xfs seems performance lower when long time seq write into ssd

["=?gb18030?b?wuvUxg==?=" <wang.yong@xxxxxxxxxxx>]

Hi All,

Recently, I meet a  strange quetion. I have done seq write (blocksize=1m) into mount folders.

If total bytes is small, the avg write rate is 370MBs (little files :   4MB * 256 * 60 )

If total bytes is big, the avg write rate is 180MBs  (a lot of files :   4MB * 256 * 600)

the raw ssd benchmark, seq write is 400MBs.

Can anybody help to explain it?  argument is wrong, or something else. 

Below argument list:

Hardware:        Intel 3750 ssd  480GB  (sata3)

centos:             7.3  x86_64

kernel:              3.10.0-514.el7.x86_64

software:          mkfs.xfs

mount feature:   /dev/sdb1  type xfs (rw,noatime,attr2,inode64,logbsize=256k,noquota)

xfs_info /dev/sdl1 :

meta-data=""              isize=512    agcount=4, agsize=28975477 blks

         =                       sectsz=4096  attr=2, projid32bit=1

         =                       crc=1        finobt=0 spinodes=0

data     =                       bsize=4096   blocks=115901905, imaxpct=25

         =                       sunit=0      swidth=0 blks

naming   =version 2              bsize=4096   ascii-ci=0 ftype=1

log      =internal               bsize=4096   blocks=56592, version=2

         =                       sectsz=4096  sunit=1 blks, lazy-count=1

realtime =none                   extsz=4096   blocks=0, rtextents=0

Tks and Rgds