THIS BRANCH WILL NOT BE MERGED --experimentation only --

.claude/RESUME.md

@@ -0,0 +1,36 @@
+# Resume — poc/otel-profiles-sbob
+
+## Active branch
+`poc/otel-profiles-sbob` off `demo/adaptive-export-config` (fork: `k8sstormcenter/pixie`).
+
+## PoC goal
+Feasibility: extend SBOB with abstracted OTel Profiles emitted by Pixie. Target = redis under bobctl test vs bobctl attack (bmlv-demo). Deadline Mon 2026-05-04.
+
+## Docs / fixtures live separately
+`~/biz/PoC/OTel/` — `state.yaml` is the authoritative status file. Markdown, mermaid PNGs, slides go there. Pixie tree only carries code.
+
+## Task tracker
+9 tasks total. #1 done. Sequence + parallelism in `~/biz/PoC/OTel/state.yaml` under `day_status`. Tracks run in 3 swimlanes Fri–Sun:
+- A (research): #2 capture → #3 userspace prototype (Q1 gate) → #4 UDAs
+- B (plumbing): #5 Profiles sink ‖ #6 planner builder → #7 PxL script → #8 e2e validation
+- C (write-up): #9 rolling draft Fri–Sun, finalize Mon AM
+
+## Staged but uncommitted
+- `bazel/repository_locations.bzl` — OTel proto pin bumped v1.3.2 → v1.10.0
+  - tarball sha256: `52c85df79badc45da7e6a8735e8090b05a961b0208756187e1492a40db2d1f5f`
+  - tag SHA: `ca839c51f706f5d53bfb46f06c3e90c3af3a52c6`
+- `bazel/external/opentelemetry.BUILD` — added `profiles_proto`, `profiles_service_proto`, `profiles_service_grpc_cc` targets matching existing trace/metric/log pattern.
+
+Bump rationale: profiles signal proto only present from v1.4.0 onward; v1development path is alpha. Risk: if existing trace/metric/log code references removed/renamed fields, build breaks. Mitigation if it bites: dual-pin with separate `com_github_opentelemetry_proto_dev` repo for profiles only.
+
+## Build verification not yet run
+Have not invoked `bazel build` against the bumped pin. First build attempt will surface any breakage.
+
+## Pending decisions awaiting user
+1. Commit checkpoints — user has a standing no-commit-without-ask rule. Currently nothing on this branch beyond the base.
+2. bmlv-demo cluster state — task #2 needs redis + pixie + bobctl up on local k3s. Status unknown.
+
+## Hard rules in force
+- No Co-Authored-By Claude / "Generated with Claude Code" on any commit, patch, or PR body.
+- No fabricated metrics in any user-facing artifact — empirical numbers from actual bmlv runs only, otherwise placeholders.
+- No upstream PRs — fork strategy. This branch lives on `k8sstormcenter/pixie`.

bazel/external/opentelemetry.BUILD

@@ -162,3 +162,44 @@ cc_grpc_library(
     grpc_only = True,
     deps = [":logs_service_proto_cc"],
 )
+
+# Profiles signal — v1development (alpha). Pinned via opentelemetry-proto v1.10.0.
+# Schema is explicitly experimental; expect to re-pin on upstream changes.
+proto_library(
+    name = "profiles_proto",
+    srcs = [
+        "opentelemetry/proto/profiles/v1development/profiles.proto",
+    ],
+    deps = [
+        ":common_proto",
+        ":resource_proto",
+    ],
+)
+
+cc_proto_library(
+    name = "profiles_proto_cc",
+    deps = [":profiles_proto"],
+)
+
+proto_library(
+    name = "profiles_service_proto",
+    srcs = [
+        "opentelemetry/proto/collector/profiles/v1development/profiles_service.proto",
+    ],
+    deps = [
+        ":profiles_proto",
+    ],
+)
+
+cc_proto_library(
+    name = "profiles_service_proto_cc",
+    deps = [":profiles_service_proto"],
+)
+
+cc_grpc_library(
+    name = "profiles_service_grpc_cc",
+    srcs = [":profiles_service_proto"],
+    generate_mocks = True,
+    grpc_only = True,
+    deps = [":profiles_service_proto_cc"],
+)

bazel/repository_locations.bzl

@@ -185,9 +185,9 @@ REPOSITORY_LOCATIONS = dict(
         urls = ["https://github.com/nlohmann/json/releases/download/v3.7.3/include.zip"],
     ),
     com_github_opentelemetry_proto = dict(
-        urls = ["https://github.com/open-telemetry/opentelemetry-proto/archive/refs/tags/v1.3.2.tar.gz"],
-        strip_prefix = "opentelemetry-proto-1.3.2",
-        sha256 = "c069c0d96137cf005d34411fa67dd3b6f1f8c64af1e7fb2fe0089a41c425acd7",
+        urls = ["https://github.com/open-telemetry/opentelemetry-proto/archive/refs/tags/v1.10.0.tar.gz"],
+        strip_prefix = "opentelemetry-proto-1.10.0",
+        sha256 = "52c85df79badc45da7e6a8735e8090b05a961b0208756187e1492a40db2d1f5f",
     ),
     com_github_packetzero_dnsparser = dict(
         sha256 = "bdf6c7f56f33725c1c32e672a4779576fb639dd2df565115778eb6be48296431",

go.mod

@@ -52,6 +52,7 @@ require (
 	github.com/ory/dockertest/v3 v3.8.1
 	github.com/ory/hydra-client-go v1.9.2
 	github.com/ory/kratos-client-go v0.10.1
+	github.com/parquet-go/parquet-go v0.25.1
 	github.com/phayes/freeport v0.0.0-20171002181615-b8543db493a5
 	github.com/prometheus/client_golang v1.14.0
 	github.com/prometheus/client_model v0.3.0
@@ -115,6 +116,7 @@ require (
 	github.com/VividCortex/ewma v1.1.1 // indirect
 	github.com/a8m/envsubst v1.3.0 // indirect
 	github.com/alecthomas/participle/v2 v2.0.0-beta.5 // indirect
+	github.com/andybalholm/brotli v1.1.0 // indirect
 	github.com/andybalholm/cascadia v1.1.0 // indirect
 	github.com/asaskevich/govalidator v0.0.0-20230301143203-a9d515a09cc2 // indirect
 	github.com/beorn7/perks v1.0.1 // indirect
@@ -171,7 +173,7 @@ require (
 	github.com/google/go-querystring v1.1.0 // indirect
 	github.com/google/gofuzz v1.2.0 // indirect
 	github.com/google/shlex v0.0.0-20191202100458-e7afc7fbc510 // indirect
-	github.com/google/uuid v1.3.0 // indirect
+	github.com/google/uuid v1.6.0 // indirect
 	github.com/googleapis/gax-go/v2 v2.7.0 // indirect
 	github.com/gorilla/securecookie v1.1.1 // indirect
 	github.com/gorilla/websocket v1.5.0 // indirect
@@ -191,7 +193,7 @@ require (
 	github.com/json-iterator/go v1.1.12 // indirect
 	github.com/jstemmer/go-junit-report v0.9.1 // indirect
 	github.com/kevinburke/ssh_config v0.0.0-20190725054713-01f96b0aa0cd // indirect
-	github.com/klauspost/compress v1.17.2 // indirect
+	github.com/klauspost/compress v1.17.9 // indirect
 	github.com/kr/pretty v0.2.1 // indirect
 	github.com/kr/text v0.2.0 // indirect
 	github.com/kylelemons/godebug v1.1.0 // indirect
@@ -232,6 +234,7 @@ require (
 	github.com/patrickmn/go-cache v2.1.0+incompatible // indirect
 	github.com/pelletier/go-toml v1.9.3 // indirect
 	github.com/peterbourgon/diskv v2.0.1+incompatible // indirect
+	github.com/pierrec/lz4/v4 v4.1.21 // indirect
 	github.com/pkg/errors v0.9.1 // indirect
 	github.com/pmezard/go-difflib v1.0.0 // indirect
 	github.com/prometheus/procfs v0.9.0 // indirect
@@ -276,7 +279,7 @@ require (
 	golang.org/x/xerrors v0.0.0-20220907171357-04be3eba64a2 // indirect
 	gomodules.xyz/jsonpatch/v2 v2.2.0 // indirect
 	google.golang.org/appengine v1.6.7 // indirect
-	google.golang.org/protobuf v1.29.1 // indirect
+	google.golang.org/protobuf v1.34.2 // indirect
 	gopkg.in/inf.v0 v0.9.1 // indirect
 	gopkg.in/ini.v1 v1.67.0 // indirect
 	gopkg.in/launchdarkly/go-jsonstream.v1 v1.0.1 // indirect
@@ -317,3 +320,5 @@ replace (
 	google.golang.org/grpc => google.golang.org/grpc v1.43.0
 	gopkg.in/yaml.v2 => gopkg.in/yaml.v2 v2.4.0
 )
+
+replace google.golang.org/protobuf => google.golang.org/protobuf v1.29.1

go.sum

@@ -87,6 +87,8 @@ github.com/alecthomas/template v0.0.0-20190718012654-fb15b899a751/go.mod h1:LOuy
 github.com/alecthomas/units v0.0.0-20151022065526-2efee857e7cf/go.mod h1:ybxpYRFXyAe+OPACYpWeL0wqObRcbAqCMya13uyzqw0=
 github.com/alecthomas/units v0.0.0-20190717042225-c3de453c63f4/go.mod h1:ybxpYRFXyAe+OPACYpWeL0wqObRcbAqCMya13uyzqw0=
 github.com/alecthomas/units v0.0.0-20190924025748-f65c72e2690d/go.mod h1:rBZYJk541a8SKzHPHnH3zbiI+7dagKZ0cgpgrD7Fyho=
+github.com/andybalholm/brotli v1.1.0 h1:eLKJA0d02Lf0mVpIDgYnqXcUn0GqVmEFny3VuID1U3M=
+github.com/andybalholm/brotli v1.1.0/go.mod h1:sms7XGricyQI9K10gOSf56VKKWS4oLer58Q+mhRPtnY=
 github.com/andybalholm/cascadia v1.1.0 h1:BuuO6sSfQNFRu1LppgbD25Hr2vLYW25JvxHs5zzsLTo=
 github.com/andybalholm/cascadia v1.1.0/go.mod h1:GsXiBklL0woXo1j/WYWtSYYC4ouU9PqHO0sqidkEA4Y=
 github.com/anmitsu/go-shlex v0.0.0-20161002113705-648efa622239 h1:kFOfPq6dUM1hTo4JG6LR5AXSUEsOjtdm0kw0FtQtMJA=
@@ -447,8 +449,8 @@ github.com/google/shlex v0.0.0-20191202100458-e7afc7fbc510 h1:El6M4kTTCOh6aBiKaU
 github.com/google/shlex v0.0.0-20191202100458-e7afc7fbc510/go.mod h1:pupxD2MaaD3pAXIBCelhxNneeOaAeabZDe5s4K6zSpQ=
 github.com/google/uuid v1.1.1/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/google/uuid v1.1.2/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
-github.com/google/uuid v1.3.0 h1:t6JiXgmwXMjEs8VusXIJk2BXHsn+wx8BZdTaoZ5fu7I=
-github.com/google/uuid v1.3.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
+github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
+github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/googleapis/gax-go/v2 v2.0.5/go.mod h1:DWXyrwAJ9X0FpwwEdw+IPEYBICEFu5mhpdKc/us6bOk=
 github.com/googleapis/gax-go/v2 v2.7.0 h1:IcsPKeInNvYi7eqSaDjiZqDDKu5rsmunY0Y1YupQSSQ=
 github.com/googleapis/gax-go/v2 v2.7.0/go.mod h1:TEop28CZZQ2y+c0VxMUmu1lV+fQx57QpBWsYpwqHJx8=
@@ -579,8 +581,8 @@ github.com/klauspost/compress v1.8.2/go.mod h1:RyIbtBH6LamlWaDj8nUwkbUhJ87Yi3uG0
 github.com/klauspost/compress v1.9.0/go.mod h1:RyIbtBH6LamlWaDj8nUwkbUhJ87Yi3uG0guNDohfE1A=
 github.com/klauspost/compress v1.9.5/go.mod h1:RyIbtBH6LamlWaDj8nUwkbUhJ87Yi3uG0guNDohfE1A=
 github.com/klauspost/compress v1.13.6/go.mod h1:/3/Vjq9QcHkK5uEr5lBEmyoZ1iFhe47etQ6QUkpK6sk=
-github.com/klauspost/compress v1.17.2 h1:RlWWUY/Dr4fL8qk9YG7DTZ7PDgME2V4csBXA8L/ixi4=
-github.com/klauspost/compress v1.17.2/go.mod h1:ntbaceVETuRiXiv4DpjP66DpAtAGkEQskQzEyD//IeE=
+github.com/klauspost/compress v1.17.9 h1:6KIumPrER1LHsvBVuDa0r5xaG0Es51mhhB9BQB2qeMA=
+github.com/klauspost/compress v1.17.9/go.mod h1:Di0epgTjJY877eYKx5yC51cX2A2Vl2ibi7bDH9ttBbw=
 github.com/klauspost/cpuid v1.2.1/go.mod h1:Pj4uuM528wm8OyEC2QMXAi2YiTZ96dNQPGgoMS4s3ek=
 github.com/konsorten/go-windows-terminal-sequences v1.0.1/go.mod h1:T0+1ngSBFLxvqU3pZ+m/2kptfBszLMUkC4ZK/EgS/cQ=
 github.com/konsorten/go-windows-terminal-sequences v1.0.2/go.mod h1:T0+1ngSBFLxvqU3pZ+m/2kptfBszLMUkC4ZK/EgS/cQ=
@@ -775,6 +777,8 @@ github.com/ory/hydra-client-go v1.9.2 h1:sbp+8zwEJvhqSxcY8HiOkXeY2FspsfSOJ5ajJ07
 github.com/ory/hydra-client-go v1.9.2/go.mod h1:TTg4Gt0SDC8+XoGtj5qzdtqxapfFW+Vmm41PFuC6n/E=
 github.com/ory/kratos-client-go v0.10.1 h1:kSRk+0leCJ1nPMS+FPho8b9WMzrKNpgszvta0Xo32QU=
 github.com/ory/kratos-client-go v0.10.1/go.mod h1:dOQIsar76K07wMPJD/6aMhrWyY+sFGEagLDLso1CpsA=
+github.com/parquet-go/parquet-go v0.25.1 h1:l7jJwNM0xrk0cnIIptWMtnSnuxRkwq53S+Po3KG8Xgo=
+github.com/parquet-go/parquet-go v0.25.1/go.mod h1:AXBuotO1XiBtcqJb/FKFyjBG4aqa3aQAAWF3ZPzCanY=
 github.com/pascaldekloe/goe v0.0.0-20180627143212-57f6aae5913c/go.mod h1:lzWF7FIEvWOWxwDKqyGYQf6ZUaNfKdP144TG7ZOy1lc=
 github.com/patrickmn/go-cache v2.1.0+incompatible h1:HRMgzkcYKYpi3C8ajMPV8OFXaaRUnok+kx1WdO15EQc=
 github.com/patrickmn/go-cache v2.1.0+incompatible/go.mod h1:3Qf8kWWT7OJRJbdiICTKqZju1ZixQ/KpMGzzAfe6+WQ=
@@ -788,6 +792,8 @@ github.com/peterbourgon/diskv v2.0.1+incompatible h1:UBdAOUP5p4RWqPBg048CAvpKN+v
 github.com/peterbourgon/diskv v2.0.1+incompatible/go.mod h1:uqqh8zWWbv1HBMNONnaR/tNboyR3/BZd58JJSHlUSCU=
 github.com/phayes/freeport v0.0.0-20171002181615-b8543db493a5 h1:rZQtoozkfsiNs36c7Tdv/gyGNzD1X1XWKO8rptVNZuM=
 github.com/phayes/freeport v0.0.0-20171002181615-b8543db493a5/go.mod h1:iIss55rKnNBTvrwdmkUpLnDpZoAHvWaiq5+iMmen4AE=
+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/pingcap/errors v0.11.4 h1:lFuQV/oaUMGcD2tqt+01ROSmJs75VG1ToEOkZIZ4nE4=
 github.com/pingcap/errors v0.11.4/go.mod h1:Oi8TUi2kEtXXLMJk9l1cGmz20kV3TaQ0usTwv5KuLY8=
 github.com/pkg/diff v0.0.0-20210226163009-20ebb0f2a09e h1:aoZm08cpOy4WuID//EZDgcC4zIxODThtZNPirFr42+A=
@@ -1327,10 +1333,6 @@ google.golang.org/genproto v0.0.0-20211208223120-3a66f561d7aa h1:I0YcKz0I7OAhddo
 google.golang.org/genproto v0.0.0-20211208223120-3a66f561d7aa/go.mod h1:5CzLGKJ67TSI2B9POpiiyGha0AjJvZIUgRMt1dSmuhc=
 google.golang.org/grpc v1.43.0 h1:Eeu7bZtDZ2DpRCsLhUlcrLnvYaMK1Gz86a+hMVvELmM=
 google.golang.org/grpc v1.43.0/go.mod h1:k+4IHHFw41K8+bbowsex27ge2rCb65oeWqe4jJ590SU=
-google.golang.org/protobuf v1.23.0/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/go.mod h1:9q0QmTI4eRPtz6boOQmLYwt+qCgq0jsYwAQnmE0givc=
-google.golang.org/protobuf v1.27.1/go.mod h1:9q0QmTI4eRPtz6boOQmLYwt+qCgq0jsYwAQnmE0givc=
 google.golang.org/protobuf v1.29.1 h1:7QBf+IK2gx70Ap/hDsOmam3GE0v9HicjfEdAxE62UoM=
 google.golang.org/protobuf v1.29.1/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
 gopkg.in/alecthomas/kingpin.v2 v2.2.6/go.mod h1:FMv+mEhP44yOT+4EoQTLFTRgOQ1FBLkstjWtayDeSgw=

src/carnot/exec/clickhouse_export_sink_node.cc

@@ -35,6 +35,9 @@ namespace px {
 namespace carnot {
 namespace exec {
 
+// TODO(ddelnano): Defend against columns that don't exist. These should be
+// ignored by the Node.
+
 using table_store::schema::RowBatch;
 using table_store::schema::RowDescriptor;
 
@@ -148,12 +151,12 @@ Status ClickHouseExportSinkNode::ConsumeNextImpl(ExecState* /*exec_state*/, cons
         break;
       }
       case types::UINT128: {
-        // UINT128 is exported as STRING (UUID format)
+        // UINT128 is exported as STRING in "high:low" format to match
+        // the ClickHouseSourceNode's parsing in clickhouse_source_node.cc
         auto col = std::make_shared<clickhouse::ColumnString>();
         for (int64_t i = 0; i < num_rows; ++i) {
           auto val = types::GetValueFromArrowArray<types::UINT128>(arrow_col.get(), i);
-          std::string uuid_str = sole::rebuild(absl::Uint128High64(val), absl::Uint128Low64(val)).str();
-          col->Append(uuid_str);
+          col->Append(absl::Substitute("$0:$1", absl::Uint128High64(val), absl::Uint128Low64(val)));
         }
         block.AppendColumn(mapping.clickhouse_column_name(), col);
         break;
@@ -164,6 +167,34 @@ Status ClickHouseExportSinkNode::ConsumeNextImpl(ExecState* /*exec_state*/, cons
     }
   }
 
+  // Auto-derive event_time from time_ if time_ is present but event_time is not.
+  // The ClickHouse table schema uses event_time (DateTime64(3), milliseconds) for
+  // partitioning and ordering, but the Pixie table has time_ (TIME64NS, nanoseconds).
+  bool has_time_ = false;
+  bool has_event_time = false;
+  int time_col_index = -1;
+  for (const auto& mapping : plan_node_->column_mappings()) {
+    if (mapping.clickhouse_column_name() == "time_") {
+      has_time_ = true;
+      time_col_index = mapping.input_column_index();
+    }
+    if (mapping.clickhouse_column_name() == "event_time") {
+      has_event_time = true;
+    }
+  }
+
+  if (has_time_ && !has_event_time && time_col_index >= 0) {
+    auto arrow_col = rb.ColumnAt(time_col_index);
+    int64_t num_rows = arrow_col->length();
+    auto event_time_col = std::make_shared<clickhouse::ColumnDateTime64>(3);
+    for (int64_t i = 0; i < num_rows; ++i) {
+      int64_t ns_val = types::GetValueFromArrowArray<types::TIME64NS>(arrow_col.get(), i);
+      // Convert nanoseconds to milliseconds for DateTime64(3)
+      event_time_col->Append(ns_val / 1000000LL);
+    }
+    block.AppendColumn("event_time", event_time_col);
+  }
+
   // Insert the block into ClickHouse
   clickhouse_client_->Insert(plan_node_->table_name(), block);
 

src/carnot/funcs/metadata/metadata_ops.cc

@@ -127,6 +127,7 @@ void RegisterMetadataOpsOrDie(px::carnot::udf::Registry* registry) {
   registry->RegisterOrDie<UPIDToDeploymentIDUDF>("upid_to_deployment_id");
   registry->RegisterOrDie<UPIDToStringUDF>("upid_to_string");
   registry->RegisterOrDie<HostnameUDF>("_exec_hostname");
+  registry->RegisterOrDie<PEMHostnameUDF>("_pem_hostname");
   registry->RegisterOrDie<HostNumCPUsUDF>("_exec_host_num_cpus");
   registry->RegisterOrDie<VizierIDUDF>("vizier_id");
   registry->RegisterOrDie<VizierNameUDF>("vizier_name");