First Parquet implementation draft

Author: alanprot

go.mod

@@ -76,11 +76,13 @@ require (
 
 require (
 	github.com/VictoriaMetrics/fastcache v1.12.2
+	github.com/axiomhq/hyperloglog v0.2.5
 	github.com/bboreham/go-loser v0.0.0-20230920113527-fcc2c21820a3
 	github.com/cespare/xxhash/v2 v2.3.0
 	github.com/google/go-cmp v0.7.0
 	github.com/hashicorp/golang-lru/v2 v2.0.7
 	github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822
+	github.com/parquet-go/parquet-go v0.25.0
 	github.com/sercand/kuberesolver/v5 v5.1.1
 	github.com/tjhop/slog-gokit v0.1.3
 	go.opentelemetry.io/collector/pdata v1.24.0
@@ -101,6 +103,7 @@ require (
 	github.com/AzureAD/microsoft-authentication-library-for-go v1.3.2 // indirect
 	github.com/alecthomas/template v0.0.0-20190718012654-fb15b899a751 // indirect
 	github.com/alicebob/gopher-json v0.0.0-20230218143504-906a9b012302 // indirect
+	github.com/andybalholm/brotli v1.1.0 // indirect
 	github.com/asaskevich/govalidator v0.0.0-20230301143203-a9d515a09cc2 // indirect
 	github.com/aws/aws-sdk-go-v2 v1.16.16 // indirect
 	github.com/aws/aws-sdk-go-v2/config v1.15.1 // indirect
@@ -171,13 +174,15 @@ require (
 	github.com/josharian/intern v1.0.0 // indirect
 	github.com/jpillora/backoff v1.0.0 // indirect
 	github.com/julienschmidt/httprouter v1.3.0 // indirect
+	github.com/kamstrup/intmap v0.5.1 // indirect
 	github.com/klauspost/cpuid/v2 v2.2.8 // indirect
 	github.com/kylelemons/godebug v1.1.0 // indirect
 	github.com/lann/builder v0.0.0-20180802200727-47ae307949d0 // indirect
 	github.com/lann/ps v0.0.0-20150810152359-62de8c46ede0 // indirect
 	github.com/mailru/easyjson v0.7.7 // indirect
 	github.com/mattn/go-colorable v0.1.13 // indirect
 	github.com/mattn/go-isatty v0.0.20 // indirect
+	github.com/mattn/go-runewidth v0.0.15 // indirect
 	github.com/matttproud/golang_protobuf_extensions v1.0.4 // indirect
 	github.com/mdlayher/socket v0.4.1 // indirect
 	github.com/mdlayher/vsock v1.2.1 // indirect
@@ -192,16 +197,19 @@ require (
 	github.com/mwitkow/go-conntrack v0.0.0-20190716064945-2f068394615f // indirect
 	github.com/ncw/swift v1.0.53 // indirect
 	github.com/oklog/run v1.1.0 // indirect
+	github.com/olekukonko/tablewriter v0.0.5 // indirect
 	github.com/open-telemetry/opentelemetry-collector-contrib/internal/exp/metrics v0.116.0 // indirect
 	github.com/open-telemetry/opentelemetry-collector-contrib/pkg/pdatautil v0.116.0 // indirect
 	github.com/open-telemetry/opentelemetry-collector-contrib/processor/deltatocumulativeprocessor v0.116.0 // indirect
+	github.com/pierrec/lz4/v4 v4.1.21 // indirect
 	github.com/pkg/browser v0.0.0-20240102092130-5ac0b6a4141c // indirect
 	github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect
 	github.com/prometheus-community/prom-label-proxy v0.8.1-0.20240127162815-c1195f9aabc0 // indirect
 	github.com/prometheus/exporter-toolkit v0.13.2 // indirect
 	github.com/prometheus/procfs v0.15.1 // indirect
 	github.com/prometheus/sigv4 v0.1.1 // indirect
 	github.com/redis/rueidis v1.0.45-alpha.1 // indirect
+	github.com/rivo/uniseg v0.4.7 // indirect
 	github.com/rs/cors v1.11.1 // indirect
 	github.com/rs/xid v1.6.0 // indirect
 	github.com/sean-/seed v0.0.0-20170313163322-e2103e2c3529 // indirect
@@ -289,3 +297,5 @@ replace gopkg.in/alecthomas/kingpin.v2 => github.com/alecthomas/kingpin v1.3.8-0
 
 // gRPC 1.66 introduced memory pooling which breaks Cortex queries. Pin 1.65.0 until we have a fix.
 replace google.golang.org/grpc => google.golang.org/grpc v1.65.0
+
+replace github.com/parquet-go/parquet-go => github.com/alanprot/parquet-go v0.25.0-rc.1

go.sum

@@ -808,6 +808,8 @@ github.com/ajstarks/deck v0.0.0-20200831202436-30c9fc6549a9/go.mod h1:JynElWSGnm
 github.com/ajstarks/deck/generate v0.0.0-20210309230005-c3f852c02e19/go.mod h1:T13YZdzov6OU0A1+RfKZiZN9ca6VeKdBdyDV+BY97Tk=
 github.com/ajstarks/svgo v0.0.0-20180226025133-644b8db467af/go.mod h1:K08gAheRH3/J6wwsYMMT4xOr94bZjxIelGM0+d/wbFw=
 github.com/ajstarks/svgo v0.0.0-20211024235047-1546f124cd8b/go.mod h1:1KcenG0jGWcpt8ov532z81sp/kMMUG485J2InIOyADM=
+github.com/alanprot/parquet-go v0.25.0-rc.1 h1:dnElcQFd6uksLIIEisC8WOs6TOc8lx/O0pUayZtr2q8=
+github.com/alanprot/parquet-go v0.25.0-rc.1/go.mod h1:OqBBRGBl7+llplCvDMql8dEKaDqjaFA/VAPw+OJiNiw=
 github.com/alecthomas/kingpin v1.3.8-0.20210301060133-17f40c25f497 h1:aDITxVUQ/3KBhpVWX57Vo9ntGTxoRw1F0T6/x/tRzNU=
 github.com/alecthomas/kingpin v1.3.8-0.20210301060133-17f40c25f497/go.mod h1:b6br6/pDFSfMkBgC96TbpOji05q5pa+v5rIlS0Y6XtI=
 github.com/alecthomas/template v0.0.0-20160405071501-a0175ee3bccc/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
@@ -828,6 +830,8 @@ github.com/aliyun/aliyun-oss-go-sdk v2.2.2+incompatible/go.mod h1:T/Aws4fEfogEE9
 github.com/allegro/bigcache v1.2.1-0.20190218064605-e24eb225f156 h1:eMwmnE/GDgah4HI848JfFxHt+iPb26b4zyfspmqY0/8=
 github.com/allegro/bigcache v1.2.1-0.20190218064605-e24eb225f156/go.mod h1:Cb/ax3seSYIx7SuZdm2G2xzfwmv3TPSk2ucNfQESPXM=
 github.com/andybalholm/brotli v1.0.4/go.mod h1:fO7iG3H7G2nSZ7m0zPUDn85XEX2GTukHGRSepvi9Eig=
+github.com/andybalholm/brotli v1.1.0 h1:eLKJA0d02Lf0mVpIDgYnqXcUn0GqVmEFny3VuID1U3M=
+github.com/andybalholm/brotli v1.1.0/go.mod h1:sms7XGricyQI9K10gOSf56VKKWS4oLer58Q+mhRPtnY=
 github.com/antihax/optional v1.0.0/go.mod h1:uupD/76wgC+ih3iEmQUL+0Ugr19nfwCT1kdvxnR2qWY=
 github.com/apache/arrow/go/v10 v10.0.1/go.mod h1:YvhnlEePVnBS4+0z3fhPfUy7W1Ikj0Ih0vcRo/gZ1M0=
 github.com/apache/arrow/go/v11 v11.0.0/go.mod h1:Eg5OsL5H+e299f7u5ssuXsuHQVEGC4xei5aX110hRiI=
@@ -877,6 +881,8 @@ github.com/aws/aws-sdk-go-v2/service/sts v1.16.19/go.mod h1:h4J3oPZQbxLhzGnk+j9d
 github.com/aws/smithy-go v1.11.1/go.mod h1:3xHYmszWVx2c0kIwQeEVf9uSm4fYZt67FBJnwub1bgM=
 github.com/aws/smithy-go v1.13.3 h1:l7LYxGuzK6/K+NzJ2mC+VvLUbae0sL3bXU//04MkmnA=
 github.com/aws/smithy-go v1.13.3/go.mod h1:Tg+OJXh4MB2R/uN61Ko2f6hTZwB/ZYGOtib8J3gBHzA=
+github.com/axiomhq/hyperloglog v0.2.5 h1:Hefy3i8nAs8zAI/tDp+wE7N+Ltr8JnwiW3875pvl0N8=
+github.com/axiomhq/hyperloglog v0.2.5/go.mod h1:DLUK9yIzpU5B6YFLjxTIcbHu1g4Y1WQb1m5RH3radaM=
 github.com/baidubce/bce-sdk-go v0.9.111 h1:yGgtPpZYUZW4uoVorQ4xnuEgVeddACydlcJKW87MDV4=
 github.com/baidubce/bce-sdk-go v0.9.111/go.mod h1:zbYJMQwE4IZuyrJiFO8tO8NbtYiKTFTbwh4eIsqjVdg=
 github.com/bboreham/go-loser v0.0.0-20230920113527-fcc2c21820a3 h1:6df1vn4bBlDDo4tARvBm7l6KA9iVMnE3NWizDeWSrps=
@@ -1328,6 +1334,8 @@ github.com/hashicorp/serf v0.10.1 h1:Z1H2J60yRKvfDYAOZLd2MU0ND4AH/WDz7xYHDWQsIPY
 github.com/hashicorp/serf v0.10.1/go.mod h1:yL2t6BqATOLGc5HF7qbFkTfXoPIY0WZdWHfEvMqbG+4=
 github.com/hetznercloud/hcloud-go/v2 v2.18.0 h1:BemrVGeWI8Kn/pvaC1jBsHZxQMnRqOydS7Ju4BERB4Q=
 github.com/hetznercloud/hcloud-go/v2 v2.18.0/go.mod h1:r5RTzv+qi8IbLcDIskTzxkFIji7Ovc8yNgepQR9M+UA=
+github.com/hexops/gotextdiff v1.0.3 h1:gitA9+qJrrTCsiCl7+kh75nPqQt1cx4ZkudSTLoUqJM=
+github.com/hexops/gotextdiff v1.0.3/go.mod h1:pSWU5MAI3yDq+fZBTazCSJysOMbxWL1BSow5/V2vxeg=
 github.com/huaweicloud/huaweicloud-sdk-go-obs v3.23.3+incompatible h1:tKTaPHNVwikS3I1rdyf1INNvgJXWSf/+TzqsiGbrgnQ=
 github.com/huaweicloud/huaweicloud-sdk-go-obs v3.23.3+incompatible/go.mod h1:l7VUhRbTKCzdOacdT4oWCwATKyvZqUOlOqr0Ous3k4s=
 github.com/iancoleman/strcase v0.2.0/go.mod h1:iwCmte+B7n89clKwxIoIXy/HfoL7AsD47ZCWhYzw7ho=
@@ -1362,6 +1370,8 @@ github.com/julienschmidt/httprouter v1.3.0 h1:U0609e9tgbseu3rBINet9P48AI/D3oJs4d
 github.com/julienschmidt/httprouter v1.3.0/go.mod h1:JR6WtHb+2LUe8TCKY3cZOxFyyO8IZAc4RVcycCCAKdM=
 github.com/jung-kurt/gofpdf v1.0.0/go.mod h1:7Id9E/uU8ce6rXgefFLlgrJj/GYY22cpxn+r32jIOes=
 github.com/jung-kurt/gofpdf v1.0.3-0.20190309125859-24315acbbda5/go.mod h1:7Id9E/uU8ce6rXgefFLlgrJj/GYY22cpxn+r32jIOes=
+github.com/kamstrup/intmap v0.5.1 h1:ENGAowczZA+PJPYYlreoqJvWgQVtAmX1l899WfYFVK0=
+github.com/kamstrup/intmap v0.5.1/go.mod h1:gWUVWHKzWj8xpJVFf5GC0O26bWmv3GqdnIX/LMT6Aq4=
 github.com/kballard/go-shellquote v0.0.0-20180428030007-95032a82bc51/go.mod h1:CzGEWj7cYgsdH8dAjBGEr58BoE7ScuLd+fwFZ44+/x8=
 github.com/keybase/go-keychain v0.0.0-20231219164618-57a3676c3af6 h1:IsMZxCuZqKuao2vNdfD82fjjgPLfyHLpR41Z88viRWs=
 github.com/keybase/go-keychain v0.0.0-20231219164618-57a3676c3af6/go.mod h1:3VeWNIJaW+O5xpRQbPp0Ybqu1vJd/pm7s2F473HRrkw=
@@ -1442,6 +1452,9 @@ github.com/mattn/go-isatty v0.0.16/go.mod h1:kYGgaQfpe5nmfYZH+SKPsOc2e4SrIfOl2e/
 github.com/mattn/go-isatty v0.0.17/go.mod h1:kYGgaQfpe5nmfYZH+SKPsOc2e4SrIfOl2e/yFXSvRLM=
 github.com/mattn/go-isatty v0.0.20 h1:xfD0iDuEKnDkl03q4limB+vH+GxLEtL/jb4xVJSWWEY=
 github.com/mattn/go-isatty v0.0.20/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
+github.com/mattn/go-runewidth v0.0.9/go.mod h1:H031xJmbD/WCDINGzjvQ9THkh0rPKHF+m2gUSrubnMI=
+github.com/mattn/go-runewidth v0.0.15 h1:UNAjwbU9l54TA3KzvqLGxwWjHmMgBUVhBiTjelZgg3U=
+github.com/mattn/go-runewidth v0.0.15/go.mod h1:Jdepj2loyihRzMpdS35Xk/zdY8IAYHsh153qUoGf23w=
 github.com/mattn/go-sqlite3 v1.14.14/go.mod h1:NyWgC/yNuGj7Q9rpYnZvas74GogHl5/Z4A/KQRfk6bU=
 github.com/mattn/go-sqlite3 v1.14.15/go.mod h1:2eHXhiwb8IkHr+BDWZGa96P6+rkvnG63S2DGjv9HUNg=
 github.com/matttproud/golang_protobuf_extensions v1.0.1/go.mod h1:D8He9yQNgCq6Z5Ld7szi9bcBfOoFv/3dc6xSMkL2PC0=
@@ -1509,6 +1522,8 @@ github.com/oklog/run v1.1.0 h1:GEenZ1cK0+q0+wsJew9qUg/DyD8k3JzYsZAi5gYi2mA=
 github.com/oklog/run v1.1.0/go.mod h1:sVPdnTZT1zYwAJeCMu2Th4T21pA3FPOQRfWjQlk7DVU=
 github.com/oklog/ulid v1.3.1 h1:EGfNDEx6MqHz8B3uNV6QAib1UR2Lm97sHi3ocA6ESJ4=
 github.com/oklog/ulid v1.3.1/go.mod h1:CirwcVhetQ6Lv90oh/F+FBtV6XMibvdAFo93nm5qn4U=
+github.com/olekukonko/tablewriter v0.0.5 h1:P2Ga83D34wi1o9J6Wh1mRuqd4mF/x/lgBS7N7AbDhec=
+github.com/olekukonko/tablewriter v0.0.5/go.mod h1:hPp6KlRPjbx+hW8ykQs1w3UBbZlj6HuIJcUGPhkA7kY=
 github.com/onsi/ginkgo v1.16.5 h1:8xi0RTUf59SOSfEtZMvwTvXYMzG4gV23XVHOZiXNtnE=
 github.com/onsi/ginkgo v1.16.5/go.mod h1:+E8gABHa3K6zRBolWtd+ROzc/U5bkGt0FwiG042wbpU=
 github.com/onsi/gomega v1.34.0 h1:eSSPsPNp6ZpsG8X1OVmOTxig+CblTc4AxpPBykhe2Os=
@@ -1527,7 +1542,7 @@ github.com/opencontainers/image-spec v1.1.0 h1:8SG7/vwALn54lVB/0yZ/MMwhFrPYtpEHQ
 github.com/opencontainers/image-spec v1.1.0/go.mod h1:W4s4sFTMaBeK1BQLXbG4AdM2szdn85PY75RI83NrTrM=
 github.com/opentracing-contrib/go-grpc v0.1.0 h1:9JHDtQXv6UL0tFF8KJB/4ApJgeOcaHp1h07d0PJjESc=
 github.com/opentracing-contrib/go-grpc v0.1.0/go.mod h1:i3/jx/TvJZ/HKidtT4XGIi/NosUEpzS9xjVJctbKZzI=
-github.com/opentracing-contrib/go-stdlib v1.1.0 h1:cZBWc4pA4e65tqTJddbflK435S0tDImj6c9BMvkdUH0=
+github.com/opentracing-contrib/go-stdlib v1.1.0 h1:hSJ8yYaiAO/k2YZUeWJWpQCPE2wRCDtxRnir0gU6wbA=
 github.com/opentracing-contrib/go-stdlib v1.1.0/go.mod h1:S0p+X9p6dcBkoMTL+Qq2VOvxKs9ys5PpYWXWqlCS0bQ=
 github.com/opentracing/opentracing-go v1.1.0/go.mod h1:UkNAQd3GIcIGf0SeVgPpRdFStlNbqXla1AfSYxPUl2o=
 github.com/opentracing/opentracing-go v1.2.0 h1:uEJPy/1a5RIPAJ0Ov+OIO8OxWu77jEv+1B0VhjKrZUs=
@@ -1546,6 +1561,8 @@ github.com/phpdave11/gofpdf v1.4.2/go.mod h1:zpO6xFn9yxo3YLyMvW8HcKWVdbNqgIfOOp2
 github.com/phpdave11/gofpdi v1.0.12/go.mod h1:vBmVV0Do6hSBHC8uKUQ71JGW+ZGQq74llk/7bXwjDoI=
 github.com/phpdave11/gofpdi v1.0.13/go.mod h1:vBmVV0Do6hSBHC8uKUQ71JGW+ZGQq74llk/7bXwjDoI=
 github.com/pierrec/lz4/v4 v4.1.15/go.mod h1:gZWDp/Ze/IJXGXf23ltt2EXimqmTUXEy0GFuRQyBid4=
+github.com/pierrec/lz4/v4 v4.1.21 h1:yOVMLb6qSIDP67pl/5F7RepeKYu/VmTyEXvuMI5d9mQ=
+github.com/pierrec/lz4/v4 v4.1.21/go.mod h1:gZWDp/Ze/IJXGXf23ltt2EXimqmTUXEy0GFuRQyBid4=
 github.com/pkg/browser v0.0.0-20240102092130-5ac0b6a4141c h1:+mdjkGKdHQG3305AYmdv1U2eRNDiU2ErMBj1gwrq8eQ=
 github.com/pkg/browser v0.0.0-20240102092130-5ac0b6a4141c/go.mod h1:7rwL4CYBLnjLxUqIJNnCWiEdr3bn6IUYi15bNlnbCCU=
 github.com/pkg/diff v0.0.0-20210226163009-20ebb0f2a09e/go.mod h1:pJLUxLENpZxwdsKMEsNbx1VGcRFpLqf3715MtcvvzbA=
@@ -1605,6 +1622,9 @@ github.com/redis/rueidis v1.0.45-alpha.1 h1:69Bu1l7gVC/qDYuGGwMwGg2rjOjSyxESol/Z
 github.com/redis/rueidis v1.0.45-alpha.1/go.mod h1:q7BfhDaPt7xxwy2nv2RqQO12/mmHflDjebpcNwWFjms=
 github.com/remyoudompheng/bigfft v0.0.0-20200410134404-eec4a21b6bb0/go.mod h1:qqbHyh8v60DhA7CoWK5oRCqLrMHRGoxYCSS9EjAz6Eo=
 github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec/go.mod h1:qqbHyh8v60DhA7CoWK5oRCqLrMHRGoxYCSS9EjAz6Eo=
+github.com/rivo/uniseg v0.2.0/go.mod h1:J6wj4VEh+S6ZtnVlnTBMWIodfgj8LQOQFoIToxlJtxc=
+github.com/rivo/uniseg v0.4.7 h1:WUdvkW8uEhrYfLC4ZzdpI2ztxP1I582+49Oc5Mq64VQ=
+github.com/rivo/uniseg v0.4.7/go.mod h1:FN3SvrM+Zdj16jyLfmOkMNblXMcoc8DfTHruCPUcx88=
 github.com/rogpeppe/fastuuid v1.2.0/go.mod h1:jVj6XXZzXRy/MSR5jhDC/2q6DgLz+nrA6LYCDYWNEvQ=
 github.com/rogpeppe/go-internal v1.3.0/go.mod h1:M8bDsm7K2OlrFYOpmOWEs/qY81heoFRclV5y23lUDJ4=
 github.com/rogpeppe/go-internal v1.6.1/go.mod h1:xXDCJY+GAPziupqXw64V24skbSoqbTEfhy4qGm1nDQc=

pkg/compactor/compaction_marker.go

@@ -0,0 +1,61 @@
+package compactor
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"io"
+	"path"
+
+	"github.com/cortexproject/cortex/pkg/storage/tsdb"
+	"github.com/efficientgo/core/errors"
+	"github.com/go-kit/log"
+	"github.com/oklog/ulid"
+	"github.com/thanos-io/objstore"
+	"github.com/thanos-io/thanos/pkg/runutil"
+)
+
+const (
+	ParquetCompactionMakerFileName = "parquet-compaction-mark.json"
+	CurrentVersion                 = 6
+)
+
+type CompactionMark struct {
+	Version int `json:"version"`
+}
+
+func (m *CompactionMark) markerFilename() string { return ParquetCompactionMakerFileName }
+
+func ReadCompactMark(ctx context.Context, id ulid.ULID, userBkt objstore.InstrumentedBucket, logger log.Logger) (*CompactionMark, error) {
+	markerPath := path.Join(id.String(), ParquetCompactionMakerFileName)
+	reader, err := userBkt.WithExpectedErrs(tsdb.IsOneOfTheExpectedErrors(userBkt.IsAccessDeniedErr, userBkt.IsObjNotFoundErr)).Get(ctx, markerPath)
+	if err != nil {
+		if userBkt.IsObjNotFoundErr(err) {
+			return &CompactionMark{}, nil
+		}
+
+		return &CompactionMark{}, err
+	}
+	defer runutil.CloseWithLogOnErr(logger, reader, "close bucket index reader")
+
+	metaContent, err := io.ReadAll(reader)
+	if err != nil {
+		return nil, errors.Wrapf(err, "read file: %s", ParquetCompactionMakerFileName)
+	}
+
+	marker := CompactionMark{}
+	err = json.Unmarshal(metaContent, &marker)
+	return &marker, err
+}
+
+func WriteCompactMark(ctx context.Context, id ulid.ULID, userBkt objstore.Bucket) error {
+	marker := CompactionMark{
+		Version: CurrentVersion,
+	}
+	markerPath := path.Join(id.String(), ParquetCompactionMakerFileName)
+	b, err := json.Marshal(marker)
+	if err != nil {
+		return err
+	}
+	return userBkt.Upload(ctx, markerPath, bytes.NewReader(b))
+}