mirror of
https://github.com/featurebasedb/featurebase.git
synced 2026-08-28 02:44:59 +00:00
* Introduce ServiceManager and Refactor DAX Integration tests
The ServiceManager provides an interface with which to manage
featurebase (dax) services (mds, queryer, computer). It replaces the
confusing interface implementations in /dax/server/server.go (which
optionally used pointers to in-process objects to satisfy an interface)
with (for now) http implementations. The thought is that even if we're
running all services in-process, we should communicate between services
over http in order to mirror what we would do in a production
environment where the services are running on different nodes.
This batch of commits does quit a lot, most of which is captured here:
- Added `path` support to `dax.Address`. Address is now a string of the form [scheme]://[host]:[port]/[path].
- Added `Holder.directiveApplied` to determine (in tests) if the computer has completed applying the latest directive. This is somewhat temporary until we improve the mds-to-computer logic.
- Removed the "service prefix" code which was prepending client URL paths with the prefix. Instead, the serviceType (mds, queryer, computer[n] is now part of `dax.Address`).
- Removed, from the dax config, the top level `StorageMethod` and `StorageDSN` and now just have `MDS.Config.DataDir`.
- Added `Computer.Config.N` to specify the number of computers to run in-process.
- Moved the `pilosa.MDS` interface to `computer.Registrar`. This is an example of getting the interfaces defined in the right packages.
- Added `SnapshotTable()` method to the mds client (to align with its API).
- Changed `Balancer.AddJob()` to `Balancer.AddJobs()` to support, for example, adding 256 partitions in a single call. Refactored some of the naive Balancer to account for this.
- Added a `Seed` to the top-level config. It's not really useful because of package `crypto/rand`.
- Added an in-memory implementation of the DisCo interface and disabled etcd in a computer service.
- Create sepearte data-dirs for each in-process computer.
- Disabled grpc in dax.
- Modified the sql3 test definition format to support multiple insert steps and separate query results (to align with those steps).
* Changes necessary to get multiple computer instance running in-process
For now the config looks like this:
```
[computer]
run = true
n = 4
```
but we can probably just change that to be something like:
```
[computer]
run = 4
```
*Issues found running multiple "computers" in-process*
- grpc was trying to bind on the same port
- changed GRPCListener from `*net.TCPListener` to `net.Listener`
- created a nopListener and set to that for now (i.e. disabled grpc)
- etcd was starting more than once
- changed dax to use in-memory implementations of the disco interfaces (i.e. stop using etcd)
- IDAllocator (which uses boltdb) was trying to open the `idalloc.db` file more than once
- realized we have to set separate data-dirs for each holder. that fixed it.
* Port dax integration tests to ManagedCommand
* Modify Balancer-related methods like AddJob to AddJobs
There were (and still are) a lot of places where we were adding on job
at a time, even when we had a long list of jobs to add. This resulted in
every job add (for example adding 1 of 256 shards) taking ~40ms, or over
10s to create a keyed table. One reason was because each job add was
making multiple boltdb transactions.
* Port over more dax integration test stuff
* Add DirectiveApplied to signify that snapshot/writes have loaded.
We use this in tests to avoid using sleeps.
This should be considered temporary; we're going to need a more robust
solution for determining when a computer node is ready to serve complete
data.
* Finish porting dax integration tests
* Improve godocs
* Remove docker-based DAX integration tests.
* go mod tidy
* Move test/managed.go to avoid package conflicts
* Modify IDK integration tests to work with ServiceManager changes
This is really just computer -> computer0
And the MDS DataDir config change.
* cleanup found during review
* echo $CI_COMMIT_REF_SLUG in CI
* remove docker image arg, use build instead
(cherry picked from commit 2843f218bc)
196 lines
5.7 KiB
Go
196 lines
5.7 KiB
Go
package service
|
|
|
|
import (
|
|
"context"
|
|
"io"
|
|
"net"
|
|
"net/http"
|
|
|
|
featurebase "github.com/molecula/featurebase/v3"
|
|
"github.com/molecula/featurebase/v3/dax"
|
|
"github.com/molecula/featurebase/v3/dax/computer"
|
|
mdsclient "github.com/molecula/featurebase/v3/dax/mds/client"
|
|
"github.com/molecula/featurebase/v3/dax/snapshotter"
|
|
snapshotterclient "github.com/molecula/featurebase/v3/dax/snapshotter/client"
|
|
"github.com/molecula/featurebase/v3/dax/writelogger"
|
|
writeloggerclient "github.com/molecula/featurebase/v3/dax/writelogger/client"
|
|
"github.com/molecula/featurebase/v3/errors"
|
|
"github.com/molecula/featurebase/v3/logger"
|
|
fbserver "github.com/molecula/featurebase/v3/server"
|
|
)
|
|
|
|
// Ensure type implements interface.
|
|
var _ dax.ComputerService = (*computerService)(nil)
|
|
|
|
type computerService struct {
|
|
addr dax.Address
|
|
cfg CommandConfig
|
|
key dax.ServiceKey
|
|
computer *fbserver.Command
|
|
logger logger.Logger
|
|
}
|
|
|
|
func New(addr dax.Address, cfg CommandConfig, logger logger.Logger) *computerService {
|
|
cfg.ComputerConfig.Advertise = addr.HostPort()
|
|
|
|
return &computerService{
|
|
addr: addr,
|
|
cfg: cfg,
|
|
logger: logger,
|
|
}
|
|
}
|
|
|
|
func (c *computerService) Start() error {
|
|
// We initialize the fbserver.Command at start (as opposed to in New()
|
|
// above) because we want to inject (via cfg.Name) the ServiceKey into the
|
|
// *fbserver.Command returned by newCommand() so that it can be used
|
|
// internally. In the future, when we have the pilosa package moved down to
|
|
// the computer package, we should be able to clean this up so that things
|
|
// happen in a reasonable order like we do with the other service types.
|
|
if c.computer == nil {
|
|
c.cfg.Name = string(c.Key())
|
|
c.computer = newCommand(c.addr, c.cfg)
|
|
|
|
if c.cfg.ComputerConfig.MDSAddress != "" {
|
|
mdsAddr := dax.Address(c.cfg.ComputerConfig.MDSAddress)
|
|
// Set mds (registrar) on computer.
|
|
if err := c.SetMDS(mdsAddr); err != nil {
|
|
return errors.Wrapf(err, "setting mds service on computer: %s, %v", c.cfg.Name, err)
|
|
}
|
|
}
|
|
}
|
|
|
|
if err := c.computer.StartNoServe(c.Address()); err != nil {
|
|
return errors.Wrap(err, "starting featurebase command")
|
|
}
|
|
|
|
if c.computer.Registrar != nil {
|
|
node := &dax.Node{
|
|
Address: c.Address(),
|
|
RoleTypes: []dax.RoleType{
|
|
dax.RoleTypeCompute,
|
|
dax.RoleTypeTranslate,
|
|
},
|
|
}
|
|
|
|
if err := c.computer.Registrar.RegisterNode(context.TODO(), node); err != nil {
|
|
return errors.Wrapf(err, "registering computer: %s", c.Address())
|
|
}
|
|
}
|
|
return nil
|
|
}
|
|
|
|
func (c *computerService) Stop() error {
|
|
return c.computer.Close()
|
|
}
|
|
|
|
func (c *computerService) Key() dax.ServiceKey {
|
|
return c.key
|
|
}
|
|
|
|
func (c *computerService) SetKey(key dax.ServiceKey) {
|
|
c.key = key
|
|
}
|
|
|
|
func (c *computerService) Address() dax.Address {
|
|
return dax.Address(c.addr.HostPort() + "/" + string(c.key))
|
|
}
|
|
|
|
func (c *computerService) HTTPHandler() http.Handler {
|
|
return c.computer.HTTPHandler()
|
|
}
|
|
|
|
func (c *computerService) SetMDS(addr dax.Address) error {
|
|
c.computer.Registrar = mdsclient.New(addr, c.logger)
|
|
return nil
|
|
}
|
|
|
|
type CommandConfig struct {
|
|
// Name is used to distinguish between locally running commands.
|
|
// For example, it's appended to DataDir so that each cmd has a
|
|
// separate data directory for its holder.
|
|
Name string
|
|
|
|
WriteLoggerRun bool
|
|
WriteLoggerConfig writelogger.Config
|
|
SnapshotterRun bool
|
|
SnapshotterConfig snapshotter.Config
|
|
ComputerConfig fbserver.Config
|
|
|
|
Listener net.Listener
|
|
RootDataDir string
|
|
|
|
Stderr io.Writer
|
|
Logger logger.Logger
|
|
}
|
|
|
|
func newCommand(addr dax.Address, cfg CommandConfig) *fbserver.Command {
|
|
// Set up WriteLogger.
|
|
// TODO(tlt): since WriteLogger is no longer a separate service (but
|
|
// rather just a directory path) its configuration could be moved under
|
|
// computer, and then get rid of WriteLogger.Run. This would become "if
|
|
// DataDir != ''". Let's do this after we get rid of the dax integration
|
|
// tests which start up separate writelogger and snapshotter containers.
|
|
var wlSvc *writelogger.WriteLogger
|
|
if cfg.WriteLoggerRun {
|
|
wlSvc = writelogger.New(writelogger.Config{
|
|
DataDir: cfg.WriteLoggerConfig.DataDir,
|
|
Logger: cfg.Logger,
|
|
})
|
|
}
|
|
|
|
// Set up Snapshotter.
|
|
var ssSvc *snapshotter.Snapshotter
|
|
if cfg.SnapshotterRun {
|
|
ssSvc = snapshotter.New(snapshotter.Config{
|
|
DataDir: cfg.SnapshotterConfig.DataDir,
|
|
Logger: cfg.Logger,
|
|
})
|
|
}
|
|
|
|
// Set the FeatureBase.Config values based on the top-level Config
|
|
// values.
|
|
cfg.ComputerConfig.Listener = &nopListener{}
|
|
cfg.ComputerConfig.Advertise = addr.HostPort()
|
|
cfg.ComputerConfig.GRPCListener = &nopListener{}
|
|
cfg.ComputerConfig.DataDir = cfg.RootDataDir + "/" + cfg.Name
|
|
|
|
var writeLoggerImpl computer.WriteLogger
|
|
if cfg.ComputerConfig.WriteLogger != "" {
|
|
writeLoggerImpl = writeloggerclient.New(dax.Address(cfg.ComputerConfig.WriteLogger))
|
|
} else if wlSvc != nil {
|
|
writeLoggerImpl = wlSvc
|
|
} else {
|
|
cfg.Logger.Warnf("No writelogger configured, dynamic scaling will not function properly.")
|
|
}
|
|
|
|
var snapshotterImpl computer.Snapshotter
|
|
if cfg.ComputerConfig.Snapshotter != "" {
|
|
snapshotterImpl = snapshotterclient.New(dax.Address(cfg.ComputerConfig.Snapshotter))
|
|
} else if ssSvc != nil {
|
|
snapshotterImpl = ssSvc
|
|
} else {
|
|
cfg.Logger.Warnf("No snapshotter configured.")
|
|
}
|
|
|
|
fbcmd := fbserver.NewCommand(cfg.Stderr,
|
|
fbserver.OptCommandSetConfig(&cfg.ComputerConfig),
|
|
fbserver.OptCommandServerOptions(
|
|
featurebase.OptServerIsComputeNode(true),
|
|
featurebase.OptServerLogger(cfg.Logger),
|
|
),
|
|
fbserver.OptCommandInjections(fbserver.Injections{
|
|
WriteLogger: writeLoggerImpl,
|
|
Snapshotter: snapshotterImpl,
|
|
IsComputeNode: true,
|
|
}),
|
|
)
|
|
|
|
return fbcmd
|
|
}
|
|
|
|
type nopListener struct{}
|
|
|
|
func (n *nopListener) Accept() (net.Conn, error) { return nil, nil }
|
|
func (n *nopListener) Close() error { return nil }
|
|
func (n *nopListener) Addr() net.Addr { return nil }
|