Igor, Some minor nits I overlooked:
Am 18.03.2015 um 17:38 schrieb Igor Mammedov: > since commit "Since" :) > dd0247e0 pc: acpi: mark all possible CPUs as enabled in SRAT > Linux kernel actually tries to use CPU to Node mapping from > QEMU provided SRAT table instead of discarding it, and that > in some cases breaks build_sched_domains() which expects > sane mapping where cores/threads belonging to the same socket > are on the same NUMA node. > > With current default round-robin mapping of VCPUs to nodes > guest ends-up with cores/threads belonging to the same socket > being on different NUMA nodes. > > For example with following CLI: > qemu-kvm -m 4G -smp 5,sockets=2,cores=4,threads=1,maxcpus=8 \ > -numa node,nodeid=0 -numa node,nodeid=1 There is no qemu-kvm upstream, use qemu-system-x86_64 instead? Isn't the 5 wrong here? I would expect sockets, cores and threads overriding that value to 8. > 2.6.32 based kernels will hang on boot due to incorrectly build "built"? > sched_group-s list in update_sd_lb_stats() > so comment in QEMU justifying dumb default mapping: > " > guest OSes must cope with this anyway, because there are BIOSes > out there in real machines which also use this scheme. > " > isn't really valid. > > Replacing default mapping with a manual, where VCPUs belonging to > the same socket are on the same NUMA node, fixes issue for "fixes the issue" > guests which can't handle nonsense topology i.e. changing CLI to: > -numa node,nodeid=0,cpus=0-3 -numa node,nodeid=1,cpus=4-7 > > So instead of simply scattering VCPUs around nodes, map > the same socket VCPUs to the same NUMA node, which is what > guest would expect from a sane hardware/BIOS. "guests"? > > Signed-off-by: Igor Mammedov <[email protected]> Regards, Andreas -- SUSE Linux GmbH, Maxfeldstr. 5, 90409 Nürnberg, Germany GF: Felix Imendörffer, Jane Smithard, Jennifer Guild, Dilip Upmanyu, Graham Norton; HRB 21284 (AG Nürnberg)
