wip collect

4 files changed, 412 insertions, 2 deletions

diff --git a/collect.go b/collect.go
new file mode 100644
index 0000000..c1e2c6d
--- /dev/null
+++ b/collect.go
@@ -0,0 +1,270 @@
+package main
+
+import (
+	"container/heap"
+	"context"
+	"crypto/sha256"
+	"encoding/json"
+	"fmt"
+	"net/http"
+	"os"
+	"os/signal"
+	"strings"
+	"sync"
+	"syscall"
+	"time"
+
+	"git.cs.kau.se/rasmoste/ct-sans/internal/chunk"
+	"git.cs.kau.se/rasmoste/ct-sans/internal/utils"
+	ct "github.com/google/certificate-transparency-go"
+	"github.com/google/certificate-transparency-go/client"
+	"github.com/google/certificate-transparency-go/jsonclient"
+	"github.com/google/certificate-transparency-go/scanner"
+	"gitlab.torproject.org/rgdd/ct/pkg/merkle"
+	"gitlab.torproject.org/rgdd/ct/pkg/metadata"
+)
+
+func collect(opts options) error {
+	b, err := os.ReadFile(fmt.Sprintf("%s/%s", opts.Directory, opts.metadataFile))
+	if err != nil {
+		return err
+	}
+	var md metadata.Metadata
+	if err := json.Unmarshal(b, &md); err != nil {
+		return err
+	}
+
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+
+	var wg sync.WaitGroup
+	defer wg.Wait()
+
+	go func() {
+		wg.Add(1)
+		defer wg.Done()
+
+		sigs := make(chan os.Signal, 1)
+		defer close(sigs)
+
+		signal.Notify(sigs, syscall.SIGINT, syscall.SIGTERM)
+		select {
+		case <-sigs:
+			fmt.Fprintf(os.Stderr, "INFO: received shutdown signal, please wait...\n")
+			cancel()
+		case <-ctx.Done():
+		}
+	}()
+
+	for _, log := range utils.Logs(md) {
+		go func(log metadata.Log) {
+			wg.Add(1)
+			defer wg.Done()
+
+			chunks := make(chan *chunk.Chunk)
+			defer close(chunks)
+
+			id, _ := log.Key.ID()
+			th, err := readState(opts, id[:])
+			if err != nil {
+				fmt.Fprintf(os.Stderr, "ERROR: %s: %v\n", *log.Description, err)
+				cancel()
+				return
+			}
+			sth, err := readSnapshot(opts, id[:])
+			if err != nil {
+				fmt.Fprintf(os.Stderr, "ERROR: %s: %v\n", *log.Description, err)
+				cancel()
+				return
+			}
+
+			cli, err := client.New(string(log.URL), &http.Client{}, jsonclient.Options{UserAgent: "wip2"})
+			if err != nil {
+				fmt.Fprintf(os.Stderr, "ERROR: %s: %v\n", *log.Description, err)
+				cancel()
+				return
+			}
+			fetcher := scanner.NewFetcher(cli, &scanner.FetcherOptions{
+				BatchSize:     int(opts.batchSize),
+				StartIndex:    th.TreeSize,
+				EndIndex:      int64(sth.TreeSize),
+				ParallelFetch: int(opts.workersPerLog),
+				Continuous:    false,
+			})
+
+			//
+			// Callback that puts downloaded certificates into a
+			// chunk that a single sequencer can verify and persist
+			//
+			callback := func(eb scanner.EntryBatch) {
+				leafHashes := [][sha256.Size]byte{}
+				for i := 0; i < len(eb.Entries); i++ {
+					leafHashes = append(leafHashes, merkle.HashLeafNode(eb.Entries[i].LeafInput))
+				}
+				sans := []string{"example.com"} // TODO: fixme
+				chunks <- &chunk.Chunk{eb.Start, leafHashes, sans}
+			}
+
+			//
+			// Sequencer that waits for sufficiently large chunks
+			// before verifying inclusion proofs and persisting an
+			// intermediate tree head (size and root hash) as well
+			// as the SANs that were observed up until that point.
+			//
+			go func() {
+				wg.Add(1)
+				defer wg.Done()
+				defer fmt.Fprintf(os.Stderr, "INFO: %s: shutdown sequencer\n", *log.Description)
+
+				h := &chunk.ChunkHeap{}
+				heap.Init(h)
+				curr := th.TreeSize
+				for {
+					select {
+					case <-ctx.Done():
+						if h.Sequence(curr) {
+							c := h.TPop()
+							if _, err := persistChunk(cli, opts, id[:], 0, c); err != nil {
+								fmt.Fprintf(os.Stderr, "ERROR: %s: %v\n", err)
+							}
+						}
+						return
+					case c, ok := <-chunks:
+						if ok {
+							h.TPush(c)
+						}
+						if !h.Sequence(curr) {
+							continue
+						}
+
+						c = h.TPop()
+						putBack, err := persistChunk(cli, opts, id[:], int64(opts.persistSize), c)
+						if err != nil {
+							cancel()
+							fmt.Fprintf(os.Stderr, "ERROR: %s: %v\n", *log.Description, err)
+							return
+						}
+						if putBack {
+							h.TPush(c)
+							continue
+						}
+
+						curr += int64(len(c.LeafHashes))
+					}
+				}
+			}()
+
+			if err := fetcher.Run(ctx, callback); err != nil {
+				fmt.Fprintf(os.Stderr, "ERROR: %s: %v\n", *log.Description, err)
+				cancel()
+				return
+			}
+
+			fmt.Fprintf(os.Stderr, "INFO: %s: fetch completed\n", *log.Description)
+			for len(chunks) > 0 {
+				select {
+				case <-ctx.Done():
+					return
+				case <-time.After(1 * time.Second):
+					fmt.Fprintf(os.Stderr, "DEBUG: %s: waiting for chunks to be consumed\n", *log.Description)
+				}
+			}
+		}(log)
+		break
+	}
+
+	time.Sleep(1 * time.Second)
+	return fmt.Errorf("TODO")
+}
+
+type treeHead struct {
+	TreeSize int64             `json:"tree_size"`
+	RootHash [sha256.Size]byte `json:root_hash"`
+}
+
+func readState(opts options, logID []byte) (treeHead, error) {
+	if _, err := os.Stat(fmt.Sprintf("%s/%x/%s", opts.logDirectory, logID, opts.stateFile)); err != nil {
+		return treeHead{0, sha256.Sum256(nil)}, nil
+	}
+	b, err := os.ReadFile(fmt.Sprintf("%s/%x/%s", opts.logDirectory, logID, opts.stateFile))
+	if err != nil {
+		return treeHead{}, err
+	}
+	var th treeHead
+	if err := json.Unmarshal(b, &th); err != nil {
+		return treeHead{}, err
+	}
+	return th, nil
+}
+
+func readSnapshot(opts options, logID []byte) (ct.SignedTreeHead, error) {
+	b, err := os.ReadFile(fmt.Sprintf("%s/%x/%s", opts.logDirectory, logID, opts.sthFile))
+	if err != nil {
+		return ct.SignedTreeHead{}, err
+	}
+	var sth ct.SignedTreeHead
+	if err := json.Unmarshal(b, &sth); err != nil {
+		return ct.SignedTreeHead{}, err
+	}
+	return sth, nil
+}
+
+func persistChunk(cli *client.LogClient, opts options, logID []byte, minSequence int64, c *chunk.Chunk) (bool, error) {
+	if len(c.LeafHashes) == 0 {
+		return false, nil // nothing to persist
+	}
+	if int64(len(c.LeafHashes)) < minSequence {
+		return true, nil // wait for more leaves
+	}
+
+	// Read persisted tree state from disk
+	th, err := readState(opts, logID)
+	if err != nil {
+		return false, err
+	}
+	if th.TreeSize != c.Start {
+		return false, fmt.Errorf("disk state says next index is %d, in-memory says %d", th.TreeSize, c.Start)
+	}
+
+	// Derive next intermediate tree state to persist
+	//
+	// Independent context because we need to run inclusion and consistency
+	// queries after the parent context is cancelled to persist on shutdown
+	//
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	p, err := cli.GetProofByHash(ctx, c.LeafHashes[0][:], uint64(c.Start+int64(len(c.LeafHashes))))
+	if err != nil {
+		fmt.Fprintf(os.Stderr, "WARNING: %x: %v\n", logID, err)
+		return true, nil // try again later
+	}
+	if p.LeafIndex != c.Start {
+		return false, fmt.Errorf("log says proof for entry %d is at index %d", c.Start, p.LeafIndex)
+	}
+	// TODO: ranged inclusion verify + consistency proof
+
+	// Persist SANs to disk
+	fp, err := os.OpenFile(fmt.Sprintf("%s/%x/%s", opts.logDirectory, logID, opts.sansFile), os.O_CREATE|os.O_APPEND|os.O_WRONLY, 0644)
+	if err != nil {
+		return false, err
+	}
+	defer fp.Close()
+	if _, err := fp.WriteString(strings.Join(c.SANs, "\n") + "\n"); err != nil {
+		return false, err
+	}
+	if err := fp.Sync(); err != nil {
+		return false, err
+	}
+
+	// Persist intermediate log state to disk
+	b, err := json.Marshal(&treeHead{c.Start + int64(len(c.LeafHashes)), [sha256.Size]byte{}})
+	if err != nil {
+		return false, err
+	}
+	if err := os.WriteFile(fmt.Sprintf("%s/%x/%s", opts.logDirectory, logID, opts.stateFile), b, 0644); err != nil {
+		return false, err
+	}
+
+	fmt.Fprintf(os.Stderr, "DEBUG: %x: persist: start=%d end=%d\n", logID, c.Start, c.Start+int64(len(c.LeafHashes)))
+	return false, nil
+}
diff --git a/go.mod b/go.mod
index aa226a0..b55cf27 100644
--- a/go.mod
+++ b/go.mod
@@ -4,10 +4,14 @@ go 1.19
 
 require (
 	github.com/go-logr/logr v1.2.0 // indirect
+	github.com/golang/protobuf v1.5.2 // indirect
 	github.com/google/certificate-transparency-go v1.1.4 // indirect
+	github.com/google/trillian v1.5.1-0.20220819043421-0a389c4bb8d9 // indirect
 	gitlab.torproject.org/rgdd/ct v0.0.0-20230115071200-fa4d0bcd1cab // indirect
 	golang.org/x/crypto v0.0.0-20220411220226-7b82a4e95df4 // indirect
 	golang.org/x/net v0.0.0-20220722155237-a158d28d115b // indirect
+	google.golang.org/genproto v0.0.0-20220706185917-7780775163c4 // indirect
+	google.golang.org/grpc v1.48.0 // indirect
 	google.golang.org/protobuf v1.28.1 // indirect
 	k8s.io/klog/v2 v2.80.1 // indirect
 )
diff --git a/go.sum b/go.sum
index 4dae2bd..8c00f2f 100644
--- a/go.sum
+++ b/go.sum
@@ -1,18 +1,146 @@
+cloud.google.com/go v0.26.0/go.mod h1:aQUYkXzVsufM+DwF1aE+0xfcU+56JwCaLick0ClmMTw=
+cloud.google.com/go v0.34.0/go.mod h1:aQUYkXzVsufM+DwF1aE+0xfcU+56JwCaLick0ClmMTw=
+github.com/BurntSushi/toml v0.3.1/go.mod h1:xHWCNGjB5oqiDr8zfno3MHue2Ht5sIBksp03qcyfWMU=
+github.com/antihax/optional v1.0.0/go.mod h1:uupD/76wgC+ih3iEmQUL+0Ugr19nfwCT1kdvxnR2qWY=
+github.com/census-instrumentation/opencensus-proto v0.2.1/go.mod h1:f6KPmirojxKA12rnyqOA5BBL4O983OfeGPqjHWSTneU=
+github.com/cespare/xxhash/v2 v2.1.1/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
+github.com/client9/misspell v0.3.4/go.mod h1:qj6jICC3Q7zFZvVWo7KLAzC3yx5G7kyvSDkc90ppPyw=
+github.com/cncf/udpa/go v0.0.0-20191209042840-269d4d468f6f/go.mod h1:M8M6+tZqaGXZJjfX53e64911xZQV5JYwmTeXPW+k8Sc=
+github.com/cncf/udpa/go v0.0.0-20201120205902-5459f2c99403/go.mod h1:WmhPx2Nbnhtbo57+VJT5O0JRkEi1Wbu0z5j0R8u5Hbk=
+github.com/cncf/udpa/go v0.0.0-20210930031921-04548b0d99d4/go.mod h1:6pvJx4me5XPnfI9Z40ddWsdw2W/uZgQLFXToKeRcDiI=
+github.com/cncf/xds/go v0.0.0-20210922020428-25de7278fc84/go.mod h1:eXthEFrGJvWHgFFCl3hGmgk+/aYT6PnTQLykKQRLhEs=
+github.com/cncf/xds/go v0.0.0-20211001041855-01bcc9b48dfe/go.mod h1:eXthEFrGJvWHgFFCl3hGmgk+/aYT6PnTQLykKQRLhEs=
+github.com/cncf/xds/go v0.0.0-20211011173535-cb28da3451f1/go.mod h1:eXthEFrGJvWHgFFCl3hGmgk+/aYT6PnTQLykKQRLhEs=
+github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/envoyproxy/go-control-plane v0.9.0/go.mod h1:YTl/9mNaCwkRvm6d1a2C3ymFceY/DCBVvsKhRF0iEA4=
+github.com/envoyproxy/go-control-plane v0.9.1-0.20191026205805-5f8ba28d4473/go.mod h1:YTl/9mNaCwkRvm6d1a2C3ymFceY/DCBVvsKhRF0iEA4=
+github.com/envoyproxy/go-control-plane v0.9.4/go.mod h1:6rpuAdCZL397s3pYoYcLgu1mIlRU8Am5FuJP05cCM98=
+github.com/envoyproxy/go-control-plane v0.9.9-0.20201210154907-fd9021fe5dad/go.mod h1:cXg6YxExXjJnVBQHBLXeUAgxn2UodCpnH306RInaBQk=
+github.com/envoyproxy/go-control-plane v0.10.2-0.20220325020618-49ff273808a1/go.mod h1:KJwIaB5Mv44NWtYuAOFCVOjcI94vtpEz2JU/D2v6IjE=
+github.com/envoyproxy/protoc-gen-validate v0.1.0/go.mod h1:iSmxcyjqTsJpI2R4NaDN7+kN2VEUnK/pcBlmesArF7c=
+github.com/ghodss/yaml v1.0.0/go.mod h1:4dBDuWmgqj2HViK6kFavaiC9ZROes6MMH2rRYeMEF04=
 github.com/go-logr/logr v1.2.0 h1:QK40JKJyMdUDz+h+xvCsru/bJhvG0UxvePV0ufL/AcE=
 github.com/go-logr/logr v1.2.0/go.mod h1:jdQByPbusPIv2/zmleS9BjJVeZ6kBagPoEUsqbVz/1A=
+github.com/golang/glog v0.0.0-20160126235308-23def4e6c14b/go.mod h1:SBH7ygxi8pfUlaOkMMuAQtPIUF8ecWP5IEl/CR7VP2Q=
+github.com/golang/mock v1.1.1/go.mod h1:oTYuIxOrZwtPieC+H1uAHpcLFnEyAGVDL/k47Jfbm0A=
+github.com/golang/protobuf v1.2.0/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
+github.com/golang/protobuf v1.3.2/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
+github.com/golang/protobuf v1.3.3/go.mod h1:vzj43D7+SQXF/4pzW/hwtAqwc6iTitCiVSaWz5lYuqw=
+github.com/golang/protobuf v1.4.0-rc.1/go.mod h1:ceaxUfeHdC40wWswd/P6IGgMaK3YpKi5j83Wpe3EHw8=
+github.com/golang/protobuf v1.4.0-rc.1.0.20200221234624-67d41d38c208/go.mod h1:xKAWHe0F5eneWXFV3EuXVDTCmh+JuBKY0li0aMyXATA=
+github.com/golang/protobuf v1.4.0-rc.2/go.mod h1:LlEzMj4AhA7rCAGe4KMBDvJI+AwstrUpVNzEA03Pprs=
+github.com/golang/protobuf v1.4.0-rc.4.0.20200313231945-b860323f09d0/go.mod h1:WU3c8KckQ9AFe+yFwt9sWVRKCVIyN9cPHBJSNnbL67w=
+github.com/golang/protobuf v1.4.0/go.mod h1:jodUvKwWbYaEsadDk5Fwe5c77LiNKVO9IDvqG2KuDX0=
+github.com/golang/protobuf v1.4.1/go.mod h1:U8fpvMrcmy5pZrNK1lt4xCsGvpyWQ/VVv6QDs8UjoX8=
+github.com/golang/protobuf v1.4.2/go.mod h1:oDoupMAO8OvCJWAcko0GGGIgR6R6ocIYbsSw735rRwI=
+github.com/golang/protobuf v1.4.3/go.mod h1:oDoupMAO8OvCJWAcko0GGGIgR6R6ocIYbsSw735rRwI=
 github.com/golang/protobuf v1.5.0/go.mod h1:FsONVRAS9T7sI+LIUmWTfcYkHO4aIWwzhcaSAoJOfIk=
+github.com/golang/protobuf v1.5.2 h1:ROPKBNFfQgOUMifHyP+KYbvpjbdoFNs+aK7DXlji0Tw=
+github.com/golang/protobuf v1.5.2/go.mod h1:XVQd3VNwM+JqD3oG2Ue2ip4fOMUkwXdXDdiuN0vRsmY=
 github.com/google/certificate-transparency-go v1.1.4 h1:hCyXHDbtqlr/lMXU0D4WgbalXL0Zk4dSWWMbPV8VrqY=
 github.com/google/certificate-transparency-go v1.1.4/go.mod h1:D6lvbfwckhNrbM9WVl1EVeMOyzC19mpIjMOI4nxBHtQ=
+github.com/google/go-cmp v0.2.0/go.mod h1:oXzfMopK8JAjlY9xF4vHSVASa0yLyX7SntLO5aqRK0M=
+github.com/google/go-cmp v0.3.0/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
+github.com/google/go-cmp v0.3.1/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
+github.com/google/go-cmp v0.4.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
+github.com/google/go-cmp v0.5.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
 github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
+github.com/google/go-cmp v0.5.6/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
+github.com/google/trillian v1.5.1-0.20220819043421-0a389c4bb8d9 h1:GFmzYtwUMi1S2mjLxfrJ/CZ9gWDG+zeLtZByg/QEBkk=
+github.com/google/trillian v1.5.1-0.20220819043421-0a389c4bb8d9/go.mod h1:vywkS3p2SgNmPL7oAWqU5PiiknzRMp+ol3a19jfY2PQ=
+github.com/google/uuid v1.1.2/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
+github.com/grpc-ecosystem/grpc-gateway v1.16.0/go.mod h1:BDjrQk3hbvj6Nolgz8mAMFbcEtjT1g+wF4CSlocrBnw=
+github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/prometheus/client_model v0.0.0-20190812154241-14fe0d1b01d4/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA=
+github.com/rogpeppe/fastuuid v1.2.0/go.mod h1:jVj6XXZzXRy/MSR5jhDC/2q6DgLz+nrA6LYCDYWNEvQ=
+github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
+github.com/stretchr/testify v1.5.1/go.mod h1:5W2xD1RspED5o8YsWQXVCued0rvSQ+mT+I5cxcmMvtA=
+github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
 gitlab.torproject.org/rgdd/ct v0.0.0-20230115071200-fa4d0bcd1cab h1:Yj/plCmxPPidqP53forpttZhUeGgzYoIvq8C6GTMN8M=
 gitlab.torproject.org/rgdd/ct v0.0.0-20230115071200-fa4d0bcd1cab/go.mod h1:dkEqBVulcsefxw3k5CX53bw88KUkTYcTRSJhMlj1Veg=
+go.opentelemetry.io/proto/otlp v0.7.0/go.mod h1:PqfVotwruBrMGOCsRd/89rSnXhoiJIqeYNgFYFoEGnI=
+golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
+golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
 golang.org/x/crypto v0.0.0-20220411220226-7b82a4e95df4 h1:kUhD7nTDoI3fVd9G4ORWrbV5NY0liEs/Jg2pv5f+bBA=
 golang.org/x/crypto v0.0.0-20220411220226-7b82a4e95df4/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
+golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
+golang.org/x/lint v0.0.0-20181026193005-c67002cb31c3/go.mod h1:UVdnD1Gm6xHRNCYTkRU2/jEulfH38KcIWyp/GAMgvoE=
+golang.org/x/lint v0.0.0-20190227174305-5b3e6a55c961/go.mod h1:wehouNa3lNwaWXcvxsM5YxQ5yQlVC4a0KAMCusXpPoU=
+golang.org/x/lint v0.0.0-20190313153728-d0100b6bd8b3/go.mod h1:6SW0HCj/g11FgYtHlgUYUwCkIfeOF89ocIRzGO/8vkc=
+golang.org/x/net v0.0.0-20180724234803-3673e40ba225/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
+golang.org/x/net v0.0.0-20180826012351-8a410e7b638d/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
+golang.org/x/net v0.0.0-20190108225652-1e06a53dbb7e/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
+golang.org/x/net v0.0.0-20190213061140-3a22650c66bd/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
+golang.org/x/net v0.0.0-20190311183353-d8887717615a/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
+golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
+golang.org/x/net v0.0.0-20200822124328-c89045814202/go.mod h1:/O7V0waA8r7cgGh81Ro3o1hOxt32SMVPicZroKQ2sZA=
+golang.org/x/net v0.0.0-20201021035429-f5854403a974/go.mod h1:sp8m0HH+o8qH0wwXwYZr8TS3Oi6o0r6Gce1SSxlDquU=
+golang.org/x/net v0.0.0-20210405180319-a5a99cb37ef4/go.mod h1:p54w0d4576C0XHj96bSt6lcn1PtDYWL6XObtHCRCNQM=
 golang.org/x/net v0.0.0-20220722155237-a158d28d115b h1:PxfKdU9lEEDYjdIzOtC4qFWgkU2rGHdKlKowJSMN9h0=
 golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
+golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
+golang.org/x/oauth2 v0.0.0-20200107190931-bf48bf16ab8d/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
+golang.org/x/sync v0.0.0-20180314180146-1d60e4601c6f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.0.0-20181108010431-42b317875d0f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.0.0-20181221193216-37e7f081c4d4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sys v0.0.0-20180830151530-49385e6e1522/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
+golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
+golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20200323222414-85ca7c5b95cd/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20210119212857-b64e53b001e4/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20210330210617-4fbd30eecc44/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20210510120138-977fb7262007/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
+golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
+golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
+golang.org/x/text v0.3.5/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
+golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
+golang.org/x/tools v0.0.0-20190114222345-bf090417da8b/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
+golang.org/x/tools v0.0.0-20190226205152-f727befe758c/go.mod h1:9Yl7xja0Znq3iFh3HoIrodX9oNMXvdceNzlUR8zjMvY=
+golang.org/x/tools v0.0.0-20190311212946-11955173bddd/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs=
+golang.org/x/tools v0.0.0-20190524140312-2c0ae7006135/go.mod h1:RgjU9mgBXZiqYHBnxXauZ1Gv1EHHAz9KjViQ78xBX0Q=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
+golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
+google.golang.org/appengine v1.1.0/go.mod h1:EbEs0AVv82hx2wNQdGPgUI5lhzA/G0D9YwlJXL52JkM=
+google.golang.org/appengine v1.4.0/go.mod h1:xpcJRLb0r/rnEns0DIKYYv+WjYCduHsrkT7/EB5XEv4=
+google.golang.org/genproto v0.0.0-20180817151627-c66870c02cf8/go.mod h1:JiN7NxoALGmiZfu7CAH4rXhgtRTLTxftemlI0sWmxmc=
+google.golang.org/genproto v0.0.0-20190819201941-24fa4b261c55/go.mod h1:DMBHOl98Agz4BDEuKkezgsaosCRResVns1a3J2ZsMNc=
+google.golang.org/genproto v0.0.0-20200513103714-09dca8ec2884/go.mod h1:55QSHmfGQM9UVYDPBsyGGes0y52j32PQ3BqQfXhyH3c=
+google.golang.org/genproto v0.0.0-20200526211855-cb27e3aa2013/go.mod h1:NbSheEEYHJ7i3ixzK3sjbqSGDJWnxyFXZblF3eUsNvo=
+google.golang.org/genproto v0.0.0-20220706185917-7780775163c4 h1:7YDGQC/0sigNGzsEWyb9s72jTxlFdwVEYNJHbfQ+Dtg=
+google.golang.org/genproto v0.0.0-20220706185917-7780775163c4/go.mod h1:KEWEmljWE5zPzLBa/oHl6DaEt9LmfH6WtH1OHIvleBA=
+google.golang.org/grpc v1.19.0/go.mod h1:mqu4LbDTu4XGKhr4mRzUsmM4RtVoemTSY81AxZiDr8c=
+google.golang.org/grpc v1.23.0/go.mod h1:Y5yQAOtifL1yxbo5wqy6BxZv8vAUGQwXBOALyacEbxg=
+google.golang.org/grpc v1.25.1/go.mod h1:c3i+UQWmh7LiEpx4sFZnkU36qjEYZ0imhYfXVyQciAY=
+google.golang.org/grpc v1.27.0/go.mod h1:qbnxyOmOxrQa7FizSgH+ReBfzJrCY1pSN7KXBS8abTk=
+google.golang.org/grpc v1.33.1/go.mod h1:fr5YgcSWrqhRRxogOsw7RzIpsmvOZ6IcH4kBYTpR3n0=
+google.golang.org/grpc v1.36.0/go.mod h1:qjiiYl8FncCW8feJPdyg3v6XW24KsRHe+dy9BAGRRjU=
+google.golang.org/grpc v1.47.0/go.mod h1:vN9eftEi1UMyUsIF80+uQXhHjbXYbm0uXoFCACuMGWk=
+google.golang.org/grpc v1.48.0 h1:rQOsyJ/8+ufEDJd/Gdsz7HG220Mh9HAhFHRGnIjda0w=
+google.golang.org/grpc v1.48.0/go.mod h1:vN9eftEi1UMyUsIF80+uQXhHjbXYbm0uXoFCACuMGWk=
+google.golang.org/protobuf v0.0.0-20200109180630-ec00e32a8dfd/go.mod h1:DFci5gLYBciE7Vtevhsrf46CRTquxDuWsQurQQe4oz8=
+google.golang.org/protobuf v0.0.0-20200221191635-4d8936d0db64/go.mod h1:kwYJMbMJ01Woi6D6+Kah6886xMZcty6N08ah7+eCXa0=
+google.golang.org/protobuf v0.0.0-20200228230310-ab0ca4ff8a60/go.mod h1:cfTl7dwQJ+fmap5saPgwCLgHXTUD7jkjRqWcaiX5VyM=
+google.golang.org/protobuf v1.20.1-0.20200309200217-e05f789c0967/go.mod h1:A+miEFZTKqfCUM6K7xSMQL9OKL/b6hQv+e19PK+JZNE=
+google.golang.org/protobuf v1.21.0/go.mod h1:47Nbq4nVaFHyn7ilMalzfO3qCViNmqZ2kzikPIcrTAo=
+google.golang.org/protobuf v1.22.0/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
+google.golang.org/protobuf v1.23.0/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
+google.golang.org/protobuf v1.23.1-0.20200526195155-81db48ad09cc/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
+google.golang.org/protobuf v1.25.0/go.mod h1:9JNX74DMeImyA3h4bdi1ymwjUzf21/xIlbajtzgsN7c=
 google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp09yW+WbY/TyQbw=
+google.golang.org/protobuf v1.26.0/go.mod h1:9q0QmTI4eRPtz6boOQmLYwt+qCgq0jsYwAQnmE0givc=
+google.golang.org/protobuf v1.27.1/go.mod h1:9q0QmTI4eRPtz6boOQmLYwt+qCgq0jsYwAQnmE0givc=
+google.golang.org/protobuf v1.28.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
 google.golang.org/protobuf v1.28.1 h1:d0NfwRgPtno5B1Wa6L2DAG+KivqkdutMf1UhdNx175w=
 google.golang.org/protobuf v1.28.1/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
+gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
+gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
+gopkg.in/yaml.v2 v2.2.3/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
+gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
+honnef.co/go/tools v0.0.0-20190102054323-c2f93a96b099/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4=
+honnef.co/go/tools v0.0.0-20190523083050-ea95bdfd59fc/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4=
 k8s.io/klog/v2 v2.80.1 h1:atnLQ121W371wYYFawwYx1aEY2eUfs4l3J72wtgAwV4=
 k8s.io/klog/v2 v2.80.1/go.mod h1:y1WjHnz7Dj687irZUWR/WLkLc5N1YHtjLdmgWjndZn0=
diff --git a/main.go b/main.go
index 0511ab7..02ed413 100644
--- a/main.go
+++ b/main.go
@@ -51,6 +51,10 @@ type options struct {
 	sthFile               string
 	stateFile             string
 	sansFile              string
+
+	workersPerLog uint64
+	batchSize     uint64
+	persistSize   uint64
 }
 
 func main() {
@@ -82,13 +86,17 @@ func main() {
 	opts.stateFile = "th.json"
 	opts.sansFile = "sans.lst"
 
+	opts.workersPerLog = 10
+	opts.batchSize = 16384
+	opts.persistSize = 256
+
 	// Hand-over to the respective subcommands
 	var err error
 	switch cmd := os.Args[1]; cmd {
 	case "snapshot":
 		err = snapshot(opts)
-	//case "collect":
-	//	err = collect(opts)
+	case "collect":
+		err = collect(opts)
 	case "assemble":
 		err = assemble(opts)
 	default: