Add Spice.ai OSS (Cayenne, Parquet single, Parquet partitioned)

spiceai-cayenne/README.md

@@ -0,0 +1,25 @@
+# Spice.ai OSS (Cayenne)
+
+[Spice.ai OSS](https://github.com/spiceai/spiceai) is a portable, single-binary
+runtime built on Apache DataFusion that federates and accelerates SQL queries
+across databases, data warehouses, and data lakes. This entry benchmarks its
+native Cayenne acceleration engine: `./load` ingests `hits.parquet` into a
+disk-backed Cayenne table (`acceleration: {engine: cayenne, mode: file}`), and
+queries are served from that acceleration through the runtime's HTTP API.
+
+Notes:
+
+- `spicepod.yaml` takes the place of `create.sql`: it defines the dataset and
+  its acceleration. The dataset keeps the source parquet schema, where
+  `EventDate` is an integer (days since epoch); the queries referencing
+  `EventDate` wrap it as `to_timestamp("EventDate" * 86400)`, matching how
+  Spice's own benchmark suite runs ClickBench. Everything else in
+  `queries.sql` is identical to the `datafusion` entry's.
+- The SQL results cache (enabled by default in Spice) is disabled in
+  `spicepod.yaml` per the benchmark caching rules.
+- The acceleration persists across restarts and the runtime skips re-ingestion
+  when the on-disk data is current, so the true-cold-run restart cycle serves
+  disk-resident data like other durable systems.
+
+Run `./benchmark.sh` on a fresh Ubuntu VM (see `lib/benchmark-common.sh` for
+the flow), or use the repo's `run-benchmark.sh` automation.

spiceai-cayenne/benchmark.sh

@@ -0,0 +1,4 @@
+#!/bin/bash
+# Thin shim — actual flow is in lib/benchmark-common.sh.
+export BENCH_DOWNLOAD_SCRIPT="download-hits-parquet-single"
+exec ../lib/benchmark-common.sh

spiceai-cayenne/check

@@ -0,0 +1,13 @@
+#!/bin/bash
+set -e
+
+# The driver starts the system before the dataset is downloaded; until
+# hits.parquet exists the dataset cannot load (the runtime stays up and
+# retries), so gate on process liveness only. Afterwards gate on
+# /v1/ready, which returns 200 only once the accelerated dataset is
+# ready to serve queries.
+if [ -e hits.parquet ]; then
+    curl -fsS http://localhost:8090/v1/ready >/dev/null
+else
+    curl -fsS http://localhost:8090/health >/dev/null
+fi

spiceai-cayenne/data-size

@@ -0,0 +1,6 @@
+#!/bin/bash
+set -e
+
+# Cayenne file-mode acceleration data (segments + metastore), written by
+# the runtime under ./.spice.
+du -sb .spice | cut -f1

spiceai-cayenne/install

@@ -0,0 +1,18 @@
+#!/bin/bash
+set -e
+
+# install.spiceai.org ships the CLI only; `spice install` then downloads
+# the runtime binary (spiced) into ~/.spice/bin.
+if [ ! -x "$HOME/.spice/bin/spice" ]; then
+    curl https://install.spiceai.org | /bin/bash
+fi
+if [ ! -x "$HOME/.spice/bin/spiced" ]; then
+    "$HOME/.spice/bin/spice" install >/dev/null 2>&1
+fi
+
+# Symlink into /usr/local/bin so sibling scripts (check, load, query,
+# start) find them unconditionally.
+sudo ln -sf "$HOME/.spice/bin/spiced" /usr/local/bin/spiced
+sudo ln -sf "$HOME/.spice/bin/spice" /usr/local/bin/spice
+
+spiced --version

spiceai-cayenne/load

@@ -0,0 +1,21 @@
+#!/bin/bash
+set -e
+
+# Idempotent: drop any prior acceleration state and restart the runtime so
+# the Cayenne acceleration performs a full ingest of hits.parquet.
+./stop >/dev/null 2>&1 || true
+rm -rf .spice spiced.log
+./start
+
+# /v1/ready returns 200 once the initial refresh has completed and the
+# dataset is queryable from the acceleration.
+for _ in $(seq 1 7200); do
+    if curl -fsS http://localhost:8090/v1/ready >/dev/null 2>&1; then
+        exit 0
+    fi
+    sleep 1
+done
+
+echo "load: dataset did not become ready within 7200s" >&2
+tail -n 50 spiced.log >&2
+exit 1

spiceai-cayenne/make-json.sh

@@ -0,0 +1,59 @@
+#!/bin/bash
+# Converts the raw `result.csv` from `benchmark.sh` plus the `Load time:` /
+# `Data size:` lines in `log` into the final json format used by the
+# benchmark dashboard.
+#
+# usage: ./make-json.sh <machine>   # saves results/<YYYYMMDD>/<machine>.json
+set -e
+
+MACHINE=$1
+[ -n "$MACHINE" ] || { echo "usage: $0 <machine>" >&2; exit 1; }
+
+DATE=$(date -u +%Y-%m-%d)
+YYYYMMDD=${DATE//-/}
+mkdir -p "results/${YYYYMMDD}"
+
+python3 - "$MACHINE" "$DATE" > "results/${YYYYMMDD}/${MACHINE}.json" <<'PY'
+import csv, json, re, sys
+
+machine, date = sys.argv[1], sys.argv[2]
+
+runs = {}
+with open("result.csv") as f:
+    for query, _try, timing in csv.reader(f):
+        runs.setdefault(int(query), []).append(
+            None if timing == "null" else float(timing))
+
+load_time = data_size = None
+qps = err_ratio = None
+with open("log") as f:
+    for line in f:
+        if m := re.match(r"Load time: ([\d.]+)", line):
+            load_time = float(m.group(1))
+        elif m := re.match(r"Data size: (\d+)", line):
+            data_size = int(m.group(1))
+        elif m := re.match(r"Concurrent QPS: ([\d.]+)", line):
+            qps = float(m.group(1))
+        elif m := re.match(r"Concurrent error ratio: ([\d.]+)", line):
+            err_ratio = float(m.group(1))
+
+template = json.load(open("template.json"))
+result = {
+    "system": template["system"],
+    "date": date,
+    "machine": machine,
+    "cluster_size": 1,
+    "proprietary": template["proprietary"],
+    "hardware": template["hardware"],
+    "tuned": template["tuned"],
+    "tags": template["tags"],
+    "load_time": load_time,
+    "data_size": data_size,
+    "concurrent_qps": qps,
+    "concurrent_error_ratio": err_ratio,
+    "result": [runs[q] for q in sorted(runs)],
+}
+print(json.dumps(result, indent=4))
+PY
+
+echo "results/${YYYYMMDD}/${MACHINE}.json"

spiceai-cayenne/queries.sql

@@ -0,0 +1,43 @@
+SELECT COUNT(*) FROM hits;
+SELECT COUNT(*) FROM hits WHERE "AdvEngineID" <> 0;
+SELECT SUM("AdvEngineID"), COUNT(*), AVG("ResolutionWidth") FROM hits;
+SELECT AVG("UserID") FROM hits;
+SELECT COUNT(DISTINCT "UserID") FROM hits;
+SELECT COUNT(DISTINCT "SearchPhrase") FROM hits;
+SELECT MIN(to_timestamp("EventDate" * 86400)), MAX(to_timestamp("EventDate" * 86400)) FROM hits;
+SELECT "AdvEngineID", COUNT(*) FROM hits WHERE "AdvEngineID" <> 0 GROUP BY "AdvEngineID" ORDER BY COUNT(*) DESC;
+SELECT "RegionID", COUNT(DISTINCT "UserID") AS u FROM hits GROUP BY "RegionID" ORDER BY u DESC LIMIT 10;
+SELECT "RegionID", SUM("AdvEngineID"), COUNT(*) AS c, AVG("ResolutionWidth"), COUNT(DISTINCT "UserID") FROM hits GROUP BY "RegionID" ORDER BY c DESC LIMIT 10;
+SELECT "MobilePhoneModel", COUNT(DISTINCT "UserID") AS u FROM hits WHERE "MobilePhoneModel" <> '' GROUP BY "MobilePhoneModel" ORDER BY u DESC LIMIT 10;
+SELECT "MobilePhone", "MobilePhoneModel", COUNT(DISTINCT "UserID") AS u FROM hits WHERE "MobilePhoneModel" <> '' GROUP BY "MobilePhone", "MobilePhoneModel" ORDER BY u DESC LIMIT 10;
+SELECT "SearchPhrase", COUNT(*) AS c FROM hits WHERE "SearchPhrase" <> '' GROUP BY "SearchPhrase" ORDER BY c DESC LIMIT 10;
+SELECT "SearchPhrase", COUNT(DISTINCT "UserID") AS u FROM hits WHERE "SearchPhrase" <> '' GROUP BY "SearchPhrase" ORDER BY u DESC LIMIT 10;
+SELECT "SearchEngineID", "SearchPhrase", COUNT(*) AS c FROM hits WHERE "SearchPhrase" <> '' GROUP BY "SearchEngineID", "SearchPhrase" ORDER BY c DESC LIMIT 10;
+SELECT "UserID", COUNT(*) FROM hits GROUP BY "UserID" ORDER BY COUNT(*) DESC LIMIT 10;
+SELECT "UserID", "SearchPhrase", COUNT(*) FROM hits GROUP BY "UserID", "SearchPhrase" ORDER BY COUNT(*) DESC LIMIT 10;
+SELECT "UserID", "SearchPhrase", COUNT(*) FROM hits GROUP BY "UserID", "SearchPhrase" LIMIT 10;
+SELECT "UserID", extract(minute FROM to_timestamp_seconds("EventTime")) AS m, "SearchPhrase", COUNT(*) FROM hits GROUP BY "UserID", m, "SearchPhrase" ORDER BY COUNT(*) DESC LIMIT 10;
+SELECT "UserID" FROM hits WHERE "UserID" = 435090932899640449;
+SELECT COUNT(*) FROM hits WHERE "URL" LIKE '%google%';
+SELECT "SearchPhrase", MIN("URL"), COUNT(*) AS c FROM hits WHERE "URL" LIKE '%google%' AND "SearchPhrase" <> '' GROUP BY "SearchPhrase" ORDER BY c DESC LIMIT 10;
+SELECT "SearchPhrase", MIN("URL"), MIN("Title"), COUNT(*) AS c, COUNT(DISTINCT "UserID") FROM hits WHERE "Title" LIKE '%Google%' AND "URL" NOT LIKE '%.google.%' AND "SearchPhrase" <> '' GROUP BY "SearchPhrase" ORDER BY c DESC LIMIT 10;
+SELECT * FROM hits WHERE "URL" LIKE '%google%' ORDER BY "EventTime" LIMIT 10;
+SELECT "SearchPhrase" FROM hits WHERE "SearchPhrase" <> '' ORDER BY "EventTime" LIMIT 10;
+SELECT "SearchPhrase" FROM hits WHERE "SearchPhrase" <> '' ORDER BY "SearchPhrase" LIMIT 10;
+SELECT "SearchPhrase" FROM hits WHERE "SearchPhrase" <> '' ORDER BY "EventTime", "SearchPhrase" LIMIT 10;
+SELECT "CounterID", AVG(length("URL")) AS l, COUNT(*) AS c FROM hits WHERE "URL" <> '' GROUP BY "CounterID" HAVING COUNT(*) > 100000 ORDER BY l DESC LIMIT 25;
+SELECT REGEXP_REPLACE("Referer", '^https?://(?:www\.)?([^/]+)/.*$', '\1') AS k, AVG(length("Referer")) AS l, COUNT(*) AS c, MIN("Referer") FROM hits WHERE "Referer" <> '' GROUP BY k HAVING COUNT(*) > 100000 ORDER BY l DESC LIMIT 25;
+SELECT SUM("ResolutionWidth"), SUM("ResolutionWidth" + 1), SUM("ResolutionWidth" + 2), SUM("ResolutionWidth" + 3), SUM("ResolutionWidth" + 4), SUM("ResolutionWidth" + 5), SUM("ResolutionWidth" + 6), SUM("ResolutionWidth" + 7), SUM("ResolutionWidth" + 8), SUM("ResolutionWidth" + 9), SUM("ResolutionWidth" + 10), SUM("ResolutionWidth" + 11), SUM("ResolutionWidth" + 12), SUM("ResolutionWidth" + 13), SUM("ResolutionWidth" + 14), SUM("ResolutionWidth" + 15), SUM("ResolutionWidth" + 16), SUM("ResolutionWidth" + 17), SUM("ResolutionWidth" + 18), SUM("ResolutionWidth" + 19), SUM("ResolutionWidth" + 20), SUM("ResolutionWidth" + 21), SUM("ResolutionWidth" + 22), SUM("ResolutionWidth" + 23), SUM("ResolutionWidth" + 24), SUM("ResolutionWidth" + 25), SUM("ResolutionWidth" + 26), SUM("ResolutionWidth" + 27), SUM("ResolutionWidth" + 28), SUM("ResolutionWidth" + 29), SUM("ResolutionWidth" + 30), SUM("ResolutionWidth" + 31), SUM("ResolutionWidth" + 32), SUM("ResolutionWidth" + 33), SUM("ResolutionWidth" + 34), SUM("ResolutionWidth" + 35), SUM("ResolutionWidth" + 36), SUM("ResolutionWidth" + 37), SUM("ResolutionWidth" + 38), SUM("ResolutionWidth" + 39), SUM("ResolutionWidth" + 40), SUM("ResolutionWidth" + 41), SUM("ResolutionWidth" + 42), SUM("ResolutionWidth" + 43), SUM("ResolutionWidth" + 44), SUM("ResolutionWidth" + 45), SUM("ResolutionWidth" + 46), SUM("ResolutionWidth" + 47), SUM("ResolutionWidth" + 48), SUM("ResolutionWidth" + 49), SUM("ResolutionWidth" + 50), SUM("ResolutionWidth" + 51), SUM("ResolutionWidth" + 52), SUM("ResolutionWidth" + 53), SUM("ResolutionWidth" + 54), SUM("ResolutionWidth" + 55), SUM("ResolutionWidth" + 56), SUM("ResolutionWidth" + 57), SUM("ResolutionWidth" + 58), SUM("ResolutionWidth" + 59), SUM("ResolutionWidth" + 60), SUM("ResolutionWidth" + 61), SUM("ResolutionWidth" + 62), SUM("ResolutionWidth" + 63), SUM("ResolutionWidth" + 64), SUM("ResolutionWidth" + 65), SUM("ResolutionWidth" + 66), SUM("ResolutionWidth" + 67), SUM("ResolutionWidth" + 68), SUM("ResolutionWidth" + 69), SUM("ResolutionWidth" + 70), SUM("ResolutionWidth" + 71), SUM("ResolutionWidth" + 72), SUM("ResolutionWidth" + 73), SUM("ResolutionWidth" + 74), SUM("ResolutionWidth" + 75), SUM("ResolutionWidth" + 76), SUM("ResolutionWidth" + 77), SUM("ResolutionWidth" + 78), SUM("ResolutionWidth" + 79), SUM("ResolutionWidth" + 80), SUM("ResolutionWidth" + 81), SUM("ResolutionWidth" + 82), SUM("ResolutionWidth" + 83), SUM("ResolutionWidth" + 84), SUM("ResolutionWidth" + 85), SUM("ResolutionWidth" + 86), SUM("ResolutionWidth" + 87), SUM("ResolutionWidth" + 88), SUM("ResolutionWidth" + 89) FROM hits;
+SELECT "SearchEngineID", "ClientIP", COUNT(*) AS c, SUM("IsRefresh"), AVG("ResolutionWidth") FROM hits WHERE "SearchPhrase" <> '' GROUP BY "SearchEngineID", "ClientIP" ORDER BY c DESC LIMIT 10;
+SELECT "WatchID", "ClientIP", COUNT(*) AS c, SUM("IsRefresh"), AVG("ResolutionWidth") FROM hits WHERE "SearchPhrase" <> '' GROUP BY "WatchID", "ClientIP" ORDER BY c DESC LIMIT 10;
+SELECT "WatchID", "ClientIP", COUNT(*) AS c, SUM("IsRefresh"), AVG("ResolutionWidth") FROM hits GROUP BY "WatchID", "ClientIP" ORDER BY c DESC LIMIT 10;
+SELECT "URL", COUNT(*) AS c FROM hits GROUP BY "URL" ORDER BY c DESC LIMIT 10;
+SELECT 1, "URL", COUNT(*) AS c FROM hits GROUP BY 1, "URL" ORDER BY c DESC LIMIT 10;
+SELECT "ClientIP", "ClientIP" - 1, "ClientIP" - 2, "ClientIP" - 3, COUNT(*) AS c FROM hits GROUP BY "ClientIP", "ClientIP" - 1, "ClientIP" - 2, "ClientIP" - 3 ORDER BY c DESC LIMIT 10;
+SELECT "URL", COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND to_timestamp("EventDate" * 86400) >= '2013-07-01' AND to_timestamp("EventDate" * 86400) <= '2013-07-31' AND "DontCountHits" = 0 AND "IsRefresh" = 0 AND "URL" <> '' GROUP BY "URL" ORDER BY PageViews DESC LIMIT 10;
+SELECT "Title", COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND to_timestamp("EventDate" * 86400) >= '2013-07-01' AND to_timestamp("EventDate" * 86400) <= '2013-07-31' AND "DontCountHits" = 0 AND "IsRefresh" = 0 AND "Title" <> '' GROUP BY "Title" ORDER BY PageViews DESC LIMIT 10;
+SELECT "URL", COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND to_timestamp("EventDate" * 86400) >= '2013-07-01' AND to_timestamp("EventDate" * 86400) <= '2013-07-31' AND "IsRefresh" = 0 AND "IsLink" <> 0 AND "IsDownload" = 0 GROUP BY "URL" ORDER BY PageViews DESC LIMIT 10 OFFSET 1000;
+SELECT "TraficSourceID", "SearchEngineID", "AdvEngineID", CASE WHEN ("SearchEngineID" = 0 AND "AdvEngineID" = 0) THEN "Referer" ELSE '' END AS Src, "URL" AS Dst, COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND to_timestamp("EventDate" * 86400) >= '2013-07-01' AND to_timestamp("EventDate" * 86400) <= '2013-07-31' AND "IsRefresh" = 0 GROUP BY "TraficSourceID", "SearchEngineID", "AdvEngineID", Src, Dst ORDER BY PageViews DESC LIMIT 10 OFFSET 1000;
+SELECT "URLHash", to_timestamp("EventDate" * 86400), COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND to_timestamp("EventDate" * 86400) >= '2013-07-01' AND to_timestamp("EventDate" * 86400) <= '2013-07-31' AND "IsRefresh" = 0 AND "TraficSourceID" IN (-1, 6) AND "RefererHash" = 3594120000172545465 GROUP BY "URLHash", to_timestamp("EventDate" * 86400) ORDER BY PageViews DESC LIMIT 10 OFFSET 100;
+SELECT "WindowClientWidth", "WindowClientHeight", COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND to_timestamp("EventDate" * 86400) >= '2013-07-01' AND to_timestamp("EventDate" * 86400) <= '2013-07-31' AND "IsRefresh" = 0 AND "DontCountHits" = 0 AND "URLHash" = 2868770270353813622 GROUP BY "WindowClientWidth", "WindowClientHeight" ORDER BY PageViews DESC LIMIT 10 OFFSET 10000;
+SELECT DATE_TRUNC('minute', to_timestamp("EventTime")::timestamp) AS M, COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND to_timestamp("EventDate" * 86400) >= '2013-07-14' AND to_timestamp("EventDate" * 86400) <= '2013-07-15' AND "IsRefresh" = 0 AND "DontCountHits" = 0 GROUP BY DATE_TRUNC('minute', to_timestamp("EventTime")::timestamp) ORDER BY DATE_TRUNC('minute', M) LIMIT 10 OFFSET 1000;

spiceai-cayenne/query

@@ -0,0 +1,24 @@
+#!/bin/bash
+# Reads a SQL query from stdin, runs it via the Spice HTTP API.
+# Stdout: query result (JSON).
+# Stderr: query runtime in fractional seconds on the last line.
+# Exit non-zero on error.
+set -e
+
+resp=$(mktemp /tmp/spiceai-query.XXXXXX)
+trap 'rm -f "$resp"' EXIT
+
+metrics=$(curl -sS -o "$resp" -w '%{http_code} %{time_total}' \
+    -H 'Content-Type: text/plain' --data-binary @- \
+    'http://localhost:8090/v1/sql')
+code=${metrics% *}
+time_total=${metrics#* }
+
+if [ "$code" != "200" ]; then
+    cat "$resp" >&2
+    echo >&2
+    exit 1
+fi
+
+cat "$resp"
+printf '%s\n' "$time_total" >&2