diff options
| author | alfred <alfred@FreeBSD.org> | 2013-01-15 19:26:17 +0000 |
|---|---|---|
| committer | alfred <alfred@FreeBSD.org> | 2013-01-15 19:26:17 +0000 |
| commit | c24045a7415012663f450adbe0ae77139d8dee0e (patch) | |
| tree | 52a94d743c3be86d898915889c3d13abb39f546d /sys/kern/subr_param.c | |
| parent | 3d394d93b6b9d2125d29b177824a45f084790397 (diff) | |
| download | FreeBSD-src-c24045a7415012663f450adbe0ae77139d8dee0e.zip FreeBSD-src-c24045a7415012663f450adbe0ae77139d8dee0e.tar.gz | |
Do not autotune ncallout to be greater than 18508.
When maxusers was unrestricted and maxfiles was allowed to autotune
much higher the result was that ncallout which was based on maxfiles
and maxproc grew much higher than was needed.
To fix this clip autotuning to the same number we would get with
the old maxusers algorithm which would stop scaling at 384
maxusers.
Growing ncalout higher is not likely to be needed since most consumers
of timeout(9) are gone and any higher value for ncallout causes the
callwheel hashes to be much larger than will even be needed for
most applications.
MFC after: 1 month
Reviewed by: mav
Diffstat (limited to 'sys/kern/subr_param.c')
| -rw-r--r-- | sys/kern/subr_param.c | 5 |
1 files changed, 4 insertions, 1 deletions
diff --git a/sys/kern/subr_param.c b/sys/kern/subr_param.c index fcb41e7..7671615 100644 --- a/sys/kern/subr_param.c +++ b/sys/kern/subr_param.c @@ -326,8 +326,11 @@ init_param2(long physpages) /* * XXX: Does the callout wheel have to be so big? + * + * Clip callout to result of previous function of maxusers maximum + * 384. This is still huge, but acceptable. */ - ncallout = 16 + maxproc + maxfiles; + ncallout = imin(16 + maxproc + maxfiles, 18508); TUNABLE_INT_FETCH("kern.ncallout", &ncallout); /* |
