Date: Sat, 31 Mar 2001 07:40:02 -0800 (PST) From: Cy Schubert - ITSD Open Systems Group <Cy.Schubert@uumail.gov.bc.ca> To: freebsd-bugs@FreeBSD.org Subject: Re: kern/10411: top, vmstat, iostat show 0% cpu idle & usage on SMP system Message-ID: <200103311540.f2VFe2I23254@freefall.freebsd.org>
next in thread | raw e-mail | index | archive | help
The following reply was made to PR kern/10411; it has been noted by GNATS. From: Cy Schubert - ITSD Open Systems Group <Cy.Schubert@uumail.gov.bc.ca> To: freebsd-gnats-submit@FreeBSD.org, bob@pmr.com Cc: Subject: Re: kern/10411: top, vmstat, iostat show 0% cpu idle & usage on SMP system Date: Sat, 31 Mar 2001 07:35:46 -0800 On a P120 system running 4.3-RC I enabled rand_irqs="1 3" and started encountering this problem about and subsequent to load being applied to the system, especially network load. I noticed that during an NFS mount the problem occurred. I would think that the extra interrupt latency caused by rand_irqs caused timekeeping problems on the P120. Adding kern.timecounter.method=1 to sysctl.conf worked around the problem. Alternatively, setting rand_irqs="NO" and reverting back to EGD (Entropy Gathering Daemon) also resolved the problem. It is recommended that it be documented somewhere that setting rand_irqs on some slower machines may cause enough interrupt latency to cause timekeeping problems and list possible workarounds. I can make EGD available as a port for users of slower systems. Regards, Phone: (250)387-8437 Cy Schubert Fax: (250)387-5766 Team Leader, Sun/Alpha Team Internet: Cy.Schubert@osg.gov.bc.ca Open Systems Group, ITSD, ISTA Province of BC To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-bugs" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200103311540.f2VFe2I23254>