writeonce/docs/examples/db-bench/main.wo

use fs
use time

-- db-bench — iteration 22's load generator. Every measured mode prints
-- one machine-parsable line per operation class:
--
--   <op> <count> <ops/sec> <p50us> <p99us>
--
-- Timing is per-operation via time.ticks (CLOCK_MONOTONIC µs);
-- percentiles come from a 1µs-bucket histogram clamped at HIST_CLAMP —
-- exact to the microsecond below the clamp, and the clamp bucket keeps
-- the tail honest (a p99 AT the clamp means "clamp or worse").
-- The wal mode prints a running `acked <n>` line after every insert
-- RETURNS (the return IS the ack): the crash battery kills this mode
-- mid-run and verify-acked proves every acknowledged row survived.

-- ---- deterministic helpers ----

fn lcg(seed: Int) -> Int {
  let x = seed * 1103515245 + 12345;
  if x < 0 {
    x = 0 - x;
  }
  return x;
}

fn item_v(i: Int) -> Int {
  return (i * 37) % 1000;
}

-- ---- the histogram (percentiles without a sort) ----

fn hist_add(mut h: map<Int, Int>, us: Int) {
  let b = us;
  if b < 0 {
    b = 0;
  }
  if b > 20000 {
    b = 20000;
  }
  if has(h, b) {
    set(h, b, get(h, b) + 1);
  } else {
    set(h, b, 1);
  }
}

fn hist_pct(h: map<Int, Int>, total: Int, pct: Int) -> Int {
  let target = total * pct / 100;
  if target < 1 {
    target = 1;
  }
  let seen = 0;
  let b = 0;
  while b <= 20000 {
    if has(h, b) {
      seen = seen + get(h, b);
      if seen >= target {
        return b;
      }
    }
    b = b + 1;
  }
  return 20000;
}

fn report(op: Text, n: Int, total_us: Int, h: map<Int, Int>) {
  let us = total_us;
  if us < 1 {
    us = 1;
  }
  let rate = n * 1000000 / us;
  print("${op} ${n} ${rate} ${hist_pct(h, n, 50)} ${hist_pct(h, n, 99)}");
}

-- ---- modes ----

-- seed N: N children, one parent per 100, k = i % (N/10) (10 rows per
-- key), v deterministic. Meta rows record the expectations verify reads.
fn seed(n: Int) -> Int {
  let h: map<Int, Int> = {};
  let kmod = n / 10;
  if kmod < 1 {
    kmod = 1;
  }
  -- bucket-major: one parent, then its 100 children, using a single ref
  -- local. (A hand-built `multi Bucket` of insert results SEGVs on drop —
  -- the compiler classifies the elements OWNED while table refs are
  -- scalar ids; recorded as a standing finding, not this iteration's fix.
  -- Query-built multis are runtime-typed and safe.)
  let vsum = 0;
  let t0 = time.ticks();
  let i = 1;
  let b = 0;
  while i <= n {
    let bref = insert Bucket { tag: "b${b}" };
    b = b + 1;
    let j = 0;
    while j < 100 and i <= n {
      let o0 = time.ticks();
      insert Item { k: i % kmod, v: item_v(i), bucket: bref };
      hist_add(h, time.ticks() - o0);
      vsum = vsum + item_v(i);
      i = i + 1;
      j = j + 1;
    }
  }
  let t1 = time.ticks();
  insert Meta { tag: "count", val: n };
  insert Meta { tag: "vsum", val: vsum };
  insert Meta { tag: "kmod", val: kmod };
  report("seed", n, t1 - t0, h);
  return 0;
}

fn meta_val(tag: Text) -> Int {
  let ms = from m in Meta where m.tag == tag take 1 select m;
  if len(ms) == 0 {
    return -1;
  }
  return ms[0].val;
}

-- read N: indexed take-1 point lookups (the point-read this surface
-- offers), keys spread by LCG over the seeded key range.
fn read_mode(n: Int) -> Int {
  let kmod = meta_val("kmod");
  if kmod < 1 {
    print_err("read: seed first");
    return 1;
  }
  let h: map<Int, Int> = {};
  let sink = 0;
  let s = 42;
  let t0 = time.ticks();
  let i = 0;
  while i < n {
    s = lcg(s);
    let key = s % kmod;
    let o0 = time.ticks();
    let xs = from x in Item where x.k == key take 1 select x;
    if len(xs) > 0 {
      sink = sink + xs[0].v;
    }
    hist_add(h, time.ticks() - o0);
    i = i + 1;
  }
  let t1 = time.ticks();
  report("read", n, t1 - t0, h);
  if sink < 0 {
    print("impossible ${sink}");
  }
  return 0;
}

-- query N: full equality probes on the k index (≈10 rows per key),
-- each materialized and counted.
fn query_mode(n: Int) -> Int {
  let kmod = meta_val("kmod");
  if kmod < 1 {
    print_err("query: seed first");
    return 1;
  }
  let h: map<Int, Int> = {};
  let rows = 0;
  let s = 7;
  let t0 = time.ticks();
  let i = 0;
  while i < n {
    s = lcg(s);
    let key = s % kmod;
    let o0 = time.ticks();
    for x in from x in Item where x.k == key select x {
      rows = rows + 1;
    }
    hist_add(h, time.ticks() - o0);
    i = i + 1;
  }
  let t1 = time.ticks();
  report("query", n, t1 - t0, h);
  print("query rows ${rows}");
  return 0;
}

-- write N: alternating inserts (disjoint k range 2e6+) and updates
-- through a query result. Corrupts vsum by design — the durability legs
-- run on their own fresh store.
fn write_mode(n: Int) -> Int {
  let kmod = meta_val("kmod");
  if kmod < 1 {
    print_err("write: seed first");
    return 1;
  }
  let bs = from b in Bucket where b.tag == "b0" take 1 select b;
  if len(bs) == 0 {
    print_err("write: no buckets");
    return 1;
  }
  let h: map<Int, Int> = {};
  let s = 99;
  let t0 = time.ticks();
  let i = 0;
  while i < n {
    let o0 = time.ticks();
    if i % 2 == 0 {
      insert Item { k: 2000000 + i, v: item_v(i), bucket: bs[0] };
    } else {
      s = lcg(s);
      let key = s % kmod;
      let xs = from x in Item where x.k == key take 1 select x;
      if len(xs) > 0 {
        xs[0].v = xs[0].v + 1;
      }
    }
    hist_add(h, time.ticks() - o0);
    i = i + 1;
  }
  let t1 = time.ticks();
  report("write", n, t1 - t0, h);
  return 0;
}

-- wal N: the crash battery's vehicle — insert-only, disjoint k range
-- (1e6+), `acked <i>` printed AFTER each insert returns (the return is
-- the ack: RAM applied, record staged, ONE commit done).
fn wal_mode(n: Int) -> Int {
  let bs = from b in Bucket where b.tag == "b0" take 1 select b;
  if len(bs) == 0 {
    push(bs, insert Bucket { tag: "b0" });
  }
  let i = 1;
  while i <= n {
    insert Item { k: 1000000 + i, v: item_v(i), bucket: bs[0] };
    print("acked ${i}");
    i = i + 1;
  }
  return 0;
}

-- verify: the store against its own Meta expectations — count, checksum,
-- one unique-index probe. Exit 3 on any mismatch.
fn verify() -> Int {
  let want_n = meta_val("count");
  let want_sum = meta_val("vsum");
  if want_n < 0 or want_sum < 0 {
    print_err("verify: no meta (seed first)");
    return 3;
  }
  let got_n = 0;
  let got_sum = 0;
  for x in from x in Item select x {
    if x.k < 1000000 {
      got_n = got_n + 1;
      got_sum = got_sum + x.v;
    }
  }
  if got_n != want_n or got_sum != want_sum {
    print_err("verify: count ${got_n}/${want_n} sum ${got_sum}/${want_sum}");
    return 3;
  }
  let bs = from b in Bucket where b.tag == "b0" take 1 select b;
  if len(bs) == 0 {
    print_err("verify: unique probe b0 missing");
    return 3;
  }
  print("verify ok ${got_n} rows sum ${got_sum}");
  return 0;
}

-- verify-acked M: after a kill -9 mid-wal — rows 1..M (k = 1e6+i) must
-- exist with the right v; rows beyond M are allowed (acked after the
-- last print landed). Exit 3 on any missing/wrong row.
fn verify_acked(m: Int) -> Int {
  let i = 1;
  while i <= m {
    let key = 1000000 + i;
    let xs = from x in Item where x.k == key take 1 select x;
    if len(xs) == 0 {
      print_err("verify-acked: row ${i} missing");
      return 3;
    }
    if xs[0].v != item_v(i) {
      print_err("verify-acked: row ${i} v ${xs[0].v} != ${item_v(i)}");
      return 3;
    }
    i = i + 1;
  }
  print("verify-acked ok ${m} rows");
  return 0;
}

-- ---- the concurrent modes (mix, msgrate) ----

fn hist_dump(h: map<Int, Int>, kind: Int) {
  let b = 0;
  while b <= 20000 {
    if has(h, b) {
      insert Hist { kind: kind, b: b, c: get(h, b) };
    }
    b = b + 1;
  }
}

-- One mixer = one actor: 90/10 read/write over the seeded store. On a
-- worker shard every statement below rides the stage-3 DB RPC — the
-- code must not know or care (transparency is the point). Done signal:
-- a Meta row main polls for (the coordination idiom this side of 31).
class Mixer {
  id: Int
  fn receive(msg: MixJob) {
    let hr: map<Int, Int> = {};
    let hw: map<Int, Int> = {};
    let s = msg.seed;
    let sink = 0;
    let i = 0;
    while i < msg.ops {
      s = lcg(s);
      let key = s % msg.kmod;
      let o0 = time.ticks();
      if i % 10 == 9 {
        let xs = from x in Item where x.k == key take 1 select x;
        if len(xs) > 0 {
          xs[0].v = xs[0].v + 1;
        }
        hist_add(hw, time.ticks() - o0);
      } else {
        let xs = from x in Item where x.k == key take 1 select x;
        if len(xs) > 0 {
          sink = sink + xs[0].v;
        }
        hist_add(hr, time.ticks() - o0);
      }
      i = i + 1;
    }
    hist_dump(hr, 0);
    hist_dump(hw, 1);
    insert Meta { tag: "mixdone${self.id}", val: sink };
  }
}

-- databasev2 4 part A: every op a durable write, C at once.
--
-- Why this leg exists. `mix` writes on one op in ten with C=4, so at most a
-- handful of writes are ever in flight and group commit has almost nothing to
-- batch: measured mean batch 1.01 over 3112 barriers, peak 3. That is a
-- property of the WORKLOAD, not of the mechanism, and without a write-
-- concurrent leg the iteration's payoff cannot be evaluated either way.
--
-- Updates rather than inserts: comparable to what `mixwrite` measures, and the
-- row count stays flat so a long run does not turn into a growth test.
-- Histogram kind 2, because a replayed store still holds the seeding run's
-- kind-0/1 Hist rows and merging those would report someone else's latencies.
class WJob {
  ops:  Int
  seed: Int
  kmod: Int
}

class WMixer {
  id: Int
  fn receive(msg: WJob) {
    let hw: map<Int, Int> = {};
    let s = msg.seed;
    let i = 0;
    while i < msg.ops {
      s = lcg(s);
      let key = s % msg.kmod;
      let o0 = time.ticks();
      for r in from x in Item where x.k == key take 1 select x {
        r.v = r.v + 1;
      }
      hist_add(hw, time.ticks() - o0);
      i = i + 1;
    }
    hist_dump(hw, 2);
    insert Meta { tag: "wmixdone${self.id}", val: msg.ops };
  }
}

fn wmix_mode(total: Int, c: Int) -> Int {
  let kmod = meta_val("kmod");
  if kmod < 1 {
    print_err("wmix: seed first");
    return 1;
  }
  let per = total / c;
  if per < 1 {
    per = 1;
  }
  let wall0 = time.ticks();
  let i = 0;
  while i < c {
    let a: actor WJob = spawn WMixer { id: i };
    send(a, WJob { ops: per, seed: 4242 + i * 7919, kmod: kmod });
    i = i + 1;
  }
  let done = 0;
  while done < c {
    time.sleep(20);
    done = 0;
    i = 0;
    while i < c {
      if meta_val("wmixdone${i}") >= 0 {
        done = done + 1;
      }
      i = i + 1;
    }
  }
  let wall = time.ticks() - wall0;
  let hw: map<Int, Int> = {};
  let nw = 0;
  for x in from x in Hist select x {
    if x.kind == 2 {
      if has(hw, x.b) {
        set(hw, x.b, get(hw, x.b) + x.c);
      } else {
        set(hw, x.b, x.c);
      }
      nw = nw + x.c;
    }
  }
  report("wmix", nw, wall, hw);
  return 0;
}

fn mix_mode(total: Int, c: Int) -> Int {
  let kmod = meta_val("kmod");
  if kmod < 1 {
    print_err("mix: seed first");
    return 1;
  }
  let per = total / c;
  if per < 1 {
    per = 1;
  }
  let wall0 = time.ticks();
  let i = 0;
  while i < c {
    let a: actor MixJob = spawn Mixer { id: i };
    send(a, MixJob { ops: per, seed: 1000 + i * 7919, kmod: kmod });
    i = i + 1;
  }
  -- poll until every mixer's done row exists
  let done = 0;
  while done < c {
    time.sleep(20);
    done = 0;
    i = 0;
    while i < c {
      if meta_val("mixdone${i}") >= 0 {
        done = done + 1;
      }
      i = i + 1;
    }
  }
  let wall = time.ticks() - wall0;
  -- merge the dumped histograms; wall time is shared by both classes
  let hr: map<Int, Int> = {};
  let hw: map<Int, Int> = {};
  let nr = 0;
  let nw = 0;
  for x in from x in Hist select x {
    if x.kind == 0 {
      if has(hr, x.b) {
        set(hr, x.b, get(hr, x.b) + x.c);
      } else {
        set(hr, x.b, x.c);
      }
      nr = nr + x.c;
    } else {
      if has(hw, x.b) {
        set(hw, x.b, get(hw, x.b) + x.c);
      } else {
        set(hw, x.b, x.c);
      }
      nw = nw + x.c;
    }
  }
  report("mixread", nr, wall, hr);
  report("mixwrite", nw, wall, hw);
  return 0;
}

-- msgrate: one-way flood — main sends N messages at a sink actor; the
-- sink counts and writes the done row at N. Spawn TWO sinks and flood
-- the second: round-robin placement puts it off the primary whenever
-- more than one shard exists, so the multi-shard number prices the
-- mutex inbox (stage-2 deviation 4's number); single-shard prices the
-- same-heap path.
class Sink {
  got: Int
  fn receive(msg: Flood) {
    self.got = self.got + 1;
    if self.got == msg.n {
      insert Meta { tag: "flooddone", val: self.got };
    }
  }
}

fn msgrate_mode(n: Int) -> Int {
  let first: actor Flood = spawn Sink { got: 0 };
  let a: actor Flood = spawn Sink { got: 0 };
  if first == a {
    print_err("msgrate: impossible");
  }
  let t0 = time.ticks();
  let i = 0;
  while i < n {
    send(a, Flood { n: n });
    i = i + 1;
  }
  while meta_val("flooddone") < 0 {
    time.sleep(5);
  }
  let us = time.ticks() - t0;
  if us < 1 {
    us = 1;
  }
  print("msgrate ${n} ${n * 1000000 / us}");
  return 0;
}

-- all N: the throughput campaign in ONE process — without WO_DATA the
-- store is RAM and dies with the process, so seed and the measured
-- modes must share a run; under WO_DATA the same mode prices the
-- durable flavor. Restart/crash legs use the separate modes.
fn all_mode(n: Int) -> Int {
  let rc = seed(n);
  if rc != 0 {
    return rc;
  }
  rc = read_mode(n / 2);
  if rc != 0 {
    return rc;
  }
  rc = query_mode(n / 10);
  if rc != 0 {
    return rc;
  }
  rc = write_mode(n / 2);
  if rc != 0 {
    return rc;
  }
  -- mix at N/10: every point lookup is O(table) today (the probe walks
  -- all slabs — a headline finding, not a bug to hide), so a read-heavy
  -- mix over a seeded store is quadratic in N. The campaign driver
  -- chooses absolute sizes; this keeps `all` finishing in minutes.
  return mix_mode(n / 10, 4);
}

fn usage() -> Int {
  print_err("usage: db-bench <mode>");
  print_err("  all N | seed N | read N | query N | write N | wal N");
  print_err("  mix N C | wmix N C | msgrate N | growth N int|text | growth-verify");
  print_err("  randread N R | replayseed N M | boot");
  print_err("  verify | verify-acked M");
  return 2;
}

-- databasev2 1: the process's own resident size, in KiB. Read here rather
-- than sampled by the driver because the driver polls /proc every 250 ms and
-- would miss the value AT a decile boundary; per-row footprint is the headline
-- number of this iteration and deserves an exact reading, not a nearby one.
-- Absence is nil by stdlib convention, so a kernel without VmRSS reports 0
-- and the driver treats the leg as unavailable rather than as zero growth.
fn self_rss_kb() -> Int {
  let st = try fs.read_all("/proc/self/status", 16384) catch (e) "";
  let i = index_of(st, "VmRSS:");
  if i < 0 {
    return 0;
  }
  let rest = substr(st, i + 6, 24);
  let n = 0;
  let j = 0;
  while j < len(rest) {
    let c = byte_at(rest, j);
    if c >= 48 and c <= 57 {
      n = n * 10 + (c - 48);
    } else {
      if n > 0 {
        return n;
      }
    }
    j = j + 1;
  }
  return n;
}

-- databasev2 1: growth N SHAPE — insert N rows of one reference shape,
-- sampling read latency as the table grows so the driver can plot the CURVE
-- rather than two endpoints. Reports one metric line per decile so the point
-- at which p99 leaves its baseline is a MEASURED sample, not an estimate.
--
-- SHAPE is "int" (Item: two Ints plus a ref, all inline slot words) or "text"
-- (Wide: three Text columns, each a separate db_text allocation on top of the
-- slab slot). Per-row footprint differs by an order of magnitude between them,
-- which is exactly why the driver reports the two separately and never a single
-- "bytes per row".
--
-- The memory CAP is the driver's job (systemd-run --user --scope), not this
-- program's: the sample just grows and reports, so the same binary serves the
-- swap-off and swap-on legs unchanged.
-- after the process is OOM-killed mid-insert, the durable prefix must be
-- intact: rows 1..M all present with the right v and no holes. M is whatever
-- survived -- the claim under test is the SHAPE of the survivor, not its size,
-- because a SIGKILL can land between any two inserts.
-- databasev2 1: randread N R -- fill N rows, then read R of them by key in a
-- Weyl-sequence order that spreads across the WHOLE range. Under a cap smaller
-- than the table most of those reads must fault a page back in.
--
-- This is the leg the swap measurement was MISSING. `growth` inserts, and
-- inserting is append-mostly: cold pages are written once and never re-read, so
-- swap cost it ~1% (148s vs 150s uncapped). Random reads over an oversized
-- table are the opposite access pattern -- and they are exactly what
-- databasev2 2's `resident: keys` creates, since it reads rows back from a log
-- larger than RAM. No RNG in the language and none needed: i*2654435761 mod n
-- is a Weyl sequence, deterministic and spread, so the two legs read the SAME
-- key order and only residency differs.
-- databasev2 1, for iteration 3: the replay "before".
--
-- `boot` does NOTHING. That is the point: with WO_DATA set the runtime replays
-- the whole WAL before main runs, so the process's wall time IS the replay cost
-- plus a fixed startup. Any mode that touches rows would mix its own work into
-- the number.
fn boot_mode() -> Int {
  print("booted");
  return 0;
}

-- Build a store with N live rows and N+M total WAL records: M updates on top of
-- N inserts. The live dataset is IDENTICAL for any M -- only the history grows.
-- That is iteration 3's whole case: with no checkpoint, boot replays HISTORY,
-- not data, so a long-lived row that has been updated a thousand times costs a
-- thousand records at every boot forever.
fn replayseed_mode(n: Int, m: Int) -> Int {
  let bref = insert Bucket { tag: "replay" };
  let i = 1;
  while i <= n {
    insert Item { k: i, v: item_v(i), bucket: bref };
    i = i + 1;
  }
  let j = 0;
  while j < m {
    let key = 1 + (j * 2654435761) % n;
    for r in from x in Item where x.k == key take 1 select x {
      r.v = r.v + 1;
    }
    j = j + 1;
  }
  print("replayseeded ${n} ${m}");
  return 0;
}

-- databasev2 2 task 7: the residency A/B, one mode per table so the two runs
-- differ ONLY in the annotation. Same fill, same Weyl key order, same read
-- count as randread_mode above — the comparison is against that leg's own
-- 273x swap figure, measured on the same box under the same cap.
-- The WIDE half of the residency A/B. Same structure as kread_all/kread_keys
-- but with Text columns, which is the only shape where dropping a payload
-- frees anything: an Int's value is its inline slot word, a Text's is a
-- separate allocation.
-- databasev2 2 task 7, the GB-scale leg. Same A/B as wread_*, but each row
-- carries ~2 KB of Text so a realistic data volume is reachable in a few
-- hundred thousand inserts rather than millions — the insert path is
-- fsync-bound at roughly 2 000 rows/s, so row COUNT is the expensive axis and
-- row SIZE is nearly free.
--
-- This is the shape the mode actually claims: data far larger than the cap,
-- with only the id map, the indexes and the (never-released) slabs resident.
fn heavy_pad() -> Text {
  let p = "0123456789abcdef0123456789abcdef";
  let out = "";
  let i = 0;
  while i < 20 { out = out .. p; i = i + 1; }
  return out;
}

fn hread_all(n: Int, r: Int) -> Int {
  let pad = heavy_pad();
  let i = 1;
  while i <= n {
    insert WideA { k: i, a: "a${i}${pad}", b: "b${i}${pad}", note: "n${i}${pad}" };
    i = i + 1;
  }
  print("hreadfilled ${n} ${self_rss_kb()}");
  let h: map<Int, Int> = {};
  let hits = 0;
  let t0 = time.ticks();
  let j = 0;
  while j < r {
    let key = 1 + (j * 2654435761) % n;
    let o0 = time.ticks();
    for row in from x in WideA where x.k == key take 1 select x {
      if len(row.a) > 0 { hits = hits + 1; }
    }
    hist_add(h, time.ticks() - o0);
    j = j + 1;
  }
  let el = time.ticks() - t0;
  report("hreadall", r, el, h);
  print("hreadallrss ${self_rss_kb()} ${hits}");
  return 0;
}

fn hread_keys(n: Int, r: Int) -> Int {
  let pad = heavy_pad();
  let i = 1;
  while i <= n {
    insert WideK { k: i, a: "a${i}${pad}", b: "b${i}${pad}", note: "n${i}${pad}" };
    i = i + 1;
  }
  print("hreadfilled ${n} ${self_rss_kb()}");
  let h: map<Int, Int> = {};
  let hits = 0;
  let t0 = time.ticks();
  let j = 0;
  while j < r {
    let key = 1 + (j * 2654435761) % n;
    let o0 = time.ticks();
    for row in from x in WideK where x.k == key take 1 select x {
      if len(row.a) > 0 { hits = hits + 1; }
    }
    hist_add(h, time.ticks() - o0);
    j = j + 1;
  }
  let el = time.ticks() - t0;
  report("hreadkeys", r, el, h);
  print("hreadkeysrss ${self_rss_kb()} ${hits}");
  return 0;
}

fn wread_all(n: Int, r: Int) -> Int {
  let pad = "0123456789abcdef0123456789abcdef";
  let i = 1;
  while i <= n {
    insert WideA { k: i, a: "a${i}${pad}", b: "b${i}${pad}", note: "n${i}${pad}${pad}" };
    i = i + 1;
  }
  print("wreadfilled ${n} ${self_rss_kb()}");
  let h: map<Int, Int> = {};
  let hits = 0;
  let t0 = time.ticks();
  let j = 0;
  while j < r {
    let key = 1 + (j * 2654435761) % n;
    let o0 = time.ticks();
    for row in from x in WideA where x.k == key take 1 select x {
      if len(row.a) > 0 { hits = hits + 1; }
    }
    hist_add(h, time.ticks() - o0);
    j = j + 1;
  }
  let el = time.ticks() - t0;
  report("wreadall", r, el, h);
  print("wreadallrss ${self_rss_kb()} ${hits}");
  return 0;
}

fn wread_keys(n: Int, r: Int) -> Int {
  let pad = "0123456789abcdef0123456789abcdef";
  let i = 1;
  while i <= n {
    insert WideK { k: i, a: "a${i}${pad}", b: "b${i}${pad}", note: "n${i}${pad}${pad}" };
    i = i + 1;
  }
  print("wreadfilled ${n} ${self_rss_kb()}");
  let h: map<Int, Int> = {};
  let hits = 0;
  let t0 = time.ticks();
  let j = 0;
  while j < r {
    let key = 1 + (j * 2654435761) % n;
    let o0 = time.ticks();
    for row in from x in WideK where x.k == key take 1 select x {
      if len(row.a) > 0 { hits = hits + 1; }
    }
    hist_add(h, time.ticks() - o0);
    j = j + 1;
  }
  let el = time.ticks() - t0;
  report("wreadkeys", r, el, h);
  print("wreadkeysrss ${self_rss_kb()} ${hits}");
  return 0;
}

fn kread_all(n: Int, r: Int) -> Int {
  let i = 1;
  while i <= n {
    insert RowA { k: i, v: item_v(i) };
    i = i + 1;
  }
  print("kreadfilled ${n} ${self_rss_kb()}");
  let h: map<Int, Int> = {};
  let hits = 0;
  let t0 = time.ticks();
  let j = 0;
  while j < r {
    let key = 1 + (j * 2654435761) % n;
    let o0 = time.ticks();
    for row in from x in RowA where x.k == key take 1 select x {
      if row.v == item_v(key) { hits = hits + 1; }
    }
    hist_add(h, time.ticks() - o0);
    j = j + 1;
  }
  let el = time.ticks() - t0;
  report("kreadall", r, el, h);
  print("kreadallrss ${self_rss_kb()} ${hits}");
  return 0;
}

fn kread_keys(n: Int, r: Int) -> Int {
  let i = 1;
  while i <= n {
    insert RowK { k: i, v: item_v(i) };
    i = i + 1;
  }
  print("kreadfilled ${n} ${self_rss_kb()}");
  let h: map<Int, Int> = {};
  let hits = 0;
  let t0 = time.ticks();
  let j = 0;
  while j < r {
    let key = 1 + (j * 2654435761) % n;
    let o0 = time.ticks();
    for row in from x in RowK where x.k == key take 1 select x {
      if row.v == item_v(key) { hits = hits + 1; }
    }
    hist_add(h, time.ticks() - o0);
    j = j + 1;
  }
  let el = time.ticks() - t0;
  report("kreadkeys", r, el, h);
  print("kreadkeysrss ${self_rss_kb()} ${hits}");
  return 0;
}

fn randread_mode(n: Int, r: Int) -> Int {
  let bref = insert Bucket { tag: "randread" };
  let i = 1;
  while i <= n {
    insert Item { k: i, v: item_v(i), bucket: bref };
    i = i + 1;
  }
  print("randreadfilled ${n} ${self_rss_kb()}");
  let h: map<Int, Int> = {};
  let hits = 0;
  let t0 = time.ticks();
  let j = 0;
  while j < r {
    let key = 1 + (j * 2654435761) % n;
    let o0 = time.ticks();
    for row in from x in Item where x.k == key take 1 select x {
      if row.v == item_v(key) {
        hits = hits + 1;
      }
    }
    hist_add(h, time.ticks() - o0);
    j = j + 1;
  }
  let el = time.ticks() - t0;
  report("randread", r, el, h);
  -- hits proves the reads RESOLVED; a collapse measured over misses is noise
  print("randreadrss ${self_rss_kb()} ${hits}");
  return 0;
}

fn growth_verify() -> Int {
  let seen: map<Int, Int> = {};
  let maxk = 0;
  for r in from x in Item select x {
    set(seen, r.k, r.v);
    if r.k > maxk {
      maxk = r.k;
    }
  }
  let i = 1;
  while i <= maxk {
    if has(seen, i) == false {
      print_err("growth-verify: hole at ${i} below max ${maxk}");
      return 3;
    }
    if get(seen, i) != item_v(i) {
      print_err("growth-verify: row ${i} v ${get(seen, i)} != ${item_v(i)}");
      return 3;
    }
    i = i + 1;
  }
  print("growthverify ${maxk}");
  return 0;
}

fn growth_mode(n: Int, shape: Text) -> Int {
  let wide = shape == "text";
  if wide == false and shape != "int" {
    print_err("db-bench: growth SHAPE must be `int` or `text`");
    return 2;
  }
  let step = n / 10;
  if step < 1 {
    step = 1;
  }
  let bref = insert Bucket { tag: "growth" };
  let pad = "0123456789abcdef0123456789abcdef";
  let i = 1;
  while i <= n {
    if wide {
      insert Wide { k: i, a: "a${i}${pad}", b: "b${i}${pad}", note: "n${i}${pad}${pad}" };
    } else {
      insert Item { k: i, v: item_v(i), bucket: bref };
    }
    -- at each decile, sample the read path against what is resident NOW
    if i % step == 0 {
      let h: map<Int, Int> = {};
      let probes = 200;
      let pt0 = time.ticks();
      let j = 0;
      while j < probes {
        let key = 1 + (j * step) % i;
        let o0 = time.ticks();
        if wide {
          for r in from x in Wide where x.k == key take 1 select x {
            hist_add(h, time.ticks() - o0);
          }
        } else {
          for r in from x in Item where x.k == key take 1 select x {
            hist_add(h, time.ticks() - o0);
          }
        }
        j = j + 1;
      }
      let pel = time.ticks() - pt0;
      -- op name carries the decile so the driver keys each sample distinctly
      report("growth${i / step}", probes, pel, h);
      -- rows and resident KiB at this decile: the driver divides to get the
      -- per-row footprint for THIS shape
      print("growthrss ${i / step} ${i} ${self_rss_kb()}");
    }
    i = i + 1;
  }
  print("growthdone ${n}");
  return 0;
}

fn main(args: multi Text) -> Int {
  if len(args) < 1 {
    return usage();
  }
  if args[0] == "verify" {
    return verify();
  }
  if args[0] == "growth-verify" {
    return growth_verify();
  }
  -- Does NOTHING. With WO_DATA set the runtime replays the whole log before
  -- main runs, so a mode with no work of its own measures replay plus a fixed
  -- process start — which is what "boot time" has to mean. Both databasev2 1
  -- (replay baseline) and databasev2 3 (checkpoint boot) price boot with it.
  if args[0] == "boot" {
    return boot_mode();
  }
  if len(args) < 2 {
    return usage();
  }
  let n = parse_int(args[1]);
  if n == nil or n < 1 {
    print_err("db-bench: <n> must be a positive number");
    return 2;
  }
  if args[0] == "all" {
    return all_mode(n);
  }
  if args[0] == "seed" {
    return seed(n);
  }
  if args[0] == "read" {
    return read_mode(n);
  }
  if args[0] == "query" {
    return query_mode(n);
  }
  if args[0] == "write" {
    return write_mode(n);
  }
  if args[0] == "wal" {
    return wal_mode(n);
  }
  if args[0] == "verify-acked" {
    return verify_acked(n);
  }
  if args[0] == "msgrate" {
    return msgrate_mode(n);
  }
  if args[0] == "growth" {
    if len(args) < 3 {
      return usage();
    }
    return growth_mode(n, args[2]);
  }
  if args[0] == "replayseed" {
    if len(args) < 3 {
      return usage();
    }
    let mm = parse_int(args[2]);
    if mm == nil or mm < 0 {
      print_err("db-bench: <m> must be zero or more");
      return 2;
    }
    return replayseed_mode(n, mm);
  }
  if args[0] == "hreadall" or args[0] == "hreadkeys" {
    if len(args) < 3 { print_err("usage: hreadall|hreadkeys N R"); return 2; }
    let hn = parse_int(args[1]);
    let hr = parse_int(args[2]);
    if hn == nil or hr == nil { print_err("db-bench: N and R must be positive"); return 2; }
    if args[0] == "hreadall" { return hread_all(hn, hr); }
    return hread_keys(hn, hr);
  }
  if args[0] == "wreadall" or args[0] == "wreadkeys" {
    if len(args) < 3 { print_err("usage: wreadall|wreadkeys N R"); return 2; }
    let wn = parse_int(args[1]);
    let wr = parse_int(args[2]);
    if wn == nil or wr == nil { print_err("db-bench: N and R must be positive"); return 2; }
    if args[0] == "wreadall" { return wread_all(wn, wr); }
    return wread_keys(wn, wr);
  }
  if args[0] == "kreadall" or args[0] == "kreadkeys" {
    if len(args) < 3 { print_err("usage: kreadall|kreadkeys N R"); return 2; }
    let n = parse_int(args[1]);
    let rr = parse_int(args[2]);
    if n == nil or rr == nil {
      print_err("db-bench: N and R must be positive numbers");
      return 2;
    }
    if args[0] == "kreadall" { return kread_all(n, rr); }
    return kread_keys(n, rr);
  }
  if args[0] == "randread" {
    if len(args) < 3 {
      return usage();
    }
    let rr = parse_int(args[2]);
    if rr == nil or rr < 1 {
      print_err("db-bench: <r> must be a positive number");
      return 2;
    }
    return randread_mode(n, rr);
  }
  if args[0] == "wmix" {
    if len(args) < 3 {
      return usage();
    }
    let wc = parse_int(args[2]);
    if wc == nil or wc < 1 {
      print_err("db-bench: <c> must be a positive number");
      return 2;
    }
    return wmix_mode(n, wc);
  }
  if args[0] == "mix" {
    if len(args) < 3 {
      return usage();
    }
    let c = parse_int(args[2]);
    if c == nil or c < 1 {
      print_err("db-bench: <c> must be a positive number");
      return 2;
    }
    return mix_mode(n, c);
  }
  return usage();
}