From 6c13f40e3d6911a12b02e04b5637be3573065387 Mon Sep 17 00:00:00 2001 From: ru Date: Tue, 13 Aug 2002 14:37:41 +0000 Subject: mdoc(7) police: Bump document date, removed (again) hard sentence breaks.. --- share/man/man7/tuning.7 | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) (limited to 'share') diff --git a/share/man/man7/tuning.7 b/share/man/man7/tuning.7 index cf110ea..daa93d3 100644 --- a/share/man/man7/tuning.7 +++ b/share/man/man7/tuning.7 @@ -4,7 +4,7 @@ .\" .\" $FreeBSD$ .\" -.Dd May 25, 2001 +.Dd June 25, 2002 .Dt TUNING 7 .Os .Sh NAME @@ -416,21 +416,28 @@ wasted memory but you should experiment to find out. .Pp The .Va vfs.write_behind -sysctl defaults to 1 (on). This tells the filesystem to issue media +sysctl defaults to 1 (on). +This tells the filesystem to issue media writes as full clusters are collected, which typically occurs when writing -large sequential files. The idea is to avoid saturating the buffer -cache with dirty buffers when it would not benefit I/O performance. However, +large sequential files. +The idea is to avoid saturating the buffer +cache with dirty buffers when it would not benefit I/O performance. +However, this may stall processes and under certain circumstances you may wish to turn it off. .Pp The .Va vfs.hirunningspace sysctl determines how much outstanding write I/O may be queued to -disk controllers system wide at any given instance. The default is +disk controllers system-wide at any given instance. +The default is usually sufficient but on machines with lots of disks you may want to bump -it up to four or five megabytes. Note that setting too high a value +it up to four or five megabytes. +Note that setting too high a value (exceeding the buffer cache's write threshold) can lead to extremely -bad clustering performance. Do not set this value arbitrarily high! Also, +bad clustering performance. +Do not set this value arbitrarily high! +Also, higher write queueing values may add latency to reads occuring at the same time. .Pp -- cgit v1.1