Phil,
I agree with the suggestion. We wanted to instantiate a set of VMs whose hosts
are located close each other. The current scheduler could not handle this use
case since it needed to return "optimal" set of hosts at the same time. The
first "optimal" host returned by the current scheduler m
All,
I have a blue print on proximity scheduler at
http://wiki.openstack.org/ProximityScheduler, and would like to get feedback on
it.
Thanks,
Joseph
- Original Message -
From: "John Paul Walters"
To: openstack@lists.launchpad.net
Cc: openstack-...@lists.openstack.org
Sent: Friday, S
Heng,
I maybe wrong as the latest code is somewhat different from the one I followed
last time, but it looks like the information is update at line 440 in
nova/nova/compute/resource_tracker.py.
Thanks,
Joseph
- Original Message -
From: "Heng Xu"
To: openstack@lists.launchpad.net
Sent
A bug fix patch that adds the extra specs matching against host aggregate is
under review at https://review.openstack.org/#/c/11449/.
Thanks,
Joseph
- Original Message -
From: "Vishvananda Ishaya"
To: "Joseph Suh"
Cc: "Patrick Petit" ,
"opens
consider the feature, but our team needs to
discuss it before we can commit to it.
Thanks,
Joseph
- Original Message -
From: "Patrick Petit"
To: "Joseph Suh"
Cc: "openstack@lists.launchpad.net (openstack@lists.launchpad.net)"
, "David Kang
Patrick,
Once a new item (key and value pair) is added to the capabilities, it can be
compared against extra_specs. The extra_specs can be populated in
instance_type_extra_specs table. The items in the extra_specs can start with
one of the keywords for operations such as ">=" and "s==". For exa
Ben,
It is possible to have the option specified in a code. Try grep -r on whole
code.
Thanks,
Joseph
- Original Message -
From: "Ben"
To: "Joseph Suh"
Cc: openstack@lists.launchpad.net
Sent: Wednesday, August 22, 2012 10:47:35 AM
Subject: Re: [Openstack]
Ben,
As the error message suggests, it is due to a duplicated option of
scheduler_host_manager. It is specified more than once somewhere.
Thanks,
Joseph
- Original Message -
From: "Ben"
To: openstack@lists.launchpad.net
Sent: Wednesday, August 22, 2012 8:27:39 AM
Subject: Re: [Opensta
Boris-Michel,
One thing that I noticed was a typo: schedulre that can cause malfunction. I am
not sure what version you are using, but recently the extra_spec checking is
moved to compute_capabilities_filter.py (ComputeCapabilitiesFilter). As far as
I understand, the current ComputeFilter does
Heng,
You can print the values in the HostState class. If you want to monitor the
changes of the values, for example, you can print (either directly or using
LOG.debug()), the values in the code where you want monitor, for example,
consume_from_instance().
Thanks,
Joseph
(w) 703-248-616
Heng,
Does scheduler log show any error message or complaints?
Thanks,
Joseph
(w) 703-248-6160
(f) 703-812-3712
http://www.east.isi.edu/~jsuh
Information Sciences Institute
University of Southern California
3811 N. Fairfax Drive Suite 200
Arlington, VA, 22203, USA
- Original Message
e 200
Arlington, VA, 22203, USA
- Original Message -
From: "Donald D Dugger"
To: "Joseph Suh" , "Sandy Walsh" ,
"Vishvananda Ishaya"
Cc: openstack@lists.launchpad.net, "Yunhong Jiang"
Sent: Tuesday, July 17, 2012 12:19:35 PM
Subject: RE: One q
1-340-2434
(f) 703-812-3712
http://www.east.isi.edu/~jsuh
Information Sciences Institute
University of Southern California
3811 N. Fairfax Drive Suite 200
Arlington, VA, 22203, USA
- Original Message -
From: "Donald D Dugger"
To: "Joseph Suh" , "Yunhong Jiang"
University of Southern California
3811 N. Fairfax Drive Suite 200
Arlington, VA, 22203, USA
- Original Message -
From: "Yunhong Jiang"
To: "Joseph Suh"
Cc: "Donald D Dugger" , openstack@lists.launchpad.net
Sent: Tuesday, July 17, 2012 11:39:54 AM
Su
Yunhong,
Thanks for your interest in our patch. The original purpose of the
instance_type_extra_specs is providing ability to specify any specs that cannot
be enumerated at the nova coding time such as hardware-specific requirements
(like gpu) or any features in the future system (like python v
Leander,
As the error message indicates, it usually comes when the option is found in
more than one place.
Thanks,
Joseph
(w) 703-248-6160
(f) 703-812-3712
http://www.east.isi.edu/~jsuh
Information Sciences Institute
University of Southern California
3811 N. Fairfax Drive Suite 200
Arlin
Gary,
Apparently, it happened to me. Tests took 13 hours and came with failure.
Thanks,
Joseph
(w) 703-248-6160
(f) 703-812-3712
3811 N. Fairfax Drive Suite 200
Arlington, VA, 22203, USA
http://www.east.isi.edu/~jsuh
- Original Message -
From: "Gary Kotton"
To: openstack@lists.la
-
From: "Leander Bessa Beernaert"
To: "Joseph Suh"
Cc: openstack@lists.launchpad.net
Sent: Monday, June 25, 2012 9:45:51 AM
Subject: Re: [Openstack] [OpenStack][Nova] No tests available in custom branch
I've tried all the options and the output is al
Leander,
Did you give -V -f option? If you post your log, it would be easier to help.
Thanks,
Joseph
(w) 703-248-6160
(c) 571-340-2434
(f) 703-812-3712
3811 N. Fairfax Drive Suite 200
Arlington, VA, 22203, USA
http://www.east.isi.edu/~jsuh
- Original Message -
From: "Leander Bessa
Trinath,
I found the following Quantun admin guide was useful for that purpose:
http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=4&ved=0CHsQFjAD&url=http%3A%2F%2Fdocs.openstack.org%2Ftrunk%2Fopenstack-network%2Fadmin%2Fquantum-admin-guide-trunk.pdf&ei=prHhT-SMMMa70QG_uJTwAw&usg=AFQjCN
Christian,
I have been working on improving filter scheduler and my current blue print is
at http://wiki.openstack.org/InstanceTypeExtraSpecsExtension and current code
is at https://review.openstack.org/#/c/8089/. If you have any question on my
code or filter scheduler, please let me know.
Tha
I'd vote case-sensitive.
Joseph
(w) 703-248-6160
(c) 571-340-2434
(f) 703-812-3712
3811 N. Fairfax Drive Suite 200
Arlington, VA, 22203, USA
http://www.east.isi.edu/~jsuh
- Original Message -
From: "Brian Waldon"
To: "openstack@lists.launchpad.net (openstack@lists.launchpad.net)"
Sarath,
There are filter and weight functions in the scheduler that might fit your
purpose.
Thanks,
Joseph
(w) 703-248-6160
(c) 571-340-2434
(f) 703-812-3712
3811 N. Fairfax Drive Suite 200
Arlington, VA, 22203, USA
http://www.east.isi.edu/~jsuh
- Original Message -
From: "Raziqu
I'd like to see how many companies are in the community in the statistics as
well.
Thanks,
Joseph
- Original Message -
From: "Jay Pipes"
To: "Anne Gentle"
Cc: openstack@lists.launchpad.net
Sent: Tuesday, September 27, 2011 11:56:13 AM
Subject: Re: [Openstack] Community metrics, develo
Kyle,
Please wait until sprint planning meeting since we don't know if this user
story will make it in this sprint. We can start working if the user story is
included in this (or future) sprint task list.
Thanks,
Joseph
- Original Message -
From: "Kyle Dunn"
To: openstack@lists.launc
Huang,
If you are willing to modify code, you might want to take a look at the code at
lp:~usc-isi/nova/hpc-trunk that has a scheduler (nova/scheduler/arch.py) that
does not allow creating new instances if cpu or other resources are used up. If
you have any question on the branch, please feel f
Luis,
You can also take a look at USC-ISI's scheduler for heterogeneous systems that
checks resource availability as well. Currently, it checks number of cpus,
memory space, and hard disk space. If available resource is not enough, it does
not allow a new instance.
The branch can be found at l
I think 1) is a clean solution. Another option is adding "frequently" used
columns to the instance table (and/or compute nodes table), but this leaves a
subjective decision on what is a frequently used column and needs constant
change whenever a new decision is made.
It seems that Jay's suggest
28 matches
Mail list logo