mirror of
https://github.com/wanderer-industries/wanderer
synced 2025-11-28 20:13:24 +00:00
Compare commits
35 Commits
fix-error-
...
v1.84.23
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
005e0c2bc6 | ||
|
|
808acb540e | ||
|
|
812582d955 | ||
|
|
f3077c0bf1 | ||
|
|
32c70cbbad | ||
|
|
8934935e10 | ||
|
|
20c8a53712 | ||
|
|
b22970fef3 | ||
|
|
cf72394ef9 | ||
|
|
e6dbba7283 | ||
|
|
843b3b86b2 | ||
|
|
bd865b9f64 | ||
|
|
ae91cd2f92 | ||
|
|
0be7a5f9d0 | ||
|
|
e15bfa426a | ||
|
|
4198e4b07a | ||
|
|
03ee08ff67 | ||
|
|
ac4dd4c28b | ||
|
|
308e81a464 | ||
|
|
6f4240d931 | ||
|
|
847b45a431 | ||
|
|
5ec97d74ca | ||
|
|
74359a5542 | ||
|
|
0020f46dd8 | ||
|
|
a6751b45c6 | ||
|
|
f48aeb5cec | ||
|
|
a5f25646c9 | ||
|
|
23cf1fd96f | ||
|
|
6f15521069 | ||
|
|
9d41e57c06 | ||
|
|
ea9a22df09 | ||
|
|
0d4fd6f214 | ||
|
|
87a6c20545 | ||
|
|
c375f4e4ce | ||
|
|
843a6d7320 |
90
CHANGELOG.md
90
CHANGELOG.md
@@ -2,6 +2,96 @@
|
||||
|
||||
<!-- changelog -->
|
||||
|
||||
## [v1.84.23](https://github.com/wanderer-industries/wanderer/compare/v1.84.22...v1.84.23) (2025-11-15)
|
||||
|
||||
|
||||
|
||||
|
||||
### Bug Fixes:
|
||||
|
||||
* core: fixed map pings cancel errors
|
||||
|
||||
## [v1.84.22](https://github.com/wanderer-industries/wanderer/compare/v1.84.21...v1.84.22) (2025-11-15)
|
||||
|
||||
|
||||
|
||||
|
||||
### Bug Fixes:
|
||||
|
||||
* core: fixed map initialization
|
||||
|
||||
## [v1.84.21](https://github.com/wanderer-industries/wanderer/compare/v1.84.20...v1.84.21) (2025-11-15)
|
||||
|
||||
|
||||
|
||||
|
||||
### Bug Fixes:
|
||||
|
||||
* core: fixed map characters adding
|
||||
|
||||
## [v1.84.20](https://github.com/wanderer-industries/wanderer/compare/v1.84.19...v1.84.20) (2025-11-15)
|
||||
|
||||
|
||||
|
||||
|
||||
### Bug Fixes:
|
||||
|
||||
* core: fixed map start issues
|
||||
|
||||
## [v1.84.19](https://github.com/wanderer-industries/wanderer/compare/v1.84.18...v1.84.19) (2025-11-14)
|
||||
|
||||
|
||||
|
||||
|
||||
### Bug Fixes:
|
||||
|
||||
* core: fixed map start issues
|
||||
|
||||
## [v1.84.18](https://github.com/wanderer-industries/wanderer/compare/v1.84.17...v1.84.18) (2025-11-14)
|
||||
|
||||
|
||||
|
||||
|
||||
### Bug Fixes:
|
||||
|
||||
* core: added gracefull map poll recovery from saved state. added map slug unique checks
|
||||
|
||||
## [v1.84.17](https://github.com/wanderer-industries/wanderer/compare/v1.84.16...v1.84.17) (2025-11-14)
|
||||
|
||||
|
||||
|
||||
|
||||
### Bug Fixes:
|
||||
|
||||
* core: fixed activity tracking issues
|
||||
|
||||
## [v1.84.16](https://github.com/wanderer-industries/wanderer/compare/v1.84.15...v1.84.16) (2025-11-13)
|
||||
|
||||
|
||||
|
||||
|
||||
### Bug Fixes:
|
||||
|
||||
* core: removed maps auto-start logic
|
||||
|
||||
## [v1.84.15](https://github.com/wanderer-industries/wanderer/compare/v1.84.14...v1.84.15) (2025-11-13)
|
||||
|
||||
|
||||
|
||||
|
||||
### Bug Fixes:
|
||||
|
||||
* core: fixed maps start/stop logic, added server downtime period support
|
||||
|
||||
## [v1.84.14](https://github.com/wanderer-industries/wanderer/compare/v1.84.13...v1.84.14) (2025-11-13)
|
||||
|
||||
|
||||
|
||||
|
||||
### Bug Fixes:
|
||||
|
||||
* Map: Fixed problem related with error if settings was removed and mapper crashed. Fixed settings reset.
|
||||
|
||||
## [v1.84.13](https://github.com/wanderer-industries/wanderer/compare/v1.84.12...v1.84.13) (2025-11-13)
|
||||
|
||||
|
||||
|
||||
@@ -27,11 +27,7 @@ config :wanderer_app,
|
||||
generators: [timestamp_type: :utc_datetime],
|
||||
ddrt: WandererApp.Map.CacheRTree,
|
||||
logger: Logger,
|
||||
pubsub_client: Phoenix.PubSub,
|
||||
wanderer_kills_base_url:
|
||||
System.get_env("WANDERER_KILLS_BASE_URL", "ws://host.docker.internal:4004"),
|
||||
wanderer_kills_service_enabled:
|
||||
System.get_env("WANDERER_KILLS_SERVICE_ENABLED", "false") == "true"
|
||||
pubsub_client: Phoenix.PubSub
|
||||
|
||||
config :wanderer_app, WandererAppWeb.Endpoint,
|
||||
adapter: Bandit.PhoenixAdapter,
|
||||
|
||||
@@ -4,7 +4,7 @@ import Config
|
||||
config :wanderer_app, WandererApp.Repo,
|
||||
username: "postgres",
|
||||
password: "postgres",
|
||||
hostname: System.get_env("DB_HOST", "localhost"),
|
||||
hostname: "localhost",
|
||||
database: "wanderer_dev",
|
||||
stacktrace: true,
|
||||
show_sensitive_data_on_connection_error: true,
|
||||
|
||||
@@ -1,8 +1,25 @@
|
||||
defmodule WandererApp.Api.Changes.SlugifyName do
|
||||
@moduledoc """
|
||||
Ensures map slugs are unique by:
|
||||
1. Slugifying the provided slug/name
|
||||
2. Checking for existing slugs (optimization)
|
||||
3. Finding next available slug with numeric suffix if needed
|
||||
4. Relying on database unique constraint as final arbiter
|
||||
|
||||
Race Condition Mitigation:
|
||||
- Optimistic check reduces DB roundtrips for most cases
|
||||
- Database unique index ensures no duplicates slip through
|
||||
- Proper error messages for constraint violations
|
||||
- Telemetry events for monitoring conflicts
|
||||
"""
|
||||
use Ash.Resource.Change
|
||||
|
||||
alias Ash.Changeset
|
||||
require Ash.Query
|
||||
require Logger
|
||||
|
||||
# Maximum number of attempts to find a unique slug
|
||||
@max_attempts 100
|
||||
|
||||
@impl true
|
||||
@spec change(Changeset.t(), keyword, Change.context()) :: Changeset.t()
|
||||
@@ -26,7 +43,7 @@ defmodule WandererApp.Api.Changes.SlugifyName do
|
||||
# Get the current record ID if this is an update operation
|
||||
current_id = Changeset.get_attribute(changeset, :id)
|
||||
|
||||
# Check if the base slug is available
|
||||
# Check if the base slug is available (optimization to avoid numeric suffixes when possible)
|
||||
if slug_available?(base_slug, current_id) do
|
||||
base_slug
|
||||
else
|
||||
@@ -35,16 +52,44 @@ defmodule WandererApp.Api.Changes.SlugifyName do
|
||||
end
|
||||
end
|
||||
|
||||
defp find_available_slug(base_slug, current_id, n) do
|
||||
defp find_available_slug(base_slug, current_id, n) when n <= @max_attempts do
|
||||
candidate_slug = "#{base_slug}-#{n}"
|
||||
|
||||
if slug_available?(candidate_slug, current_id) do
|
||||
# Emit telemetry when we had to use a suffix (indicates potential conflict)
|
||||
:telemetry.execute(
|
||||
[:wanderer_app, :map, :slug_suffix_used],
|
||||
%{suffix_number: n},
|
||||
%{base_slug: base_slug, final_slug: candidate_slug}
|
||||
)
|
||||
|
||||
candidate_slug
|
||||
else
|
||||
find_available_slug(base_slug, current_id, n + 1)
|
||||
end
|
||||
end
|
||||
|
||||
defp find_available_slug(base_slug, _current_id, n) when n > @max_attempts do
|
||||
# Fallback: use timestamp suffix if we've tried too many numeric suffixes
|
||||
# This handles edge cases where many maps have similar names
|
||||
timestamp = System.system_time(:millisecond)
|
||||
fallback_slug = "#{base_slug}-#{timestamp}"
|
||||
|
||||
Logger.warning(
|
||||
"Slug generation exceeded #{@max_attempts} attempts for '#{base_slug}', using timestamp fallback",
|
||||
base_slug: base_slug,
|
||||
fallback_slug: fallback_slug
|
||||
)
|
||||
|
||||
:telemetry.execute(
|
||||
[:wanderer_app, :map, :slug_fallback_used],
|
||||
%{attempts: n},
|
||||
%{base_slug: base_slug, fallback_slug: fallback_slug}
|
||||
)
|
||||
|
||||
fallback_slug
|
||||
end
|
||||
|
||||
defp slug_available?(slug, current_id) do
|
||||
query =
|
||||
WandererApp.Api.Map
|
||||
@@ -60,9 +105,20 @@ defmodule WandererApp.Api.Changes.SlugifyName do
|
||||
|> Ash.Query.limit(1)
|
||||
|
||||
case Ash.read(query) do
|
||||
{:ok, []} -> true
|
||||
{:ok, _} -> false
|
||||
{:error, _} -> false
|
||||
{:ok, []} ->
|
||||
true
|
||||
|
||||
{:ok, _existing} ->
|
||||
false
|
||||
|
||||
{:error, error} ->
|
||||
# Log error but be conservative - assume slug is not available
|
||||
Logger.warning("Error checking slug availability",
|
||||
slug: slug,
|
||||
error: inspect(error)
|
||||
)
|
||||
|
||||
false
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
@@ -31,7 +31,7 @@ defmodule WandererApp.Api.Map do
|
||||
routes do
|
||||
base("/maps")
|
||||
get(:by_slug, route: "/:slug")
|
||||
index :read
|
||||
# index :read
|
||||
post(:new)
|
||||
patch(:update)
|
||||
delete(:destroy)
|
||||
|
||||
@@ -187,6 +187,10 @@ defmodule WandererApp.Character do
|
||||
{:ok, result} ->
|
||||
{:ok, result |> prepare_search_results()}
|
||||
|
||||
{:error, error} ->
|
||||
Logger.warning("#{__MODULE__} failed search: #{inspect(error)}")
|
||||
{:ok, []}
|
||||
|
||||
error ->
|
||||
Logger.warning("#{__MODULE__} failed search: #{inspect(error)}")
|
||||
{:ok, []}
|
||||
|
||||
@@ -8,7 +8,7 @@ defmodule WandererApp.Character.TrackerPool do
|
||||
:tracked_ids,
|
||||
:uuid,
|
||||
:characters,
|
||||
server_online: true
|
||||
server_online: false
|
||||
]
|
||||
|
||||
@name __MODULE__
|
||||
|
||||
@@ -12,7 +12,7 @@ defmodule WandererApp.Character.TransactionsTracker.Impl do
|
||||
total_balance: 0,
|
||||
transactions: [],
|
||||
retries: 5,
|
||||
server_online: true,
|
||||
server_online: false,
|
||||
status: :started
|
||||
]
|
||||
|
||||
@@ -75,7 +75,7 @@ defmodule WandererApp.Character.TransactionsTracker.Impl do
|
||||
|
||||
def handle_event(
|
||||
:update_corp_wallets,
|
||||
%{character: character} = state
|
||||
%{character: character, server_online: true} = state
|
||||
) do
|
||||
Process.send_after(self(), :update_corp_wallets, @update_interval)
|
||||
|
||||
@@ -88,26 +88,26 @@ defmodule WandererApp.Character.TransactionsTracker.Impl do
|
||||
:update_corp_wallets,
|
||||
state
|
||||
) do
|
||||
Process.send_after(self(), :update_corp_wallets, :timer.seconds(15))
|
||||
Process.send_after(self(), :update_corp_wallets, @update_interval)
|
||||
|
||||
state
|
||||
end
|
||||
|
||||
def handle_event(
|
||||
:check_wallets,
|
||||
%{wallets: []} = state
|
||||
%{character: character, wallets: wallets, server_online: true} = state
|
||||
) do
|
||||
Process.send_after(self(), :check_wallets, :timer.seconds(5))
|
||||
Process.send_after(self(), :check_wallets, @update_interval)
|
||||
|
||||
state
|
||||
end
|
||||
|
||||
def handle_event(
|
||||
:check_wallets,
|
||||
%{character: character, wallets: wallets} = state
|
||||
) do
|
||||
check_wallets(wallets, character)
|
||||
|
||||
state
|
||||
end
|
||||
|
||||
def handle_event(
|
||||
:check_wallets,
|
||||
state
|
||||
) do
|
||||
Process.send_after(self(), :check_wallets, @update_interval)
|
||||
|
||||
state
|
||||
|
||||
@@ -53,8 +53,8 @@ defmodule WandererApp.Map do
|
||||
{:ok, map} ->
|
||||
map
|
||||
|
||||
_ ->
|
||||
Logger.error(fn -> "Failed to get map #{map_id}" end)
|
||||
error ->
|
||||
Logger.error("Failed to get map #{map_id}: #{inspect(error)}")
|
||||
%{}
|
||||
end
|
||||
end
|
||||
@@ -183,9 +183,31 @@ defmodule WandererApp.Map do
|
||||
|
||||
def add_characters!(map, []), do: map
|
||||
|
||||
def add_characters!(%{map_id: map_id} = map, [character | rest]) do
|
||||
add_character(map_id, character)
|
||||
add_characters!(map, rest)
|
||||
def add_characters!(%{map_id: map_id} = map, characters) when is_list(characters) do
|
||||
# Get current characters list once
|
||||
current_characters = Map.get(map, :characters, [])
|
||||
|
||||
characters_ids =
|
||||
characters
|
||||
|> Enum.map(fn %{id: char_id} -> char_id end)
|
||||
|
||||
# Filter out characters that already exist
|
||||
new_character_ids =
|
||||
characters_ids
|
||||
|> Enum.reject(fn char_id -> char_id in current_characters end)
|
||||
|
||||
# If all characters already exist, return early
|
||||
if new_character_ids == [] do
|
||||
map
|
||||
else
|
||||
case update_map(map_id, %{characters: new_character_ids ++ current_characters}) do
|
||||
{:commit, map} ->
|
||||
map
|
||||
|
||||
_ ->
|
||||
map
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
def add_character(
|
||||
@@ -198,61 +220,10 @@ defmodule WandererApp.Map do
|
||||
|
||||
case not (characters |> Enum.member?(character_id)) do
|
||||
true ->
|
||||
WandererApp.Character.get_map_character(map_id, character_id)
|
||||
|> case do
|
||||
{:ok,
|
||||
%{
|
||||
alliance_id: alliance_id,
|
||||
corporation_id: corporation_id,
|
||||
solar_system_id: solar_system_id,
|
||||
structure_id: structure_id,
|
||||
station_id: station_id,
|
||||
ship: ship_type_id,
|
||||
ship_name: ship_name
|
||||
}} ->
|
||||
map_id
|
||||
|> update_map(%{characters: [character_id | characters]})
|
||||
map_id
|
||||
|> update_map(%{characters: [character_id | characters]})
|
||||
|
||||
# WandererApp.Cache.insert(
|
||||
# "map:#{map_id}:character:#{character_id}:alliance_id",
|
||||
# alliance_id
|
||||
# )
|
||||
|
||||
# WandererApp.Cache.insert(
|
||||
# "map:#{map_id}:character:#{character_id}:corporation_id",
|
||||
# corporation_id
|
||||
# )
|
||||
|
||||
# WandererApp.Cache.insert(
|
||||
# "map:#{map_id}:character:#{character_id}:solar_system_id",
|
||||
# solar_system_id
|
||||
# )
|
||||
|
||||
# WandererApp.Cache.insert(
|
||||
# "map:#{map_id}:character:#{character_id}:structure_id",
|
||||
# structure_id
|
||||
# )
|
||||
|
||||
# WandererApp.Cache.insert(
|
||||
# "map:#{map_id}:character:#{character_id}:station_id",
|
||||
# station_id
|
||||
# )
|
||||
|
||||
# WandererApp.Cache.insert(
|
||||
# "map:#{map_id}:character:#{character_id}:ship_type_id",
|
||||
# ship_type_id
|
||||
# )
|
||||
|
||||
# WandererApp.Cache.insert(
|
||||
# "map:#{map_id}:character:#{character_id}:ship_name",
|
||||
# ship_name
|
||||
# )
|
||||
|
||||
:ok
|
||||
|
||||
error ->
|
||||
error
|
||||
end
|
||||
:ok
|
||||
|
||||
_ ->
|
||||
{:error, :already_exists}
|
||||
|
||||
@@ -9,8 +9,8 @@ defmodule WandererApp.Map.Manager do
|
||||
|
||||
alias WandererApp.Map.Server
|
||||
|
||||
@maps_start_per_second 10
|
||||
@maps_start_interval 1000
|
||||
@maps_start_chunk_size 20
|
||||
@maps_start_interval 500
|
||||
@maps_queue :maps_queue
|
||||
@check_maps_queue_interval :timer.seconds(1)
|
||||
|
||||
@@ -58,9 +58,9 @@ defmodule WandererApp.Map.Manager do
|
||||
{:ok, pings_cleanup_timer} =
|
||||
:timer.send_interval(@pings_cleanup_interval, :cleanup_pings)
|
||||
|
||||
safe_async_task(fn ->
|
||||
start_last_active_maps()
|
||||
end)
|
||||
# safe_async_task(fn ->
|
||||
# start_last_active_maps()
|
||||
# end)
|
||||
|
||||
{:ok,
|
||||
%{
|
||||
@@ -153,7 +153,7 @@ defmodule WandererApp.Map.Manager do
|
||||
@maps_queue
|
||||
|> WandererApp.Queue.to_list!()
|
||||
|> Enum.uniq()
|
||||
|> Enum.chunk_every(@maps_start_per_second)
|
||||
|> Enum.chunk_every(@maps_start_chunk_size)
|
||||
|
||||
WandererApp.Queue.clear(@maps_queue)
|
||||
|
||||
|
||||
@@ -4,7 +4,7 @@ defmodule WandererApp.Map.MapPool do
|
||||
|
||||
require Logger
|
||||
|
||||
alias WandererApp.Map.Server
|
||||
alias WandererApp.Map.{MapPoolState, Server}
|
||||
|
||||
defstruct [
|
||||
:map_ids,
|
||||
@@ -15,6 +15,7 @@ defmodule WandererApp.Map.MapPool do
|
||||
@cache :map_pool_cache
|
||||
@registry :map_pool_registry
|
||||
@unique_registry :unique_map_pool_registry
|
||||
@map_pool_limit 10
|
||||
|
||||
@garbage_collection_interval :timer.hours(4)
|
||||
@systems_cleanup_timeout :timer.minutes(30)
|
||||
@@ -25,7 +26,17 @@ defmodule WandererApp.Map.MapPool do
|
||||
def new(), do: __struct__()
|
||||
def new(args), do: __struct__(args)
|
||||
|
||||
def start_link(map_ids) do
|
||||
# Accept both {uuid, map_ids} tuple (from supervisor restart) and just map_ids (legacy)
|
||||
def start_link({uuid, map_ids}) when is_binary(uuid) and is_list(map_ids) do
|
||||
GenServer.start_link(
|
||||
@name,
|
||||
{uuid, map_ids},
|
||||
name: Module.concat(__MODULE__, uuid)
|
||||
)
|
||||
end
|
||||
|
||||
# For backward compatibility - generate UUID if only map_ids provided
|
||||
def start_link(map_ids) when is_list(map_ids) do
|
||||
uuid = UUID.uuid1()
|
||||
|
||||
GenServer.start_link(
|
||||
@@ -37,13 +48,42 @@ defmodule WandererApp.Map.MapPool do
|
||||
|
||||
@impl true
|
||||
def init({uuid, map_ids}) do
|
||||
{:ok, _} = Registry.register(@unique_registry, Module.concat(__MODULE__, uuid), map_ids)
|
||||
# Check for crash recovery - if we have previous state in ETS, merge it with new map_ids
|
||||
{final_map_ids, recovery_info} =
|
||||
case MapPoolState.get_pool_state(uuid) do
|
||||
{:ok, recovered_map_ids} ->
|
||||
# Merge and deduplicate map IDs
|
||||
merged = Enum.uniq(recovered_map_ids ++ map_ids)
|
||||
recovery_count = length(recovered_map_ids)
|
||||
|
||||
Logger.info(
|
||||
"[Map Pool #{uuid}] Crash recovery detected: recovering #{recovery_count} maps",
|
||||
pool_uuid: uuid,
|
||||
recovered_maps: recovered_map_ids,
|
||||
new_maps: map_ids,
|
||||
total_maps: length(merged)
|
||||
)
|
||||
|
||||
# Emit telemetry for crash recovery
|
||||
:telemetry.execute(
|
||||
[:wanderer_app, :map_pool, :recovery, :start],
|
||||
%{recovered_map_count: recovery_count, total_map_count: length(merged)},
|
||||
%{pool_uuid: uuid}
|
||||
)
|
||||
|
||||
{merged, %{recovered: true, count: recovery_count}}
|
||||
|
||||
{:error, :not_found} ->
|
||||
# Normal startup, no previous state to recover
|
||||
{map_ids, %{recovered: false}}
|
||||
end
|
||||
|
||||
# Register with empty list - maps will be added as they're started in handle_continue
|
||||
{:ok, _} = Registry.register(@unique_registry, Module.concat(__MODULE__, uuid), [])
|
||||
{:ok, _} = Registry.register(@registry, __MODULE__, uuid)
|
||||
|
||||
map_ids
|
||||
|> Enum.each(fn id ->
|
||||
Cachex.put(@cache, id, uuid)
|
||||
end)
|
||||
# Don't pre-populate cache - will be populated as maps start in handle_continue
|
||||
# This prevents duplicates when recovering
|
||||
|
||||
state =
|
||||
%{
|
||||
@@ -52,23 +92,100 @@ defmodule WandererApp.Map.MapPool do
|
||||
}
|
||||
|> new()
|
||||
|
||||
{:ok, state, {:continue, {:start, map_ids}}}
|
||||
{:ok, state, {:continue, {:start, {final_map_ids, recovery_info}}}}
|
||||
end
|
||||
|
||||
@impl true
|
||||
def terminate(_reason, _state) do
|
||||
def terminate(reason, %{uuid: uuid} = _state) do
|
||||
# On graceful shutdown, clean up ETS state
|
||||
# On crash, keep ETS state for recovery
|
||||
case reason do
|
||||
:normal ->
|
||||
Logger.debug("[Map Pool #{uuid}] Graceful shutdown, cleaning up ETS state")
|
||||
MapPoolState.delete_pool_state(uuid)
|
||||
|
||||
:shutdown ->
|
||||
Logger.debug("[Map Pool #{uuid}] Graceful shutdown, cleaning up ETS state")
|
||||
MapPoolState.delete_pool_state(uuid)
|
||||
|
||||
{:shutdown, _} ->
|
||||
Logger.debug("[Map Pool #{uuid}] Graceful shutdown, cleaning up ETS state")
|
||||
MapPoolState.delete_pool_state(uuid)
|
||||
|
||||
_ ->
|
||||
Logger.warning(
|
||||
"[Map Pool #{uuid}] Abnormal termination (#{inspect(reason)}), keeping ETS state for recovery"
|
||||
)
|
||||
|
||||
# Keep ETS state for crash recovery
|
||||
:ok
|
||||
end
|
||||
|
||||
:ok
|
||||
end
|
||||
|
||||
@impl true
|
||||
def handle_continue({:start, map_ids}, state) do
|
||||
def handle_continue({:start, {map_ids, recovery_info}}, state) do
|
||||
Logger.info("#{@name} started")
|
||||
|
||||
map_ids
|
||||
|> Enum.each(fn map_id ->
|
||||
GenServer.cast(self(), {:start_map, map_id})
|
||||
end)
|
||||
# Track recovery statistics
|
||||
start_time = System.monotonic_time(:millisecond)
|
||||
initial_count = length(map_ids)
|
||||
|
||||
# Start maps synchronously and accumulate state changes
|
||||
{new_state, failed_maps} =
|
||||
map_ids
|
||||
|> Enum.reduce({state, []}, fn map_id, {current_state, failed} ->
|
||||
case do_start_map(map_id, current_state) do
|
||||
{:ok, updated_state} ->
|
||||
{updated_state, failed}
|
||||
|
||||
{:error, reason} ->
|
||||
Logger.error("[Map Pool] Failed to start map #{map_id}: #{reason}")
|
||||
|
||||
# Emit telemetry for individual map recovery failure
|
||||
if recovery_info.recovered do
|
||||
:telemetry.execute(
|
||||
[:wanderer_app, :map_pool, :recovery, :map_failed],
|
||||
%{map_id: map_id},
|
||||
%{pool_uuid: state.uuid, reason: reason}
|
||||
)
|
||||
end
|
||||
|
||||
{current_state, [map_id | failed]}
|
||||
end
|
||||
end)
|
||||
|
||||
# Calculate final statistics
|
||||
end_time = System.monotonic_time(:millisecond)
|
||||
duration_ms = end_time - start_time
|
||||
successful_count = length(new_state.map_ids)
|
||||
failed_count = length(failed_maps)
|
||||
|
||||
# Log and emit telemetry for recovery completion
|
||||
if recovery_info.recovered do
|
||||
Logger.info(
|
||||
"[Map Pool #{state.uuid}] Crash recovery completed: #{successful_count}/#{initial_count} maps recovered in #{duration_ms}ms",
|
||||
pool_uuid: state.uuid,
|
||||
recovered_count: successful_count,
|
||||
failed_count: failed_count,
|
||||
total_count: initial_count,
|
||||
duration_ms: duration_ms,
|
||||
failed_maps: failed_maps
|
||||
)
|
||||
|
||||
:telemetry.execute(
|
||||
[:wanderer_app, :map_pool, :recovery, :complete],
|
||||
%{
|
||||
recovered_count: successful_count,
|
||||
failed_count: failed_count,
|
||||
duration_ms: duration_ms
|
||||
},
|
||||
%{pool_uuid: state.uuid}
|
||||
)
|
||||
end
|
||||
|
||||
# Schedule periodic tasks
|
||||
Process.send_after(self(), :backup_state, @backup_state_timeout)
|
||||
Process.send_after(self(), :cleanup_systems, 15_000)
|
||||
Process.send_after(self(), :cleanup_characters, @characters_cleanup_timeout)
|
||||
@@ -77,56 +194,372 @@ defmodule WandererApp.Map.MapPool do
|
||||
# Start message queue monitoring
|
||||
Process.send_after(self(), :monitor_message_queue, :timer.seconds(30))
|
||||
|
||||
{:noreply, state}
|
||||
{:noreply, new_state}
|
||||
end
|
||||
|
||||
@impl true
|
||||
def handle_continue({:init_map, map_id}, %{uuid: uuid} = state) do
|
||||
# Perform the actual map initialization asynchronously
|
||||
# This runs after the GenServer.call has already returned
|
||||
start_time = System.monotonic_time(:millisecond)
|
||||
|
||||
try do
|
||||
# Initialize the map state and start the map server using extracted helper
|
||||
do_initialize_map_server(map_id)
|
||||
|
||||
duration = System.monotonic_time(:millisecond) - start_time
|
||||
|
||||
Logger.info("[Map Pool #{uuid}] Map #{map_id} initialized successfully in #{duration}ms")
|
||||
|
||||
# Emit telemetry for slow initializations
|
||||
if duration > 5_000 do
|
||||
Logger.warning("[Map Pool #{uuid}] Slow map initialization: #{map_id} took #{duration}ms")
|
||||
|
||||
:telemetry.execute(
|
||||
[:wanderer_app, :map_pool, :slow_init],
|
||||
%{duration_ms: duration},
|
||||
%{map_id: map_id, pool_uuid: uuid}
|
||||
)
|
||||
end
|
||||
|
||||
{:noreply, state}
|
||||
rescue
|
||||
e ->
|
||||
duration = System.monotonic_time(:millisecond) - start_time
|
||||
|
||||
Logger.error("""
|
||||
[Map Pool #{uuid}] Failed to initialize map #{map_id} after #{duration}ms: #{Exception.message(e)}
|
||||
#{Exception.format_stacktrace(__STACKTRACE__)}
|
||||
""")
|
||||
|
||||
# Rollback: Remove from state, registry, cache, and ETS using extracted helper
|
||||
new_state = do_unregister_map(map_id, uuid, state)
|
||||
|
||||
# Emit telemetry for failed initialization
|
||||
:telemetry.execute(
|
||||
[:wanderer_app, :map_pool, :init_failed],
|
||||
%{duration_ms: duration},
|
||||
%{map_id: map_id, pool_uuid: uuid, reason: Exception.message(e)}
|
||||
)
|
||||
|
||||
{:noreply, new_state}
|
||||
end
|
||||
end
|
||||
|
||||
@impl true
|
||||
def handle_cast(:stop, state), do: {:stop, :normal, state}
|
||||
|
||||
@impl true
|
||||
def handle_cast({:start_map, map_id}, %{map_ids: map_ids, uuid: uuid} = state) do
|
||||
if map_id not in map_ids do
|
||||
Registry.update_value(@unique_registry, Module.concat(__MODULE__, uuid), fn r_map_ids ->
|
||||
[map_id | r_map_ids]
|
||||
def handle_call({:start_map, map_id}, _from, %{map_ids: map_ids, uuid: uuid} = state) do
|
||||
# Enforce capacity limit to prevent pool overload due to race conditions
|
||||
if length(map_ids) >= @map_pool_limit do
|
||||
Logger.warning(
|
||||
"[Map Pool #{uuid}] Pool at capacity (#{length(map_ids)}/#{@map_pool_limit}), " <>
|
||||
"rejecting map #{map_id} and triggering new pool creation"
|
||||
)
|
||||
|
||||
# Trigger a new pool creation attempt asynchronously
|
||||
# This allows the system to create a new pool for this map
|
||||
spawn(fn ->
|
||||
WandererApp.Map.MapPoolDynamicSupervisor.start_map(map_id)
|
||||
end)
|
||||
|
||||
Cachex.put(@cache, map_id, uuid)
|
||||
|
||||
map_id
|
||||
|> WandererApp.Map.get_map_state!()
|
||||
|> Server.Impl.start_map()
|
||||
|
||||
{:noreply, %{state | map_ids: [map_id | map_ids]}}
|
||||
{:reply, :ok, state}
|
||||
else
|
||||
{:noreply, state}
|
||||
# Check if map is already started or being initialized
|
||||
if map_id in map_ids do
|
||||
Logger.debug("[Map Pool #{uuid}] Map #{map_id} already in pool")
|
||||
{:reply, {:ok, :already_started}, state}
|
||||
else
|
||||
# Pre-register the map in registry and cache to claim ownership
|
||||
# This prevents race conditions where multiple pools try to start the same map
|
||||
registry_result =
|
||||
Registry.update_value(@unique_registry, Module.concat(__MODULE__, uuid), fn r_map_ids ->
|
||||
[map_id | r_map_ids]
|
||||
end)
|
||||
|
||||
case registry_result do
|
||||
{_new_value, _old_value} ->
|
||||
# Add to cache
|
||||
Cachex.put(@cache, map_id, uuid)
|
||||
|
||||
# Add to state
|
||||
new_state = %{state | map_ids: [map_id | map_ids]}
|
||||
|
||||
# Persist state to ETS
|
||||
MapPoolState.save_pool_state(uuid, new_state.map_ids)
|
||||
|
||||
Logger.debug("[Map Pool #{uuid}] Map #{map_id} queued for async initialization")
|
||||
|
||||
# Return immediately and initialize asynchronously
|
||||
{:reply, {:ok, :initializing}, new_state, {:continue, {:init_map, map_id}}}
|
||||
|
||||
:error ->
|
||||
Logger.error("[Map Pool #{uuid}] Failed to register map #{map_id} in registry")
|
||||
{:reply, {:error, :registration_failed}, state}
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
@impl true
|
||||
def handle_cast(
|
||||
def handle_call(
|
||||
{:stop_map, map_id},
|
||||
%{map_ids: map_ids, uuid: uuid} = state
|
||||
_from,
|
||||
state
|
||||
) do
|
||||
case do_stop_map(map_id, state) do
|
||||
{:ok, new_state} ->
|
||||
{:reply, :ok, new_state}
|
||||
|
||||
{:error, reason} ->
|
||||
{:reply, {:error, reason}, state}
|
||||
end
|
||||
end
|
||||
|
||||
defp do_start_map(map_id, %{map_ids: map_ids, uuid: uuid} = state) do
|
||||
if map_id in map_ids do
|
||||
# Map already started
|
||||
{:ok, state}
|
||||
else
|
||||
# Track what operations succeeded for potential rollback
|
||||
completed_operations = []
|
||||
|
||||
try do
|
||||
# Step 1: Update Registry (most critical, do first)
|
||||
registry_result =
|
||||
Registry.update_value(@unique_registry, Module.concat(__MODULE__, uuid), fn r_map_ids ->
|
||||
[map_id | r_map_ids]
|
||||
end)
|
||||
|
||||
completed_operations = [:registry | completed_operations]
|
||||
|
||||
case registry_result do
|
||||
{new_value, _old_value} when is_list(new_value) ->
|
||||
:ok
|
||||
|
||||
:error ->
|
||||
raise "Failed to update registry for pool #{uuid}"
|
||||
end
|
||||
|
||||
# Step 2: Add to cache
|
||||
case Cachex.put(@cache, map_id, uuid) do
|
||||
{:ok, _} ->
|
||||
:ok
|
||||
|
||||
{:error, reason} ->
|
||||
raise "Failed to add to cache: #{inspect(reason)}"
|
||||
end
|
||||
|
||||
completed_operations = [:cache | completed_operations]
|
||||
|
||||
# Step 3: Start the map server using extracted helper
|
||||
do_initialize_map_server(map_id)
|
||||
|
||||
completed_operations = [:map_server | completed_operations]
|
||||
|
||||
# Step 4: Update GenServer state (last, as this is in-memory and fast)
|
||||
new_state = %{state | map_ids: [map_id | map_ids]}
|
||||
|
||||
# Step 5: Persist state to ETS for crash recovery
|
||||
MapPoolState.save_pool_state(uuid, new_state.map_ids)
|
||||
|
||||
Logger.debug("[Map Pool] Successfully started map #{map_id} in pool #{uuid}")
|
||||
{:ok, new_state}
|
||||
rescue
|
||||
e ->
|
||||
Logger.error("""
|
||||
[Map Pool] Failed to start map #{map_id} (completed: #{inspect(completed_operations)}): #{Exception.message(e)}
|
||||
#{Exception.format_stacktrace(__STACKTRACE__)}
|
||||
""")
|
||||
|
||||
# Attempt rollback of completed operations
|
||||
rollback_start_map_operations(map_id, uuid, completed_operations)
|
||||
|
||||
{:error, Exception.message(e)}
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
defp rollback_start_map_operations(map_id, uuid, completed_operations) do
|
||||
Logger.warning("[Map Pool] Attempting to rollback start_map operations for #{map_id}")
|
||||
|
||||
# Rollback in reverse order
|
||||
if :map_server in completed_operations do
|
||||
Logger.debug("[Map Pool] Rollback: Stopping map server for #{map_id}")
|
||||
|
||||
try do
|
||||
Server.Impl.stop_map(map_id)
|
||||
rescue
|
||||
e ->
|
||||
Logger.error("[Map Pool] Rollback failed to stop map server: #{Exception.message(e)}")
|
||||
end
|
||||
end
|
||||
|
||||
if :cache in completed_operations do
|
||||
Logger.debug("[Map Pool] Rollback: Removing #{map_id} from cache")
|
||||
|
||||
case Cachex.del(@cache, map_id) do
|
||||
{:ok, _} ->
|
||||
:ok
|
||||
|
||||
{:error, reason} ->
|
||||
Logger.error("[Map Pool] Rollback failed for cache: #{inspect(reason)}")
|
||||
end
|
||||
end
|
||||
|
||||
if :registry in completed_operations do
|
||||
Logger.debug("[Map Pool] Rollback: Removing #{map_id} from registry")
|
||||
|
||||
try do
|
||||
Registry.update_value(@unique_registry, Module.concat(__MODULE__, uuid), fn r_map_ids ->
|
||||
r_map_ids |> Enum.reject(fn id -> id == map_id end)
|
||||
end)
|
||||
rescue
|
||||
e ->
|
||||
Logger.error("[Map Pool] Rollback failed for registry: #{Exception.message(e)}")
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
defp do_stop_map(map_id, %{map_ids: map_ids, uuid: uuid} = state) do
|
||||
# Track what operations succeeded for potential rollback
|
||||
completed_operations = []
|
||||
|
||||
try do
|
||||
# Step 1: Update Registry (most critical, do first)
|
||||
registry_result =
|
||||
Registry.update_value(@unique_registry, Module.concat(__MODULE__, uuid), fn r_map_ids ->
|
||||
r_map_ids |> Enum.reject(fn id -> id == map_id end)
|
||||
end)
|
||||
|
||||
completed_operations = [:registry | completed_operations]
|
||||
|
||||
case registry_result do
|
||||
{new_value, _old_value} when is_list(new_value) ->
|
||||
:ok
|
||||
|
||||
:error ->
|
||||
raise "Failed to update registry for pool #{uuid}"
|
||||
end
|
||||
|
||||
# Step 2: Delete from cache
|
||||
case Cachex.del(@cache, map_id) do
|
||||
{:ok, _} ->
|
||||
:ok
|
||||
|
||||
{:error, reason} ->
|
||||
raise "Failed to delete from cache: #{inspect(reason)}"
|
||||
end
|
||||
|
||||
completed_operations = [:cache | completed_operations]
|
||||
|
||||
# Step 3: Stop the map server (clean up all map resources)
|
||||
map_id
|
||||
|> Server.Impl.stop_map()
|
||||
|
||||
completed_operations = [:map_server | completed_operations]
|
||||
|
||||
# Step 4: Update GenServer state (last, as this is in-memory and fast)
|
||||
new_state = %{state | map_ids: map_ids |> Enum.reject(fn id -> id == map_id end)}
|
||||
|
||||
# Step 5: Persist state to ETS for crash recovery
|
||||
MapPoolState.save_pool_state(uuid, new_state.map_ids)
|
||||
|
||||
Logger.debug("[Map Pool] Successfully stopped map #{map_id} from pool #{uuid}")
|
||||
{:ok, new_state}
|
||||
rescue
|
||||
e ->
|
||||
Logger.error("""
|
||||
[Map Pool] Failed to stop map #{map_id} (completed: #{inspect(completed_operations)}): #{Exception.message(e)}
|
||||
#{Exception.format_stacktrace(__STACKTRACE__)}
|
||||
""")
|
||||
|
||||
# Attempt rollback of completed operations
|
||||
rollback_stop_map_operations(map_id, uuid, completed_operations)
|
||||
|
||||
{:error, Exception.message(e)}
|
||||
end
|
||||
end
|
||||
|
||||
# Helper function to initialize the map server (no state management)
|
||||
# This extracts the common map initialization logic used in both
|
||||
# synchronous (do_start_map) and asynchronous ({:init_map, map_id}) paths
|
||||
defp do_initialize_map_server(map_id) do
|
||||
map_id
|
||||
|> WandererApp.Map.get_map_state!()
|
||||
|> Server.Impl.start_map()
|
||||
end
|
||||
|
||||
# Helper function to unregister a map from all tracking
|
||||
# Used for rollback when map initialization fails in the async path
|
||||
defp do_unregister_map(map_id, uuid, state) do
|
||||
# Remove from registry
|
||||
Registry.update_value(@unique_registry, Module.concat(__MODULE__, uuid), fn r_map_ids ->
|
||||
r_map_ids |> Enum.reject(fn id -> id == map_id end)
|
||||
Enum.reject(r_map_ids, &(&1 == map_id))
|
||||
end)
|
||||
|
||||
# Remove from cache
|
||||
Cachex.del(@cache, map_id)
|
||||
|
||||
map_id
|
||||
|> Server.Impl.stop_map()
|
||||
# Update state
|
||||
new_state = %{state | map_ids: Enum.reject(state.map_ids, &(&1 == map_id))}
|
||||
|
||||
{:noreply, %{state | map_ids: map_ids |> Enum.reject(fn id -> id == map_id end)}}
|
||||
# Update ETS
|
||||
MapPoolState.save_pool_state(uuid, new_state.map_ids)
|
||||
|
||||
new_state
|
||||
end
|
||||
|
||||
defp rollback_stop_map_operations(map_id, uuid, completed_operations) do
|
||||
Logger.warning("[Map Pool] Attempting to rollback stop_map operations for #{map_id}")
|
||||
|
||||
# Rollback in reverse order
|
||||
if :cache in completed_operations do
|
||||
Logger.debug("[Map Pool] Rollback: Re-adding #{map_id} to cache")
|
||||
|
||||
case Cachex.put(@cache, map_id, uuid) do
|
||||
{:ok, _} ->
|
||||
:ok
|
||||
|
||||
{:error, reason} ->
|
||||
Logger.error("[Map Pool] Rollback failed for cache: #{inspect(reason)}")
|
||||
end
|
||||
end
|
||||
|
||||
if :registry in completed_operations do
|
||||
Logger.debug("[Map Pool] Rollback: Re-adding #{map_id} to registry")
|
||||
|
||||
try do
|
||||
Registry.update_value(@unique_registry, Module.concat(__MODULE__, uuid), fn r_map_ids ->
|
||||
if map_id in r_map_ids do
|
||||
r_map_ids
|
||||
else
|
||||
[map_id | r_map_ids]
|
||||
end
|
||||
end)
|
||||
rescue
|
||||
e ->
|
||||
Logger.error("[Map Pool] Rollback failed for registry: #{Exception.message(e)}")
|
||||
end
|
||||
end
|
||||
|
||||
# Note: We don't rollback map_server stop as Server.Impl.stop_map() is idempotent
|
||||
# and the cleanup operations are safe to leave in a "stopped" state
|
||||
end
|
||||
|
||||
@impl true
|
||||
def handle_call(:error, _, state), do: {:stop, :error, :ok, state}
|
||||
|
||||
@impl true
|
||||
def handle_info(:backup_state, %{map_ids: map_ids} = state) do
|
||||
def handle_info(:backup_state, %{map_ids: map_ids, uuid: uuid} = state) do
|
||||
Process.send_after(self(), :backup_state, @backup_state_timeout)
|
||||
|
||||
try do
|
||||
# Persist pool state to ETS
|
||||
MapPoolState.save_pool_state(uuid, map_ids)
|
||||
|
||||
# Backup individual map states to database
|
||||
map_ids
|
||||
|> Task.async_stream(
|
||||
fn map_id ->
|
||||
@@ -231,25 +664,38 @@ defmodule WandererApp.Map.MapPool do
|
||||
Process.send_after(self(), :garbage_collect, @garbage_collection_interval)
|
||||
|
||||
try do
|
||||
map_ids
|
||||
|> Enum.each(fn map_id ->
|
||||
# presence_character_ids =
|
||||
# WandererApp.Cache.lookup!("map_#{map_id}:presence_character_ids", [])
|
||||
# Process each map and accumulate state changes
|
||||
new_state =
|
||||
map_ids
|
||||
|> Enum.reduce(state, fn map_id, current_state ->
|
||||
presence_character_ids =
|
||||
WandererApp.Cache.lookup!("map_#{map_id}:presence_character_ids", [])
|
||||
|
||||
# if presence_character_ids |> Enum.empty?() do
|
||||
Logger.info(
|
||||
"#{uuid}: No more characters present on: #{map_id}, shutting down map server..."
|
||||
)
|
||||
if presence_character_ids |> Enum.empty?() do
|
||||
Logger.info(
|
||||
"#{uuid}: No more characters present on: #{map_id}, shutting down map server..."
|
||||
)
|
||||
|
||||
GenServer.cast(self(), {:stop_map, map_id})
|
||||
# end
|
||||
end)
|
||||
case do_stop_map(map_id, current_state) do
|
||||
{:ok, updated_state} ->
|
||||
Logger.debug("#{uuid}: Successfully stopped map #{map_id}")
|
||||
updated_state
|
||||
|
||||
{:error, reason} ->
|
||||
Logger.error("#{uuid}: Failed to stop map #{map_id}: #{reason}")
|
||||
current_state
|
||||
end
|
||||
else
|
||||
current_state
|
||||
end
|
||||
end)
|
||||
|
||||
{:noreply, new_state}
|
||||
rescue
|
||||
e ->
|
||||
Logger.error(Exception.message(e))
|
||||
Logger.error("#{uuid}: Garbage collection error: #{Exception.message(e)}")
|
||||
{:noreply, state}
|
||||
end
|
||||
|
||||
{:noreply, state}
|
||||
end
|
||||
|
||||
@impl true
|
||||
@@ -309,6 +755,57 @@ defmodule WandererApp.Map.MapPool do
|
||||
{:noreply, state}
|
||||
end
|
||||
|
||||
def handle_info(:map_deleted, %{map_ids: map_ids} = state) do
|
||||
# When a map is deleted, stop all maps in this pool that are deleted
|
||||
# This is a graceful shutdown triggered by user action
|
||||
Logger.info("[Map Pool #{state.uuid}] Received map_deleted event, stopping affected maps")
|
||||
|
||||
# Check which of our maps were deleted and stop them
|
||||
new_state =
|
||||
map_ids
|
||||
|> Enum.reduce(state, fn map_id, current_state ->
|
||||
# Check if the map still exists in the database
|
||||
case WandererApp.MapRepo.get(map_id) do
|
||||
{:ok, %{deleted: true}} ->
|
||||
Logger.info("[Map Pool #{state.uuid}] Map #{map_id} was deleted, stopping it")
|
||||
|
||||
case do_stop_map(map_id, current_state) do
|
||||
{:ok, updated_state} ->
|
||||
updated_state
|
||||
|
||||
{:error, reason} ->
|
||||
Logger.error(
|
||||
"[Map Pool #{state.uuid}] Failed to stop deleted map #{map_id}: #{reason}"
|
||||
)
|
||||
|
||||
current_state
|
||||
end
|
||||
|
||||
{:ok, _map} ->
|
||||
# Map still exists and is not deleted
|
||||
current_state
|
||||
|
||||
{:error, _} ->
|
||||
# Map doesn't exist, should stop it
|
||||
Logger.info("[Map Pool #{state.uuid}] Map #{map_id} not found, stopping it")
|
||||
|
||||
case do_stop_map(map_id, current_state) do
|
||||
{:ok, updated_state} ->
|
||||
updated_state
|
||||
|
||||
{:error, reason} ->
|
||||
Logger.error(
|
||||
"[Map Pool #{state.uuid}] Failed to stop missing map #{map_id}: #{reason}"
|
||||
)
|
||||
|
||||
current_state
|
||||
end
|
||||
end
|
||||
end)
|
||||
|
||||
{:noreply, new_state}
|
||||
end
|
||||
|
||||
def handle_info(event, state) do
|
||||
try do
|
||||
Server.Impl.handle_event(event)
|
||||
|
||||
@@ -8,6 +8,7 @@ defmodule WandererApp.Map.MapPoolDynamicSupervisor do
|
||||
@registry :map_pool_registry
|
||||
@unique_registry :unique_map_pool_registry
|
||||
@map_pool_limit 10
|
||||
@genserver_call_timeout :timer.minutes(2)
|
||||
|
||||
@name __MODULE__
|
||||
|
||||
@@ -30,23 +31,109 @@ defmodule WandererApp.Map.MapPoolDynamicSupervisor do
|
||||
start_child([map_id], pools |> Enum.count())
|
||||
|
||||
pid ->
|
||||
GenServer.cast(pid, {:start_map, map_id})
|
||||
result = GenServer.call(pid, {:start_map, map_id}, @genserver_call_timeout)
|
||||
|
||||
case result do
|
||||
{:ok, :initializing} ->
|
||||
Logger.debug(
|
||||
"[Map Pool Supervisor] Map #{map_id} queued for async initialization"
|
||||
)
|
||||
|
||||
result
|
||||
|
||||
{:ok, :already_started} ->
|
||||
Logger.debug("[Map Pool Supervisor] Map #{map_id} already started")
|
||||
result
|
||||
|
||||
:ok ->
|
||||
# Legacy synchronous response (from crash recovery path)
|
||||
Logger.debug("[Map Pool Supervisor] Map #{map_id} started synchronously")
|
||||
result
|
||||
|
||||
other ->
|
||||
Logger.warning(
|
||||
"[Map Pool Supervisor] Unexpected response for map #{map_id}: #{inspect(other)}"
|
||||
)
|
||||
|
||||
other
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
def stop_map(map_id) do
|
||||
{:ok, pool_uuid} = Cachex.get(@cache, map_id)
|
||||
case Cachex.get(@cache, map_id) do
|
||||
{:ok, nil} ->
|
||||
# Cache miss - try to find the pool by scanning the registry
|
||||
Logger.warning(
|
||||
"Cache miss for map #{map_id}, scanning registry for pool containing this map"
|
||||
)
|
||||
|
||||
case Registry.lookup(
|
||||
@unique_registry,
|
||||
Module.concat(WandererApp.Map.MapPool, pool_uuid)
|
||||
) do
|
||||
find_pool_by_scanning_registry(map_id)
|
||||
|
||||
{:ok, pool_uuid} ->
|
||||
# Cache hit - use the pool_uuid to lookup the pool
|
||||
case Registry.lookup(
|
||||
@unique_registry,
|
||||
Module.concat(WandererApp.Map.MapPool, pool_uuid)
|
||||
) do
|
||||
[] ->
|
||||
Logger.warning(
|
||||
"Pool with UUID #{pool_uuid} not found in registry for map #{map_id}, scanning registry"
|
||||
)
|
||||
|
||||
find_pool_by_scanning_registry(map_id)
|
||||
|
||||
[{pool_pid, _}] ->
|
||||
GenServer.call(pool_pid, {:stop_map, map_id}, @genserver_call_timeout)
|
||||
end
|
||||
|
||||
{:error, reason} ->
|
||||
Logger.error("Failed to lookup map #{map_id} in cache: #{inspect(reason)}")
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
defp find_pool_by_scanning_registry(map_id) do
|
||||
case Registry.lookup(@registry, WandererApp.Map.MapPool) do
|
||||
[] ->
|
||||
Logger.debug("No map pools found in registry for map #{map_id}")
|
||||
:ok
|
||||
|
||||
[{pool_pid, _}] ->
|
||||
GenServer.cast(pool_pid, {:stop_map, map_id})
|
||||
pools ->
|
||||
# Scan all pools to find the one containing this map_id
|
||||
found_pool =
|
||||
Enum.find_value(pools, fn {_pid, uuid} ->
|
||||
case Registry.lookup(
|
||||
@unique_registry,
|
||||
Module.concat(WandererApp.Map.MapPool, uuid)
|
||||
) do
|
||||
[{pool_pid, map_ids}] ->
|
||||
if map_id in map_ids do
|
||||
{pool_pid, uuid}
|
||||
else
|
||||
nil
|
||||
end
|
||||
|
||||
_ ->
|
||||
nil
|
||||
end
|
||||
end)
|
||||
|
||||
case found_pool do
|
||||
{pool_pid, pool_uuid} ->
|
||||
Logger.info(
|
||||
"Found map #{map_id} in pool #{pool_uuid} via registry scan, updating cache"
|
||||
)
|
||||
|
||||
# Update the cache to fix the inconsistency
|
||||
Cachex.put(@cache, map_id, pool_uuid)
|
||||
GenServer.call(pool_pid, {:stop_map, map_id}, @genserver_call_timeout)
|
||||
|
||||
nil ->
|
||||
Logger.debug("Map #{map_id} not found in any pool registry")
|
||||
:ok
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
@@ -79,9 +166,13 @@ defmodule WandererApp.Map.MapPoolDynamicSupervisor do
|
||||
end
|
||||
|
||||
defp start_child(map_ids, pools_count) do
|
||||
case DynamicSupervisor.start_child(@name, {WandererApp.Map.MapPool, map_ids}) do
|
||||
# Generate UUID for the new pool - this will be used for crash recovery
|
||||
uuid = UUID.uuid1()
|
||||
|
||||
# Pass both UUID and map_ids to the pool for crash recovery support
|
||||
case DynamicSupervisor.start_child(@name, {WandererApp.Map.MapPool, {uuid, map_ids}}) do
|
||||
{:ok, pid} ->
|
||||
Logger.info("Starting map pool, total map_pools: #{pools_count + 1}")
|
||||
Logger.info("Starting map pool #{uuid}, total map_pools: #{pools_count + 1}")
|
||||
{:ok, pid}
|
||||
|
||||
{:error, {:already_started, pid}} ->
|
||||
|
||||
190
lib/wanderer_app/map/map_pool_state.ex
Normal file
190
lib/wanderer_app/map/map_pool_state.ex
Normal file
@@ -0,0 +1,190 @@
|
||||
defmodule WandererApp.Map.MapPoolState do
|
||||
@moduledoc """
|
||||
Helper module for persisting MapPool state to ETS for crash recovery.
|
||||
|
||||
This module provides functions to save and retrieve MapPool state from an ETS table.
|
||||
The state survives GenServer crashes but is lost on node restart, which ensures
|
||||
automatic recovery from crashes while avoiding stale state on system restart.
|
||||
|
||||
## ETS Table Ownership
|
||||
|
||||
The ETS table `:map_pool_state_table` is owned by the MapPoolSupervisor,
|
||||
ensuring it survives individual MapPool process crashes.
|
||||
|
||||
## State Format
|
||||
|
||||
State is stored as tuples: `{pool_uuid, map_ids, last_updated_timestamp}`
|
||||
where:
|
||||
- `pool_uuid` is the unique identifier for the pool (key)
|
||||
- `map_ids` is a list of map IDs managed by this pool
|
||||
- `last_updated_timestamp` is the Unix timestamp of the last update
|
||||
"""
|
||||
|
||||
require Logger
|
||||
|
||||
@table_name :map_pool_state_table
|
||||
@stale_threshold_hours 24
|
||||
|
||||
@doc """
|
||||
Initializes the ETS table for storing MapPool state.
|
||||
|
||||
This should be called by the MapPoolSupervisor during initialization.
|
||||
The table is created as:
|
||||
- `:set` - Each pool UUID has exactly one entry
|
||||
- `:public` - Any process can read/write
|
||||
- `:named_table` - Can be accessed by name
|
||||
|
||||
Returns the table reference or raises if table already exists.
|
||||
"""
|
||||
@spec init_table() :: :ets.table()
|
||||
def init_table do
|
||||
:ets.new(@table_name, [:set, :public, :named_table])
|
||||
end
|
||||
|
||||
@doc """
|
||||
Saves the current state of a MapPool to ETS.
|
||||
|
||||
## Parameters
|
||||
- `uuid` - The unique identifier for the pool
|
||||
- `map_ids` - List of map IDs currently managed by this pool
|
||||
|
||||
## Examples
|
||||
|
||||
iex> MapPoolState.save_pool_state("pool-123", [1, 2, 3])
|
||||
:ok
|
||||
"""
|
||||
@spec save_pool_state(String.t(), [integer()]) :: :ok
|
||||
def save_pool_state(uuid, map_ids) when is_binary(uuid) and is_list(map_ids) do
|
||||
timestamp = System.system_time(:second)
|
||||
true = :ets.insert(@table_name, {uuid, map_ids, timestamp})
|
||||
|
||||
Logger.debug("Saved MapPool state for #{uuid}: #{length(map_ids)} maps",
|
||||
pool_uuid: uuid,
|
||||
map_count: length(map_ids)
|
||||
)
|
||||
|
||||
:ok
|
||||
end
|
||||
|
||||
@doc """
|
||||
Retrieves the saved state for a MapPool from ETS.
|
||||
|
||||
## Parameters
|
||||
- `uuid` - The unique identifier for the pool
|
||||
|
||||
## Returns
|
||||
- `{:ok, map_ids}` if state exists
|
||||
- `{:error, :not_found}` if no state exists for this UUID
|
||||
|
||||
## Examples
|
||||
|
||||
iex> MapPoolState.get_pool_state("pool-123")
|
||||
{:ok, [1, 2, 3]}
|
||||
|
||||
iex> MapPoolState.get_pool_state("non-existent")
|
||||
{:error, :not_found}
|
||||
"""
|
||||
@spec get_pool_state(String.t()) :: {:ok, [integer()]} | {:error, :not_found}
|
||||
def get_pool_state(uuid) when is_binary(uuid) do
|
||||
case :ets.lookup(@table_name, uuid) do
|
||||
[{^uuid, map_ids, _timestamp}] ->
|
||||
{:ok, map_ids}
|
||||
|
||||
[] ->
|
||||
{:error, :not_found}
|
||||
end
|
||||
end
|
||||
|
||||
@doc """
|
||||
Deletes the state for a MapPool from ETS.
|
||||
|
||||
This should be called when a pool is gracefully shut down.
|
||||
|
||||
## Parameters
|
||||
- `uuid` - The unique identifier for the pool
|
||||
|
||||
## Examples
|
||||
|
||||
iex> MapPoolState.delete_pool_state("pool-123")
|
||||
:ok
|
||||
"""
|
||||
@spec delete_pool_state(String.t()) :: :ok
|
||||
def delete_pool_state(uuid) when is_binary(uuid) do
|
||||
true = :ets.delete(@table_name, uuid)
|
||||
|
||||
Logger.debug("Deleted MapPool state for #{uuid}", pool_uuid: uuid)
|
||||
|
||||
:ok
|
||||
end
|
||||
|
||||
@doc """
|
||||
Removes stale entries from the ETS table.
|
||||
|
||||
Entries are considered stale if they haven't been updated in the last
|
||||
#{@stale_threshold_hours} hours. This helps prevent the table from growing
|
||||
unbounded due to pool UUIDs that are no longer in use.
|
||||
|
||||
Returns the number of entries deleted.
|
||||
|
||||
## Examples
|
||||
|
||||
iex> MapPoolState.cleanup_stale_entries()
|
||||
{:ok, 3}
|
||||
"""
|
||||
@spec cleanup_stale_entries() :: {:ok, non_neg_integer()}
|
||||
def cleanup_stale_entries do
|
||||
stale_threshold = System.system_time(:second) - @stale_threshold_hours * 3600
|
||||
|
||||
match_spec = [
|
||||
{
|
||||
{:"$1", :"$2", :"$3"},
|
||||
[{:<, :"$3", stale_threshold}],
|
||||
[:"$1"]
|
||||
}
|
||||
]
|
||||
|
||||
stale_uuids = :ets.select(@table_name, match_spec)
|
||||
|
||||
Enum.each(stale_uuids, fn uuid ->
|
||||
:ets.delete(@table_name, uuid)
|
||||
|
||||
Logger.info("Cleaned up stale MapPool state for #{uuid}",
|
||||
pool_uuid: uuid,
|
||||
reason: :stale
|
||||
)
|
||||
end)
|
||||
|
||||
{:ok, length(stale_uuids)}
|
||||
end
|
||||
|
||||
@doc """
|
||||
Returns all pool states currently stored in ETS.
|
||||
|
||||
Useful for debugging and monitoring.
|
||||
|
||||
## Examples
|
||||
|
||||
iex> MapPoolState.list_all_states()
|
||||
[
|
||||
{"pool-123", [1, 2, 3], 1699564800},
|
||||
{"pool-456", [4, 5], 1699564900}
|
||||
]
|
||||
"""
|
||||
@spec list_all_states() :: [{String.t(), [integer()], integer()}]
|
||||
def list_all_states do
|
||||
:ets.tab2list(@table_name)
|
||||
end
|
||||
|
||||
@doc """
|
||||
Returns the count of pool states currently stored in ETS.
|
||||
|
||||
## Examples
|
||||
|
||||
iex> MapPoolState.count_states()
|
||||
5
|
||||
"""
|
||||
@spec count_states() :: non_neg_integer()
|
||||
def count_states do
|
||||
:ets.info(@table_name, :size)
|
||||
end
|
||||
end
|
||||
@@ -2,6 +2,8 @@ defmodule WandererApp.Map.MapPoolSupervisor do
|
||||
@moduledoc false
|
||||
use Supervisor
|
||||
|
||||
alias WandererApp.Map.MapPoolState
|
||||
|
||||
@name __MODULE__
|
||||
@registry :map_pool_registry
|
||||
@unique_registry :unique_map_pool_registry
|
||||
@@ -11,10 +13,15 @@ defmodule WandererApp.Map.MapPoolSupervisor do
|
||||
end
|
||||
|
||||
def init(_args) do
|
||||
# Initialize ETS table for MapPool state persistence
|
||||
# This table survives individual MapPool crashes but is lost on node restart
|
||||
MapPoolState.init_table()
|
||||
|
||||
children = [
|
||||
{Registry, [keys: :unique, name: @unique_registry]},
|
||||
{Registry, [keys: :duplicate, name: @registry]},
|
||||
{WandererApp.Map.MapPoolDynamicSupervisor, []}
|
||||
{WandererApp.Map.MapPoolDynamicSupervisor, []},
|
||||
{WandererApp.Map.Reconciler, []}
|
||||
]
|
||||
|
||||
Supervisor.init(children, strategy: :rest_for_one, max_restarts: 10)
|
||||
|
||||
280
lib/wanderer_app/map/map_reconciler.ex
Normal file
280
lib/wanderer_app/map/map_reconciler.ex
Normal file
@@ -0,0 +1,280 @@
|
||||
defmodule WandererApp.Map.Reconciler do
|
||||
@moduledoc """
|
||||
Periodically reconciles map state across different stores (Cache, Registry, GenServer state)
|
||||
to detect and fix inconsistencies that may prevent map servers from restarting.
|
||||
"""
|
||||
use GenServer
|
||||
|
||||
require Logger
|
||||
|
||||
@cache :map_pool_cache
|
||||
@registry :map_pool_registry
|
||||
@unique_registry :unique_map_pool_registry
|
||||
@reconciliation_interval :timer.minutes(5)
|
||||
|
||||
def start_link(_opts) do
|
||||
GenServer.start_link(__MODULE__, [], name: __MODULE__)
|
||||
end
|
||||
|
||||
@impl true
|
||||
def init(_opts) do
|
||||
Logger.info("Starting Map Reconciler")
|
||||
schedule_reconciliation()
|
||||
{:ok, %{}}
|
||||
end
|
||||
|
||||
@impl true
|
||||
def handle_info(:reconcile, state) do
|
||||
schedule_reconciliation()
|
||||
|
||||
try do
|
||||
reconcile_state()
|
||||
rescue
|
||||
e ->
|
||||
Logger.error("""
|
||||
[Map Reconciler] reconciliation error: #{Exception.message(e)}
|
||||
#{Exception.format_stacktrace(__STACKTRACE__)}
|
||||
""")
|
||||
end
|
||||
|
||||
{:noreply, state}
|
||||
end
|
||||
|
||||
@doc """
|
||||
Manually trigger a reconciliation (useful for testing or manual cleanup)
|
||||
"""
|
||||
def trigger_reconciliation do
|
||||
GenServer.cast(__MODULE__, :reconcile_now)
|
||||
end
|
||||
|
||||
@impl true
|
||||
def handle_cast(:reconcile_now, state) do
|
||||
try do
|
||||
reconcile_state()
|
||||
rescue
|
||||
e ->
|
||||
Logger.error("""
|
||||
[Map Reconciler] manual reconciliation error: #{Exception.message(e)}
|
||||
#{Exception.format_stacktrace(__STACKTRACE__)}
|
||||
""")
|
||||
end
|
||||
|
||||
{:noreply, state}
|
||||
end
|
||||
|
||||
defp schedule_reconciliation do
|
||||
Process.send_after(self(), :reconcile, @reconciliation_interval)
|
||||
end
|
||||
|
||||
defp reconcile_state do
|
||||
Logger.debug("[Map Reconciler] Starting state reconciliation")
|
||||
|
||||
# Get started_maps from cache
|
||||
{:ok, started_maps} = WandererApp.Cache.lookup("started_maps", [])
|
||||
|
||||
# Get all maps from registries
|
||||
registry_maps = get_all_registry_maps()
|
||||
|
||||
# Detect zombie maps (in started_maps but not in any registry)
|
||||
zombie_maps = started_maps -- registry_maps
|
||||
# Detect orphan maps (in registry but not in started_maps)
|
||||
orphan_maps = registry_maps -- started_maps
|
||||
|
||||
# Detect cache inconsistencies (map_pool_cache pointing to wrong or non-existent pools)
|
||||
cache_inconsistencies = find_cache_inconsistencies(registry_maps)
|
||||
|
||||
stats = %{
|
||||
total_started_maps: length(started_maps),
|
||||
total_registry_maps: length(registry_maps),
|
||||
zombie_maps: length(zombie_maps),
|
||||
orphan_maps: length(orphan_maps),
|
||||
cache_inconsistencies: length(cache_inconsistencies)
|
||||
}
|
||||
|
||||
Logger.info("[Map Reconciler] Reconciliation stats: #{inspect(stats)}")
|
||||
|
||||
# Emit telemetry
|
||||
:telemetry.execute(
|
||||
[:wanderer_app, :map, :reconciliation],
|
||||
stats,
|
||||
%{}
|
||||
)
|
||||
|
||||
# Clean up zombie maps
|
||||
cleanup_zombie_maps(zombie_maps)
|
||||
|
||||
# Fix orphan maps
|
||||
fix_orphan_maps(orphan_maps)
|
||||
|
||||
# Fix cache inconsistencies
|
||||
fix_cache_inconsistencies(cache_inconsistencies)
|
||||
|
||||
Logger.debug("[Map Reconciler] State reconciliation completed")
|
||||
end
|
||||
|
||||
defp get_all_registry_maps do
|
||||
case Registry.lookup(@registry, WandererApp.Map.MapPool) do
|
||||
[] ->
|
||||
[]
|
||||
|
||||
pools ->
|
||||
pools
|
||||
|> Enum.flat_map(fn {_pid, uuid} ->
|
||||
case Registry.lookup(
|
||||
@unique_registry,
|
||||
Module.concat(WandererApp.Map.MapPool, uuid)
|
||||
) do
|
||||
[{_pool_pid, map_ids}] -> map_ids
|
||||
_ -> []
|
||||
end
|
||||
end)
|
||||
|> Enum.uniq()
|
||||
end
|
||||
end
|
||||
|
||||
defp find_cache_inconsistencies(registry_maps) do
|
||||
registry_maps
|
||||
|> Enum.filter(fn map_id ->
|
||||
case Cachex.get(@cache, map_id) do
|
||||
{:ok, nil} ->
|
||||
# Map in registry but not in cache
|
||||
true
|
||||
|
||||
{:ok, pool_uuid} ->
|
||||
# Check if the pool_uuid actually exists in registry
|
||||
case Registry.lookup(
|
||||
@unique_registry,
|
||||
Module.concat(WandererApp.Map.MapPool, pool_uuid)
|
||||
) do
|
||||
[] ->
|
||||
# Cache points to non-existent pool
|
||||
true
|
||||
|
||||
[{_pool_pid, map_ids}] ->
|
||||
# Check if this map is actually in the pool's map_ids
|
||||
map_id not in map_ids
|
||||
|
||||
_ ->
|
||||
false
|
||||
end
|
||||
|
||||
{:error, _} ->
|
||||
true
|
||||
end
|
||||
end)
|
||||
end
|
||||
|
||||
defp cleanup_zombie_maps([]), do: :ok
|
||||
|
||||
defp cleanup_zombie_maps(zombie_maps) do
|
||||
Logger.warning("[Map Reconciler] Found #{length(zombie_maps)} zombie maps: #{inspect(zombie_maps)}")
|
||||
|
||||
Enum.each(zombie_maps, fn map_id ->
|
||||
Logger.info("[Map Reconciler] Cleaning up zombie map: #{map_id}")
|
||||
|
||||
# Remove from started_maps cache
|
||||
WandererApp.Cache.insert_or_update(
|
||||
"started_maps",
|
||||
[],
|
||||
fn started_maps ->
|
||||
started_maps |> Enum.reject(fn started_map_id -> started_map_id == map_id end)
|
||||
end
|
||||
)
|
||||
|
||||
# Clean up any stale map_pool_cache entries
|
||||
Cachex.del(@cache, map_id)
|
||||
|
||||
# Clean up map-specific caches
|
||||
WandererApp.Cache.delete("map_#{map_id}:started")
|
||||
WandererApp.Cache.delete("map_characters-#{map_id}")
|
||||
WandererApp.Map.CacheRTree.clear_tree("rtree_#{map_id}")
|
||||
WandererApp.Map.delete_map_state(map_id)
|
||||
|
||||
:telemetry.execute(
|
||||
[:wanderer_app, :map, :reconciliation, :zombie_cleanup],
|
||||
%{count: 1},
|
||||
%{map_id: map_id}
|
||||
)
|
||||
end)
|
||||
end
|
||||
|
||||
defp fix_orphan_maps([]), do: :ok
|
||||
|
||||
defp fix_orphan_maps(orphan_maps) do
|
||||
Logger.warning("[Map Reconciler] Found #{length(orphan_maps)} orphan maps: #{inspect(orphan_maps)}")
|
||||
|
||||
Enum.each(orphan_maps, fn map_id ->
|
||||
Logger.info("[Map Reconciler] Fixing orphan map: #{map_id}")
|
||||
|
||||
# Add to started_maps cache
|
||||
WandererApp.Cache.insert_or_update(
|
||||
"started_maps",
|
||||
[map_id],
|
||||
fn existing ->
|
||||
[map_id | existing] |> Enum.uniq()
|
||||
end
|
||||
)
|
||||
|
||||
:telemetry.execute(
|
||||
[:wanderer_app, :map, :reconciliation, :orphan_fixed],
|
||||
%{count: 1},
|
||||
%{map_id: map_id}
|
||||
)
|
||||
end)
|
||||
end
|
||||
|
||||
defp fix_cache_inconsistencies([]), do: :ok
|
||||
|
||||
defp fix_cache_inconsistencies(inconsistent_maps) do
|
||||
Logger.warning(
|
||||
"[Map Reconciler] Found #{length(inconsistent_maps)} cache inconsistencies: #{inspect(inconsistent_maps)}"
|
||||
)
|
||||
|
||||
Enum.each(inconsistent_maps, fn map_id ->
|
||||
Logger.info("[Map Reconciler] Fixing cache inconsistency for map: #{map_id}")
|
||||
|
||||
# Find the correct pool for this map
|
||||
case find_pool_for_map(map_id) do
|
||||
{:ok, pool_uuid} ->
|
||||
Logger.info("[Map Reconciler] Updating cache: #{map_id} -> #{pool_uuid}")
|
||||
Cachex.put(@cache, map_id, pool_uuid)
|
||||
|
||||
:telemetry.execute(
|
||||
[:wanderer_app, :map, :reconciliation, :cache_fixed],
|
||||
%{count: 1},
|
||||
%{map_id: map_id, pool_uuid: pool_uuid}
|
||||
)
|
||||
|
||||
:error ->
|
||||
Logger.warning("[Map Reconciler] Could not find pool for map #{map_id}, removing from cache")
|
||||
Cachex.del(@cache, map_id)
|
||||
end
|
||||
end)
|
||||
end
|
||||
|
||||
defp find_pool_for_map(map_id) do
|
||||
case Registry.lookup(@registry, WandererApp.Map.MapPool) do
|
||||
[] ->
|
||||
:error
|
||||
|
||||
pools ->
|
||||
pools
|
||||
|> Enum.find_value(:error, fn {_pid, uuid} ->
|
||||
case Registry.lookup(
|
||||
@unique_registry,
|
||||
Module.concat(WandererApp.Map.MapPool, uuid)
|
||||
) do
|
||||
[{_pool_pid, map_ids}] ->
|
||||
if map_id in map_ids do
|
||||
{:ok, uuid}
|
||||
else
|
||||
nil
|
||||
end
|
||||
|
||||
_ ->
|
||||
nil
|
||||
end
|
||||
end)
|
||||
end
|
||||
end
|
||||
end
|
||||
@@ -401,7 +401,7 @@ defmodule WandererApp.Map.Server.ConnectionsImpl do
|
||||
)
|
||||
else
|
||||
error ->
|
||||
Logger.error("Failed to update_linked_signature_time_status: #{inspect(error)}")
|
||||
Logger.warning("Failed to update_linked_signature_time_status: #{inspect(error)}")
|
||||
end
|
||||
end
|
||||
|
||||
@@ -537,6 +537,12 @@ defmodule WandererApp.Map.Server.ConnectionsImpl do
|
||||
|
||||
Impl.broadcast!(map_id, :add_connection, connection)
|
||||
|
||||
Impl.broadcast!(map_id, :maybe_link_signature, %{
|
||||
character_id: character_id,
|
||||
solar_system_source: old_location.solar_system_id,
|
||||
solar_system_target: location.solar_system_id
|
||||
})
|
||||
|
||||
# ADDITIVE: Also broadcast to external event system (webhooks/WebSocket)
|
||||
WandererApp.ExternalEvents.broadcast(map_id, :connection_added, %{
|
||||
connection_id: connection.id,
|
||||
@@ -548,19 +554,12 @@ defmodule WandererApp.Map.Server.ConnectionsImpl do
|
||||
time_status: connection.time_status
|
||||
})
|
||||
|
||||
{:ok, _} =
|
||||
WandererApp.User.ActivityTracker.track_map_event(:map_connection_added, %{
|
||||
character_id: character_id,
|
||||
user_id: character.user_id,
|
||||
map_id: map_id,
|
||||
solar_system_source_id: old_location.solar_system_id,
|
||||
solar_system_target_id: location.solar_system_id
|
||||
})
|
||||
|
||||
Impl.broadcast!(map_id, :maybe_link_signature, %{
|
||||
WandererApp.User.ActivityTracker.track_map_event(:map_connection_added, %{
|
||||
character_id: character_id,
|
||||
solar_system_source: old_location.solar_system_id,
|
||||
solar_system_target: location.solar_system_id
|
||||
user_id: character.user_id,
|
||||
map_id: map_id,
|
||||
solar_system_source_id: old_location.solar_system_id,
|
||||
solar_system_target_id: location.solar_system_id
|
||||
})
|
||||
|
||||
:ok
|
||||
|
||||
@@ -25,6 +25,7 @@ defmodule WandererApp.Map.Server.Impl do
|
||||
]
|
||||
|
||||
@pubsub_client Application.compile_env(:wanderer_app, :pubsub_client)
|
||||
@ddrt Application.compile_env(:wanderer_app, :ddrt)
|
||||
|
||||
@connections_cleanup_timeout :timer.minutes(1)
|
||||
|
||||
@@ -45,19 +46,77 @@ defmodule WandererApp.Map.Server.Impl do
|
||||
}
|
||||
|> new()
|
||||
|
||||
with {:ok, map} <-
|
||||
WandererApp.MapRepo.get(map_id, [
|
||||
:owner,
|
||||
:characters,
|
||||
acls: [
|
||||
:owner_id,
|
||||
members: [:role, :eve_character_id, :eve_corporation_id, :eve_alliance_id]
|
||||
]
|
||||
]),
|
||||
{:ok, systems} <- WandererApp.MapSystemRepo.get_visible_by_map(map_id),
|
||||
{:ok, connections} <- WandererApp.MapConnectionRepo.get_by_map(map_id),
|
||||
{:ok, subscription_settings} <-
|
||||
WandererApp.Map.SubscriptionManager.get_active_map_subscription(map_id) do
|
||||
# Parallelize database queries for faster initialization
|
||||
start_time = System.monotonic_time(:millisecond)
|
||||
|
||||
tasks = [
|
||||
Task.async(fn ->
|
||||
{:map,
|
||||
WandererApp.MapRepo.get(map_id, [
|
||||
:owner,
|
||||
:characters,
|
||||
acls: [
|
||||
:owner_id,
|
||||
members: [:role, :eve_character_id, :eve_corporation_id, :eve_alliance_id]
|
||||
]
|
||||
])}
|
||||
end),
|
||||
Task.async(fn ->
|
||||
{:systems, WandererApp.MapSystemRepo.get_visible_by_map(map_id)}
|
||||
end),
|
||||
Task.async(fn ->
|
||||
{:connections, WandererApp.MapConnectionRepo.get_by_map(map_id)}
|
||||
end),
|
||||
Task.async(fn ->
|
||||
{:subscription, WandererApp.Map.SubscriptionManager.get_active_map_subscription(map_id)}
|
||||
end)
|
||||
]
|
||||
|
||||
results = Task.await_many(tasks, :timer.seconds(15))
|
||||
|
||||
duration = System.monotonic_time(:millisecond) - start_time
|
||||
|
||||
# Emit telemetry for slow initializations
|
||||
if duration > 5_000 do
|
||||
Logger.warning("[Map Server] Slow map state initialization: #{map_id} took #{duration}ms")
|
||||
|
||||
:telemetry.execute(
|
||||
[:wanderer_app, :map, :slow_init],
|
||||
%{duration_ms: duration},
|
||||
%{map_id: map_id}
|
||||
)
|
||||
end
|
||||
|
||||
# Extract results
|
||||
map_result =
|
||||
Enum.find_value(results, fn
|
||||
{:map, result} -> result
|
||||
_ -> nil
|
||||
end)
|
||||
|
||||
systems_result =
|
||||
Enum.find_value(results, fn
|
||||
{:systems, result} -> result
|
||||
_ -> nil
|
||||
end)
|
||||
|
||||
connections_result =
|
||||
Enum.find_value(results, fn
|
||||
{:connections, result} -> result
|
||||
_ -> nil
|
||||
end)
|
||||
|
||||
subscription_result =
|
||||
Enum.find_value(results, fn
|
||||
{:subscription, result} -> result
|
||||
_ -> nil
|
||||
end)
|
||||
|
||||
# Process results
|
||||
with {:ok, map} <- map_result,
|
||||
{:ok, systems} <- systems_result,
|
||||
{:ok, connections} <- connections_result,
|
||||
{:ok, subscription_settings} <- subscription_result do
|
||||
initial_state
|
||||
|> init_map(
|
||||
map,
|
||||
@@ -88,7 +147,6 @@ defmodule WandererApp.Map.Server.Impl do
|
||||
"maps:#{map_id}"
|
||||
)
|
||||
|
||||
WandererApp.Map.CacheRTree.init_tree("rtree_#{map_id}", %{width: 150, verbose: false})
|
||||
Process.send_after(self(), {:update_characters, map_id}, @update_characters_timeout)
|
||||
|
||||
Process.send_after(
|
||||
@@ -358,6 +416,13 @@ defmodule WandererApp.Map.Server.Impl do
|
||||
update_options(map_id, options)
|
||||
end
|
||||
|
||||
def handle_event(:map_deleted) do
|
||||
# Map has been deleted - this event is handled by MapPool to stop the server
|
||||
# and by MapLive to redirect users. Nothing to do here.
|
||||
Logger.debug("Map deletion event received, will be handled by MapPool")
|
||||
:ok
|
||||
end
|
||||
|
||||
def handle_event({ref, _result}) when is_reference(ref) do
|
||||
Process.demonitor(ref, [:flush])
|
||||
end
|
||||
@@ -452,6 +517,8 @@ defmodule WandererApp.Map.Server.Impl do
|
||||
) do
|
||||
{:ok, options} = WandererApp.MapRepo.options_to_form_data(initial_map)
|
||||
|
||||
@ddrt.init_tree("rtree_#{map_id}", %{width: 150, verbose: false})
|
||||
|
||||
map =
|
||||
initial_map
|
||||
|> WandererApp.Map.new()
|
||||
|
||||
@@ -521,6 +521,10 @@ defmodule WandererApp.Map.Server.SystemsImpl do
|
||||
|
||||
:ok
|
||||
|
||||
{:error, error} ->
|
||||
Logger.warning("Failed to create system: #{inspect(error, pretty: true)}")
|
||||
:ok
|
||||
|
||||
error ->
|
||||
Logger.warning("Failed to create system: #{inspect(error, pretty: true)}")
|
||||
:ok
|
||||
@@ -642,13 +646,12 @@ defmodule WandererApp.Map.Server.SystemsImpl do
|
||||
position_y: system.position_y
|
||||
})
|
||||
|
||||
{:ok, _} =
|
||||
WandererApp.User.ActivityTracker.track_map_event(:system_added, %{
|
||||
character_id: character_id,
|
||||
user_id: user_id,
|
||||
map_id: map_id,
|
||||
solar_system_id: solar_system_id
|
||||
})
|
||||
WandererApp.User.ActivityTracker.track_map_event(:system_added, %{
|
||||
character_id: character_id,
|
||||
user_id: user_id,
|
||||
map_id: map_id,
|
||||
solar_system_id: solar_system_id
|
||||
})
|
||||
end
|
||||
|
||||
defp maybe_update_extra_info(system, nil), do: system
|
||||
@@ -805,6 +808,10 @@ defmodule WandererApp.Map.Server.SystemsImpl do
|
||||
|
||||
update_map_system_last_activity(map_id, updated_system)
|
||||
else
|
||||
{:error, error} ->
|
||||
Logger.error("Failed to update system: #{inspect(error, pretty: true)}")
|
||||
:ok
|
||||
|
||||
error ->
|
||||
Logger.error("Failed to update system: #{inspect(error, pretty: true)}")
|
||||
:ok
|
||||
|
||||
@@ -3,11 +3,25 @@ defmodule WandererApp.MapPingsRepo do
|
||||
|
||||
require Logger
|
||||
|
||||
def get_by_id(ping_id),
|
||||
do: WandererApp.Api.MapPing.by_id!(ping_id) |> Ash.load([:system])
|
||||
def get_by_id(ping_id) do
|
||||
case WandererApp.Api.MapPing.by_id(ping_id) do
|
||||
{:ok, ping} ->
|
||||
ping |> Ash.load([:system])
|
||||
|
||||
def get_by_map(map_id),
|
||||
do: WandererApp.Api.MapPing.by_map!(%{map_id: map_id}) |> Ash.load([:character, :system])
|
||||
error ->
|
||||
error
|
||||
end
|
||||
end
|
||||
|
||||
def get_by_map(map_id) do
|
||||
case WandererApp.Api.MapPing.by_map(%{map_id: map_id}) do
|
||||
{:ok, ping} ->
|
||||
ping |> Ash.load([:character, :system])
|
||||
|
||||
error ->
|
||||
error
|
||||
end
|
||||
end
|
||||
|
||||
def get_by_map_and_system!(map_id, system_id),
|
||||
do: WandererApp.Api.MapPing.by_map_and_system!(%{map_id: map_id, system_id: system_id})
|
||||
|
||||
@@ -11,7 +11,9 @@ defmodule WandererApp.Server.ServerStatusTracker do
|
||||
:server_version,
|
||||
:start_time,
|
||||
:vip,
|
||||
:retries
|
||||
:retries,
|
||||
:in_forced_downtime,
|
||||
:downtime_notified
|
||||
]
|
||||
|
||||
@retries_count 3
|
||||
@@ -21,9 +23,17 @@ defmodule WandererApp.Server.ServerStatusTracker do
|
||||
retries: @retries_count,
|
||||
server_version: "0",
|
||||
start_time: "0",
|
||||
vip: true
|
||||
vip: true,
|
||||
in_forced_downtime: false,
|
||||
downtime_notified: false
|
||||
}
|
||||
|
||||
# EVE Online daily downtime period (UTC/GMT)
|
||||
@downtime_start_hour 10
|
||||
@downtime_start_minute 58
|
||||
@downtime_end_hour 11
|
||||
@downtime_end_minute 2
|
||||
|
||||
@refresh_interval :timer.minutes(1)
|
||||
|
||||
@logger Application.compile_env(:wanderer_app, :logger)
|
||||
@@ -57,13 +67,51 @@ defmodule WandererApp.Server.ServerStatusTracker do
|
||||
def handle_info(
|
||||
:refresh_status,
|
||||
%{
|
||||
retries: retries
|
||||
retries: retries,
|
||||
in_forced_downtime: was_in_downtime
|
||||
} = state
|
||||
) do
|
||||
Process.send_after(self(), :refresh_status, @refresh_interval)
|
||||
Task.async(fn -> get_server_status(retries) end)
|
||||
|
||||
{:noreply, state}
|
||||
in_downtime = in_forced_downtime?()
|
||||
|
||||
cond do
|
||||
# Entering downtime period - broadcast offline status immediately
|
||||
in_downtime and not was_in_downtime ->
|
||||
@logger.info("#{__MODULE__} entering forced downtime period (10:58-11:02 GMT)")
|
||||
|
||||
downtime_status = %{
|
||||
players: 0,
|
||||
server_version: "downtime",
|
||||
start_time: DateTime.utc_now() |> DateTime.to_iso8601(),
|
||||
vip: true
|
||||
}
|
||||
|
||||
Phoenix.PubSub.broadcast(
|
||||
WandererApp.PubSub,
|
||||
"server_status",
|
||||
{:server_status, downtime_status}
|
||||
)
|
||||
|
||||
{:noreply,
|
||||
%{state | in_forced_downtime: true, downtime_notified: true}
|
||||
|> Map.merge(downtime_status)}
|
||||
|
||||
# Currently in downtime - skip API call
|
||||
in_downtime ->
|
||||
{:noreply, state}
|
||||
|
||||
# Exiting downtime period - resume normal operations
|
||||
not in_downtime and was_in_downtime ->
|
||||
@logger.info("#{__MODULE__} exiting forced downtime period, resuming normal operations")
|
||||
Task.async(fn -> get_server_status(retries) end)
|
||||
{:noreply, %{state | in_forced_downtime: false, downtime_notified: false}}
|
||||
|
||||
# Normal operation
|
||||
true ->
|
||||
Task.async(fn -> get_server_status(retries) end)
|
||||
{:noreply, state}
|
||||
end
|
||||
end
|
||||
|
||||
@impl true
|
||||
@@ -155,4 +203,19 @@ defmodule WandererApp.Server.ServerStatusTracker do
|
||||
vip: false
|
||||
}
|
||||
end
|
||||
|
||||
# Checks if the current UTC time falls within the forced downtime period (10:58-11:02 GMT).
|
||||
defp in_forced_downtime? do
|
||||
now = DateTime.utc_now()
|
||||
current_hour = now.hour
|
||||
current_minute = now.minute
|
||||
|
||||
# Convert times to minutes since midnight for easier comparison
|
||||
current_time_minutes = current_hour * 60 + current_minute
|
||||
downtime_start_minutes = @downtime_start_hour * 60 + @downtime_start_minute
|
||||
downtime_end_minutes = @downtime_end_hour * 60 + @downtime_end_minute
|
||||
|
||||
current_time_minutes >= downtime_start_minutes and
|
||||
current_time_minutes < downtime_end_minutes
|
||||
end
|
||||
end
|
||||
|
||||
@@ -1,16 +1,57 @@
|
||||
defmodule WandererApp.User.ActivityTracker do
|
||||
@moduledoc false
|
||||
@moduledoc """
|
||||
Activity tracking wrapper that ensures audit logging never crashes application logic.
|
||||
|
||||
Activity tracking is best-effort and errors are logged but not propagated to callers.
|
||||
This prevents race conditions (e.g., duplicate activity records) from affecting
|
||||
critical business operations like character tracking or connection management.
|
||||
"""
|
||||
require Logger
|
||||
|
||||
def track_map_event(
|
||||
event_type,
|
||||
metadata
|
||||
),
|
||||
do: WandererApp.Map.Audit.track_map_event(event_type, metadata)
|
||||
@doc """
|
||||
Track a map-related event. Always returns `{:ok, result}` even on error.
|
||||
|
||||
def track_acl_event(
|
||||
event_type,
|
||||
metadata
|
||||
),
|
||||
do: WandererApp.Map.Audit.track_acl_event(event_type, metadata)
|
||||
Errors (such as unique constraint violations from concurrent operations)
|
||||
are logged but do not propagate to prevent crashing critical application logic.
|
||||
"""
|
||||
def track_map_event(event_type, metadata) do
|
||||
case WandererApp.Map.Audit.track_map_event(event_type, metadata) do
|
||||
{:ok, result} ->
|
||||
{:ok, result}
|
||||
|
||||
{:error, error} ->
|
||||
Logger.warning("Failed to track map event (non-critical)",
|
||||
event_type: event_type,
|
||||
map_id: metadata[:map_id],
|
||||
error: inspect(error),
|
||||
reason: :best_effort_tracking
|
||||
)
|
||||
|
||||
# Return success to prevent crashes - activity tracking is best-effort
|
||||
{:ok, nil}
|
||||
end
|
||||
end
|
||||
|
||||
@doc """
|
||||
Track an ACL-related event. Always returns `{:ok, result}` even on error.
|
||||
|
||||
Errors are logged but do not propagate to prevent crashing critical application logic.
|
||||
"""
|
||||
def track_acl_event(event_type, metadata) do
|
||||
case WandererApp.Map.Audit.track_acl_event(event_type, metadata) do
|
||||
{:ok, result} ->
|
||||
{:ok, result}
|
||||
|
||||
{:error, error} ->
|
||||
Logger.warning("Failed to track ACL event (non-critical)",
|
||||
event_type: event_type,
|
||||
acl_id: metadata[:acl_id],
|
||||
error: inspect(error),
|
||||
reason: :best_effort_tracking
|
||||
)
|
||||
|
||||
# Return success to prevent crashes - activity tracking is best-effort
|
||||
{:ok, nil}
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
@@ -59,14 +59,13 @@ defmodule WandererAppWeb.MapConnectionsEventHandler do
|
||||
character_id: main_character_id
|
||||
})
|
||||
|
||||
{:ok, _} =
|
||||
WandererApp.User.ActivityTracker.track_map_event(:map_connection_added, %{
|
||||
character_id: main_character_id,
|
||||
user_id: current_user_id,
|
||||
map_id: map_id,
|
||||
solar_system_source_id: "#{solar_system_source_id}" |> String.to_integer(),
|
||||
solar_system_target_id: "#{solar_system_target_id}" |> String.to_integer()
|
||||
})
|
||||
WandererApp.User.ActivityTracker.track_map_event(:map_connection_added, %{
|
||||
character_id: main_character_id,
|
||||
user_id: current_user_id,
|
||||
map_id: map_id,
|
||||
solar_system_source_id: "#{solar_system_source_id}" |> String.to_integer(),
|
||||
solar_system_target_id: "#{solar_system_target_id}" |> String.to_integer()
|
||||
})
|
||||
|
||||
{:noreply, socket}
|
||||
end
|
||||
@@ -149,7 +148,6 @@ defmodule WandererAppWeb.MapConnectionsEventHandler do
|
||||
end
|
||||
end
|
||||
|
||||
{:ok, _} =
|
||||
WandererApp.User.ActivityTracker.track_map_event(:map_connection_removed, %{
|
||||
character_id: main_character_id,
|
||||
user_id: current_user_id,
|
||||
@@ -202,7 +200,6 @@ defmodule WandererAppWeb.MapConnectionsEventHandler do
|
||||
_ -> nil
|
||||
end
|
||||
|
||||
{:ok, _} =
|
||||
WandererApp.User.ActivityTracker.track_map_event(:map_connection_updated, %{
|
||||
character_id: main_character_id,
|
||||
user_id: current_user_id,
|
||||
|
||||
@@ -21,59 +21,85 @@ defmodule WandererAppWeb.MapCoreEventHandler do
|
||||
:refresh_permissions,
|
||||
%{assigns: %{current_user: current_user, map_slug: map_slug}} = socket
|
||||
) do
|
||||
{:ok, %{id: map_id, user_permissions: user_permissions, owner_id: owner_id}} =
|
||||
map_slug
|
||||
|> WandererApp.Api.Map.get_map_by_slug!()
|
||||
|> Ash.load(:user_permissions, actor: current_user)
|
||||
try do
|
||||
{:ok, %{id: map_id, user_permissions: user_permissions, owner_id: owner_id}} =
|
||||
map_slug
|
||||
|> WandererApp.Api.Map.get_map_by_slug!()
|
||||
|> Ash.load(:user_permissions, actor: current_user)
|
||||
|
||||
user_permissions =
|
||||
WandererApp.Permissions.get_map_permissions(
|
||||
user_permissions,
|
||||
owner_id,
|
||||
current_user.characters |> Enum.map(& &1.id)
|
||||
)
|
||||
user_permissions =
|
||||
WandererApp.Permissions.get_map_permissions(
|
||||
user_permissions,
|
||||
owner_id,
|
||||
current_user.characters |> Enum.map(& &1.id)
|
||||
)
|
||||
|
||||
case user_permissions do
|
||||
%{view_system: false} ->
|
||||
socket
|
||||
|> Phoenix.LiveView.put_flash(:error, "Your access to the map have been revoked.")
|
||||
|> Phoenix.LiveView.push_navigate(to: ~p"/maps")
|
||||
case user_permissions do
|
||||
%{view_system: false} ->
|
||||
socket
|
||||
|> Phoenix.LiveView.put_flash(:error, "Your access to the map have been revoked.")
|
||||
|> Phoenix.LiveView.push_navigate(to: ~p"/maps")
|
||||
|
||||
%{track_character: track_character} ->
|
||||
{:ok, map_characters} =
|
||||
case WandererApp.MapCharacterSettingsRepo.get_tracked_by_map_filtered(
|
||||
map_id,
|
||||
current_user.characters |> Enum.map(& &1.id)
|
||||
) do
|
||||
{:ok, settings} ->
|
||||
{:ok,
|
||||
settings
|
||||
|> Enum.map(fn s -> s |> Ash.load!(:character) |> Map.get(:character) end)}
|
||||
%{track_character: track_character} ->
|
||||
{:ok, map_characters} =
|
||||
case WandererApp.MapCharacterSettingsRepo.get_tracked_by_map_filtered(
|
||||
map_id,
|
||||
current_user.characters |> Enum.map(& &1.id)
|
||||
) do
|
||||
{:ok, settings} ->
|
||||
{:ok,
|
||||
settings
|
||||
|> Enum.map(fn s -> s |> Ash.load!(:character) |> Map.get(:character) end)}
|
||||
|
||||
_ ->
|
||||
{:ok, []}
|
||||
end
|
||||
|
||||
case track_character do
|
||||
false ->
|
||||
:ok = WandererApp.Character.TrackingUtils.untrack(map_characters, map_id, self())
|
||||
|
||||
_ ->
|
||||
{:ok, []}
|
||||
:ok =
|
||||
WandererApp.Character.TrackingUtils.track(
|
||||
map_characters,
|
||||
map_id,
|
||||
true,
|
||||
self()
|
||||
)
|
||||
end
|
||||
|
||||
case track_character do
|
||||
false ->
|
||||
:ok = WandererApp.Character.TrackingUtils.untrack(map_characters, map_id, self())
|
||||
socket
|
||||
|> assign(user_permissions: user_permissions)
|
||||
|> MapEventHandler.push_map_event(
|
||||
"user_permissions",
|
||||
user_permissions
|
||||
)
|
||||
end
|
||||
rescue
|
||||
error in Ash.Error.Invalid.MultipleResults ->
|
||||
Logger.error("Multiple maps found with slug '#{map_slug}' during refresh_permissions",
|
||||
slug: map_slug,
|
||||
error: inspect(error)
|
||||
)
|
||||
|
||||
_ ->
|
||||
:ok =
|
||||
WandererApp.Character.TrackingUtils.track(
|
||||
map_characters,
|
||||
map_id,
|
||||
true,
|
||||
self()
|
||||
)
|
||||
end
|
||||
# Emit telemetry for monitoring
|
||||
:telemetry.execute(
|
||||
[:wanderer_app, :map, :duplicate_slug_detected],
|
||||
%{count: 1},
|
||||
%{slug: map_slug, operation: :refresh_permissions}
|
||||
)
|
||||
|
||||
# Return socket unchanged - permissions won't refresh but won't crash
|
||||
socket
|
||||
|
||||
error ->
|
||||
Logger.error("Error refreshing permissions for map slug '#{map_slug}'",
|
||||
slug: map_slug,
|
||||
error: inspect(error)
|
||||
)
|
||||
|
||||
socket
|
||||
|> assign(user_permissions: user_permissions)
|
||||
|> MapEventHandler.push_map_event(
|
||||
"user_permissions",
|
||||
user_permissions
|
||||
)
|
||||
end
|
||||
end
|
||||
|
||||
|
||||
@@ -165,13 +165,12 @@ defmodule WandererAppWeb.MapRoutesEventHandler do
|
||||
solar_system_id: solar_system_id
|
||||
})
|
||||
|
||||
{:ok, _} =
|
||||
WandererApp.User.ActivityTracker.track_map_event(:hub_added, %{
|
||||
character_id: main_character_id,
|
||||
user_id: current_user.id,
|
||||
map_id: map_id,
|
||||
solar_system_id: solar_system_id
|
||||
})
|
||||
WandererApp.User.ActivityTracker.track_map_event(:hub_added, %{
|
||||
character_id: main_character_id,
|
||||
user_id: current_user.id,
|
||||
map_id: map_id,
|
||||
solar_system_id: solar_system_id
|
||||
})
|
||||
|
||||
{:noreply, socket}
|
||||
else
|
||||
@@ -204,13 +203,12 @@ defmodule WandererAppWeb.MapRoutesEventHandler do
|
||||
solar_system_id: solar_system_id
|
||||
})
|
||||
|
||||
{:ok, _} =
|
||||
WandererApp.User.ActivityTracker.track_map_event(:hub_removed, %{
|
||||
character_id: main_character_id,
|
||||
user_id: current_user.id,
|
||||
map_id: map_id,
|
||||
solar_system_id: solar_system_id
|
||||
})
|
||||
WandererApp.User.ActivityTracker.track_map_event(:hub_removed, %{
|
||||
character_id: main_character_id,
|
||||
user_id: current_user.id,
|
||||
map_id: map_id,
|
||||
solar_system_id: solar_system_id
|
||||
})
|
||||
|
||||
{:noreply, socket}
|
||||
end
|
||||
|
||||
@@ -250,15 +250,14 @@ defmodule WandererAppWeb.MapSystemsEventHandler do
|
||||
|> Map.put_new(key_atom, value)
|
||||
])
|
||||
|
||||
{:ok, _} =
|
||||
WandererApp.User.ActivityTracker.track_map_event(:system_updated, %{
|
||||
character_id: main_character_id,
|
||||
user_id: current_user.id,
|
||||
map_id: map_id,
|
||||
solar_system_id: "#{solar_system_id}" |> String.to_integer(),
|
||||
key: key_atom,
|
||||
value: value
|
||||
})
|
||||
WandererApp.User.ActivityTracker.track_map_event(:system_updated, %{
|
||||
character_id: main_character_id,
|
||||
user_id: current_user.id,
|
||||
map_id: map_id,
|
||||
solar_system_id: "#{solar_system_id}" |> String.to_integer(),
|
||||
key: key_atom,
|
||||
value: value
|
||||
})
|
||||
end
|
||||
|
||||
{:noreply, socket}
|
||||
|
||||
@@ -74,6 +74,13 @@ defmodule WandererAppWeb.MapLive do
|
||||
"You don't have main character set, please update it in tracking settings (top right icon)."
|
||||
)}
|
||||
|
||||
def handle_info(:map_deleted, socket),
|
||||
do:
|
||||
{:noreply,
|
||||
socket
|
||||
|> put_flash(:info, "This map has been deleted.")
|
||||
|> push_navigate(to: ~p"/maps")}
|
||||
|
||||
def handle_info(:no_access, socket),
|
||||
do:
|
||||
{:noreply,
|
||||
|
||||
@@ -1,6 +1,8 @@
|
||||
defmodule WandererAppWeb.MapsLive do
|
||||
use WandererAppWeb, :live_view
|
||||
|
||||
alias Phoenix.LiveView.AsyncResult
|
||||
|
||||
require Logger
|
||||
|
||||
@pubsub_client Application.compile_env(:wanderer_app, :pubsub_client)
|
||||
@@ -275,17 +277,57 @@ defmodule WandererAppWeb.MapsLive do
|
||||
:telemetry.execute([:wanderer_app, :map, :created], %{count: 1})
|
||||
maybe_create_default_acl(form, new_map)
|
||||
|
||||
# Reload maps synchronously to avoid timing issues with flash messages
|
||||
{:ok, %{maps: maps}} = load_maps(current_user)
|
||||
|
||||
{:noreply,
|
||||
socket
|
||||
|> assign_async(:maps, fn ->
|
||||
load_maps(current_user)
|
||||
end)
|
||||
|> put_flash(
|
||||
:info,
|
||||
"Map '#{new_map.name}' created successfully with slug '#{new_map.slug}'"
|
||||
)
|
||||
|> assign(:maps, AsyncResult.ok(maps))
|
||||
|> push_patch(to: ~p"/maps")}
|
||||
|
||||
{:error, %Ash.Error.Invalid{errors: errors}} ->
|
||||
# Check for slug uniqueness constraint violation
|
||||
slug_error =
|
||||
Enum.find(errors, fn error ->
|
||||
case error do
|
||||
%{field: :slug} -> true
|
||||
%{message: message} when is_binary(message) -> String.contains?(message, "unique")
|
||||
_ -> false
|
||||
end
|
||||
end)
|
||||
|
||||
error_message =
|
||||
if slug_error do
|
||||
"A map with this name already exists. The system will automatically adjust the name if needed. Please try again."
|
||||
else
|
||||
errors
|
||||
|> Enum.map(fn error ->
|
||||
field = Map.get(error, :field, "field")
|
||||
message = Map.get(error, :message, "validation error")
|
||||
"#{field}: #{message}"
|
||||
end)
|
||||
|> Enum.join(", ")
|
||||
end
|
||||
|
||||
Logger.warning("Map creation failed",
|
||||
form: form,
|
||||
errors: inspect(errors),
|
||||
slug_error: slug_error != nil
|
||||
)
|
||||
|
||||
{:noreply,
|
||||
socket
|
||||
|> put_flash(:error, "Failed to create map: #{error_message}")
|
||||
|> assign(error: error_message)}
|
||||
|
||||
{:error, %{errors: errors}} ->
|
||||
error_message =
|
||||
errors
|
||||
|> Enum.map(fn %{field: _field} = error ->
|
||||
|> Enum.map(fn error ->
|
||||
"#{Map.get(error, :message, "Field validation error")}"
|
||||
end)
|
||||
|> Enum.join(", ")
|
||||
@@ -296,9 +338,14 @@ defmodule WandererAppWeb.MapsLive do
|
||||
|> assign(error: error_message)}
|
||||
|
||||
{:error, error} ->
|
||||
Logger.error("Unexpected error creating map",
|
||||
form: form,
|
||||
error: inspect(error)
|
||||
)
|
||||
|
||||
{:noreply,
|
||||
socket
|
||||
|> put_flash(:error, "Failed to create map")
|
||||
|> put_flash(:error, "Failed to create map. Please try again.")
|
||||
|> assign(error: error)}
|
||||
end
|
||||
end
|
||||
@@ -342,99 +389,156 @@ defmodule WandererAppWeb.MapsLive do
|
||||
%{"form" => form} = _params,
|
||||
%{assigns: %{map_slug: map_slug, current_user: current_user}} = socket
|
||||
) do
|
||||
{:ok, map} =
|
||||
map_slug
|
||||
|> WandererApp.Api.Map.get_map_by_slug!()
|
||||
|> Ash.load(:acls)
|
||||
case get_map_by_slug_safely(map_slug) do
|
||||
{:ok, map} ->
|
||||
# Successfully found the map, proceed with loading and updating
|
||||
{:ok, map_with_acls} = Ash.load(map, :acls)
|
||||
|
||||
scope =
|
||||
form
|
||||
|> Map.get("scope")
|
||||
|> case do
|
||||
"" -> "wormholes"
|
||||
scope -> scope
|
||||
end
|
||||
scope =
|
||||
form
|
||||
|> Map.get("scope")
|
||||
|> case do
|
||||
"" -> "wormholes"
|
||||
scope -> scope
|
||||
end
|
||||
|
||||
form =
|
||||
form
|
||||
|> Map.put("acls", form["acls"] || [])
|
||||
|> Map.put("scope", scope)
|
||||
|> Map.put(
|
||||
"only_tracked_characters",
|
||||
(form["only_tracked_characters"] || "false") |> String.to_existing_atom()
|
||||
)
|
||||
form =
|
||||
form
|
||||
|> Map.put("acls", form["acls"] || [])
|
||||
|> Map.put("scope", scope)
|
||||
|> Map.put(
|
||||
"only_tracked_characters",
|
||||
(form["only_tracked_characters"] || "false") |> String.to_existing_atom()
|
||||
)
|
||||
|
||||
map
|
||||
|> WandererApp.Api.Map.update(form)
|
||||
|> case do
|
||||
{:ok, _updated_map} ->
|
||||
{added_acls, removed_acls} = map.acls |> Enum.map(& &1.id) |> _get_acls_diff(form["acls"])
|
||||
map_with_acls
|
||||
|> WandererApp.Api.Map.update(form)
|
||||
|> case do
|
||||
{:ok, _updated_map} ->
|
||||
{added_acls, removed_acls} =
|
||||
map_with_acls.acls |> Enum.map(& &1.id) |> _get_acls_diff(form["acls"])
|
||||
|
||||
Phoenix.PubSub.broadcast(
|
||||
WandererApp.PubSub,
|
||||
"maps:#{map.id}",
|
||||
{:map_acl_updated, map.id, added_acls, removed_acls}
|
||||
)
|
||||
Phoenix.PubSub.broadcast(
|
||||
WandererApp.PubSub,
|
||||
"maps:#{map_with_acls.id}",
|
||||
{:map_acl_updated, map_with_acls.id, added_acls, removed_acls}
|
||||
)
|
||||
|
||||
{:ok, tracked_characters} =
|
||||
WandererApp.Maps.get_tracked_map_characters(map.id, current_user)
|
||||
{:ok, tracked_characters} =
|
||||
WandererApp.Maps.get_tracked_map_characters(map_with_acls.id, current_user)
|
||||
|
||||
first_tracked_character_id = Enum.map(tracked_characters, & &1.id) |> List.first()
|
||||
first_tracked_character_id = Enum.map(tracked_characters, & &1.id) |> List.first()
|
||||
|
||||
added_acls
|
||||
|> Enum.each(fn acl_id ->
|
||||
{:ok, _} =
|
||||
WandererApp.User.ActivityTracker.track_map_event(:map_acl_added, %{
|
||||
character_id: first_tracked_character_id,
|
||||
user_id: current_user.id,
|
||||
map_id: map.id,
|
||||
acl_id: acl_id
|
||||
})
|
||||
end)
|
||||
added_acls
|
||||
|> Enum.each(fn acl_id ->
|
||||
WandererApp.User.ActivityTracker.track_map_event(:map_acl_added, %{
|
||||
character_id: first_tracked_character_id,
|
||||
user_id: current_user.id,
|
||||
map_id: map_with_acls.id,
|
||||
acl_id: acl_id
|
||||
})
|
||||
end)
|
||||
|
||||
removed_acls
|
||||
|> Enum.each(fn acl_id ->
|
||||
{:ok, _} =
|
||||
WandererApp.User.ActivityTracker.track_map_event(:map_acl_removed, %{
|
||||
character_id: first_tracked_character_id,
|
||||
user_id: current_user.id,
|
||||
map_id: map.id,
|
||||
acl_id: acl_id
|
||||
})
|
||||
end)
|
||||
removed_acls
|
||||
|> Enum.each(fn acl_id ->
|
||||
WandererApp.User.ActivityTracker.track_map_event(:map_acl_removed, %{
|
||||
character_id: first_tracked_character_id,
|
||||
user_id: current_user.id,
|
||||
map_id: map_with_acls.id,
|
||||
acl_id: acl_id
|
||||
})
|
||||
end)
|
||||
|
||||
{:noreply,
|
||||
socket
|
||||
|> push_navigate(to: ~p"/maps")}
|
||||
|
||||
{:error, error} ->
|
||||
{:noreply,
|
||||
socket
|
||||
|> put_flash(:error, "Failed to update map")
|
||||
|> assign(error: error)}
|
||||
end
|
||||
|
||||
{:error, :multiple_results} ->
|
||||
{:noreply,
|
||||
socket
|
||||
|> put_flash(
|
||||
:error,
|
||||
"Multiple maps found with this identifier. Please contact support to resolve this issue."
|
||||
)
|
||||
|> push_navigate(to: ~p"/maps")}
|
||||
|
||||
{:error, error} ->
|
||||
{:error, :not_found} ->
|
||||
{:noreply,
|
||||
socket
|
||||
|> put_flash(:error, "Failed to update map")
|
||||
|> assign(error: error)}
|
||||
|> put_flash(:error, "Map not found")
|
||||
|> push_navigate(to: ~p"/maps")}
|
||||
|
||||
{:error, _reason} ->
|
||||
{:noreply,
|
||||
socket
|
||||
|> put_flash(:error, "Failed to load map. Please try again.")
|
||||
|> push_navigate(to: ~p"/maps")}
|
||||
end
|
||||
end
|
||||
|
||||
def handle_event("delete", %{"data" => map_slug} = _params, socket) do
|
||||
map =
|
||||
map_slug
|
||||
|> WandererApp.Api.Map.get_map_by_slug!()
|
||||
|> WandererApp.Api.Map.mark_as_deleted!()
|
||||
case get_map_by_slug_safely(map_slug) do
|
||||
{:ok, map} ->
|
||||
# Successfully found the map, proceed with deletion
|
||||
deleted_map = WandererApp.Api.Map.mark_as_deleted!(map)
|
||||
|
||||
Phoenix.PubSub.broadcast(
|
||||
WandererApp.PubSub,
|
||||
"maps:#{map.id}",
|
||||
:map_deleted
|
||||
)
|
||||
Phoenix.PubSub.broadcast(
|
||||
WandererApp.PubSub,
|
||||
"maps:#{deleted_map.id}",
|
||||
:map_deleted
|
||||
)
|
||||
|
||||
current_user = socket.assigns.current_user
|
||||
current_user = socket.assigns.current_user
|
||||
|
||||
{:noreply,
|
||||
socket
|
||||
|> assign_async(:maps, fn ->
|
||||
load_maps(current_user)
|
||||
end)
|
||||
|> push_patch(to: ~p"/maps")}
|
||||
# Reload maps synchronously to avoid timing issues with flash messages
|
||||
{:ok, %{maps: maps}} = load_maps(current_user)
|
||||
|
||||
{:noreply,
|
||||
socket
|
||||
|> assign(:maps, AsyncResult.ok(maps))
|
||||
|> push_patch(to: ~p"/maps")}
|
||||
|
||||
{:error, :multiple_results} ->
|
||||
# Multiple maps found with this slug - data integrity issue
|
||||
# Reload maps synchronously
|
||||
{:ok, %{maps: maps}} = load_maps(socket.assigns.current_user)
|
||||
|
||||
{:noreply,
|
||||
socket
|
||||
|> put_flash(
|
||||
:error,
|
||||
"Multiple maps found with this identifier. Please contact support to resolve this issue."
|
||||
)
|
||||
|> assign(:maps, AsyncResult.ok(maps))}
|
||||
|
||||
{:error, :not_found} ->
|
||||
# Map not found
|
||||
# Reload maps synchronously
|
||||
{:ok, %{maps: maps}} = load_maps(socket.assigns.current_user)
|
||||
|
||||
{:noreply,
|
||||
socket
|
||||
|> put_flash(:error, "Map not found or already deleted")
|
||||
|> assign(:maps, AsyncResult.ok(maps))
|
||||
|> push_patch(to: ~p"/maps")}
|
||||
|
||||
{:error, _reason} ->
|
||||
# Other error
|
||||
# Reload maps synchronously
|
||||
{:ok, %{maps: maps}} = load_maps(socket.assigns.current_user)
|
||||
|
||||
{:noreply,
|
||||
socket
|
||||
|> put_flash(:error, "Failed to delete map. Please try again.")
|
||||
|> assign(:maps, AsyncResult.ok(maps))}
|
||||
end
|
||||
end
|
||||
|
||||
def handle_event(
|
||||
@@ -683,4 +787,49 @@ defmodule WandererAppWeb.MapsLive do
|
||||
map
|
||||
|> Map.put(:acls, acls |> Enum.map(&map_acl/1))
|
||||
end
|
||||
|
||||
@doc """
|
||||
Safely retrieves a map by slug, handling the case where multiple maps
|
||||
with the same slug exist (database integrity issue).
|
||||
|
||||
Returns:
|
||||
- `{:ok, map}` - Single map found
|
||||
- `{:error, :multiple_results}` - Multiple maps found (logs error)
|
||||
- `{:error, :not_found}` - No map found
|
||||
- `{:error, reason}` - Other error
|
||||
"""
|
||||
defp get_map_by_slug_safely(slug) do
|
||||
try do
|
||||
map = WandererApp.Api.Map.get_map_by_slug!(slug)
|
||||
{:ok, map}
|
||||
rescue
|
||||
error in Ash.Error.Invalid.MultipleResults ->
|
||||
Logger.error("Multiple maps found with slug '#{slug}' - database integrity issue",
|
||||
slug: slug,
|
||||
error: inspect(error)
|
||||
)
|
||||
|
||||
# Emit telemetry for monitoring
|
||||
:telemetry.execute(
|
||||
[:wanderer_app, :map, :duplicate_slug_detected],
|
||||
%{count: 1},
|
||||
%{slug: slug, operation: :get_by_slug}
|
||||
)
|
||||
|
||||
# Return error - caller should handle this appropriately
|
||||
{:error, :multiple_results}
|
||||
|
||||
error in Ash.Error.Query.NotFound ->
|
||||
Logger.debug("Map not found with slug: #{slug}")
|
||||
{:error, :not_found}
|
||||
|
||||
error ->
|
||||
Logger.error("Error retrieving map by slug",
|
||||
slug: slug,
|
||||
error: inspect(error)
|
||||
)
|
||||
|
||||
{:error, :unknown_error}
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
2
mix.exs
2
mix.exs
@@ -3,7 +3,7 @@ defmodule WandererApp.MixProject do
|
||||
|
||||
@source_url "https://github.com/wanderer-industries/wanderer"
|
||||
|
||||
@version "1.84.13"
|
||||
@version "1.84.23"
|
||||
|
||||
def project do
|
||||
[
|
||||
|
||||
@@ -0,0 +1,212 @@
|
||||
defmodule WandererApp.Repo.Migrations.EnsureNoDuplicateMapSlugs do
|
||||
@moduledoc """
|
||||
Final migration to ensure all duplicate map slugs are removed and unique index exists.
|
||||
|
||||
This migration:
|
||||
1. Checks for any remaining duplicate slugs
|
||||
2. Fixes duplicates by renaming them (keeps oldest, renames newer ones)
|
||||
3. Ensures unique index exists on maps_v1.slug
|
||||
4. Verifies no duplicates remain after migration
|
||||
|
||||
Safe to run multiple times (idempotent).
|
||||
"""
|
||||
use Ecto.Migration
|
||||
import Ecto.Query
|
||||
require Logger
|
||||
|
||||
def up do
|
||||
IO.puts("\n=== Starting Map Slug Deduplication Migration ===\n")
|
||||
|
||||
# Step 1: Check for duplicates
|
||||
duplicate_count = count_duplicates()
|
||||
|
||||
if duplicate_count > 0 do
|
||||
IO.puts("Found #{duplicate_count} duplicate slug(s) - proceeding with cleanup...")
|
||||
|
||||
# Step 2: Drop index temporarily if it exists (to allow updates)
|
||||
drop_index_if_exists()
|
||||
|
||||
# Step 3: Fix all duplicates
|
||||
fix_duplicate_slugs()
|
||||
|
||||
# Step 4: Recreate unique index
|
||||
ensure_unique_index()
|
||||
else
|
||||
IO.puts("No duplicate slugs found - ensuring unique index exists...")
|
||||
ensure_unique_index()
|
||||
end
|
||||
|
||||
# Step 5: Final verification
|
||||
verify_no_duplicates()
|
||||
|
||||
IO.puts("\n=== Migration completed successfully! ===\n")
|
||||
end
|
||||
|
||||
def down do
|
||||
# This migration is idempotent and only fixes data integrity issues
|
||||
# No need to revert as it doesn't change schema in a harmful way
|
||||
IO.puts("This migration does not need to be reverted")
|
||||
:ok
|
||||
end
|
||||
|
||||
defp count_duplicates do
|
||||
duplicates_query = """
|
||||
SELECT COUNT(*) as duplicate_count
|
||||
FROM (
|
||||
SELECT slug
|
||||
FROM maps_v1
|
||||
WHERE deleted = false
|
||||
GROUP BY slug
|
||||
HAVING COUNT(*) > 1
|
||||
) duplicates
|
||||
"""
|
||||
|
||||
case repo().query(duplicates_query, []) do
|
||||
{:ok, %{rows: [[count]]}} ->
|
||||
count
|
||||
{:error, error} ->
|
||||
IO.puts("Error counting duplicates: #{inspect(error)}")
|
||||
0
|
||||
end
|
||||
end
|
||||
|
||||
defp drop_index_if_exists do
|
||||
index_exists_query = """
|
||||
SELECT EXISTS (
|
||||
SELECT 1
|
||||
FROM pg_indexes
|
||||
WHERE tablename = 'maps_v1'
|
||||
AND indexname = 'maps_v1_unique_slug_index'
|
||||
)
|
||||
"""
|
||||
|
||||
case repo().query(index_exists_query, []) do
|
||||
{:ok, %{rows: [[true]]}} ->
|
||||
IO.puts("Temporarily dropping unique index to allow updates...")
|
||||
execute("DROP INDEX IF EXISTS maps_v1_unique_slug_index")
|
||||
IO.puts("✓ Index dropped")
|
||||
|
||||
{:ok, %{rows: [[false]]}} ->
|
||||
IO.puts("No existing index to drop")
|
||||
|
||||
{:error, error} ->
|
||||
IO.puts("Error checking index: #{inspect(error)}")
|
||||
end
|
||||
end
|
||||
|
||||
defp fix_duplicate_slugs do
|
||||
# Get all duplicate slugs with their IDs and timestamps
|
||||
# Order by inserted_at to keep the oldest one unchanged
|
||||
duplicates_query = """
|
||||
SELECT
|
||||
slug,
|
||||
array_agg(id::text ORDER BY inserted_at ASC, id ASC) as ids,
|
||||
array_agg(name ORDER BY inserted_at ASC, id ASC) as names
|
||||
FROM maps_v1
|
||||
WHERE deleted = false
|
||||
GROUP BY slug
|
||||
HAVING COUNT(*) > 1
|
||||
ORDER BY slug
|
||||
"""
|
||||
|
||||
case repo().query(duplicates_query, []) do
|
||||
{:ok, %{rows: rows}} when length(rows) > 0 ->
|
||||
IO.puts("\nFixing #{length(rows)} duplicate slug(s)...")
|
||||
|
||||
Enum.each(rows, fn [slug, ids, names] ->
|
||||
IO.puts("\n Processing: '#{slug}' (#{length(ids)} duplicates)")
|
||||
|
||||
# Keep the first one (oldest by inserted_at), rename the rest
|
||||
[keep_id | rename_ids] = ids
|
||||
[keep_name | rename_names] = names
|
||||
|
||||
IO.puts(" ✓ Keeping: #{keep_id} - '#{keep_name}'")
|
||||
|
||||
# Rename duplicates
|
||||
rename_ids
|
||||
|> Enum.zip(rename_names)
|
||||
|> Enum.with_index(2)
|
||||
|> Enum.each(fn {{id_string, name}, n} ->
|
||||
new_slug = generate_unique_slug(slug, n)
|
||||
|
||||
# Use parameterized query for safety
|
||||
update_query = "UPDATE maps_v1 SET slug = $1 WHERE id::text = $2"
|
||||
repo().query!(update_query, [new_slug, id_string])
|
||||
|
||||
IO.puts(" → Renamed: #{id_string} - '#{name}' to slug '#{new_slug}'")
|
||||
end)
|
||||
end)
|
||||
|
||||
IO.puts("\n✓ All duplicate slugs fixed!")
|
||||
|
||||
{:ok, %{rows: []}} ->
|
||||
IO.puts("No duplicate slugs to fix")
|
||||
|
||||
{:error, error} ->
|
||||
IO.puts("Error finding duplicates: #{inspect(error)}")
|
||||
raise "Failed to query duplicate slugs: #{inspect(error)}"
|
||||
end
|
||||
end
|
||||
|
||||
defp generate_unique_slug(base_slug, n) when n >= 2 do
|
||||
candidate = "#{base_slug}-#{n}"
|
||||
|
||||
# Check if this slug already exists
|
||||
check_query = "SELECT COUNT(*) FROM maps_v1 WHERE slug = $1 AND deleted = false"
|
||||
|
||||
case repo().query!(check_query, [candidate]) do
|
||||
%{rows: [[0]]} ->
|
||||
candidate
|
||||
%{rows: [[_count]]} ->
|
||||
# Try next number
|
||||
generate_unique_slug(base_slug, n + 1)
|
||||
end
|
||||
end
|
||||
|
||||
defp ensure_unique_index do
|
||||
# Check if index exists
|
||||
index_exists_query = """
|
||||
SELECT EXISTS (
|
||||
SELECT 1
|
||||
FROM pg_indexes
|
||||
WHERE tablename = 'maps_v1'
|
||||
AND indexname = 'maps_v1_unique_slug_index'
|
||||
)
|
||||
"""
|
||||
|
||||
case repo().query(index_exists_query, []) do
|
||||
{:ok, %{rows: [[true]]}} ->
|
||||
IO.puts("✓ Unique index on slug already exists")
|
||||
|
||||
{:ok, %{rows: [[false]]}} ->
|
||||
IO.puts("Creating unique index on slug column...")
|
||||
|
||||
create_if_not_exists(
|
||||
index(:maps_v1, [:slug],
|
||||
unique: true,
|
||||
name: :maps_v1_unique_slug_index,
|
||||
where: "deleted = false"
|
||||
)
|
||||
)
|
||||
|
||||
IO.puts("✓ Unique index created successfully!")
|
||||
|
||||
{:error, error} ->
|
||||
IO.puts("Error checking index: #{inspect(error)}")
|
||||
raise "Failed to check index existence: #{inspect(error)}"
|
||||
end
|
||||
end
|
||||
|
||||
defp verify_no_duplicates do
|
||||
IO.puts("\nVerifying no duplicates remain...")
|
||||
|
||||
remaining_duplicates = count_duplicates()
|
||||
|
||||
if remaining_duplicates > 0 do
|
||||
IO.puts("❌ ERROR: #{remaining_duplicates} duplicate(s) still exist!")
|
||||
raise "Migration failed: duplicates still exist after cleanup"
|
||||
else
|
||||
IO.puts("✓ Verification passed: No duplicates found")
|
||||
end
|
||||
end
|
||||
end
|
||||
463
test/integration/map/map_pool_crash_integration_test.exs
Normal file
463
test/integration/map/map_pool_crash_integration_test.exs
Normal file
@@ -0,0 +1,463 @@
|
||||
defmodule WandererApp.Map.MapPoolCrashIntegrationTest do
|
||||
@moduledoc """
|
||||
Integration tests for MapPool crash recovery.
|
||||
|
||||
These tests verify end-to-end crash recovery behavior including:
|
||||
- MapPool GenServer crashes and restarts
|
||||
- State recovery from ETS
|
||||
- Registry and cache consistency after recovery
|
||||
- Telemetry events during recovery
|
||||
- Multi-pool scenarios
|
||||
|
||||
Note: Many tests are skipped as they require full map infrastructure
|
||||
(database, Server.Impl, map data, etc.) to be set up.
|
||||
"""
|
||||
|
||||
use ExUnit.Case, async: false
|
||||
|
||||
alias WandererApp.Map.{MapPool, MapPoolDynamicSupervisor, MapPoolState}
|
||||
|
||||
@cache :map_pool_cache
|
||||
@registry :map_pool_registry
|
||||
@unique_registry :unique_map_pool_registry
|
||||
@ets_table :map_pool_state_table
|
||||
|
||||
setup do
|
||||
# Clean up any existing test data
|
||||
cleanup_test_data()
|
||||
|
||||
# Check if required infrastructure is running
|
||||
supervisor_running? = Process.whereis(MapPoolDynamicSupervisor) != nil
|
||||
|
||||
ets_exists? =
|
||||
try do
|
||||
:ets.info(@ets_table) != :undefined
|
||||
rescue
|
||||
_ -> false
|
||||
end
|
||||
|
||||
on_exit(fn ->
|
||||
cleanup_test_data()
|
||||
end)
|
||||
|
||||
{:ok, supervisor_running: supervisor_running?, ets_exists: ets_exists?}
|
||||
end
|
||||
|
||||
defp cleanup_test_data do
|
||||
# Clean up test caches
|
||||
WandererApp.Cache.delete("started_maps")
|
||||
Cachex.clear(@cache)
|
||||
|
||||
# Clean up ETS entries
|
||||
if :ets.whereis(@ets_table) != :undefined do
|
||||
:ets.match_delete(@ets_table, {:"$1", :"$2", :"$3"})
|
||||
end
|
||||
end
|
||||
|
||||
defp find_pool_pid(uuid) do
|
||||
pool_name = Module.concat(MapPool, uuid)
|
||||
|
||||
case Registry.lookup(@unique_registry, pool_name) do
|
||||
[{pid, _value}] -> {:ok, pid}
|
||||
[] -> {:error, :not_found}
|
||||
end
|
||||
end
|
||||
|
||||
describe "End-to-end crash recovery" do
|
||||
@tag :skip
|
||||
@tag :integration
|
||||
test "MapPool recovers all maps after abnormal crash" do
|
||||
# This test would:
|
||||
# 1. Start a MapPool with test maps via MapPoolDynamicSupervisor
|
||||
# 2. Verify maps are running and state is in ETS
|
||||
# 3. Simulate crash using GenServer.call(pool_pid, :error)
|
||||
# 4. Wait for supervisor to restart the pool
|
||||
# 5. Verify all maps are recovered
|
||||
# 6. Verify Registry, Cache, and ETS are consistent
|
||||
|
||||
# Requires:
|
||||
# - Test map data in database
|
||||
# - Server.Impl.start_map to work with test data
|
||||
# - Full supervision tree running
|
||||
|
||||
:ok
|
||||
end
|
||||
|
||||
@tag :skip
|
||||
@tag :integration
|
||||
test "MapPool preserves ETS state on abnormal termination" do
|
||||
# This test would:
|
||||
# 1. Start a MapPool with maps
|
||||
# 2. Force crash
|
||||
# 3. Verify ETS state is preserved (not deleted)
|
||||
# 4. Verify new pool instance recovers from ETS
|
||||
|
||||
:ok
|
||||
end
|
||||
|
||||
@tag :skip
|
||||
@tag :integration
|
||||
test "MapPool cleans ETS state on graceful shutdown" do
|
||||
# This test would:
|
||||
# 1. Start a MapPool with maps
|
||||
# 2. Gracefully stop the pool (GenServer.cast(pool_pid, :stop))
|
||||
# 3. Verify ETS state is deleted
|
||||
# 4. Verify new pool starts with empty state
|
||||
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
describe "Multi-pool crash scenarios" do
|
||||
@tag :skip
|
||||
@tag :integration
|
||||
test "multiple pools crash and recover independently" do
|
||||
# This test would:
|
||||
# 1. Start multiple MapPool instances with different maps
|
||||
# 2. Crash one pool
|
||||
# 3. Verify only that pool recovers, others unaffected
|
||||
# 4. Verify no cross-pool state corruption
|
||||
|
||||
:ok
|
||||
end
|
||||
|
||||
@tag :skip
|
||||
@tag :integration
|
||||
test "concurrent pool crashes don't corrupt recovery state" do
|
||||
# This test would:
|
||||
# 1. Start multiple pools
|
||||
# 2. Crash multiple pools simultaneously
|
||||
# 3. Verify all pools recover correctly
|
||||
# 4. Verify no ETS corruption or race conditions
|
||||
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
describe "State consistency after recovery" do
|
||||
@tag :skip
|
||||
@tag :integration
|
||||
test "Registry state matches recovered state" do
|
||||
# This test would verify that after recovery:
|
||||
# - unique_registry has correct map_ids for pool UUID
|
||||
# - map_pool_registry has correct pool UUID entry
|
||||
# - All map_ids in Registry match ETS state
|
||||
|
||||
:ok
|
||||
end
|
||||
|
||||
@tag :skip
|
||||
@tag :integration
|
||||
test "Cache state matches recovered state" do
|
||||
# This test would verify that after recovery:
|
||||
# - map_pool_cache has correct map_id -> uuid mappings
|
||||
# - started_maps cache includes all recovered maps
|
||||
# - No orphaned cache entries
|
||||
|
||||
:ok
|
||||
end
|
||||
|
||||
@tag :skip
|
||||
@tag :integration
|
||||
test "Map servers are actually running after recovery" do
|
||||
# This test would:
|
||||
# 1. Recover maps from crash
|
||||
# 2. Verify each map's GenServer is actually running
|
||||
# 3. Verify maps respond to requests
|
||||
# 4. Verify map state is correct
|
||||
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
describe "Recovery failure handling" do
|
||||
@tag :skip
|
||||
@tag :integration
|
||||
test "recovery continues when individual map fails to start" do
|
||||
# This test would:
|
||||
# 1. Save state with maps [1, 2, 3] to ETS
|
||||
# 2. Delete map 2 from database
|
||||
# 3. Trigger recovery
|
||||
# 4. Verify maps 1 and 3 recover successfully
|
||||
# 5. Verify map 2 failure is logged and telemetry emitted
|
||||
# 6. Verify pool continues with maps [1, 3]
|
||||
|
||||
:ok
|
||||
end
|
||||
|
||||
@tag :skip
|
||||
@tag :integration
|
||||
test "recovery handles maps already running in different pool" do
|
||||
# This test would simulate a race condition where:
|
||||
# 1. Pool A crashes with map X
|
||||
# 2. Before recovery, map X is started in Pool B
|
||||
# 3. Pool A tries to recover map X
|
||||
# 4. Verify conflict is detected and handled gracefully
|
||||
|
||||
:ok
|
||||
end
|
||||
|
||||
@tag :skip
|
||||
@tag :integration
|
||||
test "recovery handles corrupted ETS state" do
|
||||
# This test would:
|
||||
# 1. Manually corrupt ETS state (invalid map IDs, wrong types, etc.)
|
||||
# 2. Trigger recovery
|
||||
# 3. Verify pool handles corruption gracefully
|
||||
# 4. Verify telemetry emitted for failures
|
||||
# 5. Verify pool continues with valid maps only
|
||||
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
describe "Telemetry during recovery" do
|
||||
test "telemetry events emitted in correct order", %{ets_exists: ets_exists?} do
|
||||
if ets_exists? do
|
||||
test_pid = self()
|
||||
events = []
|
||||
|
||||
# Attach handlers for all recovery events
|
||||
:telemetry.attach_many(
|
||||
"test-recovery-events",
|
||||
[
|
||||
[:wanderer_app, :map_pool, :recovery, :start],
|
||||
[:wanderer_app, :map_pool, :recovery, :complete],
|
||||
[:wanderer_app, :map_pool, :recovery, :map_failed]
|
||||
],
|
||||
fn event, measurements, metadata, _config ->
|
||||
send(test_pid, {:telemetry_event, event, measurements, metadata})
|
||||
end,
|
||||
nil
|
||||
)
|
||||
|
||||
uuid = "test-pool-#{:rand.uniform(1_000_000)}"
|
||||
|
||||
# Simulate recovery sequence
|
||||
# 1. Start event
|
||||
:telemetry.execute(
|
||||
[:wanderer_app, :map_pool, :recovery, :start],
|
||||
%{recovered_map_count: 3, total_map_count: 3},
|
||||
%{pool_uuid: uuid}
|
||||
)
|
||||
|
||||
# 2. Complete event (in real recovery, this comes after all maps start)
|
||||
:telemetry.execute(
|
||||
[:wanderer_app, :map_pool, :recovery, :complete],
|
||||
%{recovered_count: 3, failed_count: 0, duration_ms: 100},
|
||||
%{pool_uuid: uuid}
|
||||
)
|
||||
|
||||
# Verify we received both events
|
||||
assert_receive {:telemetry_event, [:wanderer_app, :map_pool, :recovery, :start], _, _},
|
||||
500
|
||||
|
||||
assert_receive {:telemetry_event, [:wanderer_app, :map_pool, :recovery, :complete], _, _},
|
||||
500
|
||||
|
||||
:telemetry.detach("test-recovery-events")
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
@tag :skip
|
||||
@tag :integration
|
||||
test "telemetry includes accurate recovery statistics" do
|
||||
# This test would verify that:
|
||||
# - recovered_map_count matches actual recovered maps
|
||||
# - failed_count matches actual failed maps
|
||||
# - duration_ms is accurate
|
||||
# - All metadata is correct
|
||||
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
describe "Interaction with Reconciler" do
|
||||
@tag :skip
|
||||
@tag :integration
|
||||
test "Reconciler doesn't interfere with crash recovery" do
|
||||
# This test would:
|
||||
# 1. Crash a pool with maps
|
||||
# 2. Trigger both recovery and reconciliation
|
||||
# 3. Verify they don't conflict
|
||||
# 4. Verify final state is consistent
|
||||
|
||||
:ok
|
||||
end
|
||||
|
||||
@tag :skip
|
||||
@tag :integration
|
||||
test "Reconciler detects failed recovery" do
|
||||
# This test would:
|
||||
# 1. Crash a pool with map X
|
||||
# 2. Make recovery fail for map X
|
||||
# 3. Run reconciler
|
||||
# 4. Verify reconciler detects and potentially fixes the issue
|
||||
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
describe "Edge cases" do
|
||||
@tag :skip
|
||||
@tag :integration
|
||||
test "recovery during pool at capacity" do
|
||||
# This test would:
|
||||
# 1. Create pool with 19 maps
|
||||
# 2. Crash pool while adding 20th map
|
||||
# 3. Verify recovery handles capacity limit
|
||||
# 4. Verify all maps start or overflow is handled
|
||||
|
||||
:ok
|
||||
end
|
||||
|
||||
@tag :skip
|
||||
@tag :integration
|
||||
test "recovery with empty map list" do
|
||||
# This test would:
|
||||
# 1. Crash pool with empty map_ids
|
||||
# 2. Verify recovery completes successfully
|
||||
# 3. Verify pool starts with no maps
|
||||
|
||||
:ok
|
||||
end
|
||||
|
||||
@tag :skip
|
||||
@tag :integration
|
||||
test "multiple crashes in quick succession" do
|
||||
# This test would:
|
||||
# 1. Crash pool
|
||||
# 2. Immediately crash again during recovery
|
||||
# 3. Verify supervisor's max_restarts is respected
|
||||
# 4. Verify state remains consistent
|
||||
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
describe "Performance under load" do
|
||||
@tag :slow
|
||||
@tag :skip
|
||||
@tag :integration
|
||||
test "recovery completes within 2 seconds for 20 maps" do
|
||||
# This test would:
|
||||
# 1. Create pool with 20 maps (pool limit)
|
||||
# 2. Crash pool
|
||||
# 3. Measure time to full recovery
|
||||
# 4. Assert recovery < 2 seconds
|
||||
|
||||
:ok
|
||||
end
|
||||
|
||||
@tag :slow
|
||||
@tag :skip
|
||||
@tag :integration
|
||||
test "recovery doesn't block other pools" do
|
||||
# This test would:
|
||||
# 1. Start multiple pools
|
||||
# 2. Crash one pool with many maps
|
||||
# 3. Verify other pools continue to operate normally during recovery
|
||||
# 4. Measure performance impact on healthy pools
|
||||
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
describe "Supervisor interaction" do
|
||||
test "ETS table survives individual pool crash", %{ets_exists: ets_exists?} do
|
||||
if ets_exists? do
|
||||
# Verify ETS table is owned by supervisor, not individual pools
|
||||
table_info = :ets.info(@ets_table)
|
||||
owner_pid = Keyword.get(table_info, :owner)
|
||||
|
||||
# Owner should be alive and be the supervisor or a system process
|
||||
assert Process.alive?(owner_pid)
|
||||
|
||||
# Verify we can still access the table
|
||||
uuid = "test-pool-#{:rand.uniform(1_000_000)}"
|
||||
MapPoolState.save_pool_state(uuid, [1, 2, 3])
|
||||
assert {:ok, [1, 2, 3]} = MapPoolState.get_pool_state(uuid)
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
@tag :skip
|
||||
@tag :integration
|
||||
test "supervisor restarts pool after crash" do
|
||||
# This test would:
|
||||
# 1. Start a pool via DynamicSupervisor
|
||||
# 2. Crash the pool
|
||||
# 3. Verify supervisor restarts it
|
||||
# 4. Verify new PID is different from old PID
|
||||
# 5. Verify pool is functional after restart
|
||||
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
describe "Database consistency" do
|
||||
@tag :skip
|
||||
@tag :integration
|
||||
test "recovered maps load latest state from database" do
|
||||
# This test would:
|
||||
# 1. Start maps with initial state
|
||||
# 2. Modify map state in database
|
||||
# 3. Crash pool
|
||||
# 4. Verify recovered maps have latest database state
|
||||
|
||||
:ok
|
||||
end
|
||||
|
||||
@tag :skip
|
||||
@tag :integration
|
||||
test "recovery uses MapState for map configuration" do
|
||||
# This test would:
|
||||
# 1. Verify recovery calls WandererApp.Map.get_map_state!/1
|
||||
# 2. Verify state comes from database MapState table
|
||||
# 3. Verify maps start with correct configuration
|
||||
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
describe "Real-world scenarios" do
|
||||
@tag :skip
|
||||
@tag :integration
|
||||
test "recovery after OOM crash" do
|
||||
# This test would simulate recovery after out-of-memory crash:
|
||||
# 1. Start pool with maps
|
||||
# 2. Simulate OOM condition
|
||||
# 3. Verify recovery completes successfully
|
||||
# 4. Verify no memory leaks after recovery
|
||||
|
||||
:ok
|
||||
end
|
||||
|
||||
@tag :skip
|
||||
@tag :integration
|
||||
test "recovery after network partition" do
|
||||
# This test would simulate recovery after network issues:
|
||||
# 1. Start maps with external dependencies
|
||||
# 2. Simulate network partition
|
||||
# 3. Crash pool
|
||||
# 4. Verify recovery handles network errors gracefully
|
||||
|
||||
:ok
|
||||
end
|
||||
|
||||
@tag :skip
|
||||
@tag :integration
|
||||
test "recovery preserves user sessions" do
|
||||
# This test would:
|
||||
# 1. Start maps with active user sessions
|
||||
# 2. Crash pool
|
||||
# 3. Verify users can continue after recovery
|
||||
# 4. Verify presence tracking works after recovery
|
||||
|
||||
:ok
|
||||
end
|
||||
end
|
||||
end
|
||||
@@ -410,7 +410,7 @@ defmodule WandererApp.Map.CacheRTreeTest do
|
||||
# Check many positions for availability (simulating auto-positioning)
|
||||
test_positions = for x <- 0..20, y <- 0..20, do: {x * 100, y * 50}
|
||||
|
||||
for {x, y} do
|
||||
for {x, y} <- test_positions do
|
||||
box = [{x, x + 130}, {y, y + 34}]
|
||||
{:ok, _ids} = CacheRTree.query(box, name)
|
||||
# Not asserting anything, just verifying queries work
|
||||
|
||||
561
test/unit/map/map_pool_crash_recovery_test.exs
Normal file
561
test/unit/map/map_pool_crash_recovery_test.exs
Normal file
@@ -0,0 +1,561 @@
|
||||
defmodule WandererApp.Map.MapPoolCrashRecoveryTest do
|
||||
use ExUnit.Case, async: false
|
||||
|
||||
alias WandererApp.Map.{MapPool, MapPoolState}
|
||||
|
||||
@cache :map_pool_cache
|
||||
@registry :map_pool_registry
|
||||
@unique_registry :unique_map_pool_registry
|
||||
@ets_table :map_pool_state_table
|
||||
|
||||
setup do
|
||||
# Clean up any existing test data
|
||||
cleanup_test_data()
|
||||
|
||||
# Check if ETS table exists
|
||||
ets_exists? =
|
||||
try do
|
||||
:ets.info(@ets_table) != :undefined
|
||||
rescue
|
||||
_ -> false
|
||||
end
|
||||
|
||||
on_exit(fn ->
|
||||
cleanup_test_data()
|
||||
end)
|
||||
|
||||
{:ok, ets_exists: ets_exists?}
|
||||
end
|
||||
|
||||
defp cleanup_test_data do
|
||||
# Clean up test caches
|
||||
WandererApp.Cache.delete("started_maps")
|
||||
Cachex.clear(@cache)
|
||||
|
||||
# Clean up ETS entries for test pools
|
||||
if :ets.whereis(@ets_table) != :undefined do
|
||||
:ets.match_delete(@ets_table, {:"$1", :"$2", :"$3"})
|
||||
end
|
||||
end
|
||||
|
||||
defp create_test_pool_with_uuid(uuid, map_ids) do
|
||||
# Manually register in unique_registry
|
||||
{:ok, _} = Registry.register(@unique_registry, Module.concat(MapPool, uuid), map_ids)
|
||||
{:ok, _} = Registry.register(@registry, MapPool, uuid)
|
||||
|
||||
# Add to cache
|
||||
Enum.each(map_ids, fn map_id ->
|
||||
Cachex.put(@cache, map_id, uuid)
|
||||
end)
|
||||
|
||||
# Save to ETS
|
||||
MapPoolState.save_pool_state(uuid, map_ids)
|
||||
|
||||
uuid
|
||||
end
|
||||
|
||||
defp get_pool_map_ids(uuid) do
|
||||
case Registry.lookup(@unique_registry, Module.concat(MapPool, uuid)) do
|
||||
[{_pid, map_ids}] -> map_ids
|
||||
[] -> []
|
||||
end
|
||||
end
|
||||
|
||||
describe "MapPoolState - ETS operations" do
|
||||
test "save_pool_state stores state in ETS", %{ets_exists: ets_exists?} do
|
||||
if ets_exists? do
|
||||
uuid = "test-pool-#{:rand.uniform(1_000_000)}"
|
||||
map_ids = [1, 2, 3]
|
||||
|
||||
assert :ok = MapPoolState.save_pool_state(uuid, map_ids)
|
||||
|
||||
# Verify it's in ETS
|
||||
assert {:ok, ^map_ids} = MapPoolState.get_pool_state(uuid)
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
test "get_pool_state returns not_found for non-existent pool", %{ets_exists: ets_exists?} do
|
||||
if ets_exists? do
|
||||
uuid = "non-existent-#{:rand.uniform(1_000_000)}"
|
||||
|
||||
assert {:error, :not_found} = MapPoolState.get_pool_state(uuid)
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
test "delete_pool_state removes state from ETS", %{ets_exists: ets_exists?} do
|
||||
if ets_exists? do
|
||||
uuid = "test-pool-#{:rand.uniform(1_000_000)}"
|
||||
map_ids = [1, 2, 3]
|
||||
|
||||
MapPoolState.save_pool_state(uuid, map_ids)
|
||||
assert {:ok, ^map_ids} = MapPoolState.get_pool_state(uuid)
|
||||
|
||||
assert :ok = MapPoolState.delete_pool_state(uuid)
|
||||
assert {:error, :not_found} = MapPoolState.get_pool_state(uuid)
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
test "save_pool_state updates existing state", %{ets_exists: ets_exists?} do
|
||||
if ets_exists? do
|
||||
uuid = "test-pool-#{:rand.uniform(1_000_000)}"
|
||||
|
||||
# Save initial state
|
||||
MapPoolState.save_pool_state(uuid, [1, 2])
|
||||
assert {:ok, [1, 2]} = MapPoolState.get_pool_state(uuid)
|
||||
|
||||
# Update state
|
||||
MapPoolState.save_pool_state(uuid, [1, 2, 3, 4])
|
||||
assert {:ok, [1, 2, 3, 4]} = MapPoolState.get_pool_state(uuid)
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
test "list_all_states returns all pool states", %{ets_exists: ets_exists?} do
|
||||
if ets_exists? do
|
||||
# Clean first
|
||||
:ets.delete_all_objects(@ets_table)
|
||||
|
||||
uuid1 = "test-pool-1-#{:rand.uniform(1_000_000)}"
|
||||
uuid2 = "test-pool-2-#{:rand.uniform(1_000_000)}"
|
||||
|
||||
MapPoolState.save_pool_state(uuid1, [1, 2])
|
||||
MapPoolState.save_pool_state(uuid2, [3, 4])
|
||||
|
||||
states = MapPoolState.list_all_states()
|
||||
assert length(states) >= 2
|
||||
|
||||
# Verify our pools are in there
|
||||
uuids = Enum.map(states, fn {uuid, _map_ids, _timestamp} -> uuid end)
|
||||
assert uuid1 in uuids
|
||||
assert uuid2 in uuids
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
test "count_states returns correct count", %{ets_exists: ets_exists?} do
|
||||
if ets_exists? do
|
||||
# Clean first
|
||||
:ets.delete_all_objects(@ets_table)
|
||||
|
||||
uuid1 = "test-pool-1-#{:rand.uniform(1_000_000)}"
|
||||
uuid2 = "test-pool-2-#{:rand.uniform(1_000_000)}"
|
||||
|
||||
MapPoolState.save_pool_state(uuid1, [1, 2])
|
||||
MapPoolState.save_pool_state(uuid2, [3, 4])
|
||||
|
||||
count = MapPoolState.count_states()
|
||||
assert count >= 2
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
describe "MapPoolState - stale entry cleanup" do
|
||||
test "cleanup_stale_entries removes old entries", %{ets_exists: ets_exists?} do
|
||||
if ets_exists? do
|
||||
uuid = "stale-pool-#{:rand.uniform(1_000_000)}"
|
||||
|
||||
# Manually insert a stale entry (24+ hours old)
|
||||
stale_timestamp = System.system_time(:second) - 25 * 3600
|
||||
:ets.insert(@ets_table, {uuid, [1, 2], stale_timestamp})
|
||||
|
||||
assert {:ok, [1, 2]} = MapPoolState.get_pool_state(uuid)
|
||||
|
||||
# Clean up stale entries
|
||||
{:ok, deleted_count} = MapPoolState.cleanup_stale_entries()
|
||||
assert deleted_count >= 1
|
||||
|
||||
# Verify stale entry was removed
|
||||
assert {:error, :not_found} = MapPoolState.get_pool_state(uuid)
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
test "cleanup_stale_entries preserves recent entries", %{ets_exists: ets_exists?} do
|
||||
if ets_exists? do
|
||||
uuid = "recent-pool-#{:rand.uniform(1_000_000)}"
|
||||
map_ids = [1, 2, 3]
|
||||
|
||||
# Save recent entry
|
||||
MapPoolState.save_pool_state(uuid, map_ids)
|
||||
|
||||
# Clean up
|
||||
MapPoolState.cleanup_stale_entries()
|
||||
|
||||
# Recent entry should still exist
|
||||
assert {:ok, ^map_ids} = MapPoolState.get_pool_state(uuid)
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
describe "Crash recovery - basic scenarios" do
|
||||
@tag :skip
|
||||
test "MapPool recovers single map after crash" do
|
||||
# This test requires a full MapPool GenServer with actual map data
|
||||
# Skipping as it needs integration with Server.Impl.start_map
|
||||
:ok
|
||||
end
|
||||
|
||||
@tag :skip
|
||||
test "MapPool recovers multiple maps after crash" do
|
||||
# Similar to above - requires full integration
|
||||
:ok
|
||||
end
|
||||
|
||||
@tag :skip
|
||||
test "MapPool merges new and recovered map_ids" do
|
||||
# Tests that if pool crashes while starting a new map,
|
||||
# both the new map and recovered maps are started
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
describe "Crash recovery - telemetry" do
|
||||
test "recovery emits start telemetry event", %{ets_exists: ets_exists?} do
|
||||
if ets_exists? do
|
||||
test_pid = self()
|
||||
|
||||
# Attach telemetry handler
|
||||
:telemetry.attach(
|
||||
"test-recovery-start",
|
||||
[:wanderer_app, :map_pool, :recovery, :start],
|
||||
fn _event, measurements, metadata, _config ->
|
||||
send(test_pid, {:telemetry_start, measurements, metadata})
|
||||
end,
|
||||
nil
|
||||
)
|
||||
|
||||
uuid = "test-pool-#{:rand.uniform(1_000_000)}"
|
||||
recovered_maps = [1, 2, 3]
|
||||
|
||||
# Save state to ETS (simulating previous run)
|
||||
MapPoolState.save_pool_state(uuid, recovered_maps)
|
||||
|
||||
# Simulate init with recovery
|
||||
# Note: Can't actually start a MapPool here without full integration,
|
||||
# but we can verify the telemetry handler is set up correctly
|
||||
|
||||
# Manually emit the event to test handler
|
||||
:telemetry.execute(
|
||||
[:wanderer_app, :map_pool, :recovery, :start],
|
||||
%{recovered_map_count: 3, total_map_count: 3},
|
||||
%{pool_uuid: uuid}
|
||||
)
|
||||
|
||||
assert_receive {:telemetry_start, measurements, metadata}, 500
|
||||
|
||||
assert measurements.recovered_map_count == 3
|
||||
assert measurements.total_map_count == 3
|
||||
assert metadata.pool_uuid == uuid
|
||||
|
||||
# Cleanup
|
||||
:telemetry.detach("test-recovery-start")
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
test "recovery emits complete telemetry event", %{ets_exists: ets_exists?} do
|
||||
if ets_exists? do
|
||||
test_pid = self()
|
||||
|
||||
:telemetry.attach(
|
||||
"test-recovery-complete",
|
||||
[:wanderer_app, :map_pool, :recovery, :complete],
|
||||
fn _event, measurements, metadata, _config ->
|
||||
send(test_pid, {:telemetry_complete, measurements, metadata})
|
||||
end,
|
||||
nil
|
||||
)
|
||||
|
||||
uuid = "test-pool-#{:rand.uniform(1_000_000)}"
|
||||
|
||||
# Manually emit the event
|
||||
:telemetry.execute(
|
||||
[:wanderer_app, :map_pool, :recovery, :complete],
|
||||
%{recovered_count: 3, failed_count: 0, duration_ms: 100},
|
||||
%{pool_uuid: uuid}
|
||||
)
|
||||
|
||||
assert_receive {:telemetry_complete, measurements, metadata}, 500
|
||||
|
||||
assert measurements.recovered_count == 3
|
||||
assert measurements.failed_count == 0
|
||||
assert measurements.duration_ms == 100
|
||||
assert metadata.pool_uuid == uuid
|
||||
|
||||
:telemetry.detach("test-recovery-complete")
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
test "recovery emits map_failed telemetry event", %{ets_exists: ets_exists?} do
|
||||
if ets_exists? do
|
||||
test_pid = self()
|
||||
|
||||
:telemetry.attach(
|
||||
"test-recovery-map-failed",
|
||||
[:wanderer_app, :map_pool, :recovery, :map_failed],
|
||||
fn _event, measurements, metadata, _config ->
|
||||
send(test_pid, {:telemetry_map_failed, measurements, metadata})
|
||||
end,
|
||||
nil
|
||||
)
|
||||
|
||||
uuid = "test-pool-#{:rand.uniform(1_000_000)}"
|
||||
failed_map_id = 123
|
||||
|
||||
# Manually emit the event
|
||||
:telemetry.execute(
|
||||
[:wanderer_app, :map_pool, :recovery, :map_failed],
|
||||
%{map_id: failed_map_id},
|
||||
%{pool_uuid: uuid, reason: "Map not found"}
|
||||
)
|
||||
|
||||
assert_receive {:telemetry_map_failed, measurements, metadata}, 500
|
||||
|
||||
assert measurements.map_id == failed_map_id
|
||||
assert metadata.pool_uuid == uuid
|
||||
assert metadata.reason == "Map not found"
|
||||
|
||||
:telemetry.detach("test-recovery-map-failed")
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
describe "Crash recovery - state persistence" do
|
||||
@tag :skip
|
||||
test "state persisted after successful map start" do
|
||||
# Would need to start actual MapPool and trigger start_map
|
||||
:ok
|
||||
end
|
||||
|
||||
@tag :skip
|
||||
test "state persisted after successful map stop" do
|
||||
# Would need to start actual MapPool and trigger stop_map
|
||||
:ok
|
||||
end
|
||||
|
||||
@tag :skip
|
||||
test "state persisted during backup_state" do
|
||||
# Would need to trigger backup_state handler
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
describe "Graceful shutdown cleanup" do
|
||||
test "ETS state cleaned on normal termination", %{ets_exists: ets_exists?} do
|
||||
if ets_exists? do
|
||||
uuid = "test-pool-#{:rand.uniform(1_000_000)}"
|
||||
map_ids = [1, 2, 3]
|
||||
|
||||
# Save state
|
||||
MapPoolState.save_pool_state(uuid, map_ids)
|
||||
assert {:ok, ^map_ids} = MapPoolState.get_pool_state(uuid)
|
||||
|
||||
# Simulate graceful shutdown by calling delete
|
||||
MapPoolState.delete_pool_state(uuid)
|
||||
|
||||
# State should be gone
|
||||
assert {:error, :not_found} = MapPoolState.get_pool_state(uuid)
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
@tag :skip
|
||||
test "ETS state preserved on abnormal termination" do
|
||||
# Would need to actually crash a MapPool to test this
|
||||
# The terminate callback would not call delete_pool_state
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
describe "Edge cases" do
|
||||
test "recovery with empty map_ids list", %{ets_exists: ets_exists?} do
|
||||
if ets_exists? do
|
||||
uuid = "test-pool-#{:rand.uniform(1_000_000)}"
|
||||
|
||||
# Save empty state
|
||||
MapPoolState.save_pool_state(uuid, [])
|
||||
assert {:ok, []} = MapPoolState.get_pool_state(uuid)
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
test "recovery with duplicate map_ids gets deduplicated", %{ets_exists: ets_exists?} do
|
||||
if ets_exists? do
|
||||
# This tests the deduplication logic in init
|
||||
# If we have [1, 2] in ETS and [2, 3] in new map_ids,
|
||||
# result should be [1, 2, 3] after Enum.uniq
|
||||
|
||||
recovered_maps = [1, 2]
|
||||
new_maps = [2, 3]
|
||||
expected = Enum.uniq(recovered_maps ++ new_maps)
|
||||
|
||||
# Should be [1, 2, 3] or [2, 3, 1] depending on order
|
||||
assert 1 in expected
|
||||
assert 2 in expected
|
||||
assert 3 in expected
|
||||
assert length(expected) == 3
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
test "large number of maps in recovery", %{ets_exists: ets_exists?} do
|
||||
if ets_exists? do
|
||||
uuid = "test-pool-#{:rand.uniform(1_000_000)}"
|
||||
# Test with 20 maps (the pool limit)
|
||||
map_ids = Enum.to_list(1..20)
|
||||
|
||||
MapPoolState.save_pool_state(uuid, map_ids)
|
||||
assert {:ok, recovered} = MapPoolState.get_pool_state(uuid)
|
||||
assert length(recovered) == 20
|
||||
assert recovered == map_ids
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
describe "Concurrent operations" do
|
||||
test "multiple pools can save state concurrently", %{ets_exists: ets_exists?} do
|
||||
if ets_exists? do
|
||||
# Create 10 pools concurrently
|
||||
tasks =
|
||||
1..10
|
||||
|> Enum.map(fn i ->
|
||||
Task.async(fn ->
|
||||
uuid = "concurrent-pool-#{i}-#{:rand.uniform(1_000_000)}"
|
||||
map_ids = [i * 10, i * 10 + 1]
|
||||
MapPoolState.save_pool_state(uuid, map_ids)
|
||||
{uuid, map_ids}
|
||||
end)
|
||||
end)
|
||||
|
||||
results = Task.await_many(tasks, 5000)
|
||||
|
||||
# Verify all pools saved successfully
|
||||
Enum.each(results, fn {uuid, expected_map_ids} ->
|
||||
assert {:ok, ^expected_map_ids} = MapPoolState.get_pool_state(uuid)
|
||||
end)
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
test "concurrent reads and writes don't corrupt state", %{ets_exists: ets_exists?} do
|
||||
if ets_exists? do
|
||||
uuid = "test-pool-#{:rand.uniform(1_000_000)}"
|
||||
MapPoolState.save_pool_state(uuid, [1, 2, 3])
|
||||
|
||||
# Spawn multiple readers and writers
|
||||
readers =
|
||||
1..5
|
||||
|> Enum.map(fn _ ->
|
||||
Task.async(fn ->
|
||||
MapPoolState.get_pool_state(uuid)
|
||||
end)
|
||||
end)
|
||||
|
||||
writers =
|
||||
1..5
|
||||
|> Enum.map(fn i ->
|
||||
Task.async(fn ->
|
||||
MapPoolState.save_pool_state(uuid, [i, i + 1])
|
||||
end)
|
||||
end)
|
||||
|
||||
# All operations should complete without error
|
||||
reader_results = Task.await_many(readers, 5000)
|
||||
writer_results = Task.await_many(writers, 5000)
|
||||
|
||||
assert Enum.all?(reader_results, fn
|
||||
{:ok, _} -> true
|
||||
_ -> false
|
||||
end)
|
||||
|
||||
assert Enum.all?(writer_results, fn :ok -> true end)
|
||||
|
||||
# Final state should be valid (one of the writer's values)
|
||||
assert {:ok, final_state} = MapPoolState.get_pool_state(uuid)
|
||||
assert is_list(final_state)
|
||||
assert length(final_state) == 2
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
describe "Performance" do
|
||||
@tag :slow
|
||||
test "recovery completes within acceptable time", %{ets_exists: ets_exists?} do
|
||||
if ets_exists? do
|
||||
uuid = "perf-pool-#{:rand.uniform(1_000_000)}"
|
||||
# Test with pool at limit (20 maps)
|
||||
map_ids = Enum.to_list(1..20)
|
||||
|
||||
# Measure save time
|
||||
{save_time_us, :ok} = :timer.tc(fn ->
|
||||
MapPoolState.save_pool_state(uuid, map_ids)
|
||||
end)
|
||||
|
||||
# Measure retrieval time
|
||||
{get_time_us, {:ok, _}} = :timer.tc(fn ->
|
||||
MapPoolState.get_pool_state(uuid)
|
||||
end)
|
||||
|
||||
# Both operations should be very fast (< 1ms)
|
||||
assert save_time_us < 1000, "Save took #{save_time_us}µs, expected < 1000µs"
|
||||
assert get_time_us < 1000, "Get took #{get_time_us}µs, expected < 1000µs"
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
@tag :slow
|
||||
test "cleanup performance with many stale entries", %{ets_exists: ets_exists?} do
|
||||
if ets_exists? do
|
||||
# Insert 100 stale entries
|
||||
stale_timestamp = System.system_time(:second) - 25 * 3600
|
||||
|
||||
1..100
|
||||
|> Enum.each(fn i ->
|
||||
uuid = "stale-pool-#{i}"
|
||||
:ets.insert(@ets_table, {uuid, [i], stale_timestamp})
|
||||
end)
|
||||
|
||||
# Measure cleanup time
|
||||
{cleanup_time_us, {:ok, deleted_count}} = :timer.tc(fn ->
|
||||
MapPoolState.cleanup_stale_entries()
|
||||
end)
|
||||
|
||||
# Should have deleted at least 100 entries
|
||||
assert deleted_count >= 100
|
||||
|
||||
# Cleanup should be reasonably fast (< 100ms for 100 entries)
|
||||
assert cleanup_time_us < 100_000,
|
||||
"Cleanup took #{cleanup_time_us}µs, expected < 100,000µs"
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
343
test/unit/map/map_pool_test.exs
Normal file
343
test/unit/map/map_pool_test.exs
Normal file
@@ -0,0 +1,343 @@
|
||||
defmodule WandererApp.Map.MapPoolTest do
|
||||
use ExUnit.Case, async: false
|
||||
|
||||
alias WandererApp.Map.{MapPool, MapPoolDynamicSupervisor, Reconciler}
|
||||
|
||||
@cache :map_pool_cache
|
||||
@registry :map_pool_registry
|
||||
@unique_registry :unique_map_pool_registry
|
||||
|
||||
setup do
|
||||
# Clean up any existing test data
|
||||
cleanup_test_data()
|
||||
|
||||
# Check if required infrastructure is running
|
||||
registries_running? =
|
||||
try do
|
||||
Registry.keys(@registry, self()) != :error
|
||||
rescue
|
||||
_ -> false
|
||||
end
|
||||
|
||||
reconciler_running? = Process.whereis(Reconciler) != nil
|
||||
|
||||
on_exit(fn ->
|
||||
cleanup_test_data()
|
||||
end)
|
||||
|
||||
{:ok, registries_running: registries_running?, reconciler_running: reconciler_running?}
|
||||
end
|
||||
|
||||
defp cleanup_test_data do
|
||||
# Clean up test caches
|
||||
WandererApp.Cache.delete("started_maps")
|
||||
Cachex.clear(@cache)
|
||||
end
|
||||
|
||||
describe "garbage collection with synchronous stop" do
|
||||
@tag :skip
|
||||
test "garbage collector successfully stops map with synchronous call" do
|
||||
# This test would require setting up a full map pool with a test map
|
||||
# Skipping for now as it requires more complex setup with actual map data
|
||||
:ok
|
||||
end
|
||||
|
||||
@tag :skip
|
||||
test "garbage collector handles stop failures gracefully" do
|
||||
# This test would verify error handling when stop fails
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
describe "cache lookup with registry fallback" do
|
||||
test "stop_map handles cache miss by scanning registry", %{registries_running: registries_running?} do
|
||||
if registries_running? do
|
||||
# Setup: Create a map_id that's not in cache but will be found in registry scan
|
||||
map_id = "test_map_#{:rand.uniform(1_000_000)}"
|
||||
|
||||
# Verify cache is empty for this map
|
||||
assert {:ok, nil} = Cachex.get(@cache, map_id)
|
||||
|
||||
# Call stop_map - should handle gracefully with fallback
|
||||
assert :ok = MapPoolDynamicSupervisor.stop_map(map_id)
|
||||
else
|
||||
# Skip test if registries not running
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
test "stop_map handles non-existent pool_uuid in registry", %{registries_running: registries_running?} do
|
||||
if registries_running? do
|
||||
map_id = "test_map_#{:rand.uniform(1_000_000)}"
|
||||
fake_uuid = "fake_uuid_#{:rand.uniform(1_000_000)}"
|
||||
|
||||
# Put fake uuid in cache that doesn't exist in registry
|
||||
Cachex.put(@cache, map_id, fake_uuid)
|
||||
|
||||
# Call stop_map - should handle gracefully with fallback
|
||||
assert :ok = MapPoolDynamicSupervisor.stop_map(map_id)
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
test "stop_map updates cache when found via registry scan", %{registries_running: registries_running?} do
|
||||
if registries_running? do
|
||||
# This test would require a running pool with registered maps
|
||||
# For now, we verify the fallback logic doesn't crash
|
||||
map_id = "test_map_#{:rand.uniform(1_000_000)}"
|
||||
assert :ok = MapPoolDynamicSupervisor.stop_map(map_id)
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
describe "state cleanup atomicity" do
|
||||
@tag :skip
|
||||
test "rollback occurs when registry update fails" do
|
||||
# This would require mocking Registry.update_value to fail
|
||||
# Skipping for now as it requires more complex mocking setup
|
||||
:ok
|
||||
end
|
||||
|
||||
@tag :skip
|
||||
test "rollback occurs when cache delete fails" do
|
||||
# This would require mocking Cachex.del to fail
|
||||
:ok
|
||||
end
|
||||
|
||||
@tag :skip
|
||||
test "successful cleanup updates all three state stores" do
|
||||
# This would verify Registry, Cache, and GenServer state are all updated
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
describe "Reconciler - zombie map detection and cleanup" do
|
||||
test "reconciler detects zombie maps in started_maps cache", %{reconciler_running: reconciler_running?} do
|
||||
if reconciler_running? do
|
||||
# Setup: Add maps to started_maps that aren't in any registry
|
||||
zombie_map_id = "zombie_map_#{:rand.uniform(1_000_000)}"
|
||||
|
||||
WandererApp.Cache.insert_or_update(
|
||||
"started_maps",
|
||||
[zombie_map_id],
|
||||
fn existing -> [zombie_map_id | existing] |> Enum.uniq() end
|
||||
)
|
||||
|
||||
# Get started_maps
|
||||
{:ok, started_maps} = WandererApp.Cache.lookup("started_maps", [])
|
||||
assert zombie_map_id in started_maps
|
||||
|
||||
# Trigger reconciliation
|
||||
send(Reconciler, :reconcile)
|
||||
# Give it time to process
|
||||
Process.sleep(200)
|
||||
|
||||
# Verify zombie was cleaned up
|
||||
{:ok, started_maps_after} = WandererApp.Cache.lookup("started_maps", [])
|
||||
refute zombie_map_id in started_maps_after
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
test "reconciler cleans up zombie map caches", %{reconciler_running: reconciler_running?} do
|
||||
if reconciler_running? do
|
||||
zombie_map_id = "zombie_map_#{:rand.uniform(1_000_000)}"
|
||||
|
||||
# Setup zombie state
|
||||
WandererApp.Cache.insert_or_update(
|
||||
"started_maps",
|
||||
[zombie_map_id],
|
||||
fn existing -> [zombie_map_id | existing] |> Enum.uniq() end
|
||||
)
|
||||
|
||||
WandererApp.Cache.insert("map_#{zombie_map_id}:started", true)
|
||||
Cachex.put(@cache, zombie_map_id, "fake_uuid")
|
||||
|
||||
# Trigger reconciliation
|
||||
send(Reconciler, :reconcile)
|
||||
Process.sleep(200)
|
||||
|
||||
# Verify all caches cleaned
|
||||
{:ok, started_maps} = WandererApp.Cache.lookup("started_maps", [])
|
||||
refute zombie_map_id in started_maps
|
||||
|
||||
{:ok, cache_entry} = Cachex.get(@cache, zombie_map_id)
|
||||
assert cache_entry == nil
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
describe "Reconciler - orphan map detection and fix" do
|
||||
@tag :skip
|
||||
test "reconciler detects orphan maps in registry" do
|
||||
# This would require setting up a pool with maps in registry
|
||||
# but not in started_maps cache
|
||||
:ok
|
||||
end
|
||||
|
||||
@tag :skip
|
||||
test "reconciler adds orphan maps to started_maps cache" do
|
||||
# This would verify orphan maps get added to the cache
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
describe "Reconciler - cache inconsistency detection and fix" do
|
||||
test "reconciler detects map with missing cache entry", %{reconciler_running: reconciler_running?} do
|
||||
if reconciler_running? do
|
||||
# This test verifies the reconciler can detect when a map
|
||||
# is in the registry but has no cache entry
|
||||
# Since we can't easily set up a full pool, we test the detection logic
|
||||
|
||||
map_id = "test_map_#{:rand.uniform(1_000_000)}"
|
||||
|
||||
# Ensure no cache entry
|
||||
Cachex.del(@cache, map_id)
|
||||
|
||||
# The reconciler would detect this if the map was in a registry
|
||||
# For now, we just verify the logic doesn't crash
|
||||
send(Reconciler, :reconcile)
|
||||
Process.sleep(200)
|
||||
|
||||
# No assertions needed - just verifying no crashes
|
||||
end
|
||||
end
|
||||
|
||||
test "reconciler detects cache pointing to non-existent pool", %{reconciler_running: reconciler_running?} do
|
||||
if reconciler_running? do
|
||||
map_id = "test_map_#{:rand.uniform(1_000_000)}"
|
||||
fake_uuid = "fake_uuid_#{:rand.uniform(1_000_000)}"
|
||||
|
||||
# Put fake uuid in cache
|
||||
Cachex.put(@cache, map_id, fake_uuid)
|
||||
|
||||
# Trigger reconciliation
|
||||
send(Reconciler, :reconcile)
|
||||
Process.sleep(200)
|
||||
|
||||
# Cache entry should be removed since pool doesn't exist
|
||||
{:ok, cache_entry} = Cachex.get(@cache, map_id)
|
||||
assert cache_entry == nil
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
describe "Reconciler - stats and telemetry" do
|
||||
test "reconciler emits telemetry events", %{reconciler_running: reconciler_running?} do
|
||||
if reconciler_running? do
|
||||
# Setup telemetry handler
|
||||
test_pid = self()
|
||||
|
||||
:telemetry.attach(
|
||||
"test-reconciliation",
|
||||
[:wanderer_app, :map, :reconciliation],
|
||||
fn _event, measurements, _metadata, _config ->
|
||||
send(test_pid, {:telemetry, measurements})
|
||||
end,
|
||||
nil
|
||||
)
|
||||
|
||||
# Trigger reconciliation
|
||||
send(Reconciler, :reconcile)
|
||||
Process.sleep(200)
|
||||
|
||||
# Should receive telemetry event
|
||||
assert_receive {:telemetry, measurements}, 500
|
||||
|
||||
assert is_integer(measurements.total_started_maps)
|
||||
assert is_integer(measurements.total_registry_maps)
|
||||
assert is_integer(measurements.zombie_maps)
|
||||
assert is_integer(measurements.orphan_maps)
|
||||
assert is_integer(measurements.cache_inconsistencies)
|
||||
|
||||
# Cleanup
|
||||
:telemetry.detach("test-reconciliation")
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
describe "Reconciler - manual trigger" do
|
||||
test "trigger_reconciliation runs reconciliation immediately", %{reconciler_running: reconciler_running?} do
|
||||
if reconciler_running? do
|
||||
zombie_map_id = "zombie_map_#{:rand.uniform(1_000_000)}"
|
||||
|
||||
# Setup zombie state
|
||||
WandererApp.Cache.insert_or_update(
|
||||
"started_maps",
|
||||
[zombie_map_id],
|
||||
fn existing -> [zombie_map_id | existing] |> Enum.uniq() end
|
||||
)
|
||||
|
||||
# Verify it exists
|
||||
{:ok, started_maps_before} = WandererApp.Cache.lookup("started_maps", [])
|
||||
assert zombie_map_id in started_maps_before
|
||||
|
||||
# Trigger manual reconciliation
|
||||
Reconciler.trigger_reconciliation()
|
||||
Process.sleep(200)
|
||||
|
||||
# Verify zombie was cleaned up
|
||||
{:ok, started_maps_after} = WandererApp.Cache.lookup("started_maps", [])
|
||||
refute zombie_map_id in started_maps_after
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
describe "edge cases and error handling" do
|
||||
test "stop_map with cache error returns ok", %{registries_running: registries_running?} do
|
||||
if registries_running? do
|
||||
map_id = "test_map_#{:rand.uniform(1_000_000)}"
|
||||
|
||||
# Even if cache operations fail, should return :ok
|
||||
assert :ok = MapPoolDynamicSupervisor.stop_map(map_id)
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
test "reconciler handles empty registries gracefully", %{reconciler_running: reconciler_running?} do
|
||||
if reconciler_running? do
|
||||
# Clear everything
|
||||
cleanup_test_data()
|
||||
|
||||
# Should not crash even with empty data
|
||||
send(Reconciler, :reconcile)
|
||||
Process.sleep(200)
|
||||
|
||||
# No assertions - just verifying no crash
|
||||
assert true
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
|
||||
test "reconciler handles nil values in caches", %{reconciler_running: reconciler_running?} do
|
||||
if reconciler_running? do
|
||||
map_id = "test_map_#{:rand.uniform(1_000_000)}"
|
||||
|
||||
# Explicitly set nil
|
||||
Cachex.put(@cache, map_id, nil)
|
||||
|
||||
# Should handle gracefully
|
||||
send(Reconciler, :reconcile)
|
||||
Process.sleep(200)
|
||||
|
||||
assert true
|
||||
else
|
||||
:ok
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
320
test/unit/map/slug_uniqueness_test.exs
Normal file
320
test/unit/map/slug_uniqueness_test.exs
Normal file
@@ -0,0 +1,320 @@
|
||||
defmodule WandererApp.Map.SlugUniquenessTest do
|
||||
@moduledoc """
|
||||
Tests for map slug uniqueness constraints and handling.
|
||||
|
||||
These tests verify that:
|
||||
1. Database unique constraint is enforced
|
||||
2. Application-level slug generation handles uniqueness
|
||||
3. Concurrent map creation doesn't create duplicates
|
||||
4. Error handling works correctly for slug conflicts
|
||||
"""
|
||||
use WandererApp.DataCase, async: false
|
||||
|
||||
alias WandererApp.Api.Map
|
||||
|
||||
require Logger
|
||||
|
||||
describe "slug uniqueness constraint" do
|
||||
setup do
|
||||
# Create a test user
|
||||
user = create_test_user()
|
||||
%{user: user}
|
||||
end
|
||||
|
||||
test "prevents duplicate slugs via database constraint", %{user: user} do
|
||||
# Create first map with a specific slug
|
||||
{:ok, _map1} =
|
||||
Map.new(%{
|
||||
name: "Test Map",
|
||||
slug: "test-map",
|
||||
owner_id: user.id,
|
||||
description: "First map",
|
||||
scope: "wormholes"
|
||||
})
|
||||
|
||||
# Attempt to create second map with same slug by bypassing Ash slug generation
|
||||
# This simulates a race condition where slug generation passes but DB insert fails
|
||||
result =
|
||||
Map.new(%{
|
||||
name: "Different Name",
|
||||
slug: "test-map",
|
||||
owner_id: user.id,
|
||||
description: "Second map",
|
||||
scope: "wormholes"
|
||||
})
|
||||
|
||||
# Should get a unique constraint error from database
|
||||
assert {:error, _error} = result
|
||||
end
|
||||
|
||||
test "automatically increments slug when duplicate detected", %{user: user} do
|
||||
# Create first map
|
||||
{:ok, map1} =
|
||||
Map.new(%{
|
||||
name: "Test Map",
|
||||
slug: "test-map",
|
||||
owner_id: user.id,
|
||||
description: "First map",
|
||||
scope: "wormholes"
|
||||
})
|
||||
|
||||
assert map1.slug == "test-map"
|
||||
|
||||
# Create second map with same name (should auto-increment slug)
|
||||
{:ok, map2} =
|
||||
Map.new(%{
|
||||
name: "Test Map",
|
||||
slug: "test-map",
|
||||
owner_id: user.id,
|
||||
description: "Second map",
|
||||
scope: "wormholes"
|
||||
})
|
||||
|
||||
# Slug should be automatically incremented
|
||||
assert map2.slug == "test-map-2"
|
||||
|
||||
# Create third map with same name
|
||||
{:ok, map3} =
|
||||
Map.new(%{
|
||||
name: "Test Map",
|
||||
slug: "test-map",
|
||||
owner_id: user.id,
|
||||
description: "Third map",
|
||||
scope: "wormholes"
|
||||
})
|
||||
|
||||
assert map3.slug == "test-map-3"
|
||||
end
|
||||
|
||||
test "handles many maps with similar names", %{user: user} do
|
||||
# Create 10 maps with the same base slug
|
||||
maps =
|
||||
for i <- 1..10 do
|
||||
{:ok, map} =
|
||||
Map.new(%{
|
||||
name: "Popular Name",
|
||||
slug: "popular-name",
|
||||
owner_id: user.id,
|
||||
description: "Map #{i}",
|
||||
scope: "wormholes"
|
||||
})
|
||||
|
||||
map
|
||||
end
|
||||
|
||||
# Verify all slugs are unique
|
||||
slugs = Enum.map(maps, & &1.slug)
|
||||
assert length(Enum.uniq(slugs)) == 10
|
||||
|
||||
# First should keep the base slug
|
||||
assert List.first(maps).slug == "popular-name"
|
||||
|
||||
# Others should be numbered
|
||||
assert "popular-name-2" in slugs
|
||||
assert "popular-name-10" in slugs
|
||||
end
|
||||
end
|
||||
|
||||
describe "concurrent slug creation (race condition)" do
|
||||
setup do
|
||||
user = create_test_user()
|
||||
%{user: user}
|
||||
end
|
||||
|
||||
@tag :slow
|
||||
test "handles concurrent map creation with identical slugs", %{user: user} do
|
||||
# Create 5 concurrent map creation requests with the same slug
|
||||
tasks =
|
||||
for i <- 1..5 do
|
||||
Task.async(fn ->
|
||||
Map.new(%{
|
||||
name: "Concurrent Test",
|
||||
slug: "concurrent-test",
|
||||
owner_id: user.id,
|
||||
description: "Concurrent map #{i}",
|
||||
scope: "wormholes"
|
||||
})
|
||||
end)
|
||||
end
|
||||
|
||||
# Wait for all tasks to complete
|
||||
results = Task.await_many(tasks, 10_000)
|
||||
|
||||
# All should either succeed or fail gracefully (no crashes)
|
||||
assert length(results) == 5
|
||||
|
||||
# Get successful results
|
||||
successful = Enum.filter(results, &match?({:ok, _}, &1))
|
||||
failed = Enum.filter(results, &match?({:error, _}, &1))
|
||||
|
||||
# At least some should succeed
|
||||
assert length(successful) > 0
|
||||
|
||||
# Extract maps from successful results
|
||||
maps = Enum.map(successful, fn {:ok, map} -> map end)
|
||||
|
||||
# Verify all successful maps have unique slugs
|
||||
slugs = Enum.map(maps, & &1.slug)
|
||||
assert length(Enum.uniq(slugs)) == length(slugs), "All successful maps should have unique slugs"
|
||||
|
||||
# Log results for visibility
|
||||
Logger.info("Concurrent test: #{length(successful)} succeeded, #{length(failed)} failed")
|
||||
Logger.info("Unique slugs created: #{inspect(slugs)}")
|
||||
end
|
||||
|
||||
@tag :slow
|
||||
test "concurrent creation with different names creates different base slugs", %{user: user} do
|
||||
# Create concurrent requests with different names (should all succeed)
|
||||
tasks =
|
||||
for i <- 1..5 do
|
||||
Task.async(fn ->
|
||||
Map.new(%{
|
||||
name: "Concurrent Map #{i}",
|
||||
slug: "concurrent-map-#{i}",
|
||||
owner_id: user.id,
|
||||
description: "Map #{i}",
|
||||
scope: "wormholes"
|
||||
})
|
||||
end)
|
||||
end
|
||||
|
||||
results = Task.await_many(tasks, 10_000)
|
||||
|
||||
# All should succeed
|
||||
assert Enum.all?(results, &match?({:ok, _}, &1))
|
||||
|
||||
# All should have different slugs
|
||||
slugs = Enum.map(results, fn {:ok, map} -> map.slug end)
|
||||
assert length(Enum.uniq(slugs)) == 5
|
||||
end
|
||||
end
|
||||
|
||||
describe "slug generation edge cases" do
|
||||
setup do
|
||||
user = create_test_user()
|
||||
%{user: user}
|
||||
end
|
||||
|
||||
test "handles very long slugs", %{user: user} do
|
||||
# Create map with name that would generate very long slug
|
||||
long_name = String.duplicate("a", 100)
|
||||
|
||||
{:ok, map} =
|
||||
Map.new(%{
|
||||
name: long_name,
|
||||
slug: long_name,
|
||||
owner_id: user.id,
|
||||
description: "Long name test",
|
||||
scope: "wormholes"
|
||||
})
|
||||
|
||||
# Slug should be truncated to max length (40 chars based on map.ex constraints)
|
||||
assert String.length(map.slug) <= 40
|
||||
end
|
||||
|
||||
test "handles special characters in slugs", %{user: user} do
|
||||
# Test that special characters are properly slugified
|
||||
{:ok, map} =
|
||||
Map.new(%{
|
||||
name: "Test: Map & Name!",
|
||||
slug: "test-map-name",
|
||||
owner_id: user.id,
|
||||
description: "Special chars test",
|
||||
scope: "wormholes"
|
||||
})
|
||||
|
||||
# Slug should only contain allowed characters
|
||||
assert map.slug =~ ~r/^[a-z0-9-]+$/
|
||||
end
|
||||
end
|
||||
|
||||
describe "slug update operations" do
|
||||
setup do
|
||||
user = create_test_user()
|
||||
|
||||
{:ok, map} =
|
||||
Map.new(%{
|
||||
name: "Original Map",
|
||||
slug: "original-map",
|
||||
owner_id: user.id,
|
||||
description: "Original",
|
||||
scope: "wormholes"
|
||||
})
|
||||
|
||||
%{user: user, map: map}
|
||||
end
|
||||
|
||||
test "updating map with same slug succeeds", %{map: map} do
|
||||
# Update other fields, keep same slug
|
||||
result =
|
||||
Map.update(map, %{
|
||||
description: "Updated description",
|
||||
slug: "original-map"
|
||||
})
|
||||
|
||||
assert {:ok, updated_map} = result
|
||||
assert updated_map.slug == "original-map"
|
||||
assert updated_map.description == "Updated description"
|
||||
end
|
||||
|
||||
test "updating to conflicting slug is handled", %{user: user, map: map} do
|
||||
# Create another map
|
||||
{:ok, _other_map} =
|
||||
Map.new(%{
|
||||
name: "Other Map",
|
||||
slug: "other-map",
|
||||
owner_id: user.id,
|
||||
description: "Other",
|
||||
scope: "wormholes"
|
||||
})
|
||||
|
||||
# Try to update first map to use other map's slug
|
||||
result =
|
||||
Map.update(map, %{
|
||||
slug: "other-map"
|
||||
})
|
||||
|
||||
# Should either fail or auto-increment
|
||||
case result do
|
||||
{:ok, updated_map} ->
|
||||
# If successful, slug should be different
|
||||
assert updated_map.slug != "other-map"
|
||||
assert updated_map.slug =~ ~r/^other-map-\d+$/
|
||||
|
||||
{:error, _} ->
|
||||
# Or it can fail with validation error
|
||||
:ok
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
describe "get_map_by_slug with duplicates" do
|
||||
setup do
|
||||
user = create_test_user()
|
||||
%{user: user}
|
||||
end
|
||||
|
||||
test "get_map_by_slug! raises on duplicates if they exist" do
|
||||
# Note: This test documents the behavior when duplicates somehow exist
|
||||
# In production, this should be prevented by our fixes
|
||||
# If duplicates exist (data integrity issue), the query should fail
|
||||
|
||||
# This is a documentation test - we can't easily create duplicates
|
||||
# due to the database constraint, but we document expected behavior
|
||||
assert true
|
||||
end
|
||||
end
|
||||
|
||||
# Helper functions
|
||||
|
||||
defp create_test_user do
|
||||
# Create a test user with necessary attributes
|
||||
{:ok, user} =
|
||||
WandererApp.Api.User.new(%{
|
||||
name: "Test User #{:rand.uniform(10_000)}",
|
||||
eve_id: :rand.uniform(100_000_000)
|
||||
})
|
||||
|
||||
user
|
||||
end
|
||||
end
|
||||
84
test/unit/user/user_activity_tracker_test.exs
Normal file
84
test/unit/user/user_activity_tracker_test.exs
Normal file
@@ -0,0 +1,84 @@
|
||||
defmodule WandererApp.User.ActivityTrackerTest do
|
||||
use WandererApp.DataCase, async: false
|
||||
|
||||
alias WandererApp.User.ActivityTracker
|
||||
|
||||
describe "track_map_event/2" do
|
||||
test "returns {:ok, result} on success" do
|
||||
# This test verifies the happy path
|
||||
# In real scenarios, this would succeed when creating a new activity record
|
||||
assert {:ok, _} = ActivityTracker.track_map_event(:test_event, %{})
|
||||
end
|
||||
|
||||
test "returns {:ok, nil} on error without crashing" do
|
||||
# This simulates the scenario where tracking fails (e.g., unique constraint violation)
|
||||
# The function should handle the error gracefully and return {:ok, nil}
|
||||
|
||||
# Note: In actual implementation, this would catch errors from:
|
||||
# - Unique constraint violations
|
||||
# - Database connection issues
|
||||
# - Invalid data
|
||||
|
||||
# The key requirement is that it NEVER crashes the calling code
|
||||
result = ActivityTracker.track_map_event(:map_connection_added, %{
|
||||
character_id: nil, # This will cause the function to skip tracking
|
||||
user_id: nil,
|
||||
map_id: nil
|
||||
})
|
||||
|
||||
# Should return success even when input is incomplete
|
||||
assert {:ok, _} = result
|
||||
end
|
||||
|
||||
test "handles errors gracefully and logs them" do
|
||||
# Verify that errors are logged for observability
|
||||
# This is important for monitoring and debugging
|
||||
|
||||
# The function should complete without raising even with incomplete data
|
||||
assert {:ok, _} = ActivityTracker.track_map_event(:map_connection_added, %{
|
||||
character_id: nil,
|
||||
user_id: nil,
|
||||
map_id: nil
|
||||
})
|
||||
end
|
||||
end
|
||||
|
||||
describe "track_acl_event/2" do
|
||||
test "returns {:ok, result} on success" do
|
||||
assert {:ok, _} = ActivityTracker.track_acl_event(:test_event, %{})
|
||||
end
|
||||
|
||||
test "returns {:ok, nil} on error without crashing" do
|
||||
result = ActivityTracker.track_acl_event(:map_acl_added, %{
|
||||
user_id: nil,
|
||||
acl_id: nil
|
||||
})
|
||||
|
||||
assert {:ok, _} = result
|
||||
end
|
||||
end
|
||||
|
||||
describe "error resilience" do
|
||||
test "always returns success tuple even on internal errors" do
|
||||
# The key guarantee is that activity tracking never crashes calling code
|
||||
# Even if the internal tracking fails (e.g., unique constraint violation),
|
||||
# the wrapper ensures a success tuple is returned
|
||||
|
||||
# This test verifies that the function signature guarantees {:ok, _}
|
||||
# regardless of internal errors
|
||||
|
||||
# Test with nil values (which will fail validation)
|
||||
assert {:ok, _} = ActivityTracker.track_map_event(:test_event, %{
|
||||
character_id: nil,
|
||||
user_id: nil,
|
||||
map_id: nil
|
||||
})
|
||||
|
||||
# Test with empty map (which will fail validation)
|
||||
assert {:ok, _} = ActivityTracker.track_map_event(:test_event, %{})
|
||||
|
||||
# The guarantee is: no matter what, it returns {:ok, _}
|
||||
# This prevents MatchError crashes in calling code
|
||||
end
|
||||
end
|
||||
end
|
||||
Reference in New Issue
Block a user