On Wed, Oct 31, 2012 at 10:54 PM, Vishvananda Ishaya
wrote:
> My patch here seems to fix the issue in the one scheduler case:
>
>
> https://github.com/vishvananda/nova/commit/2eaf796e60bd35319fe6add6dd04359546a21682
>
> If you could give that a try on your scheduler node and see if it fixes it
>
Hi Vish,
I like to idea to keep host states in memory (or external caching like
memcached). This should fix the root cause why core filter doesn't
work for Jonathan in his case, but for memory, I think we still need
to find a way to handle those hypervisors don't allocated entire
memory for guest
On Oct 31, 2012, at 5:57 PM, Vishvananda Ishaya wrote:
>
> Looking at the code it appears that the relevent info is being sent down to
> the compute node. That said I can't seem to repro your issue with even just
> the ram filter. I can't get it to overallocate on one node unless I
> specifi
On Oct 31, 2012, at 1:44 PM, Jonathan Proulx wrote:
> I'd only been pushing these options to the host the scheduler runs on, is it
> that simple? I'm delight if I'm an an idiot and just need a few line in a
> config file, but puzzled why this was (seemingly at least) working with
> Essex, c
On Wed, Oct 31, 2012 at 3:53 PM, Vishvananda Ishaya
wrote:
>
> On Oct 31, 2012, at 12:25 PM, Jonathan Proulx wrote:
> >
> > again despite:
> > scheduler_available_filters=nova.scheduler.filters.standard_filters
> >
> scheduler_default_filters=AvailabilityZoneFilter,RamFilter,CoreFilter,ComputeFil
On Oct 31, 2012, at 12:25 PM, Jonathan Proulx wrote:
>
> again despite:
> scheduler_available_filters=nova.scheduler.filters.standard_filters
> scheduler_default_filters=AvailabilityZoneFilter,RamFilter,CoreFilter,ComputeFilter,RetryFilter
> cpu_allocation_ratio=1.0
> ram_allocation_ratio=1.0
I
On Wed, Oct 31, 2012 at 1:47 PM, Huang Zhiteng wrote:
> Hi Jonathan,
>
> If I understand correctly, that bug is about multiple scheduler
There is only a single process, I was reading it as relating to
include threads within a single process, but they should clearly be
able to serialize this withi
Hi Jonathan,
If I understand correctly, that bug is about multiple scheduler
instances(processes) doing scheduler at the same time. When compute
node found itself unable to fulfil a create_instance request, it'll
resend the request back to scheduler (max_retry is to avoid endless
retry). From you
Hi All
While the RetryScheduler may not have been designed specifically to
fix this issue https://bugs.launchpad.net/nova/+bug/1011852 suggests
that it is meant to fix it, well if "it" is a scheduler race condition
which is my suspicion.
This is my current scheduler config which gives the failure
On Wed, Oct 31, 2012 at 10:40:57AM +0800, Huang Zhiteng wrote:
> On Wed, Oct 31, 2012 at 10:07 AM, Vishvananda Ishaya
> wrote:
> >
> > On Oct 30, 2012, at 7:01 PM, Huang Zhiteng wrote:
> >
> >> I'd suggest the same ratio too. But besides memory overcommitment, I
> >> suspect this issue is also r
On Wed, Oct 31, 2012 at 10:07 AM, Vishvananda Ishaya
wrote:
>
> On Oct 30, 2012, at 7:01 PM, Huang Zhiteng wrote:
>
>> I'd suggest the same ratio too. But besides memory overcommitment, I
>> suspect this issue is also related to how KVM do memory allocation (it
>> doesn't do actual allocation of
On Oct 30, 2012, at 7:01 PM, Huang Zhiteng wrote:
> I'd suggest the same ratio too. But besides memory overcommitment, I
> suspect this issue is also related to how KVM do memory allocation (it
> doesn't do actual allocation of the entire memory for guest when
> booting). I've seen compute node
On Wed, Oct 31, 2012 at 12:21 AM, Jonathan Proulx wrote:
> Hi All,
>
> I'm having what I consider serious issues with teh scheduler in
> Folsom. It seems to relate to the introdution of threading in the
> scheduler.
How many scheduler instances do you have?
>
> For a number of local reason we pre
On Wed, Oct 31, 2012 at 6:55 AM, Vishvananda Ishaya
wrote:
> The retry scheduler is NOT meant to be a workaround for this. It sounds like
> the ram filter is not working properly somehow. Have you changed the setting
> for ram_allocation_ratio? It defaults to 1.5 allowing overallocation, but in
>
The retry scheduler is NOT meant to be a workaround for this. It sounds like
the ram filter is not working properly somehow. Have you changed the setting
for ram_allocation_ratio? It defaults to 1.5 allowing overallocation, but in
your case you may want 1.0.
I would be using the following two conf
Hi All,
I'm having what I consider serious issues with teh scheduler in
Folsom. It seems to relate to the introdution of threading in the
scheduler.
For a number of local reason we prefer to have instances start on the
compute node with the least amount of free RAM that is still enough to
satisf
16 matches
Mail list logo
