On Thu, Mar 12, 2026 at 12:39 PM Xuneng Zhou <[email protected]> wrote:
>
> On Thu, Mar 12, 2026 at 11:42 AM Michael Paquier <[email protected]> wrote:
> >
> > On Thu, Mar 12, 2026 at 06:33:08AM +0900, Michael Paquier wrote:
> > > Thanks for doing that. On my side, I am going to look at the gin and
> > > hash vacuum paths first with more testing as these don't use a custom
> > > callback. I don't think that I am going to need a lot of convincing,
> > > but I'd rather produce some numbers myself because doing something.
> > > I'll tweak a mounting point with the delay trick, as well.
> >
> > While debug_io_direct has been helping a bit, the trick for the delay
> > to throttle the IO activity has helped much more with my runtime
> > numbers. I have mounted a separate partition with a delay of 5ms,
> > disabled checkums (this part did not make a real difference), and
> > evicted shared buffers for relation and indexes before the VACUUM.
> >
> > Then I got better numbers. Here is an extract:
> > - worker=3:
> > gin_vacuum (100k tuples) base= 1448.2ms patch= 572.5ms 2.53x
> > ( 60.5%) (reads=175→104, io_time=1382.70→506.64ms)
> > gin_vacuum (300k tuples) base= 3728.0ms patch= 1332.0ms 2.80x
> > ( 64.3%) (reads=486→293, io_time=3669.89→1266.27ms)
> > bloom_vacuum (100k tuples) base= 21826.8ms patch= 17220.3ms 1.27x
> > ( 21.1%) (reads=485→117, io_time=4773.33→270.56ms)
> > bloom_vacuum (300k tuples) base= 67054.0ms patch= 53164.7ms 1.26x
> > ( 20.7%) (reads=1431.5→327.5, io_time=13880.2→381.395ms)
> > - io_uring:
> > gin_vacuum (100k tuples) base= 1240.3ms patch= 360.5ms 3.44x
> > ( 70.9%) (reads=175→104, io_time=1175.35→299.75ms)
> > gin_vacuum (300k tuples) base= 2829.9ms patch= 642.0ms 4.41x
> > ( 77.3%) (reads=465.5→293, io_time=2768.46→579.04ms)
> > bloom_vacuum (100k tuples) base= 22121.7ms patch= 17532.3ms 1.26x
> > ( 20.7%) (reads=485→117, io_time=4850.46→285.28ms)
> > bloom_vacuum (300k tuples) base= 67058.0ms patch= 53118.0ms 1.26x
> > ( 20.8%) (reads=1431.5→327.5, io_time=13870.9→305.44ms)
> >
> > The higher the number of tuples, the better the performance for each
> > individual operation, but the tests take a much longer time (tens of
> > seconds vs tens of minutes). For GIN, the numbers can be quite good
> > once these reads are pushed. For bloom, the runtime is improved, and
> > the IO numbers are much better.
> >
>
> -- io_uring, medium size
>
> bloom_vacuum_medium base= 8355.2ms patch= 715.0ms 11.68x
> ( 91.4%) (reads=4732→1056, io_time=7699.47→86.52ms)
> pgstattuple_medium base= 4012.8ms patch= 213.7ms 18.78x
> ( 94.7%) (reads=2006→2006, io_time=4001.66→200.24ms)
> pgstatindex_medium base= 5490.6ms patch= 37.9ms 144.88x
> ( 99.3%) (reads=2745→173, io_time=5481.54→7.82ms)
> hash_vacuum_medium base= 34483.4ms patch= 2703.5ms 12.75x
> ( 92.2%) (reads=19166→3901, io_time=31948.33→308.05ms)
> wal_logging_medium base= 7778.6ms patch= 7814.5ms 1.00x
> ( -0.5%) (reads=2857→2845, io_time=11.84→11.45ms)
>
> -- worker, medium size
> bloom_vacuum_medium base= 8376.2ms patch= 747.7ms 11.20x
> ( 91.1%) (reads=4732→1056, io_time=7688.91→65.49ms)
> pgstattuple_medium base= 4012.7ms patch= 339.0ms 11.84x
> ( 91.6%) (reads=2006→2006, io_time=4002.23→49.99ms)
> pgstatindex_medium base= 5490.3ms patch= 38.3ms 143.23x
> ( 99.3%) (reads=2745→173, io_time=5480.60→16.24ms)
> hash_vacuum_medium base= 34638.4ms patch= 2940.2ms 11.78x
> ( 91.5%) (reads=19166→3901, io_time=31881.61→242.01ms)
> wal_logging_medium base= 7440.1ms patch= 7434.0ms 1.00x
> ( 0.1%) (reads=2861→2825, io_time=10.62→10.71ms)
>
Our io_time metric currently measures only read time and ignores write
I/O, which can be misleading. We now separate it into read_time and
write_time.
-- write-delay 2 ms
WORKROOT=/srv/pg_delayed SIZES=small REPS=3
./run_streaming_benchmark.sh --baseline --io-method worker
--io-workers 12 --test hash_vacuum --direct-io --read-delay 2
--write-delay 2
v6-0004-Streamify-hash-index-VACUUM-primary-bucket-page-r.patch
hash_vacuum_small base= 16652.8ms patch= 13493.2ms 1.23x
( 19.0%) (reads=2338→815, read_time=4136.19→884.79ms,
writes=6218→6206, write_time=12313.81→12289.58ms)
-- write-delay 0 ms
WORKROOT=/srv/pg_delayed SIZES=small REPS=3
./run_streaming_benchmark.sh --baseline --io-method worker
--io-workers 12 --test hash_vacuum --direct-io --read-delay 2
--write-delay 0
v6-0004-Streamify-hash-index-VACUUM-primary-bucket-page-r.patch
hash_vacuum_small base= 4310.2ms patch= 1146.7ms 3.76x
( 73.4%) (reads=2338→815, read_time=4002.24→833.47ms,
writes=6218→6206, write_time=186.69→140.96ms)
--
Best,
Xuneng
#!/usr/bin/env bash
set -euo pipefail
###############################################################################
# Streaming Read Patches Benchmark
#
# Usage: ./run_streaming_bench.sh [OPTIONS] <patch>
#
# Options:
# --clean Remove existing builds and start fresh
# --baseline Also build and test vanilla PostgreSQL for comparison
# --test TEST Run specific test (bloom_scan, bloom_vacuum, pgstattuple,
# pgstatindex, gin_vacuum, wal_logging, hash_vacuum, or "all")
# --io-method MODE I/O method: io_uring, worker, or sync (default: io_uring)
# --io-workers N Number of I/O workers for worker mode (default: 3)
# --io-concurrency N Max concurrent I/Os per process (default: 64)
# --direct-io Enable direct IO (debug_io_direct=data), bypasses OS page cache
# --read-delay MS Simulate read latency via dm_delay (requires pre-created device)
# --write-delay MS Simulate write latency via dm_delay (default: 0, requires --read-delay)
# --profile Enable perf profiling and flamegraph generation
#
# Environment:
# WORKROOT Base directory (default: $HOME/pg_bench)
# REPS Repetitions per test (default: 5)
# SIZES Table sizes to test (default: "large")
# FLAMEGRAPH_DIR Path to FlameGraph tools (default: $HOME/FlameGraph)
# DM_DELAY_DEV dm_delay device name for --read-delay (default: "delayed")
###############################################################################
log() { printf '\033[1;34m==>\033[0m %s\n' "$*"; }
die() { printf '\033[1;31mERROR:\033[0m %s\n' "$*" >&2; exit 1; }
# --- CLI parsing ---
CLEAN=0
BASELINE=0
DO_PROFILE=0
DIRECT_IO=0
IO_DELAY_MS=""
WRITE_DELAY_MS="0"
TEST="all"
IO_METHOD="${IO_METHOD:-io_uring}"
IO_WORKERS="${IO_WORKERS:-3}"
IO_MAX_CONCURRENCY="${IO_MAX_CONCURRENCY:-64}"
DM_DELAY_DEV="${DM_DELAY_DEV:-delayed}"
PATCH=""
while [[ $# -gt 0 ]]; do
case "$1" in
--clean) CLEAN=1 ;;
--baseline) BASELINE=1 ;;
--profile) DO_PROFILE=1 ;;
--direct-io) DIRECT_IO=1 ;;
--read-delay) IO_DELAY_MS="$2"; shift ;;
--write-delay) WRITE_DELAY_MS="$2"; shift ;;
--test) TEST="$2"; shift ;;
--io-method) IO_METHOD="$2"; shift ;;
--io-workers) IO_WORKERS="$2"; shift ;;
--io-concurrency) IO_MAX_CONCURRENCY="$2"; shift ;;
-h|--help) sed -n '3,27p' "$0" | sed 's/^# \?//'; exit 0 ;;
-*) die "Unknown option: $1" ;;
*) PATCH="$1" ;;
esac
shift
done
# Validate io_method
case "$IO_METHOD" in
io_uring|worker|sync) ;;
*) die "Invalid --io-method: $IO_METHOD (must be io_uring, worker, or sync)" ;;
esac
# Validate dm_delay device if --read-delay is used
if [[ -n "$IO_DELAY_MS" ]]; then
command -v dmsetup >/dev/null 2>&1 || die "--read-delay requires dmsetup (sudo apt install dmsetup)"
sudo dmsetup status "$DM_DELAY_DEV" >/dev/null 2>&1 \
|| die "dm_delay device '$DM_DELAY_DEV' not found. Create it first, e.g.:\n umount /srv && dmsetup create $DM_DELAY_DEV --table \"0 \$(blockdev --getsz /dev/DEVICE) delay /dev/DEVICE 0 $IO_DELAY_MS\" && mount /dev/mapper/$DM_DELAY_DEV /srv/"
fi
[[ -z "$PATCH" ]] && die "Usage: $0 [--clean] [--baseline] [--test TEST] <patch>"
[[ ! -f "$PATCH" ]] && die "Patch not found: $PATCH"
[[ "$PATCH" != /* ]] && PATCH="$PWD/$PATCH"
# --- Profiling validation ---
FLAMEGRAPH_DIR="${FLAMEGRAPH_DIR:-$HOME/FlameGraph}"
PERF_SUDO="${PERF_SUDO:-sudo}"
PERF_EVENT="${PERF_EVENT:-cycles}" # cycles = user+kernel; cycles:u = user-only
if [[ $DO_PROFILE -eq 1 ]]; then
command -v perf >/dev/null 2>&1 || die "Need perf (sudo apt install linux-tools-$(uname -r))"
[[ -x "$FLAMEGRAPH_DIR/stackcollapse-perf.pl" ]] || die "Missing $FLAMEGRAPH_DIR/stackcollapse-perf.pl (git clone https://github.com/brendangregg/FlameGraph)"
[[ -x "$FLAMEGRAPH_DIR/flamegraph.pl" ]] || die "Missing $FLAMEGRAPH_DIR/flamegraph.pl"
fi
# --- Configuration ---
WORKROOT="${WORKROOT:-$HOME/pg_bench}"
REPS="${REPS:-5}"
SIZES="${SIZES:-large}"
ROOT_BASE="$WORKROOT/vanilla"
PATCH_TAG=$(basename "$PATCH" .patch | tr -dc '[:alnum:]_-' | cut -c1-40)
ROOT_PATCH="$WORKROOT/$PATCH_TAG"
# --- Helpers ---
pg() { echo "$1/pg/bin/$2"; }
pick_port() {
for p in $(seq "${1:-5432}" 60000); do
lsof -iTCP:"$p" -sTCP:LISTEN >/dev/null 2>&1 || { echo "$p"; return; }
done
die "No free port found"
}
set_io_delay() {
local ms="$1"
[[ -z "$IO_DELAY_MS" ]] && return
local table size dev
table=$(sudo dmsetup table "$DM_DELAY_DEV")
size=$(echo "$table" | awk '{print $2}')
dev=$(echo "$table" | awk '{print $4}')
log "Setting dm_delay on $DM_DELAY_DEV to ${ms}ms read / ${WRITE_DELAY_MS}ms write"
sudo dmsetup suspend "$DM_DELAY_DEV"
sudo dmsetup reload "$DM_DELAY_DEV" --table "0 $size delay $dev 0 $ms $dev 0 $WRITE_DELAY_MS"
sudo dmsetup resume "$DM_DELAY_DEV"
}
# --- Build PostgreSQL ---
build_pg() {
local ROOT="$1" PATCH_FILE="${2:-}"
[[ $CLEAN -eq 1 ]] && rm -rf "$ROOT"
if [[ ! -x "$(pg "$ROOT" initdb)" ]]; then
log "Building PostgreSQL: $ROOT"
mkdir -p "$ROOT"
git clone --depth 1 https://github.com/postgres/postgres "$ROOT/src" 2>/dev/null
cd "$ROOT/src"
[[ -n "$PATCH_FILE" ]] && { log "Applying patch"; git apply "$PATCH_FILE"; }
./configure --prefix="$ROOT/pg" --with-liburing \
CFLAGS='-O2 -ggdb3 -fno-omit-frame-pointer' >/dev/null 2>&1
make -j"$(nproc)" install >/dev/null 2>&1
else
log "Reusing build: $ROOT"
cd "$ROOT/src"
fi
# Always install contribs (idempotent, catches reused builds missing new extensions)
make -C contrib/bloom install >/dev/null 2>&1
make -C contrib/pgstattuple install >/dev/null 2>&1
make -C contrib/pg_buffercache install >/dev/null 2>&1
make -C contrib/pg_prewarm install >/dev/null 2>&1
}
# --- Cluster management ---
init_cluster() {
local ROOT="$1" PORT="$2"
rm -rf "$ROOT/data"
"$(pg "$ROOT" initdb)" -D "$ROOT/data" --no-locale >/dev/null 2>&1
cat >> "$ROOT/data/postgresql.conf" <<EOF
port = $PORT
listen_addresses = '127.0.0.1'
shared_buffers = '32GB'
effective_io_concurrency = 200
io_method = $IO_METHOD
io_workers = $IO_WORKERS
io_max_concurrency = $IO_MAX_CONCURRENCY
track_io_timing = on
track_wal_io_timing = on
synchronous_commit = on
autovacuum = off
checkpoint_timeout = 1h
max_wal_size = 10GB
max_parallel_workers_per_gather = 0
EOF
[[ $DIRECT_IO -eq 1 ]] && echo "debug_io_direct = data" >> "$ROOT/data/postgresql.conf"
"$(pg "$ROOT" pg_ctl)" -D "$ROOT/data" -l "$ROOT/server.log" start -w >/dev/null
psql_run "$ROOT" "$PORT" -c "CREATE EXTENSION IF NOT EXISTS pg_buffercache;"
psql_run "$ROOT" "$PORT" -c "CREATE EXTENSION IF NOT EXISTS pg_prewarm;"
}
stop_cluster() {
local ROOT="$1"
"$(pg "$ROOT" pg_ctl)" -D "$ROOT/data" stop -m fast 2>/dev/null || true
}
drop_caches() {
local ROOT="$1" PORT="$2"
shift 2
local rels=("$@")
# Evict target relations from shared buffers (no PG restart needed)
for rel in "${rels[@]}"; do
psql_run "$ROOT" "$PORT" -c "SELECT pg_buffercache_evict_relation('${rel}'::regclass);" >/dev/null
done
# Drop OS page cache (skip with direct IO — no page cache involved)
if [[ $DIRECT_IO -eq 0 ]]; then
sync
echo 3 | sudo tee /proc/sys/vm/drop_caches >/dev/null 2>&1 || true
sleep 2
fi
}
psql_run() {
local ROOT="$1" PORT="$2"
shift 2
"$(pg "$ROOT" psql)" -h 127.0.0.1 -p "$PORT" -d postgres -v ON_ERROR_STOP=1 -Atq "$@"
}
# --- Timing ---
run_timed() {
local ROOT="$1" PORT="$2" SQL="$3"
local ms
# -X: ignore .psqlrc, -v ON_ERROR_STOP=1: fail on SQL errors
# Parse last Time: line, handle both "ms" and "s" units
ms=$("$(pg "$ROOT" psql)" -h 127.0.0.1 -p "$PORT" -d postgres -X -v ON_ERROR_STOP=1 -At \
-c '\timing on' -c "$SQL" 2>&1 | \
awk '
/Time:/ {
val=$2; unit=$3;
if (unit=="ms") ms=val;
else if (unit=="s") ms=val*1000;
}
END { if (ms=="") exit 1; printf "%.3f\n", ms; }
')
# Validate numeric output
[[ "$ms" =~ ^[0-9]+(\.[0-9]+)?$ ]] || { echo "ERROR: Non-numeric timing: $ms" >&2; return 1; }
echo "$ms"
}
# --- I/O Stats ---
# Run SQL and capture timing + I/O stats from pg_stat_io
# Resets stats before query, waits for flush, then reads absolute values
# Note: pg_stat_io has PGSTAT_MIN_INTERVAL=1000ms flush delay, so we wait 1.5s
# after the query to ensure stats are flushed to shared memory.
# Note: pg_stat_io counts I/O operations, not pages (with io_combine_limit=128kB,
# up to 16 pages per operation). This is expected behavior.
# Returns: ms,reads,read_time,writes,write_time
run_timed_with_io() {
local ROOT="$1" PORT="$2" SQL="$3"
local result
# Reset stats, run query, wait for flush, read absolute values
# - Filter by client backend and io worker (excludes bgwriter/checkpointer)
# - 1.5s delay allows stats to flush (PGSTAT_MIN_INTERVAL=1000ms)
result=$("$(pg "$ROOT" psql)" -h 127.0.0.1 -p "$PORT" -d postgres -X -v ON_ERROR_STOP=1 <<EOSQL
SELECT pg_stat_reset_shared('io');
\\timing on
$SQL
\\timing off
SELECT pg_sleep(1.5);
\\t on
SELECT
COALESCE(SUM(reads),0)::bigint,
COALESCE(SUM(read_time),0)::numeric(12,2),
COALESCE(SUM(writes),0)::bigint,
COALESCE(SUM(write_time),0)::numeric(12,2)
FROM pg_stat_io
WHERE object = 'relation' AND backend_type IN ('client backend', 'io worker');
EOSQL
2>&1)
# Parse timing (last Time: line)
local ms
ms=$(echo "$result" | awk '
/Time:/ {
val=$2; unit=$3;
if (unit=="ms") ms=val;
else if (unit=="s") ms=val*1000;
}
END { if (ms=="") exit 1; printf "%.3f\n", ms; }
')
# Parse I/O stats (last non-empty line with pipe separator: reads|read_time|writes|write_time)
local reads read_time writes write_time
local io_line
io_line=$(echo "$result" | grep '|' | tail -1)
reads=$(echo "$io_line" | cut -d'|' -f1 | tr -d ' ')
read_time=$(echo "$io_line" | cut -d'|' -f2 | tr -d ' ')
writes=$(echo "$io_line" | cut -d'|' -f3 | tr -d ' ')
write_time=$(echo "$io_line" | cut -d'|' -f4 | tr -d ' ')
# Default to 0 if not found
[[ "$reads" =~ ^-?[0-9]+$ ]] || reads=0
[[ "$read_time" =~ ^-?[0-9]+(\.[0-9]+)?$ ]] || read_time=0
[[ "$writes" =~ ^-?[0-9]+$ ]] || writes=0
[[ "$write_time" =~ ^-?[0-9]+(\.[0-9]+)?$ ]] || write_time=0
echo "$ms,$reads,$read_time,$writes,$write_time"
}
# --- Statistics ---
calc_median() {
awk -F, 'NR>1{a[++n]=$2}END{
if(n==0){print 0; exit}
for(i=1;i<=n;i++)for(j=i+1;j<=n;j++)if(a[i]>a[j]){t=a[i];a[i]=a[j];a[j]=t}
print (n%2)?a[int(n/2)+1]:(a[n/2]+a[n/2+1])/2
}' "$1"
}
calc_median_col() {
local file="$1" col="$2"
awk -F, -v col="$col" 'NR>1{a[++n]=$col}END{
if(n==0){print 0; exit}
for(i=1;i<=n;i++)for(j=i+1;j<=n;j++)if(a[i]>a[j]){t=a[i];a[i]=a[j];a[j]=t}
print (n%2)?a[int(n/2)+1]:(a[n/2]+a[n/2+1])/2
}' "$file"
}
calc_stats() {
local csv="$1"
awk -F, 'NR>1{a[++n]=$2;s+=$2}END{
if(n==0)exit
for(i=1;i<=n;i++)for(j=i+1;j<=n;j++)if(a[i]>a[j]){t=a[i];a[i]=a[j];a[j]=t}
med=(n%2)?a[int(n/2)+1]:(a[n/2]+a[n/2+1])/2
avg=s/n; for(i=1;i<=n;i++)ss+=(a[i]-avg)^2; sd=sqrt(ss/n)
printf "median=%.1fms mean=%.1f±%.1fms n=%d", med, avg, sd, n
}' "$csv"
}
# --- Profiling ---
# Run a SQL command under perf, attaching to the backend PID.
# Generates perf.data and flamegraph SVG.
# profile_sql ROOT PORT LABEL SQL
profile_sql() {
[[ $DO_PROFILE -ne 1 ]] && return
local ROOT="$1" PORT="$2" LABEL="$3" SQL="$4"
local PROF_DIR="$ROOT/profile"
mkdir -p "$PROF_DIR"
local PERF_DATA="$PROF_DIR/${LABEL}.perf.data"
local SVG="$PROF_DIR/${LABEL}.svg"
local psql_bin
psql_bin="$(pg "$ROOT" psql)"
# Use a unique application_name to find the backend PID
local APP="prof_${LABEL}_$$"
# Launch a psql session that will first identify itself, then run the SQL
# The pg_sleep() gives us time to find the backend PID and attach perf
PGAPPNAME="$APP" "$psql_bin" -h 127.0.0.1 -p "$PORT" -d postgres \
-X -v ON_ERROR_STOP=1 <<EOSQL >/dev/null 2>&1 &
SELECT pg_sleep(2);
$SQL
EOSQL
local QUERY_SHELL_PID=$!
# Find the backend PID via pg_stat_activity
local BACKEND_PID=""
for ((n=0; n<100; n++)); do
BACKEND_PID=$("$psql_bin" -h 127.0.0.1 -p "$PORT" -d postgres -Atq \
-c "SELECT pid FROM pg_stat_activity WHERE application_name='${APP}' ORDER BY backend_start DESC LIMIT 1;" 2>/dev/null)
[[ -n "$BACKEND_PID" && -d "/proc/$BACKEND_PID" ]] && break
sleep 0.05
done
if [[ -z "$BACKEND_PID" || ! -d "/proc/$BACKEND_PID" ]]; then
log "WARNING: Could not find backend PID for profiling, skipping"
wait "$QUERY_SHELL_PID" 2>/dev/null || true
return
fi
log "Profiling backend PID $BACKEND_PID → $PERF_DATA"
# Attach perf to the backend; we explicitly kill -INT it after the query finishes
$PERF_SUDO perf record -g --call-graph dwarf \
-p "$BACKEND_PID" -o "$PERF_DATA" \
--event="$PERF_EVENT" 2>/dev/null &
local PERF_PID=$!
sleep 0.1
# Verify perf actually started (permissions, valid PID, etc.)
if ! kill -0 "$PERF_PID" 2>/dev/null; then
log "WARNING: perf record failed to start (permissions/config?), skipping flamegraph"
wait "$QUERY_SHELL_PID" 2>/dev/null || true
return
fi
# Wait for the query to finish
wait "$QUERY_SHELL_PID" 2>/dev/null || true
# Give perf a moment to flush, then stop it
sleep 0.5
$PERF_SUDO kill -INT "$PERF_PID" 2>/dev/null || true; wait "$PERF_PID" 2>/dev/null || true
# Generate flamegraph
generate_flamegraph "$PERF_DATA" "$SVG" "$LABEL"
}
# Convert perf.data → flamegraph SVG
# generate_flamegraph PERF_DATA SVG_PATH TITLE
generate_flamegraph() {
local PERF_DATA="$1" SVG="$2" TITLE="$3"
[[ -f "$PERF_DATA" ]] || return
local FOLDED="${PERF_DATA%.perf.data}.folded"
if $PERF_SUDO perf script -i "$PERF_DATA" 2>/dev/null \
| "$FLAMEGRAPH_DIR/stackcollapse-perf.pl" > "$FOLDED" 2>/dev/null \
&& [[ -s "$FOLDED" ]]; then
"$FLAMEGRAPH_DIR/flamegraph.pl" --title "$TITLE" --countname samples \
"$FOLDED" > "$SVG" 2>/dev/null
log "Flamegraph: $SVG"
rm -f "$FOLDED"
else
log "WARNING: Failed to generate flamegraph for $TITLE"
rm -f "$FOLDED"
fi
}
# --- Benchmark runner ---
# benchmark ROOT PORT NAME SQL RELATION [RELATION...]
benchmark() {
local ROOT="$1" PORT="$2" NAME="$3" SQL="$4"
shift 4
local rels=("$@")
local OUT="$ROOT/results/${NAME}.csv"
mkdir -p "$ROOT/results"
echo "run,ms,reads,read_time_ms,writes,write_time_ms" > "$OUT"
for ((i=1; i<=REPS; i++)); do
drop_caches "$ROOT" "$PORT" "${rels[@]}"
local result ms reads read_time writes write_time
result=$(run_timed_with_io "$ROOT" "$PORT" "$SQL")
IFS=',' read -r ms reads read_time writes write_time <<<"$result"
echo "$i,$ms,$reads,$read_time,$writes,$write_time" >> "$OUT"
log "$NAME [$i/$REPS]: ${ms}ms (reads=$reads, read_time=${read_time}ms, writes=$writes, write_time=${write_time}ms)"
done
}
# --- Data setup functions ---
setup_bloom() {
local ROOT="$1" PORT="$2" SIZE="$3"
local NROWS
case "$SIZE" in
small) NROWS=100000 ;;
medium) NROWS=1000000 ;;
large) NROWS=10000000 ;;
esac
log "Creating Bloom test data ($SIZE: $NROWS rows)"
psql_run "$ROOT" "$PORT" <<SQL
CREATE EXTENSION IF NOT EXISTS bloom;
DROP TABLE IF EXISTS bloom_test;
CREATE TABLE bloom_test (id INT, data TEXT, val1 INT, val2 INT);
INSERT INTO bloom_test SELECT i, 'data_'||i, i%1000, i%100 FROM generate_series(1,$NROWS) i;
CREATE INDEX bloom_idx ON bloom_test USING bloom (val1, val2);
VACUUM ANALYZE bloom_test;
CHECKPOINT;
SQL
}
setup_pgstattuple() {
local ROOT="$1" PORT="$2" SIZE="$3"
local NROWS
case "$SIZE" in
small) NROWS=100000 ;;
medium) NROWS=1000000 ;;
large) NROWS=10000000 ;;
esac
log "Creating pgstattuple test data ($SIZE: $NROWS rows)"
psql_run "$ROOT" "$PORT" <<SQL
CREATE EXTENSION IF NOT EXISTS pgstattuple;
DROP TABLE IF EXISTS heap_test;
CREATE TABLE heap_test (id SERIAL PRIMARY KEY, data TEXT);
INSERT INTO heap_test (data) SELECT repeat('x',100) FROM generate_series(1,$NROWS);
VACUUM ANALYZE heap_test;
CHECKPOINT;
SQL
}
setup_pgstatindex() {
local ROOT="$1" PORT="$2" SIZE="$3"
local NROWS
case "$SIZE" in
small) NROWS=100000 ;;
medium) NROWS=1000000 ;;
large) NROWS=10000000 ;;
esac
log "Creating pgstatindex test data ($SIZE: $NROWS rows)"
psql_run "$ROOT" "$PORT" <<SQL
CREATE EXTENSION IF NOT EXISTS pgstattuple;
DROP TABLE IF EXISTS idx_test;
CREATE TABLE idx_test (id SERIAL PRIMARY KEY, data TEXT);
INSERT INTO idx_test (data) SELECT 'data_row_' || i || '_' || repeat('x',50) FROM generate_series(1,$NROWS) i;
VACUUM ANALYZE idx_test;
CHECKPOINT;
SQL
}
setup_gin() {
local ROOT="$1" PORT="$2" SIZE="$3"
local NROWS
case "$SIZE" in
small) NROWS=100000 ;;
medium) NROWS=1000000 ;;
large) NROWS=5000000 ;;
esac
log "Creating GIN test data ($SIZE: $NROWS rows)"
psql_run "$ROOT" "$PORT" <<SQL
DROP TABLE IF EXISTS gin_test;
-- No PRIMARY KEY: isolate GIN index vacuum from btree overhead
CREATE TABLE gin_test (id INT, tags TEXT[]);
INSERT INTO gin_test (id, tags)
SELECT i, ARRAY(SELECT 'tag_'||(random()*100)::int FROM generate_series(1,5))
FROM generate_series(1,$NROWS) i;
CREATE INDEX gin_idx ON gin_test USING gin (tags);
VACUUM ANALYZE gin_test;
CHECKPOINT;
SQL
}
setup_hash() {
local ROOT="$1" PORT="$2" SIZE="$3"
local NROWS
case "$SIZE" in
small) NROWS=500000 ;;
medium) NROWS=5000000 ;;
large) NROWS=20000000 ;;
esac
log "Creating Hash test data ($SIZE: $NROWS unique values)"
psql_run "$ROOT" "$PORT" <<SQL
DROP TABLE IF EXISTS hash_test;
-- No PRIMARY KEY: isolate hash index vacuum from btree overhead
CREATE TABLE hash_test (id INT, data TEXT);
INSERT INTO hash_test SELECT i, 'x' FROM generate_series(1,$NROWS) i;
CREATE INDEX hash_idx ON hash_test USING hash (id);
VACUUM ANALYZE hash_test;
CHECKPOINT;
SQL
}
setup_wal() {
local ROOT="$1" PORT="$2" SIZE="$3"
local NROWS
case "$SIZE" in
small) NROWS=1000000 ;;
medium) NROWS=5000000 ;;
large) NROWS=20000000 ;;
esac
log "Creating table for GIN index build / log_newpage_range test ($SIZE: $NROWS rows)"
psql_run "$ROOT" "$PORT" <<SQL
DROP TABLE IF EXISTS wal_test;
-- Table with tsvector column for GIN indexing (full-text search)
-- GIN index builds always call log_newpage_range() at the end of
-- ginbuild() (gininsert.c) to WAL-log all index pages.
CREATE TABLE wal_test (id INT, doc TEXT, doc_tsv TSVECTOR);
INSERT INTO wal_test
SELECT i,
'word' || (random()*10000)::int || ' term' || (random()*10000)::int
|| ' token' || (random()*5000)::int || ' phrase' || (random()*8000)::int,
to_tsvector('simple',
'word' || (random()*10000)::int || ' term' || (random()*10000)::int
|| ' token' || (random()*5000)::int || ' phrase' || (random()*8000)::int)
FROM generate_series(1,$NROWS) i;
VACUUM ANALYZE wal_test;
CHECKPOINT;
SQL
}
# --- Test functions ---
test_bloom_scan() {
local ROOT="$1" PORT="$2" LABEL="$3" SIZE="$4"
setup_bloom "$ROOT" "$PORT" "$SIZE"
benchmark "$ROOT" "$PORT" "${LABEL}_bloom_scan_${SIZE}" \
"SET enable_seqscan=off; SELECT COUNT(*) FROM bloom_test WHERE val1=42 AND val2=7;" \
bloom_test bloom_idx
# Profile after benchmark reps: shared_buffers memory already faulted in,
# so page-fault noise is gone; drop_caches ensures cold IO for the profile.
if [[ $DO_PROFILE -eq 1 ]]; then
drop_caches "$ROOT" "$PORT" bloom_test bloom_idx
profile_sql "$ROOT" "$PORT" "${LABEL}_bloom_scan_${SIZE}" \
"SET enable_seqscan=off; SELECT COUNT(*) FROM bloom_test WHERE val1=42 AND val2=7;"
fi
}
test_bloom_vacuum() {
local ROOT="$1" PORT="$2" LABEL="$3" SIZE="$4"
local OUT="$ROOT/results/${LABEL}_bloom_vacuum_${SIZE}.csv"
mkdir -p "$ROOT/results"
echo "run,ms,reads,read_time_ms,writes,write_time_ms" > "$OUT"
for ((i=1; i<=REPS; i++)); do
# Fresh table each run for consistent state
setup_bloom "$ROOT" "$PORT" "$SIZE"
# Create 10% dead tuples
psql_run "$ROOT" "$PORT" -c "DELETE FROM bloom_test WHERE id % 10 = 0;"
drop_caches "$ROOT" "$PORT" bloom_test bloom_idx
local result ms reads read_time writes write_time
result=$(run_timed_with_io "$ROOT" "$PORT" "VACUUM bloom_test;")
IFS=',' read -r ms reads read_time writes write_time <<<"$result"
echo "$i,$ms,$reads,$read_time,$writes,$write_time" >> "$OUT"
log "${LABEL}_bloom_vacuum_${SIZE} [$i/$REPS]: ${ms}ms (reads=$reads, read_time=${read_time}ms, writes=$writes, write_time=${write_time}ms)"
done
if [[ $DO_PROFILE -eq 1 ]]; then
setup_bloom "$ROOT" "$PORT" "$SIZE"
psql_run "$ROOT" "$PORT" -c "DELETE FROM bloom_test WHERE id % 10 = 0;"
drop_caches "$ROOT" "$PORT" bloom_test bloom_idx
profile_sql "$ROOT" "$PORT" "${LABEL}_bloom_vacuum_${SIZE}" "VACUUM bloom_test;"
fi
}
test_pgstattuple() {
local ROOT="$1" PORT="$2" LABEL="$3" SIZE="$4"
local OUT="$ROOT/results/${LABEL}_pgstattuple_${SIZE}.csv"
mkdir -p "$ROOT/results"
echo "run,ms,reads,read_time_ms,writes,write_time_ms" > "$OUT"
# Setup once — rolled-back DELETE keeps layout identical across all reps
setup_pgstattuple "$ROOT" "$PORT" "$SIZE"
# Rolled-back DELETE clears the all-visible bit in the Visibility Map so
# pgstattuple_approx must actually read those pages (it skips all-visible pages).
# Using ROLLBACK keeps the physical layout identical across all reps (no TOAST
# out-of-page updates, no dirty pages to flush from shared_buffers).
psql_run "$ROOT" "$PORT" -c "BEGIN; DELETE FROM heap_test WHERE id % 500 = 0; ROLLBACK;"
# Warmup pass: The rolled-back DELETE left every touched tuple with an xmax
# pointing to the aborted transaction but no hint bits set. On the first
# pgstattuple_approx call, HeapTupleSatisfiesVacuum → HeapTupleSatisfiesVacuumHorizon
# must resolve each such xmax: TransactionIdIsInProgress (ProcArray scan) then
# TransactionIdDidCommit (CLOG lookup) — only then can it call SetHintBits to
# stamp HEAP_XMAX_INVALID and MarkBufferDirtyHint. Without this warmup, rep 1
# pays ~1100ms extra CPU for those CLOG/ProcArray lookups. Subsequent reps hit
# the early-exit at "if (t_infomask & HEAP_XMAX_INVALID) return HEAPTUPLE_LIVE"
# and skip the expensive path entirely.
# After this pass, the dirtied hint-bit pages are flushed to disk via
# drop_caches, so all reps start from the same on-disk state.
psql_run "$ROOT" "$PORT" -c "SELECT * FROM pgstattuple_approx('heap_test');" >/dev/null
for ((i=1; i<=REPS; i++)); do
drop_caches "$ROOT" "$PORT" heap_test heap_test_pkey
local result ms reads read_time writes write_time
result=$(run_timed_with_io "$ROOT" "$PORT" "SELECT * FROM pgstattuple_approx('heap_test');")
IFS=',' read -r ms reads read_time writes write_time <<<"$result"
echo "$i,$ms,$reads,$read_time,$writes,$write_time" >> "$OUT"
log "${LABEL}_pgstattuple_${SIZE} [$i/$REPS]: ${ms}ms (reads=$reads, read_time=${read_time}ms, writes=$writes, write_time=${write_time}ms)"
done
if [[ $DO_PROFILE -eq 1 ]]; then
psql_run "$ROOT" "$PORT" -c "BEGIN; DELETE FROM heap_test WHERE id % 500 = 0; ROLLBACK;"
drop_caches "$ROOT" "$PORT" heap_test heap_test_pkey
profile_sql "$ROOT" "$PORT" "${LABEL}_pgstattuple_${SIZE}" \
"SELECT * FROM pgstattuple_approx('heap_test');"
fi
}
test_pgstatindex() {
local ROOT="$1" PORT="$2" LABEL="$3" SIZE="$4"
setup_pgstatindex "$ROOT" "$PORT" "$SIZE"
benchmark "$ROOT" "$PORT" "${LABEL}_pgstatindex_${SIZE}" \
"SELECT * FROM pgstatindex('idx_test_pkey');" \
idx_test idx_test_pkey
if [[ $DO_PROFILE -eq 1 ]]; then
drop_caches "$ROOT" "$PORT" idx_test idx_test_pkey
profile_sql "$ROOT" "$PORT" "${LABEL}_pgstatindex_${SIZE}" \
"SELECT * FROM pgstatindex('idx_test_pkey');"
fi
}
test_gin_vacuum() {
local ROOT="$1" PORT="$2" LABEL="$3" SIZE="$4"
local OUT="$ROOT/results/${LABEL}_gin_vacuum_${SIZE}.csv"
mkdir -p "$ROOT/results"
echo "run,ms,reads,read_time_ms,writes,write_time_ms" > "$OUT"
for ((i=1; i<=REPS; i++)); do
# Fresh table each run for consistent state
setup_gin "$ROOT" "$PORT" "$SIZE"
drop_caches "$ROOT" "$PORT" gin_test gin_idx
local result ms reads read_time writes write_time
# VACUUM ANALYZE forces ginvacuumcleanup() to run and scan all pages
result=$(run_timed_with_io "$ROOT" "$PORT" "VACUUM ANALYZE gin_test;")
IFS=',' read -r ms reads read_time writes write_time <<<"$result"
echo "$i,$ms,$reads,$read_time,$writes,$write_time" >> "$OUT"
log "${LABEL}_gin_vacuum_${SIZE} [$i/$REPS]: ${ms}ms (reads=$reads, read_time=${read_time}ms, writes=$writes, write_time=${write_time}ms)"
done
if [[ $DO_PROFILE -eq 1 ]]; then
setup_gin "$ROOT" "$PORT" "$SIZE"
drop_caches "$ROOT" "$PORT" gin_test gin_idx
profile_sql "$ROOT" "$PORT" "${LABEL}_gin_vacuum_${SIZE}" "VACUUM ANALYZE gin_test;"
fi
}
test_hash_vacuum() {
local ROOT="$1" PORT="$2" LABEL="$3" SIZE="$4"
local OUT="$ROOT/results/${LABEL}_hash_vacuum_${SIZE}.csv"
mkdir -p "$ROOT/results"
echo "run,ms,reads,read_time_ms,writes,write_time_ms" > "$OUT"
for ((i=1; i<=REPS; i++)); do
# Fresh table each run for consistent state
setup_hash "$ROOT" "$PORT" "$SIZE"
# Create 10% dead tuples
psql_run "$ROOT" "$PORT" -c "DELETE FROM hash_test WHERE id % 10 = 0;"
drop_caches "$ROOT" "$PORT" hash_test hash_idx
local result ms reads read_time writes write_time
result=$(run_timed_with_io "$ROOT" "$PORT" "VACUUM hash_test;")
IFS=',' read -r ms reads read_time writes write_time <<<"$result"
echo "$i,$ms,$reads,$read_time,$writes,$write_time" >> "$OUT"
log "${LABEL}_hash_vacuum_${SIZE} [$i/$REPS]: ${ms}ms (reads=$reads, read_time=${read_time}ms, writes=$writes, write_time=${write_time}ms)"
done
if [[ $DO_PROFILE -eq 1 ]]; then
setup_hash "$ROOT" "$PORT" "$SIZE"
psql_run "$ROOT" "$PORT" -c "DELETE FROM hash_test WHERE id % 10 = 0;"
drop_caches "$ROOT" "$PORT" hash_test hash_idx
profile_sql "$ROOT" "$PORT" "${LABEL}_hash_vacuum_${SIZE}" "VACUUM hash_test;"
fi
}
test_wal_logging() {
local ROOT="$1" PORT="$2" LABEL="$3" SIZE="$4"
local OUT="$ROOT/results/${LABEL}_wal_logging_${SIZE}.csv"
mkdir -p "$ROOT/results"
echo "run,ms,reads,read_time_ms,writes,write_time_ms" > "$OUT"
# Build table once - only rebuild index each rep
setup_wal "$ROOT" "$PORT" "$SIZE"
local WAL_SQL="CREATE INDEX wal_test_gin_idx ON wal_test USING gin (doc_tsv);"
for ((i=1; i<=REPS; i++)); do
# Drop index from previous iteration
psql_run "$ROOT" "$PORT" -c "DROP INDEX IF EXISTS wal_test_gin_idx;"
# Drop OS caches - source table pages are COLD on disk
drop_caches "$ROOT" "$PORT" wal_test
# CREATE INDEX on GIN (tsvector_ops):
# - GIN always uses the same build path: ginbuild() populates the
# index in memory, flushes to disk, then calls log_newpage_range()
# to read ALL index pages and write them to WAL (gininsert.c:785-790)
local result ms reads read_time writes write_time
result=$(run_timed_with_io "$ROOT" "$PORT" "$WAL_SQL")
IFS=',' read -r ms reads read_time writes write_time <<<"$result"
echo "$i,$ms,$reads,$read_time,$writes,$write_time" >> "$OUT"
log "${LABEL}_wal_logging_${SIZE} [$i/$REPS]: ${ms}ms (reads=$reads, read_time=${read_time}ms, writes=$writes, write_time=${write_time}ms)"
done
if [[ $DO_PROFILE -eq 1 ]]; then
psql_run "$ROOT" "$PORT" -c "DROP INDEX IF EXISTS wal_test_gin_idx;"
drop_caches "$ROOT" "$PORT" wal_test
profile_sql "$ROOT" "$PORT" "${LABEL}_wal_logging_${SIZE}" "$WAL_SQL"
fi
}
# --- Run tests for a build ---
warmup_catalog() {
local ROOT="$1" PORT="$2"
# Explicitly prewarm catalog tables and their indexes into shared_buffers
# so rep 1 doesn't pay disk-read cost for catalog pages.
# pg_buffercache_evict_relation only evicts the test relation, not catalogs,
# so these stay warm across all reps.
psql_run "$ROOT" "$PORT" <<SQL >/dev/null
SELECT pg_prewarm('pg_class', 'buffer');
SELECT pg_prewarm('pg_attribute', 'buffer');
SELECT pg_prewarm('pg_namespace', 'buffer');
SELECT pg_prewarm('pg_proc', 'buffer');
SELECT pg_prewarm('pg_type', 'buffer');
SQL
}
run_tests() {
local ROOT="$1" LABEL="$2"
local PORT
PORT=$(pick_port)
log "[$LABEL] Starting cluster on port $PORT"
init_cluster "$ROOT" "$PORT"
warmup_catalog "$ROOT" "$PORT"
set_io_delay "$IO_DELAY_MS"
trap "stop_cluster '$ROOT'" EXIT
for SIZE in $SIZES; do
case "$TEST" in
bloom_scan) test_bloom_scan "$ROOT" "$PORT" "$LABEL" "$SIZE" ;;
bloom_vacuum) test_bloom_vacuum "$ROOT" "$PORT" "$LABEL" "$SIZE" ;;
pgstattuple) test_pgstattuple "$ROOT" "$PORT" "$LABEL" "$SIZE" ;;
pgstatindex) test_pgstatindex "$ROOT" "$PORT" "$LABEL" "$SIZE" ;;
gin_vacuum) test_gin_vacuum "$ROOT" "$PORT" "$LABEL" "$SIZE" ;;
hash_vacuum) test_hash_vacuum "$ROOT" "$PORT" "$LABEL" "$SIZE" ;;
wal_logging) test_wal_logging "$ROOT" "$PORT" "$LABEL" "$SIZE" ;;
all)
test_bloom_vacuum "$ROOT" "$PORT" "$LABEL" "$SIZE"
test_pgstattuple "$ROOT" "$PORT" "$LABEL" "$SIZE"
test_pgstatindex "$ROOT" "$PORT" "$LABEL" "$SIZE"
test_hash_vacuum "$ROOT" "$PORT" "$LABEL" "$SIZE"
test_wal_logging "$ROOT" "$PORT" "$LABEL" "$SIZE"
;;
*) die "Unknown test: $TEST" ;;
esac
done
stop_cluster "$ROOT"
trap - EXIT
}
# --- Compare results ---
compare_results() {
local base_csv="$1" patch_csv="$2" label="$3"
[[ ! -f "$base_csv" || ! -f "$patch_csv" ]] && return
local base_med patch_med
base_med=$(calc_median "$base_csv")
patch_med=$(calc_median "$patch_csv")
# Guard against empty or zero values to prevent division by zero
[[ -z "$base_med" || "$base_med" == "0" ]] && base_med="0.001"
[[ -z "$patch_med" || "$patch_med" == "0" ]] && patch_med="0.001"
local speedup pct
speedup=$(awk "BEGIN { printf \"%.2f\", $base_med / $patch_med }")
pct=$(awk "BEGIN { printf \"%.1f\", ($base_med - $patch_med) / $base_med * 100 }")
local io_info=""
if head -1 "$base_csv" | grep -q "reads"; then
# Standard test: columns are run,ms,reads,read_time_ms,writes,write_time_ms
local base_reads patch_reads base_rtime patch_rtime base_writes patch_writes base_wtime patch_wtime
base_reads=$(calc_median_col "$base_csv" 3)
patch_reads=$(calc_median_col "$patch_csv" 3)
base_rtime=$(calc_median_col "$base_csv" 4)
patch_rtime=$(calc_median_col "$patch_csv" 4)
base_writes=$(calc_median_col "$base_csv" 5)
patch_writes=$(calc_median_col "$patch_csv" 5)
base_wtime=$(calc_median_col "$base_csv" 6)
patch_wtime=$(calc_median_col "$patch_csv" 6)
# Default to 0 if empty
[[ -z "$base_reads" ]] && base_reads=0
[[ -z "$patch_reads" ]] && patch_reads=0
[[ -z "$base_rtime" ]] && base_rtime=0
[[ -z "$patch_rtime" ]] && patch_rtime=0
[[ -z "$base_writes" ]] && base_writes=0
[[ -z "$patch_writes" ]] && patch_writes=0
[[ -z "$base_wtime" ]] && base_wtime=0
[[ -z "$patch_wtime" ]] && patch_wtime=0
io_info=" (reads=${base_reads}→${patch_reads}, read_time=${base_rtime}→${patch_rtime}ms, writes=${base_writes}→${patch_writes}, write_time=${base_wtime}→${patch_wtime}ms)"
fi
printf "%-26s base=%8.1fms patch=%8.1fms %5.2fx (%5.1f%%)%s\n" \
"$label" "$base_med" "$patch_med" "$speedup" "$pct" "$io_info"
}
print_summary() {
echo ""
echo "═══════════════════════════════════════════════════════════════════════"
echo " STREAMING READ BENCHMARK RESULTS "
echo "═══════════════════════════════════════════════════════════════════════"
echo ""
if [[ $BASELINE -eq 1 ]]; then
printf "%-26s %-17s %-17s %-7s %-7s %s\n" "TEST" "BASELINE" "PATCHED" "SPEEDUP" "CHANGE" "I/O TIME"
echo "─────────────────────────────────────────────────────────────────────────────────────────────────"
for SIZE in $SIZES; do
for test_name in bloom_scan bloom_vacuum pgstattuple pgstatindex gin_vacuum hash_vacuum wal_logging; do
[[ "$TEST" != "all" && "$TEST" != "$test_name" ]] && continue
compare_results \
"$ROOT_BASE/results/base_${test_name}_${SIZE}.csv" \
"$ROOT_PATCH/results/patched_${test_name}_${SIZE}.csv" \
"${test_name}_${SIZE}"
done
done
else
echo "Results (patched only):"
echo ""
for f in "$ROOT_PATCH/results/"*.csv; do
[[ -f "$f" ]] || continue
printf "%-40s %s\n" "$(basename "$f" .csv):" "$(calc_stats "$f")"
done
fi
echo ""
echo "═══════════════════════════════════════════════════════════════════════"
echo "CSV files: $ROOT_PATCH/results/"
[[ $BASELINE -eq 1 ]] && echo "Baseline: $ROOT_BASE/results/"
# List generated flamegraphs
if [[ $DO_PROFILE -eq 1 ]]; then
local svgs=()
for dir in "$ROOT_BASE/profile" "$ROOT_PATCH/profile"; do
[[ -d "$dir" ]] || continue
for svg in "$dir"/*.svg; do
[[ -f "$svg" ]] && svgs+=("$svg")
done
done
if [[ ${#svgs[@]} -gt 0 ]]; then
echo ""
echo "Flamegraphs:"
for svg in "${svgs[@]}"; do echo " $svg"; done
fi
fi
echo "═══════════════════════════════════════════════════════════════════════"
}
# --- Main ---
main() {
log "Streaming Read Benchmark"
log "Patch: $PATCH ($PATCH_TAG)"
log "Tests: $TEST"
log "Sizes: $SIZES"
log "Reps: $REPS"
log "I/O: $IO_METHOD (workers=$IO_WORKERS, concurrency=$IO_MAX_CONCURRENCY)"
[[ $DIRECT_IO -eq 1 ]] && log "Direct IO: enabled (debug_io_direct=data)"
[[ -n "$IO_DELAY_MS" ]] && log "I/O delay: ${IO_DELAY_MS}ms read / ${WRITE_DELAY_MS}ms write via dm_delay ($DM_DELAY_DEV)"
[[ $DO_PROFILE -eq 1 ]] && log "Profile: enabled (flamegraphs → <root>/profile/)"
# Build
if [[ $BASELINE -eq 1 ]]; then
build_pg "$ROOT_BASE" ""
fi
build_pg "$ROOT_PATCH" "$PATCH"
# Run tests
if [[ $BASELINE -eq 1 ]]; then
log "Running baseline tests"
run_tests "$ROOT_BASE" "base"
fi
log "Running patched tests"
run_tests "$ROOT_PATCH" "patched"
# Summary
print_summary
}
main
