MySQL 在大量行锁后崩溃

Question

我在 Windows Server 2008 R2 上使用 MySQL 5.7.14 x64

有时(一天中随机多次)mysql 会因该堆栈跟踪而崩溃

11:44:40 UTC - mysqld got exception 0x80000003 ;
This could be because you hit a bug. It is also possible that this binary
or one of the libraries it was linked against is corrupt, improperly built,
or misconfigured. This error can also be caused by malfunctioning hardware.
Attempting to collect some information that could help diagnose the problem.
As this is a crash and something is definitely wrong, the information
collection process might fail.

key_buffer_size=8388608
read_buffer_size=65536
max_used_connections=369
max_threads=2800
thread_count=263
connection_count=263
It is possible that mysqld could use up to 
key_buffer_size + (read_buffer_size + sort_buffer_size)*max_threads = 3195125 K  bytes of memory
Hope that's ok; if not, decrease some variables in the equation.

Thread pointer: 0x2ee2b72b0
Attempting backtrace. You can use the following information to find out
where mysqld died. If you see no messages after this, something went
terribly wrong...
13fe1bad2    mysqld.exe!my_sigabrt_handler()[my_thr_init.c:449]
1401c7979    mysqld.exe!raise()[winsig.c:587]
1401c6870    mysqld.exe!abort()[abort.c:82]
13ff1dd38    mysqld.exe!ut_dbg_assertion_failed()[ut0dbg.cc:67]
13ff1df51    mysqld.exe!ib::fatal::~fatal()[ut0ut.cc:916]
13ff0e008    mysqld.exe!buf_LRU_check_size_of_non_data_objects()[buf0lru.cc:1219]
13ff0f4ab    mysqld.exe!buf_LRU_get_free_block()[buf0lru.cc:1303]
1400305cb    mysqld.exe!buf_block_alloc()[buf0buf.cc:557]
13ff3767e    mysqld.exe!mem_heap_create_block_func()[mem0mem.cc:319]
13ff37499    mysqld.exe!mem_heap_add_block()[mem0mem.cc:408]
13ffd87f4    mysqld.exe!RecLock::lock_alloc()[lock0lock.cc:1441]
13ffd795c    mysqld.exe!RecLock::create()[lock0lock.cc:1534]
13ffd73a6    mysqld.exe!RecLock::add_to_waitq()[lock0lock.cc:1735]
13ffdcaaa    mysqld.exe!lock_rec_lock_slow()[lock0lock.cc:2007]
13ffdc6ce    mysqld.exe!lock_rec_lock()[lock0lock.cc:2081]
13ffd8cc7    mysqld.exe!lock_clust_rec_read_check_and_lock()[lock0lock.cc:6307]
140076fe3    mysqld.exe!row_ins_set_shared_rec_lock()[row0ins.cc:1502]
140072927    mysqld.exe!row_ins_check_foreign_constraint()[row0ins.cc:1739]
140072de8    mysqld.exe!row_ins_check_foreign_constraints()[row0ins.cc:1932]
140075d69    mysqld.exe!row_ins_sec_index_entry()[row0ins.cc:3356]
1400758a6    mysqld.exe!row_ins_index_entry_step()[row0ins.cc:3583]
140071b30    mysqld.exe!row_ins()[row0ins.cc:3721]
14007755a    mysqld.exe!row_ins_step()[row0ins.cc:3907]
13ffaad50    mysqld.exe!row_insert_for_mysql_using_ins_graph()[row0mysql.cc:1735]
13fe7a7d3    mysqld.exe!ha_innobase::write_row()[ha_innodb.cc:7489]
13f6e5531    mysqld.exe!handler::ha_write_row()[handler.cc:7891]
13f8e54de    mysqld.exe!write_record()[sql_insert.cc:1860]
13f8e916a    mysqld.exe!read_sep_field()[sql_load.cc:1222]
13f8e7af4    mysqld.exe!mysql_load()[sql_load.cc:563]
13f716e86    mysqld.exe!mysql_execute_command()[sql_parse.cc:3649]
13f7194b3    mysqld.exe!mysql_parse()[sql_parse.cc:5565]
13f71267d    mysqld.exe!dispatch_command()[sql_parse.cc:1430]
13f71368a    mysqld.exe!do_command()[sql_parse.cc:997]
13f6d82bc    mysqld.exe!handle_connection()[connection_handler_per_thread.cc:300]
140105122    mysqld.exe!pfs_spawn_thread()[pfs.cc:2191]
13fe1b93b    mysqld.exe!win_thread_start()[my_thread.c:38]
1401c73ef    mysqld.exe!_callthreadstartex()[threadex.c:376]
1401c763a    mysqld.exe!_threadstartex()[threadex.c:354]
772859bd    kernel32.dll!BaseThreadInitThunk()
773ba2e1    ntdll.dll!RtlUserThreadStart() 

目前仅活跃 2 笔交易

---TRANSACTION 1111758443, ACTIVE 565 sec
mysql tables in use 7, locked 7
7527 lock struct(s), heap size 876752, 721803 row lock(s), undo log entries 379321
MySQL thread id 166068, OS thread handle 1508, query id 112695582 localhost converter Waiting for table level lock
delete from pl

using

import_k2b_product_links ipl inner join k2b_products pSource on ipl.src_product = pSource.article and pSource.account_id = 22

inner join k2b_products pDest on ipl.dst_product = pDest.article and pDest.account_id = 22

inner join k2b_product_links pl on pl.src_product_id = pSource.id and pl.dst_product = pDest.id

where ipl.action = 1
---TRANSACTION 1111759716, ACTIVE 496 sec inserting, thread declared inside InnoDB 1
mysql tables in use 4, locked 4
7 lock struct(s), heap size 1304535248, 102060778 row lock(s), undo log entries 1
MySQL thread id 19436, OS thread handle 11664, query id 112301161 localhost exchange_central
LOAD DATA INFILE 'd:/kdm/temp/webCentral/ufrd1uwx.v2r'

    INTO TABLE k2b_orders

    FIELDS TERMINATED BY ',' OPTIONALLY ENCLOSED BY '"'

  LINES TERMINATED BY '\n'

(id_status, dt, account_id, sms_sended, params, update_ts, exported, id_editor, dt_offset, device_id, gen, changer_device_id, total, creator_device_id, id, dt_server, device_category_id, original_params, order_num, sended, editor_comment, admin_comment)

不明白为什么事务1111758443等待表级锁？

为什么事务 1111759716 锁定 102060778 行，而它只从外部文件加载一行并显示在撤消日志条目 1 中？

由于这种巨大的锁定和崩溃的已知原因，我必须进行哪些调查。

谢谢!

Answer 1

有两件事让我认为崩溃并不是“真正的”问题。

日志中的两个查询都显示“巨大”时间，例如 ACTIVE 565 秒。

而且这些都很大:

max_used_connections=369
max_threads=2800
thread_count=263
connection_count=263

当有数百个线程同时事件时，InnoDB 就会陷入困境。吞吐量停滞，延迟急剧上升。

一种治疗方法是避免过多的连接。有时最好在客户端完成此操作。什么是客户？例如，Apache 有 MaxClients。十几个 Apache(每个 MaxClients = 50)将尝试打开 600 个连接。一个 Apache 可能无法有效地同时处理 50 个线程。降低该数字。

是否有任何VIEWs在欺骗我们？

另一件事是追求表级锁。让我们看看SHOW CREATE TABLE 所涉及的表。检查适当的索引。

import_k2b_product_links: INDEX(action, ...)
k2b_products: INDEX(account_id, src_product)   -- in either order
k2b_products: INDEX(account_id, dest_product)  -- in either order
k2b_product_links:  INDEX(src_product_id, dest_product_id) -- or PK, see below

k2b_product_links 是一个多:多映射表吗？如果是这样，请按照讨论 Here 删除 id auto_increment .

索引建议(如果有用)可以加快DELETE速度，从而减少可能的争用。