Bumping the read-ahead count once more, to value equivalent to 512 KiB on

most system, based on benchmark results on a low-end fibre channel SAN
under VMWare:

vfs.read_max		read performance
8  (historical default)	83 MB/s
16 (recent bump)	131 MB/s
32 (this version)	152 MB/s
64			157 MB/s

(results are +/- 3 MB/s)

As read-ahead is heuristic, based on past IO requests, it shouldn't be
problematic. The new default is still smaller then in other OSes.
This commit is contained in:
Ivan Voras 2010-08-09 22:56:10 +00:00
parent dd8c13d589
commit e98c5c7813
Notes: svn2git 2020-12-20 02:59:44 +00:00
svn path=/head/; revision=211126

View file

@ -71,7 +71,7 @@ static int write_behind = 1;
SYSCTL_INT(_vfs, OID_AUTO, write_behind, CTLFLAG_RW, &write_behind, 0,
"Cluster write-behind; 0: disable, 1: enable, 2: backed off");
static int read_max = 16;
static int read_max = 32;
SYSCTL_INT(_vfs, OID_AUTO, read_max, CTLFLAG_RW, &read_max, 0,
"Cluster read-ahead max block count");