mirror of
https://github.com/opencloud-eu/opencloud.git
synced 2026-08-01 10:20:52 -04:00
Migrate the search index in place instead of a full Tika re-crawl when the shared search.SchemaRevision is bumped. bleve (single instance): rebuild from the existing documents into a temp index and atomically swap, with crash recovery; auto-migrate on startup (opt-out via SEARCH_ENGINE_BLEVE_AUTO_MIGRATE). OpenSearch (scaled): versioned indices <base>-v<rev> (no alias), filled from the newest older index via a create-only scroll reindex - idempotent, never overwrites, safe to run live. 'opencloud search index migrate' fills the current-revision index; 'opencloud search index prune' drops older ones. Per-document fixups are gated on the source schema version. Trash preserved, geopoint siblings synthesized, all fields round-tripped.
228 lines
8.1 KiB
Go
228 lines
8.1 KiB
Go
package command
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
"os/signal"
|
|
"time"
|
|
|
|
"github.com/opencloud-eu/opencloud/pkg/config/configlog"
|
|
"github.com/opencloud-eu/opencloud/pkg/generators"
|
|
"github.com/opencloud-eu/opencloud/pkg/log"
|
|
"github.com/opencloud-eu/opencloud/pkg/registry"
|
|
"github.com/opencloud-eu/opencloud/pkg/runner"
|
|
ogrpc "github.com/opencloud-eu/opencloud/pkg/service/grpc"
|
|
"github.com/opencloud-eu/opencloud/pkg/tracing"
|
|
"github.com/opencloud-eu/opencloud/pkg/version"
|
|
"github.com/opencloud-eu/opencloud/services/search/pkg/bleve"
|
|
"github.com/opencloud-eu/opencloud/services/search/pkg/config"
|
|
"github.com/opencloud-eu/opencloud/services/search/pkg/config/parser"
|
|
"github.com/opencloud-eu/opencloud/services/search/pkg/content"
|
|
searchmapping "github.com/opencloud-eu/opencloud/services/search/pkg/mapping"
|
|
"github.com/opencloud-eu/opencloud/services/search/pkg/metrics"
|
|
"github.com/opencloud-eu/opencloud/services/search/pkg/opensearch"
|
|
bleveQuery "github.com/opencloud-eu/opencloud/services/search/pkg/query/bleve"
|
|
"github.com/opencloud-eu/opencloud/services/search/pkg/search"
|
|
"github.com/opencloud-eu/opencloud/services/search/pkg/server/debug"
|
|
"github.com/opencloud-eu/opencloud/services/search/pkg/server/grpc"
|
|
svcEvent "github.com/opencloud-eu/opencloud/services/search/pkg/service/event"
|
|
|
|
"github.com/opencloud-eu/reva/v2/pkg/events/raw"
|
|
"github.com/opencloud-eu/reva/v2/pkg/rgrpc/todo/pool"
|
|
"github.com/spf13/cobra"
|
|
)
|
|
|
|
// Server is the entrypoint for the server command.
|
|
func Server(cfg *config.Config) *cobra.Command {
|
|
return &cobra.Command{
|
|
Use: "server",
|
|
Short: fmt.Sprintf("start the %s service without runtime (unsupervised mode)", cfg.Service.Name),
|
|
PreRunE: func(cmd *cobra.Command, args []string) error {
|
|
return configlog.ReturnFatal(parser.ParseConfig(cfg))
|
|
},
|
|
RunE: func(cmd *cobra.Command, args []string) error {
|
|
logger := log.Configure(cfg.Service.Name, cfg.Commons, cfg.LogLevel)
|
|
traceProvider, err := tracing.GetTraceProvider(cmd.Context(), cfg.Commons.TracesExporter, cfg.Service.Name)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
cfg.GrpcClient, err = ogrpc.NewClient(
|
|
append(ogrpc.GetClientOptions(cfg.GRPCClientTLS), ogrpc.WithTraceProvider(traceProvider))...,
|
|
)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
var cancel context.CancelFunc
|
|
if cfg.Context == nil {
|
|
cfg.Context, cancel = signal.NotifyContext(context.Background(), runner.StopSignals...)
|
|
defer cancel()
|
|
}
|
|
ctx := cfg.Context
|
|
|
|
mtrcs := metrics.New()
|
|
mtrcs.BuildInfo.WithLabelValues(version.GetString()).Set(1)
|
|
|
|
// initialize search engine
|
|
var eng search.Engine
|
|
switch cfg.Engine.Type {
|
|
case "bleve":
|
|
// with AutoMigrate a schema revision bump rebuilds the index in
|
|
// place instead of refusing to start. Safe for bleve because a
|
|
// single instance holds the datapath lock.
|
|
idx, classification, migrated, err := bleve.OpenOrMigrate(cfg.Engine.Bleve.Datapath, cfg.Engine.Bleve.AutoMigrate, logger)
|
|
if migrated > 0 {
|
|
logger.Info().Int("documents", migrated).Msgf("the bleve index at %s was rebuilt for the new schema revision; %s", cfg.Engine.Bleve.Datapath, rescanRecommendation)
|
|
}
|
|
// warn before the error check: the new mapping may already be
|
|
// persisted, then later startups classify equal and stay silent
|
|
if classification.Verdict == searchmapping.VerdictAdditive {
|
|
logger.Warn().
|
|
Strs("fields", classification.NewFields).
|
|
Msgf("the bleve index at %s was built with an older schema; the new fields were added to the index schema, but documents indexed before the upgrade do not contain them and queries on these fields will miss those documents until they are re-indexed; to re-index everything run: opencloud search index --all-spaces --force-rescan", cfg.Engine.Bleve.Datapath)
|
|
}
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
defer func() {
|
|
if err = idx.Close(); err != nil {
|
|
logger.Error().Err(err).Msg("could not close bleve index")
|
|
}
|
|
}()
|
|
|
|
eng = bleve.NewBackend(idx, bleveQuery.DefaultCreator, logger)
|
|
case "open-search":
|
|
client, err := opensearch.NewClient(cfg.Engine.OpenSearch.Client)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
// the revision is in the index name, so each instance uses its own
|
|
// index and rollouts never share one; a pre-rollout migrate builds it
|
|
indexName := opensearch.TargetIndex(cfg.Engine.OpenSearch.ResourceIndex.Name)
|
|
|
|
// a hung cluster must fail the start, not block it forever
|
|
startupCtx, cancelStartup := context.WithTimeout(ctx, time.Minute)
|
|
openSearchBackend, err := opensearch.NewBackend(startupCtx, indexName, client, logger)
|
|
cancelStartup()
|
|
if err != nil {
|
|
return fmt.Errorf("failed to create OpenSearch backend: %w", err)
|
|
}
|
|
|
|
eng = openSearchBackend
|
|
default:
|
|
return fmt.Errorf("unknown search engine: %s", cfg.Engine.Type)
|
|
}
|
|
|
|
// initialize gateway selector
|
|
selector, err := pool.GatewaySelector(cfg.Reva.Address, pool.WithRegistry(registry.GetRegistry()), pool.WithTracerProvider(traceProvider))
|
|
if err != nil {
|
|
logger.Fatal().Err(err).Msg("could not get reva gateway selector")
|
|
return err
|
|
}
|
|
|
|
// initialize search content extractor
|
|
var extractor content.Extractor
|
|
switch cfg.Extractor.Type {
|
|
case "basic":
|
|
if extractor, err = content.NewBasicExtractor(logger); err != nil {
|
|
return err
|
|
}
|
|
case "tika":
|
|
if extractor, err = content.NewTikaExtractor(selector, logger, cfg); err != nil {
|
|
return err
|
|
}
|
|
default:
|
|
return fmt.Errorf("unknown search extractor: %s", cfg.Extractor.Type)
|
|
}
|
|
|
|
ss := search.NewService(selector, eng, extractor, mtrcs, logger, cfg)
|
|
|
|
// setup the servers
|
|
gr := runner.NewGroup()
|
|
|
|
if !cfg.GRPC.Disabled {
|
|
grpcServer, err := grpc.Server(
|
|
grpc.Config(cfg),
|
|
grpc.Logger(logger),
|
|
grpc.Name(cfg.Service.Name),
|
|
grpc.Context(ctx),
|
|
grpc.Metrics(mtrcs),
|
|
grpc.JWTSecret(cfg.TokenManager.JWTSecret),
|
|
grpc.TraceProvider(traceProvider),
|
|
grpc.GatewaySelector(selector),
|
|
grpc.Searcher(ss),
|
|
)
|
|
if err != nil {
|
|
logger.Error().Err(err).Str("transport", "grpc").Msg("Failed to initialize server")
|
|
return err
|
|
}
|
|
|
|
gr.Add(runner.NewGoMicroGrpcServerRunner(cfg.Service.Name+".grpc", grpcServer))
|
|
} else {
|
|
logger.Info().Msg("gRPC server disabled, not starting gRPC service")
|
|
}
|
|
|
|
if !cfg.Events.Disabled {
|
|
connName := generators.GenerateConnectionName(cfg.Service.Name, generators.NTypeBus)
|
|
bus, err := raw.FromConfig(context.Background(), connName, raw.Config{
|
|
Endpoint: cfg.Events.Endpoint,
|
|
Cluster: cfg.Events.Cluster,
|
|
EnableTLS: cfg.Events.EnableTLS,
|
|
TLSInsecure: cfg.Events.TLSInsecure,
|
|
TLSRootCACertificate: cfg.Events.TLSRootCACertificate,
|
|
AuthUsername: cfg.Events.AuthUsername,
|
|
AuthPassword: cfg.Events.AuthPassword,
|
|
MaxAckPending: cfg.Events.MaxAckPending,
|
|
AckWait: cfg.Events.AckWait,
|
|
})
|
|
if err != nil {
|
|
logger.Error().Err(err).Msg("Failed to create event bus client")
|
|
return err
|
|
}
|
|
|
|
eventSvc, err := svcEvent.New(ctx, bus, logger, traceProvider, mtrcs, ss, cfg.Events.DebounceDuration, cfg.Events.NumConsumers, cfg.Events.AsyncUploads)
|
|
if err != nil {
|
|
logger.Error().Err(err).Str("transport", "event").Msg("Failed to initialize server")
|
|
return err
|
|
}
|
|
|
|
gr.Add(runner.New(cfg.Service.Name+".svc", func() error {
|
|
return eventSvc.Run()
|
|
}, func() {
|
|
eventSvc.Close()
|
|
}))
|
|
} else {
|
|
logger.Info().Msg("event listening disabled, not starting event service")
|
|
}
|
|
|
|
// always start a debug server
|
|
{
|
|
debugServer, err := debug.Server(
|
|
debug.Logger(logger),
|
|
debug.Context(ctx),
|
|
debug.Config(cfg),
|
|
)
|
|
if err != nil {
|
|
logger.Error().Err(err).Str("transport", "debug").Msg("Failed to initialize server")
|
|
return err
|
|
}
|
|
|
|
gr.Add(runner.NewGolangHttpServerRunner(cfg.Service.Name+".debug", debugServer))
|
|
}
|
|
|
|
grResults := gr.Run(ctx)
|
|
|
|
// return the first non-nil error found in the results
|
|
for _, grResult := range grResults {
|
|
if grResult.RunnerError != nil {
|
|
return grResult.RunnerError
|
|
}
|
|
}
|
|
return nil
|
|
},
|
|
}
|
|
}
|