In brief
我正在开发一个(梦想中的)游戏,我的后端堆栈是 Node.js 和带有 Knex 的 PostgreSQL(9.6)。我在这里保存所有玩家数据,我需要经常请求它。
其中一个请求需要进行 10 个简单的选择来提取数据,这就是问题开始的地方:如果服务器同时只处理 1 个请求,这些查询非常快(~1 毫秒)。但是,如果服务器并行处理许多请求(100-400),则查询执行时间会大大降低(每个查询可能长达几秒)
Details
为了更加客观,我将描述服务器的请求目标、选择查询和我收到的结果。
关于系统
我在 Digital Ocean 4cpu/8gb Droplet 上运行节点代码,并在同一配置上运行 Postgres(2 个不同的 Droplet,相同的配置)
关于请求
它需要执行一些游戏操作,为此他从数据库中选择 2 个玩家的数据
DDL
玩家数据由5张表表示:
CREATE TABLE public.player_profile(
id integer NOT NULL DEFAULT nextval('player_profile_id_seq'::regclass),
public_data integer NOT NULL,
private_data integer NOT NULL,
current_active_deck_num smallint NOT NULL DEFAULT '0'::smallint,
created_at bigint NOT NULL DEFAULT '0'::bigint,
CONSTRAINT player_profile_pkey PRIMARY KEY (id),
CONSTRAINT player_profile_private_data_foreign FOREIGN KEY (private_data)
REFERENCES public.profile_private_data (id) MATCH SIMPLE
ON UPDATE NO ACTION
ON DELETE NO ACTION,
CONSTRAINT player_profile_public_data_foreign FOREIGN KEY (public_data)
REFERENCES public.profile_public_data (id) MATCH SIMPLE
ON UPDATE NO ACTION
ON DELETE NO ACTION
);
CREATE TABLE public.player_character_data(
id integer NOT NULL DEFAULT nextval('player_character_data_id_seq'::regclass),
owner_player integer NOT NULL,
character_id integer NOT NULL,
experience_counter integer NOT NULL,
level_counter integer NOT NULL,
character_name character varying(255) COLLATE pg_catalog."default" NOT NULL,
created_at bigint NOT NULL DEFAULT '0'::bigint,
CONSTRAINT player_character_data_pkey PRIMARY KEY (id),
CONSTRAINT player_character_data_owner_player_foreign FOREIGN KEY (owner_player)
REFERENCES public.player_profile (id) MATCH SIMPLE
ON UPDATE NO ACTION
ON DELETE NO ACTION
);
CREATE TABLE public.player_cards(
id integer NOT NULL DEFAULT nextval('player_cards_id_seq'::regclass),
card_id integer NOT NULL,
owner_player integer NOT NULL,
card_level integer NOT NULL,
first_deck boolean NOT NULL,
consumables integer NOT NULL,
second_deck boolean NOT NULL DEFAULT false,
third_deck boolean NOT NULL DEFAULT false,
quality character varying(10) COLLATE pg_catalog."default" NOT NULL DEFAULT 'none'::character varying,
CONSTRAINT player_cards_pkey PRIMARY KEY (id),
CONSTRAINT player_cards_owner_player_foreign FOREIGN KEY (owner_player)
REFERENCES public.player_profile (id) MATCH SIMPLE
ON UPDATE NO ACTION
ON DELETE NO ACTION
);
CREATE TABLE public.player_character_equipment(
id integer NOT NULL DEFAULT nextval('player_character_equipment_id_seq'::regclass),
owner_character integer NOT NULL,
item_id integer NOT NULL,
item_level integer NOT NULL,
item_type character varying(20) COLLATE pg_catalog."default" NOT NULL,
is_equipped boolean NOT NULL,
slot_num integer,
CONSTRAINT player_character_equipment_pkey PRIMARY KEY (id),
CONSTRAINT player_character_equipment_owner_character_foreign FOREIGN KEY (owner_character)
REFERENCES public.player_character_data (id) MATCH SIMPLE
ON UPDATE NO ACTION
ON DELETE NO ACTION
);
CREATE TABLE public.player_character_runes(
id integer NOT NULL DEFAULT nextval('player_character_runes_id_seq'::regclass),
owner_character integer NOT NULL,
item_id integer NOT NULL,
slot_num integer,
decay_start_timestamp bigint,
CONSTRAINT player_character_runes_pkey PRIMARY KEY (id),
CONSTRAINT player_character_runes_owner_character_foreign FOREIGN KEY (owner_character)
REFERENCES public.player_character_data (id) MATCH SIMPLE
ON UPDATE NO ACTION
ON DELETE NO ACTION
);
带索引
knex.raw('create index "player_cards_owner_player_first_deck_index" on "player_cards"("owner_player") WHERE first_deck = TRUE');
knex.raw('create index "player_cards_owner_player_second_deck_index" on "player_cards"("owner_player") WHERE second_deck = TRUE');
knex.raw('create index "player_cards_owner_player_third_deck_index" on "player_cards"("owner_player") WHERE third_deck = TRUE');
knex.raw('create index "player_character_equipment_owner_character_is_equipped_index" on "player_character_equipment" ("owner_character") WHERE is_equipped = TRUE');
knex.raw('create index "player_character_runes_owner_character_slot_num_not_null_index" on "player_character_runes" ("owner_character") WHERE slot_num IS NOT NULL');
The code
第一个查询
async.parallel([
cb => tx('player_character_data')
.select('character_id', 'id')
.where('owner_player', playerId)
.limit(1)
.asCallback(cb),
cb => tx('player_character_data')
.select('character_id', 'id')
.where('owner_player', enemyId)
.limit(1)
.asCallback(cb)
], callbackFn);
第二次查询
async.parallel([
cb => tx('player_profile')
.select('current_active_deck_num')
.where('id', playerId)
.asCallback(cb),
cb => tx('player_profile')
.select('current_active_deck_num')
.where('id', enemyId)
.asCallback(cb)
], callbackFn);
Third q
playerQ = { first_deck: true }
enemyQ = { first_deck: true }
MAX_CARDS_IN_DECK = 5
async.parallel([
cb => tx('player_cards')
.select('card_id', 'card_level')
.where('owner_player', playerId)
.andWhere(playerQ)
.limit(MAX_CARDS_IN_DECK)
.asCallback(cb),
cb => tx('player_cards')
.select('card_id', 'card_level')
.where('owner_player', enemyId)
.andWhere(enemyQ)
.limit(MAX_CARDS_IN_DECK)
.asCallback(cb)
], callbackFn);
Fourth q
MAX_EQUIPPED_ITEMS = 3
async.parallel([
cb => tx('player_character_equipment')
.select('item_id', 'item_level')
.where('owner_character', playerCharacterUniqueId)
.andWhere('is_equipped', true)
.limit(MAX_EQUIPPED_ITEMS)
.asCallback(cb),
cb => tx('player_character_equipment')
.select('item_id', 'item_level')
.where('owner_character', enemyCharacterUniqueId)
.andWhere('is_equipped', true)
.limit(MAX_EQUIPPED_ITEMS)
.asCallback(cb)
], callbackFn);
第五个
runeSlotsMax = 3
async.parallel([
cb => tx('player_character_runes')
.select('item_id', 'decay_start_timestamp')
.where('owner_character', playerCharacterUniqueId)
.whereNotNull('slot_num')
.limit(runeSlotsMax)
.asCallback(cb),
cb => tx('player_character_runes')
.select('item_id', 'decay_start_timestamp')
.where('owner_character', enemyCharacterUniqueId)
.whereNotNull('slot_num')
.limit(runeSlotsMax)
.asCallback(cb)
], callbackFn);
解释(分析)
仅索引扫描,规划和执行时间
时间本身
(total是请求数,min/max/avg/median用于响应时间)
- 4个并发请求:
{ "total": 300, "avg": 1.81, "median": 2, "min": 1, "max": 6 }
- 400 concurrent requests:
-
{ "total": 300, "avg": 209.57666666666665, "median": 176, "min": 9, "max": 1683 }
- 首先选择
-
{ "total": 300, "avg": 2105.9, "median": 2005, "min": 1563, "max": 4074 }
- 最后选择
我尝试将执行时间超过 100 毫秒的慢速查询放入日志中 - 什么也没有。还尝试将连接池大小增加到并行请求数 - 也没有。