Merge #135844

135844: vecbench: add vector benchmarking CLI r=drewkimball a=andy-kimball

Add a CLI that makes it easy to benchmark the quality and performance of vector indexing. The CLI downloads test datasets from a GCP bucket and then builds and searches the index. It outputs results in a spreadsheet-friendly format like this:
```
  unsplash-512-euclidean
  1000000 train vectors, 1000 test vectors, 512 dimensions, 16/128 min/max partitions, base beam size 8

  beam	recall	leaf	all	full	partns	qps
  1	22.10%	91	247	23.61	4.00	1357.12
  2	31.35%	182	339	27.65	5.00	1867.50
  4	47.86%	362	610	31.96	8.00	1783.30
  8	67.96%	727	1220	35.70	15.00	1729.00
  16	82.00%	1450	2302	40.41	27.00	1629.65
  32	90.70%	2894	4462	44.17	51.00	1301.63
  64	95.61%	5783	8772	47.30	99.00	791.74
  128	98.32%	11559	17374	49.60	195.00	535.10
  256	99.47%	23099	34391	50.83	387.00	298.24
  512	99.83%	46150	57517	51.28	644.00	189.69
```

Epic: CRDB-42943

Release note: None

Co-authored-by: Andrew Kimball <andyk@cockroachlabs.com>

.gitignore

@@ -14,7 +14,6 @@ artifacts
 /bin.*
 /lib
 /lib.*
-/tmp
 .buildinfo
 # cockroach-data, cockroach{,.race}-{darwin,linux,windows}-*
 /cockroach*
@@ -33,6 +32,8 @@ work-Fuzz*
 # Instrumentation artifacts.
 /instrument*
 .instrumentor_exclusions.tmp
+# Temp files.
+tmp/
 
 # Custom or private env vars (e.g. internal keys, access tokens, etc).
 customenv.mk

pkg/BUILD.bazel

@@ -1265,6 +1265,8 @@ GO_TARGETS = [
     "//pkg/cmd/urlcheck/lib/urlcheck:urlcheck",
     "//pkg/cmd/urlcheck:urlcheck",
     "//pkg/cmd/urlcheck:urlcheck_lib",
+    "//pkg/cmd/vecbench:vecbench",
+    "//pkg/cmd/vecbench:vecbench_lib",
     "//pkg/cmd/whoownsit:whoownsit",
     "//pkg/cmd/whoownsit:whoownsit_lib",
     "//pkg/cmd/workload:workload",

pkg/cmd/vecbench/BUILD.bazel

@@ -0,0 +1,25 @@
+load("@io_bazel_rules_go//go:def.bzl", "go_binary", "go_library")
+
+go_library(
+    name = "vecbench_lib",
+    srcs = ["main.go"],
+    importpath = "github.com/cockroachdb/cockroach/pkg/cmd/vecbench",
+    visibility = ["//visibility:private"],
+    deps = [
+        "//pkg/sql/vecindex",
+        "//pkg/sql/vecindex/quantize",
+        "//pkg/sql/vecindex/vecstore",
+        "//pkg/util/stop",
+        "//pkg/util/timeutil",
+        "//pkg/util/vector",
+        "@com_github_cockroachdb_errors//:errors",
+        "@com_github_cockroachdb_errors//oserror",
+        "@com_google_cloud_go_storage//:storage",
+    ],
+)
+
+go_binary(
+    name = "vecbench",
+    embed = [":vecbench_lib"],
+    visibility = ["//visibility:public"],
+)