I ran into pretty interesting behavior today. We needed to dump and reload large database and we had pretty good IO subsystem so we started number of mysqldump processes in parallel. Unlike in other case when we did load in parallel, dump in parallel did not increase IO rate significantly and we could still see just about 1.5 average outstanding IO requests to the disk.
Lets look at SHOW INNODB STATUS:
——–
FILE I/O
——–
I/O thread 0 state: waiting for i/o request (insert buffer
thread)
I/O thread 1 state: waiting for i/o request (log thread)
I/O thread 2 state: doing file i/o (read thread) ev set
I/O thread 3 state: waiting for i/o request (write thread)
Pending normal aio reads: 256, aio writes: 0,
ibuf aio reads: 0, log i/o’s: 0, sync i/o’s: 0
Pending flushes (fsync) log: 0; buffer pool: 0
112084404 OS file reads, 29836003 OS file writes, 2038246 OS …