Block cache: implement posix_fadvise for file read (SSD) (bypass OS page cache)

VladRodionov commented 10 years ago

We do not need page cache for SSD at all. SOme other perf tips:

SSD optimization tips

Your data are placed on XFS filesystem (mounted with "noatime,nodiratime,nobarrier" options) and your storage device is managed by "noop" or "deadline" I/O scheduler (see previous tests for details).
You're using O_DIRECT within your InnoDB config (don't know yet if using 4K page size will really bring some improvement over 16K as there will be x4 times more pages to manage within the same memory space, which may require x4 times more lock events and other overheads.. - while in term of Writes/sec potential performance the difference is not so big! - from the presented test results in most cases it's only 80K vs 60K writes/sec -- but of course a real result from a real database workload will be better ;-)).
And, finally, be sure your write activity is not focused on a single data file! - they should at last be more or equal than 4 to be sure your performance is not lowered from the beginning by the filesystem layer!

VladRodionov commented 10 years ago

Some code can be found in Hadoop NativeIO. As since we are running under Hadoop anyway, its good to re-use existing library.

VladRodionov commented 10 years ago

For Linux DIRECT IO we can try the following:

fcntl(fd, F_SETFL, flags | O_DIRECT) -set O_DIRECT flag for already opened file http://linux.die.net/man/2/fcntl

VladRodionov commented 10 years ago

Another option: limit page cache size:

It can be done on SUSE: (see SUSE) It can be done in RH/Centos: echo '1' > /proc/sys/vm/pagecache (?)

Linux page cache is evil, especially when it grows unbounded.

VladRodionov commented 10 years ago

I did initial code check in. This 'bypass page cache' works on Mac OSX, but not on Linux yet.

VladRodionov / bigbase