Date: Sat, 13 Jul 2002 00:19:54 -0700 (PDT) From: Matthew Dillon <dillon@apollo.backplane.com> To: hawkeyd@visi.com (D J Hawkey Jr) Cc: freebsd-stable@freebsd.org Subject: Re: tuning(7) request was: Re: Performance boost with kernel options in FBSD 4.6 Message-ID: <200207130719.g6D7JsDS076879@apollo.backplane.com> References: <04a601c228dc$c6dbb980$681663cf_icarz.com@ns.sol.net> <200207111930.g6BJUX5m096974_apollo.backplane.com@ns.sol.net> <200207120344.g6C3iDS63523@sheol.localdomain>
next in thread | previous in thread | raw e-mail | index | archive | help
:In your estimation, would it affect the case of several chained pipes,
:[doing|waiting on] disk I/O? Or, say, a complex SQL query?
:
:Sorry for my naivete, but would increasing the HZ have the effect of making
:the rest of my activities "snappier" in the above situation? Or is this
:still too vague?
:
:The machines are 700Mhz Celerons and "better", mostly IDE, BTW.
:
:Thanks,
:Dave
Anything that blocks on lots of little I/O's, which a complex SQL query
will do, can monopolize the system's resources. But if the data
is well cached a complex sql query will simply be cpu bound and the
scheduler will take care of it.
In anycase, you just have to play with HZ to find out whether it has
any effect.
-Matt
Matthew Dillon
<dillon@backplane.com>
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-stable" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200207130719.g6D7JsDS076879>