[Libvir] [RFC][PATCH 1/2] Tested NUMA patches for available memory and topology

[Daniel Veillard]

On Fri, Sep 28, 2007 at 06:42:10AM -0400, beth kon wrote:
> Richard W.M. Jones wrote:
> 
> >beth kon wrote:
> >
> >>Patch for accessing available memory.
> >
> >
> >--- libvirt.danielpatch/src/driver.h    2007-09-11 15:29:43.000000000 
> >-0400
> >+++ libvirt.cellsMemory/src/driver.h    2007-09-27 18:39:52.000000000 
> >-0400
> >@@ -258,8 +258,9 @@ typedef virDriver *virDriverPtr;
> > typedef int
> >     (*virDrvNodeGetCellsFreeMemory)
> >                     (virConnectPtr conn,
> >-                     unsigned long *freeMems,
> >-             int nbCells);
> >+                     long long *freeMems,
> >
> >This needs to be declared unsigned long long.  If you configure with 
> >--enable-compile-warnings=error then the compiler will catch these 
> >sorts of errors.
> >
> >--- libvirt.danielpatch/src/xend_internal.c    2007-09-10 
> >17:35:39.000000000 -0400
> >+++ libvirt.cellsMemory/src/xend_internal.c    2007-09-27 
> >18:39:52.000000000 -0400
> >@@ -1954,6 +1954,8 @@ xenDaemonOpen(virConnectPtr conn, const
> > {
> >     xmlURIPtr uri = NULL;
> >     int ret;
> >+
> >+    virNodeInfo nodeInfo;
> >
> >This variable is never used.
> >
> >[ And from part 2/2 of the patch ]
> >
> >+ * getNumber:
> >
> >sscanf?
> 
> The reason I created this is because I also wanted to find the length of 
> the segment so I could add it to the parsing offset to check what was 
> next in the string.  That level of checking may be unnecessary 
> (overkill), and in any case could be more easily achieved using 
> something like sscanf for some token portion of the string. As I said, I 
> am *certain* there is a prettier way to do this!
> 
> >
> >[ And in general ]
> >
> >I compiled this version & was hoping to test it, but I don't seem to 
> >have the right combination of Xen to make it work.  At least I don't 
> >see any <topology> section in the XML capabilities.  What patches do I 
> >need for Xen to make this work?  I have a 2 socket AMD machine which I 
> >assume should work with this.
> 
> Daniel has built the kernel and xen rpms with the needed patches.

  People can fetch those (based on RHEL-5.1 rpms base) from
    http://veillard.com/NUMA/
the kernel-xen and xen(-devel) should be sufficient . Server is on my ADSL
line please do not DoS it or I will be even slower than usual :-)

Daniel

-- 
Red Hat Virtualization group http://redhat.com/virtualization/
Daniel Veillard      | virtualization library  http://libvirt.org/
veillard at redhat.com  | libxml GNOME XML XSLT toolkit  http://xmlsoft.org/
http://veillard.com/ | Rpmfind RPM search engine  http://rpmfind.net/