Re: [Qemu-devel] [PATCH 0/7] spapr: rework memory nodes

2014-06-18 Thread Nishanth Aravamudan
On 18.06.2014 [16:33:55 -0300], Eduardo Habkost wrote: > On Wed, Jun 18, 2014 at 11:28:53AM -0700, Nishanth Aravamudan wrote: > > On 17.06.2014 [16:22:33 -0300], Eduardo Habkost wrote: > > > On Tue, Jun 17, 2014 at 11:38:16AM -0700, Nishanth Aravamudan wrote: > > > > On 17.06.2014 [11:07:00 -0300],

Re: [Qemu-devel] [PATCH 0/7] spapr: rework memory nodes

2014-06-18 Thread Eduardo Habkost
On Wed, Jun 18, 2014 at 11:28:53AM -0700, Nishanth Aravamudan wrote: > On 17.06.2014 [16:22:33 -0300], Eduardo Habkost wrote: > > On Tue, Jun 17, 2014 at 11:38:16AM -0700, Nishanth Aravamudan wrote: > > > On 17.06.2014 [11:07:00 -0300], Eduardo Habkost wrote: > > > > > > > > If it is canonical and

Re: [Qemu-devel] [PATCH 0/7] spapr: rework memory nodes

2014-06-18 Thread Nishanth Aravamudan
On 17.06.2014 [16:22:33 -0300], Eduardo Habkost wrote: > On Tue, Jun 17, 2014 at 11:38:16AM -0700, Nishanth Aravamudan wrote: > > On 17.06.2014 [11:07:00 -0300], Eduardo Habkost wrote: > > > > > > If it is canonical and kosher way of using NUMA in QEMU, ok, we can use > > > > it. > > > > I just f

Re: [Qemu-devel] [PATCH 0/7] spapr: rework memory nodes

2014-06-17 Thread Eduardo Habkost
On Tue, Jun 17, 2014 at 11:38:16AM -0700, Nishanth Aravamudan wrote: > On 17.06.2014 [11:07:00 -0300], Eduardo Habkost wrote: > > > > If it is canonical and kosher way of using NUMA in QEMU, ok, we can use > > > it. > > > I just fail to see why we need a requirement for nodes to go consequently >

Re: [Qemu-devel] [PATCH 0/7] spapr: rework memory nodes

2014-06-17 Thread Nishanth Aravamudan
On 17.06.2014 [11:07:00 -0300], Eduardo Habkost wrote: > > If it is canonical and kosher way of using NUMA in QEMU, ok, we can use it. > > I just fail to see why we need a requirement for nodes to go consequently > > here. And it confuses me as a user a bit if I can add "-numa > > node,nodeid=22"

Re: [Qemu-devel] [PATCH 0/7] spapr: rework memory nodes

2014-06-17 Thread Nishanth Aravamudan
On 16.06.2014 [22:41:08 -0300], Eduardo Habkost wrote: > On Mon, Jun 16, 2014 at 05:25:00PM -0700, Nishanth Aravamudan wrote: > [...] > > > But you seem to claim you need 3 nodes with non-contiguous IDs. In that > > > case, which exactly is the guest-visible difference you expect to get > > > betwe

Re: [Qemu-devel] [PATCH 0/7] spapr: rework memory nodes

2014-06-17 Thread Nishanth Aravamudan
On 16.06.2014 [22:37:00 -0300], Eduardo Habkost wrote: > On Mon, Jun 16, 2014 at 05:25:00PM -0700, Nishanth Aravamudan wrote: > > On 16.06.2014 [17:51:50 -0300], Eduardo Habkost wrote: > > > On Mon, Jun 16, 2014 at 06:16:29PM +1000, Alexey Kardashevskiy wrote: > > > > On 06/16/2014 05:53 PM, Alexey

Re: [Qemu-devel] [PATCH 0/7] spapr: rework memory nodes

2014-06-17 Thread Eduardo Habkost
On Tue, Jun 17, 2014 at 03:51:35PM +1000, Alexey Kardashevskiy wrote: > On 06/17/2014 06:51 AM, Eduardo Habkost wrote: > > On Mon, Jun 16, 2014 at 06:16:29PM +1000, Alexey Kardashevskiy wrote: > >> On 06/16/2014 05:53 PM, Alexey Kardashevskiy wrote: > >>> c4177479 "spapr: make sure RMA is in first

Re: [Qemu-devel] [PATCH 0/7] spapr: rework memory nodes

2014-06-16 Thread Alexey Kardashevskiy
On 06/17/2014 06:51 AM, Eduardo Habkost wrote: > On Mon, Jun 16, 2014 at 06:16:29PM +1000, Alexey Kardashevskiy wrote: >> On 06/16/2014 05:53 PM, Alexey Kardashevskiy wrote: >>> c4177479 "spapr: make sure RMA is in first mode of first memory node" >>> introduced regression which prevents from runni

Re: [Qemu-devel] [PATCH 0/7] spapr: rework memory nodes

2014-06-16 Thread Eduardo Habkost
On Mon, Jun 16, 2014 at 05:25:00PM -0700, Nishanth Aravamudan wrote: [...] > > But you seem to claim you need 3 nodes with non-contiguous IDs. In that > > case, which exactly is the guest-visible difference you expect to get > > between: > > -numa node,nodeid=0,cpus=0-7,memory=0 \ > > -numa nod

Re: [Qemu-devel] [PATCH 0/7] spapr: rework memory nodes

2014-06-16 Thread Eduardo Habkost
On Mon, Jun 16, 2014 at 05:25:00PM -0700, Nishanth Aravamudan wrote: > On 16.06.2014 [17:51:50 -0300], Eduardo Habkost wrote: > > On Mon, Jun 16, 2014 at 06:16:29PM +1000, Alexey Kardashevskiy wrote: > > > On 06/16/2014 05:53 PM, Alexey Kardashevskiy wrote: > > > > c4177479 "spapr: make sure RMA is

Re: [Qemu-devel] [PATCH 0/7] spapr: rework memory nodes

2014-06-16 Thread Nishanth Aravamudan
On 16.06.2014 [17:51:50 -0300], Eduardo Habkost wrote: > On Mon, Jun 16, 2014 at 06:16:29PM +1000, Alexey Kardashevskiy wrote: > > On 06/16/2014 05:53 PM, Alexey Kardashevskiy wrote: > > > c4177479 "spapr: make sure RMA is in first mode of first memory node" > > > introduced regression which preven

Re: [Qemu-devel] [PATCH 0/7] spapr: rework memory nodes

2014-06-16 Thread Eduardo Habkost
On Mon, Jun 16, 2014 at 06:16:29PM +1000, Alexey Kardashevskiy wrote: > On 06/16/2014 05:53 PM, Alexey Kardashevskiy wrote: > > c4177479 "spapr: make sure RMA is in first mode of first memory node" > > introduced regression which prevents from running guests with memoryless > > NUMA node#0 which ma

Re: [Qemu-devel] [PATCH 0/7] spapr: rework memory nodes

2014-06-16 Thread Nishanth Aravamudan
On 16.06.2014 [18:16:29 +1000], Alexey Kardashevskiy wrote: > On 06/16/2014 05:53 PM, Alexey Kardashevskiy wrote: > > c4177479 "spapr: make sure RMA is in first mode of first memory node" > > introduced regression which prevents from running guests with memoryless > > NUMA node#0 which may happen o

Re: [Qemu-devel] [PATCH 0/7] spapr: rework memory nodes

2014-06-16 Thread Alexey Kardashevskiy
On 06/16/2014 05:53 PM, Alexey Kardashevskiy wrote: > c4177479 "spapr: make sure RMA is in first mode of first memory node" > introduced regression which prevents from running guests with memoryless > NUMA node#0 which may happen on real POWER8 boxes and which would make > sense to debug in QEMU. >