, pid)
|
|
|
|
if err != nil {
|
|
|
|
return Error.Wrap(err)
|
|
|
|
}
|
|
|
|
|
|
|
|
// deletes pointer from pointerdb
|
|
|
|
return s.pdb.Delete(ctx, path, nil)
|
|
|
|
}
|
|
|
|
|
|
|
|
// lookupNodes calls Lookup to get node addresses from the overlay
|
|
|
|
func (s *segmentStore) lookupNodes(ctx context.Context, seg *ppb.RemoteSegment) (
|
|
|
|
nodes []*opb.Node, err error) {
|
|
|
|
nodes = make([]*opb.Node, len(seg.GetRemotePieces()))
|
|
|
|
for i, p := range seg.GetRemotePieces() {
|
|
|
|
node, err := s.oc.Lookup(ctx, kademlia.StringToNodeID(p.GetNodeId()))
|
|
|
|
if err != nil {
|
|
|
|
// TODO better error handling: failing to lookup a few nodes should
|
|
|
|
// not fail the request
|
|
|
|
return nil, Error.Wrap(err)
|
|
|
|
}
|
|
|
|
nodes[i] = node
|
|
|
|
}
|
|
|
|
return nodes, nil
|
|
|
|
}
|
|
|
|
|
|
|
|
// List retrieves paths to segments and their metadata stored in the pointerdb
|
|
|
|
func (s *segmentStore) List(ctx context.Context, prefix, startAfter,
|
|
|
|
endBefore paths.Path, recursive bool, limit int, metaFlags uint64) (
|
|
|
|
items []storage.ListItem, more bool, err error) {
|
|
|
|
defer mon.Task()(&ctx)(&err)
|
|
|
|
|
captplanet (#159)
* captplanet
I kind of went overboard this weekend.
The major goal of this changeset is to provide an environment
for local development where all of the various services can
be easily run together. Developing on Storj v3 should be as
easy as running a setup command and a run command!
To do this, this changeset introduces a new tool called
captplanet, which combines the powers of the Overlay Cache,
the PointerDB, the PieceStore, Kademlia, the Minio Gateway,
etc.
Running 40 farmers and a heavy client inside the same process
forced a rethinking of the "services" that we had. To
avoid confusion by reusing prior terms, this changeset
introduces two new types: Providers and Responsibilities.
I wanted to avoid as many merge conflicts as possible, so
I left the existing Services and code for now, but if people
like this route we can clean up the duplication.
A Responsibility is a collection of gRPC methods and
corresponding state. The following systems are examples of
Responsibilities:
* Kademlia
* OverlayCache
* PointerDB
* StatDB
* PieceStore
* etc.
A Provider is a collection of Responsibilities that
share an Identity, such as:
* The heavy client
* The farmer
* The gateway
An Identity is a public/private key pair, a node id, etc.
Farmers all need different Identities, so captplanet
needs to support running multiple concurrent Providers
with different Identities.
Each Responsibility and Provider should allow for configuration
of multiple copies on its own so creating Responsibilities and
Providers use a new workflow.
To make a Responsibility, one should create a "config"
struct, such as:
```
type Config struct {
RepairThreshold int `help:"If redundancy falls below this number of
pieces, repair is triggered" default:"30"`
SuccessThreshold int `help:"If redundancy is above this number then
no additional uploads are needed" default:"40"`
}
```
To use "config" structs, this changeset introduces another
new library called 'cfgstruct', which allows for the configuration
of arbitrary structs through flagsets, and thus through cobra and
viper.
cfgstruct relies on Go's "struct tags" feature to document
help information and default values. Config structs can be
configured via cfgstruct.Bind for binding the struct to a flagset.
Because this configuration system makes setup and configuration
easier *in general*, additional commands are provided that allow
for easy standup of separate Providers. Please make sure to
check out:
* cmd/captplanet/farmer/main.go (a new farmer binary)
* cmd/captplanet/hc/main.go (a new heavy client binary)
* cmd/captplanet/gw/main.go (a new minio gateway binary)
Usage:
```
$ go install -v storj.io/storj/cmd/captplanet
$ captplanet setup
$ captplanet run
```
Configuration is placed by default in `~/.storj/capt/`
Other changes:
* introduces new config structs for currently existing
Responsibilities that conform to the new Responsibility
interface. Please see the `pkg/*/config.go` files for
examples.
* integrates the PointerDB API key with other global
configuration via flags, instead of through environment
variables through viper like it's been doing. (ultimately
this should also change to use the PointerDB config
struct but this is an okay shortterm solution).
* changes the Overlay cache to use a URL for database
configuration instead of separate redis and bolt config
settings.
* stubs out some peer identity skeleton code (but not the
meat).
* Fixes the SegmentStore to use the overlay client and
pointerdb clients instead of gRPC client code directly
* Leaves a very clear spot where we need to tie the object to
stream to segment store together. There's sort of a "golden
spike" opportunity to connect all the train tracks together
at the bottom of pkg/miniogw/config.go, labeled with a
bunch of TODOs.
Future stuff:
* I now prefer this design over the original
pkg/process.Service thing I had been pushing before (sorry!)
* The experience of trying to have multiple farmers
configurable concurrently led me to prefer config structs
over global flags (I finally came around) or using viper
directly. I think global flags are okay sometimes but in
general going forward we should try and get all relevant
config into config structs.
* If you all like this direction, I think we can go delete my
old Service interfaces and a bunch of flags and clean up a
bunch of stuff.
* If you don't like this direction, it's no sweat at all, and
despite how much code there is here I'm not very tied to any
of this! Considering a lot of this was written between midnight
and 6 am, it might not be any good!
* bind tests
2018-07-24 17:08:28 +01:00
|
|
|
res, more, err := s.pdb.List(ctx, startAfter, int64(limit), nil)
|
2018-07-23 21:05:02 +01:00
|
|
|
if err != nil {
|
|
|
|
return nil, false, Error.Wrap(err)
|
|
|
|
}
|
|
|
|
|
|
|
|
items = make([]storage.ListItem, len(res))
|
|
|
|
|
|
|
|
for i, path := range res {
|
|
|
|
items[i].Path = paths.New(string(path))
|
|
|
|
// TODO items[i].Meta =
|
|
|
|
}
|
|
|
|
|
|
|
|
return items, more, nil
|
|
|
|
}
|