[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Xen-devel] [PATCH v1][RFC] xen balloon driver numa support, libxl interface



>>> On 12.08.13 at 15:18, Yechen Li <lccycc123@xxxxxxxxx> wrote:
>   This small patch implements a numa support of memory operation for libxl
>   The command is: xl mem-set-numa [-e] vmid memorysize nodeid
>   To pass the parameters to balloon driver in kernel, I add a file of 
> xen-store
> as /local/domain/(id)/memory/target_nid, hoping this is ok....
> 
>   It's my first time submitting a patch, please point out the problems so 
> that I could work better in future, thanks very much!

The main problem here is the lack of a consumer of this ...

> @@ -3754,7 +3761,10 @@ retry_transaction:
>          abort_transaction = 1;
>          goto out;
>      }
> -
> +    //lcc:
> +    LIBXL__LOG(ctx, LIBXL__LOG_DEBUG, "target_nid = %d focus= %d", 
> node_specify, (int) nodeexact);
> +    libxl__xs_write(gc, t, libxl__sprintf(gc, "%s/memory/target_nid",
> +                dompath), "%"PRId32" %"PRId32, node_specify, (int)nodeexact);

... new Xenbus node. Without (so far) a true view into the
host topology, even if you added a respective consumer to the
balloon driver, how would that driver honor such a request?
And even if it knew about host topology, unless the virtual
topology in the subject domain sufficiently closely resembled the
host's, it would - afaict - still have no way of obtaining suitable
memory from the page allocator.

Jan


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel


 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.