Your answer might lie with */proc/sys/vm/pagecache:* * * *http://kbase.redhat.com/faq/docs/DOC-7055*
http://www.ibm.com/developerworks/linux/library/l-adfly.html On Thu, Feb 11, 2010 at 9:19 AM, Martin, Terry R. (CMS/CTR) (CTR) < [email protected]> wrote: > HI Offer, > > Unfortunately this is the way it works under z/Linux. Of course because > of the way z/VM tries to Share memory once memory for a z/Linux guest is > pushed into cache it is not considered when z/VM is trying to manage the > memory by taking from one to give to another, it limits z/VM in its' > memory management process. In Linux he sees having a bunch o f cache as > a good thing because he has use of the cache and allows in most cases > for better performance. So as you can see there is a conflict here. The > hope is that these types of conflicts including double paging due to the > same LRU approach used by both z/Linux and z/VM, as well as a way to > dynamically prioritize the workloads for not only z/VM but for processes > running in z/Linux can be resolved. > > Anyway for now the best approach for the cache is to try to size the > memory of the z/Linux guest to where you just see a very small amount of > SWAPPING and make this SWAPPING go to VDISK. VDISK SWAPPING is a memory > speed in z/VM so it is very fast. This will set the behavior so that > z/Linux does not cache. I know from my own experiences that this is not > always an easy thing to nail down but for the most part I have been able > to balance this between the OSs'. > > Thank You, > > Terry Martin > Lockheed Martin - Citic > z/OS and z/VM Performance Tuning and Operating Systems Support > Office - 443 348-2102 > Cell - 443 632-4191 > > > -----Original Message----- > From: Linux on 390 Port [mailto:[email protected]] On Behalf Of > Offer Baruch > Sent: Thursday, February 11, 2010 8:18 AM > To: [email protected] > Subject: Linux file system cache > > Hi all, > > One of the problems with Linux under VM (not just z/VM I guess) is that > no > matter how much memory you allocate to the guest it will consume it all > as > cache. > It just seems reasonable to be able to limit this cache to a user > defined > value leaving the rest of it for the applications. > Sadly I couldn't find a parameter to enforce this limit. > So, my question is, is there a way to limit the cache? If not, why? > Obviously this caching method is just not good enough under VM. > Decreasing and increasing memory for a guest is quite disruptive and > adding > 100M to an oracle guest just looks bad :-) > > Thanks! > Offer Baruch > > No virus found in this outgoing message. > Checked by AVG - www.avg.com > Version: 9.0.733 / Virus Database: 271.1.1/2680 - Release Date: 02/10/10 > 21:38:00 > > ---------------------------------------------------------------------- > 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
