Do you have 100% cpu usage? HMC can tell that. If it's so, than is this user or system load?
Linux on 390 Port <LINUX-390@VM.MARIST.EDU> írta 2005.08.16 20:38:54 időpontban: > Some additional comments, to everyone who has offered advice: > > - We have a dedicated processor so it's not an LPAR weight issue. That > was my first guess, but we've confirmed the processor is dedicated. > - We have a -very- large number of devices defined to the LPAR, and > since at our site we tend to keep each LPAR configured similarly, Linux > is seeing them all. We are considering reworking the device > configuration for -this- particular LPAR to greatly restrict the number > of devices. I -do- suspect this will help. > > Thanks for the advice and I'll keep you all posted on any further > status. > > -----Original Message----- > From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of > Post, Mark K > Sent: Tuesday, August 16, 2005 1:31 PM > To: LINUX-390@VM.MARIST.EDU > Subject: Re: SLES 9 in an LPAR > > I wondering how many devices are defined to the LPAR in the IOCDS. Any > idea? > > > Mark Post > > -----Original Message----- > From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of > Scully, William P > Sent: Tuesday, August 16, 2005 12:13 PM > To: LINUX-390@VM.MARIST.EDU > Subject: SLES 9 in an LPAR > > > I'm having a performance problem. > > I was asked to install SLES 9 64-bit into an LPAR. To create the server > I got my hands on the needed DASD and conducted the install of Linux > under z/VM. The virtual hardware configuration (DASD and OSA addresses) > were specified as would be used on the LPAR. As usual, the installation > went well. The resulting copy of Linux can be booted under z/VM in > perhaps a minute or two. > > However when I attempt to start this copy of Linux in an LPAR (512M and > one dedicated CPU in an IFL on a 2094-313), it runs so slow you might > think the software was written by folks in Redmond, Washington. It > takes perhaps 15-20 minutes to boot. At times it seems to be completely > unresponsive, even to the directly-connected HMC "Operating System > Message" panel. > > I've encoded the so-called kernel timer patch both enabled and disabled, > to no avail. And limited the DASD the kernel is to use with a > DASD=nnnn-nnnn phrase in zipl.conf. But clearly I've missed something > pretty obvious. Anyone have an idea? > > ---------------------------------------------------------------------- > For LINUX-390 subscribe / signoff / archive access instructions, send > email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or > visit http://www.marist.edu/htbin/wlvindex?LINUX-390 > > ---------------------------------------------------------------------- > For LINUX-390 subscribe / signoff / archive access instructions, send > email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or > visit http://www.marist.edu/htbin/wlvindex?LINUX-390 > > ---------------------------------------------------------------------- > For LINUX-390 subscribe / signoff / archive access instructions, > send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit > http://www.marist.edu/htbin/wlvindex?LINUX-390 ---------------------------------------------------------------------- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
