The MannaLedger counted the day's consumption in memory. A restart
forgot it, and the next cycle gathered the same day's provision whole.
While manna was an emptyDir that took the kohen's hand; with the
provision on a volume (41a3e51) a crash loop alone would have refilled
the jar, once per crash. Ish l'fi ochlo — Shemot 16:18.
- After every cycle that eats, the day's consumption is written to
ledger.json beside the provision file (tmp + rename; on the manna
volume in production).
- A process that starts while today's record is on disk takes the day
up at once (handle_continue), so /kodesh/status never shows an
untouched jar that is half eaten; otherwise the first load of the day
resumes from it.
- Another day's record is ignored. A record that is not a ledger
(bad JSON, negative or non-integer counts) is ignored with a warning.
The record can only reduce what remains.
- At the day boundary the record goes with the surplus. A release
within the same day (the late-provision re-gather) lets go of the
allocation and keeps the record.
- If the file cannot be written the ledger says so and keeps counting
in memory; the cycle is not stopped by its own bookkeeping.
- MannaLedger.reset/0 (tests) forgets the record; test_helper clears
any record an interrupted run left behind.
test/manna_ledger_persistence_test.exs — 13 tests, restarting the
ledger under its real supervisor. All fail without the change.
Read before committing: Elixir 474/0 on seeds 0 7 42 99 191243. Built
image, real container restarts against a mounted manna directory:
3 of 5 units eaten → restart → status shows 3 before any request →
2 more served, the 6th refused → restart → still refused.
Found while writing the tests, not changed: killing the ledger more
than three times in five seconds takes the whole application down (OTP
restart intensity, one_for_one defaults). On the pod that is a
container restart — which now resumes the day instead of refilling it.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
234 lines
8.7 KiB
Elixir
234 lines
8.7 KiB
Elixir
defmodule VavPipeline.MannaLedgerPersistenceTest do
|
|
@moduledoc """
|
|
What is eaten stays eaten.
|
|
|
|
Until 2026-10-04 the ledger lived only in memory. A restart forgot the
|
|
day's consumption and the next cycle gathered the whole provision again.
|
|
That was hidden while manna was an emptyDir (a restart emptied the jar
|
|
too, and the kohen had to refill it by hand); once the provision was put
|
|
on a volume, a crash loop alone would have refilled it.
|
|
|
|
These tests restart the ledger process under its real supervisor — a new
|
|
process, an empty state, the same disk — and ask what it remembers.
|
|
"""
|
|
|
|
use ExUnit.Case, async: false
|
|
|
|
alias VavPipeline.{HaltMonitor, Manna, MannaLedger}
|
|
|
|
setup do
|
|
if HaltMonitor.halted?(), do: HaltMonitor.resolve("manna persistence test setup")
|
|
MannaLedger.reset()
|
|
write_provision(10)
|
|
|
|
on_exit(fn ->
|
|
MannaLedger.reset()
|
|
File.rm(Manna.provision_file())
|
|
end)
|
|
|
|
:ok
|
|
end
|
|
|
|
describe "the record" do
|
|
test "is written beside the provision, with today's date, when a cycle eats" do
|
|
refute File.exists?(MannaLedger.ledger_file())
|
|
|
|
assert {:ok, :loaded} = MannaLedger.load_provision()
|
|
assert {:ok, 7} = MannaLedger.consume(:compute_units, 3)
|
|
|
|
assert Path.dirname(MannaLedger.ledger_file()) == Path.dirname(Manna.provision_file())
|
|
record = MannaLedger.ledger_file() |> File.read!() |> Jason.decode!()
|
|
|
|
assert record["cycle_date"] == today()
|
|
assert record["consumed"]["compute_units"] == 3
|
|
assert record["consumed"]["api_calls_external"] == 0
|
|
end
|
|
|
|
test "is not written by a refused consumption" do
|
|
assert {:ok, :loaded} = MannaLedger.load_provision()
|
|
assert {:error, :provision_exhausted} = MannaLedger.consume(:compute_units, 11)
|
|
refute File.exists?(MannaLedger.ledger_file())
|
|
end
|
|
end
|
|
|
|
describe "a restart in the middle of the day" do
|
|
test "resumes the count — the provision is not gathered whole again" do
|
|
assert {:ok, :loaded} = MannaLedger.load_provision()
|
|
assert {:ok, 6} = MannaLedger.consume(:compute_units, 4)
|
|
|
|
restart_ledger()
|
|
|
|
# The new process takes the day up as it starts — before any cycle
|
|
# asks — so the status never shows an untouched jar.
|
|
ledger = MannaLedger.ledger()
|
|
assert ledger.cycle_date == today()
|
|
assert ledger.allocated.compute_units == 10
|
|
assert ledger.consumed.compute_units == 4
|
|
|
|
assert {:ok, :already_loaded} = MannaLedger.load_provision()
|
|
assert MannaLedger.remaining(:compute_units) == 6
|
|
|
|
# And it keeps counting from there.
|
|
assert {:ok, 5} = MannaLedger.consume(:compute_units, 1)
|
|
end
|
|
|
|
test "an exhausted day stays exhausted — a crash loop does not refill the jar" do
|
|
assert {:ok, :loaded} = MannaLedger.load_provision()
|
|
assert {:ok, 0} = MannaLedger.consume(:compute_units, 10)
|
|
|
|
for _ <- 1..3 do
|
|
restart_ledger()
|
|
assert {:waiting, :provision_exhausted} = Manna.gather_for_cycle()
|
|
end
|
|
end
|
|
|
|
test "the whole cycle path: gather, restart, gather" do
|
|
assert :ok = Manna.gather_for_cycle()
|
|
assert :ok = Manna.gather_for_cycle()
|
|
restart_ledger()
|
|
assert :ok = Manna.gather_for_cycle()
|
|
assert MannaLedger.ledger().consumed.compute_units == 3
|
|
end
|
|
end
|
|
|
|
describe "a restart with nothing to resume" do
|
|
test "no record: the new process holds no day until the first cycle" do
|
|
restart_ledger()
|
|
assert MannaLedger.ledger().cycle_date == nil
|
|
assert {:ok, :loaded} = MannaLedger.load_provision()
|
|
assert MannaLedger.remaining(:compute_units) == 10
|
|
end
|
|
|
|
test "a record but no provision: nothing is resumed into an empty day" do
|
|
assert {:ok, :loaded} = MannaLedger.load_provision()
|
|
assert {:ok, 9} = MannaLedger.consume(:compute_units, 1)
|
|
File.rm!(Manna.provision_file())
|
|
|
|
restart_ledger()
|
|
assert MannaLedger.remaining(:compute_units) == 0
|
|
|
|
# The vessel waits. (Which of the two waiting reasons it gives is
|
|
# the ledger's older behaviour for a day pinned with no provision;
|
|
# the router answers MANNA_DEPLETED for both.)
|
|
assert {:waiting, reason} = Manna.gather_for_cycle()
|
|
assert reason in [:no_provision, :provision_exhausted]
|
|
end
|
|
end
|
|
|
|
describe "what the record may not do" do
|
|
test "another day's record is not this day's — it is ignored" do
|
|
write_record(%{"cycle_date" => "2026-01-01", "consumed" => %{"compute_units" => 9}})
|
|
|
|
assert {:ok, :loaded} = MannaLedger.load_provision()
|
|
assert MannaLedger.remaining(:compute_units) == 10
|
|
end
|
|
|
|
test "a record that is not a ledger is ignored, and the cycle goes on" do
|
|
for garbage <- [
|
|
"not json",
|
|
Jason.encode!(%{"cycle_date" => today(), "consumed" => "all of it"}),
|
|
Jason.encode!(%{"cycle_date" => today(), "consumed" => %{"compute_units" => -5}}),
|
|
Jason.encode!(%{"cycle_date" => today(), "consumed" => %{"compute_units" => "3"}})
|
|
] do
|
|
MannaLedger.reset()
|
|
File.write!(MannaLedger.ledger_file(), garbage)
|
|
|
|
assert {:ok, :loaded} = MannaLedger.load_provision()
|
|
assert MannaLedger.remaining(:compute_units) == 10
|
|
assert {:ok, 9} = MannaLedger.consume(:compute_units, 1)
|
|
end
|
|
end
|
|
|
|
test "it can only take away: a record larger than the provision leaves nothing" do
|
|
write_record(%{"cycle_date" => today(), "consumed" => %{"compute_units" => 500}})
|
|
|
|
assert {:ok, :loaded} = MannaLedger.load_provision()
|
|
assert MannaLedger.remaining(:compute_units) == 0
|
|
assert {:error, :provision_exhausted} = MannaLedger.consume(:compute_units, 1)
|
|
end
|
|
end
|
|
|
|
describe "release" do
|
|
test "at a day boundary the record goes with the surplus" do
|
|
# The ledger holds no day (cycle_date nil ≠ today), as it does when
|
|
# the day it loaded has passed and been released.
|
|
write_record(%{"cycle_date" => "2026-01-01", "consumed" => %{"compute_units" => 2}})
|
|
|
|
assert {:ok, _} = MannaLedger.enforce_cycle_boundary()
|
|
refute File.exists?(MannaLedger.ledger_file())
|
|
end
|
|
|
|
test "a release within the same day lets go of the allocation, not the memory" do
|
|
assert {:ok, :loaded} = MannaLedger.load_provision()
|
|
assert {:ok, 8} = MannaLedger.consume(:compute_units, 2)
|
|
|
|
# Manna.gather_for_cycle/0 does this when a provision arrives late.
|
|
assert {:ok, _} = MannaLedger.enforce_cycle_boundary()
|
|
assert File.exists?(MannaLedger.ledger_file())
|
|
|
|
assert {:ok, :loaded} = MannaLedger.load_provision()
|
|
assert MannaLedger.remaining(:compute_units) == 8
|
|
end
|
|
|
|
test "reset forgets the record (tests must not leak a day into each other)" do
|
|
assert {:ok, :loaded} = MannaLedger.load_provision()
|
|
assert {:ok, 9} = MannaLedger.consume(:compute_units, 1)
|
|
assert File.exists?(MannaLedger.ledger_file())
|
|
|
|
MannaLedger.reset()
|
|
refute File.exists?(MannaLedger.ledger_file())
|
|
end
|
|
end
|
|
|
|
# ------------------------------------------------------------
|
|
# Helpers
|
|
# ------------------------------------------------------------
|
|
|
|
defp today, do: Date.utc_today() |> Date.to_iso8601()
|
|
|
|
# Bring the ledger down and up again through its own supervisor — a
|
|
# new process with a new, empty state, and the file on disk untouched.
|
|
# That is a restart, not a reset.
|
|
#
|
|
# (Done with terminate_child/restart_child rather than Process.exit:
|
|
# this file restarts the ledger six times in well under five seconds,
|
|
# and a supervisor that sees more than three CRASHES in five seconds
|
|
# gives up and takes the application down with it — as the first
|
|
# version of this test found out.)
|
|
defp restart_ledger do
|
|
old = Process.whereis(MannaLedger)
|
|
:ok = Supervisor.terminate_child(VavPipeline.Supervisor, MannaLedger)
|
|
{:ok, new} = Supervisor.restart_child(VavPipeline.Supervisor, MannaLedger)
|
|
assert new != old
|
|
assert Process.whereis(MannaLedger) == new
|
|
end
|
|
|
|
defp write_record(record) do
|
|
File.mkdir_p!(Path.dirname(MannaLedger.ledger_file()))
|
|
File.write!(MannaLedger.ledger_file(), Jason.encode!(record))
|
|
end
|
|
|
|
defp write_provision(compute_units) do
|
|
expires = DateTime.utc_now() |> DateTime.add(6 * 3600) |> DateTime.to_iso8601()
|
|
|
|
provision = %{
|
|
"date" => today(),
|
|
"provision" => %{
|
|
"compute_units" => compute_units,
|
|
"memory_mb" => 512,
|
|
"api_calls_external" => 5,
|
|
"storage_delta_mb" => 2,
|
|
"sanhedrin_panels_max" => 2
|
|
},
|
|
"type" => "regular",
|
|
"expires_at" => expires,
|
|
"written_by" => "manna_ledger_persistence_test",
|
|
"written_at" => DateTime.utc_now() |> DateTime.to_iso8601()
|
|
}
|
|
|
|
path = Manna.provision_file()
|
|
File.mkdir_p!(Path.dirname(path))
|
|
File.write!(path, Jason.encode!(provision))
|
|
end
|
|
end
|