Re: [libvirt] [PATCH 1/1] qemu: host NUMA hugepage policy without guest NUMA

On Wed, Oct 12, 2016 at 10:27:50AM +0200, Martin Kletzander wrote: Thanks for taking a look at this :-) The point of using a memory-backend-file is that with it, the NUMA policy can be specified to QEMU, but with -mem-path it can't. It seems to be a way to tell QEMU to apply NUMA policy in the right place. It does seem odd to me to use memory-backend-file without attaching the backend to a guest NUMA node, but it seems to do the right thing in this case. (If there are guest NUMA nodes, or if hugepages aren't being used, policy is correctly applied.) I'll describe my test case in detail, perhaps there's something I don't understand happening. * I set up a machine with two (fake) NUMA nodes (0 and 1), with 2G of hugepages on node 1, and none on node 0. * I create a 2G guest using virt-install: virt-install --name ppc --memory=2048 --disk ~/tmp/tmp.qcow2 --cdrom ~/tmp/ubuntu-16.04-server-ppc64el.iso --wait 0 --virt-type qemu --memorybacking hugepages=on --graphics vnc --arch ppc64le * I "virsh destroy" and then "virsh edit" to add this block to the guest XML: <numatune> <memory mode='strict' nodeset='0'/> </numatune> * "virsh start", and the machine starts (I believe it should fail due to insufficient memory satasfying the policy). * "numastat -p $(pidof qemu-system-ppc64)" shows something like this: Per-node process memory usage (in MBs) for PID 8048 (qemu-system-ppc) Node 0 Node 1 Total --------------- --------------- --------------- Huge 0.00 2048.00 2048.00 Heap 8.12 0.00 8.12 Stack 0.03 0.00 0.03 Private 35.80 6.10 41.90 ---------------- --------------- --------------- --------------- Total 43.95 2054.10 2098.05 So it looks like it's allocated hugepages from node 1, isn't this violating the policy I set via numatune? OK. I'm not sure if I understand this; this function used to add "-mem-path" and it would now add either "-mem-path" or a memory backend (with the same path), both doing the same kind of configuration (is that not the case?). I did see that it must not be called twice (which was already the case, I think), but I convinced myself that it would only be called once: There are only two callers of qemuBuildMemPathStr(). One is in qemuBuildMemCommandLine() and it is protected by "if (!virDomainNumaGetNodeCount(def->numa)", and the other is in qemuBuildNumaArgStr() and the (only) call to that is protected by "if (virDomainNumaGetNodeCount(def->numa)". Is that safe enough? Oops, yes. OK. I understand. I'm interested to see what you think of the test case :-) Cheers, Sam.