Re: [Openstack] Requirement - x86
Ganesh For lab purpose a single box would also be fine. I started off that way. However, adding more nodes would allow splitting services across them and experimenting on a multinode setup. Cheers Nandakumar On Oct 17, 2012 8:40 AM, Ganesh Hariharan ghariha...@gmail.com wrote: Nandakumar, thanks much... i have some more basic queries, please excuse :) Is the minimum hardware requirement (like good to have ) for a full fledged Internet based access to Compute infra setups... also, like to dwelve more into other services that I can configure and test them as well.. essentially for learning lab purpose,,, thanks On 10/16/12, Nandakumar Pezhery nandakuma...@gmail.com wrote: Ganesh, you may refer the Folsom install guide http://docs.openstack.org/install/ or https://github.com/mseknibilel/OpenStack-Folsom-Install-guide/blob/master/OpenStack_Folsom_Install_Guide_WebVersion.rst or installation guide for Redhat http://docs.openstack.org/trunk/openstack-compute/install/yum/content/ Rgds Nandakumar On Tue, Oct 16, 2012 at 1:55 PM, Ganesh Hariharan ghariha...@gmail.comwrote: Hi, I am a novice to openstack... Please guide me through compute and storage setupss... any ready reckoners... Thanks ___ Mailing list: https://launchpad.net/~openstack Post to : openstack@lists.launchpad.net Unsubscribe : https://launchpad.net/~openstack More help : https://help.launchpad.net/ListHelp ___ Mailing list: https://launchpad.net/~openstack Post to : openstack@lists.launchpad.net Unsubscribe : https://launchpad.net/~openstack More help : https://help.launchpad.net/ListHelp
[Openstack] Quantum OVS Agent as service
Hi all, If we run Quantum OVS Agent as a service ... '*service quantum-plugin-openvswitch-agent start*', it is unable to start the agent. It is throwing the following error to '/var/log/quantum/agent-ovs.log' *Stderr: 'Device br-eth1 does not exist.\n'* *2012-10-16 12:48:10ERROR [quantum.plugins.openvswitch.agent.ovs_quantum_agent] Bridge br-eth1 for physical network default does not exist* * * if we run the agent manually like the following command, it is able to start: */usr/bin/quantum-openvswitch-agent -- --config-file=/etc/quantum/plugins/openvswitch/ovs_quantum_plugin.ini --log-file=/var/log/quantum/agent-ovs.log --config-file=/etc/quantum/quantum.conf* Please suggest. -- Srikanth. ___ Mailing list: https://launchpad.net/~openstack Post to : openstack@lists.launchpad.net Unsubscribe : https://launchpad.net/~openstack More help : https://help.launchpad.net/ListHelp
Re: [Openstack] Unconference CompatibleOne
FYI: slides on OCCI that were presented at Open World Forum and CloudCamp Paris: http://www.cloudcomp.ch/2012/10/icclabs-present-on-occi-at-owfcloudcamp-paris/ On 16 Oct 2012, at 15:48, jean-pierre laisne jplai...@gmail.com wrote: There will be a talk about interoperability and portability (multi-cloud, federation, etc.) with CompatibleOne and OCCI during the unconference sessions on Wednesday 17 at 11:00. If you are interested, please join us. Thanks, Jean-Pierre. ___ Mailing list: https://launchpad.net/~openstack Post to : openstack@lists.launchpad.net Unsubscribe : https://launchpad.net/~openstack More help : https://help.launchpad.net/ListHelp ___ Mailing list: https://launchpad.net/~openstack Post to : openstack@lists.launchpad.net Unsubscribe : https://launchpad.net/~openstack More help : https://help.launchpad.net/ListHelp
[Openstack] Can you add new vNICs to running VMs?
Hi, Is it possible to add more vNICs to running VMs? For example a VM is started with one interface that is connected to subnet1. If there is a need to add an another interface/subnet, is it possible to do this without shutting down/ starting again the VM? Best regards, Johanna ___ Mailing list: https://launchpad.net/~openstack Post to : openstack@lists.launchpad.net Unsubscribe : https://launchpad.net/~openstack More help : https://help.launchpad.net/ListHelp
Re: [Openstack] Can you add new vNICs to running VMs?
yes,with support of devices hotplug,we can add ports created by quantum to the instances,and I am working on this feather . 2012/10/17 Heinonen, Johanna (NSN - FI/Espoo) johanna.heino...@nsn.com: Hi, Is it possible to add more vNICs to running VMs? For example a VM is started with one interface that is connected to subnet1. If there is a need to add an another interface/subnet, is it possible to do this without shutting down/ starting again the VM? Best regards, Johanna ___ Mailing list: https://launchpad.net/~openstack Post to : openstack@lists.launchpad.net Unsubscribe : https://launchpad.net/~openstack More help : https://help.launchpad.net/ListHelp -- Yaguang Tang ___ Mailing list: https://launchpad.net/~openstack Post to : openstack@lists.launchpad.net Unsubscribe : https://launchpad.net/~openstack More help : https://help.launchpad.net/ListHelp
[Openstack] 回复: Can you add new vNICs to running VMs?
Hi Yaguang, Do you mean even for vCPU it is the same case? If it is, which project will implement the similar feature then? Regards, Howard - Reply message - 发件人: heut2008 heut2...@gmail.com 收件人: Heinonen, Johanna (NSN - FI/Espoo) johanna.heino...@nsn.com 抄送: openstack@lists.launchpad.net 主题: [Openstack] Can you add new vNICs to running VMs? 日期: 周三, 10 月 17 日, 2012 年 9:59 下午 yes,with support of devices hotplug,we can add ports created by quantum to the instances,and I am working on this feather . 2012/10/17 Heinonen, Johanna (NSN - FI/Espoo) johanna.heino...@nsn.com: Hi, Is it possible to add more vNICs to running VMs? For example a VM is started with one interface that is connected to subnet1. If there is a need to add an another interface/subnet, is it possible to do this without shutting down/ starting again the VM? Best regards, Johanna ___ Mailing list: https://launchpad.net/~openstack Post to : openstack@lists.launchpad.net Unsubscribe : https://launchpad.net/~openstack More help : https://help.launchpad.net/ListHelp -- Yaguang Tang ___ Mailing list: https://launchpad.net/~openstack Post to : openstack@lists.launchpad.net Unsubscribe : https://launchpad.net/~openstack More help : https://help.launchpad.net/ListHelp ___ Mailing list: https://launchpad.net/~openstack Post to : openstack@lists.launchpad.net Unsubscribe : https://launchpad.net/~openstack More help : https://help.launchpad.net/ListHelp
[Openstack] CLA Contributor list is missing from the wiki?
I tried to approve a few new CLA signers and noticed that the http://wiki.openstack.org/Contributors page is missing. Trying to restore a previous version resulted in an error. Could someone with appropriate admin rights look into this? thanks, Pádraig. ___ Mailing list: https://launchpad.net/~openstack Post to : openstack@lists.launchpad.net Unsubscribe : https://launchpad.net/~openstack More help : https://help.launchpad.net/ListHelp
Re: [Openstack] Quantum OVS Agent as service
It sounds like your config file is saying that you have an OVS bridge named br-eth1, but it looks like you do not. Did you intend to do this, or is this a config copied from somewhere else? If you actually intended to use VLANs that send traffic out eth1, you can do the following: # create bridge ovs-vsctl add-br br-eth1 # add eth1 as a port on this bridge ovs-vsctl add-port br-eth1 eth1 dan On Wed, Oct 17, 2012 at 1:53 AM, Srikanth Kumar Lingala srikanthkumar.ling...@gmail.com wrote: Hi all, If we run Quantum OVS Agent as a service ... 'service quantum-plugin-openvswitch-agent start', it is unable to start the agent. It is throwing the following error to '/var/log/quantum/agent-ovs.log' Stderr: 'Device br-eth1 does not exist.\n' 2012-10-16 12:48:10ERROR [quantum.plugins.openvswitch.agent.ovs_quantum_agent] Bridge br-eth1 for physical network default does not exist if we run the agent manually like the following command, it is able to start: /usr/bin/quantum-openvswitch-agent -- --config-file=/etc/quantum/plugins/openvswitch/ovs_quantum_plugin.ini --log-file=/var/log/quantum/agent-ovs.log --config-file=/etc/quantum/quantum.conf Please suggest. -- Srikanth. ___ Mailing list: https://launchpad.net/~openstack Post to : openstack@lists.launchpad.net Unsubscribe : https://launchpad.net/~openstack More help : https://help.launchpad.net/ListHelp -- ~~~ Dan Wendlandt Nicira, Inc: www.nicira.com twitter: danwendlandt ~~~ ___ Mailing list: https://launchpad.net/~openstack Post to : openstack@lists.launchpad.net Unsubscribe : https://launchpad.net/~openstack More help : https://help.launchpad.net/ListHelp
Re: [Openstack] CLA Contributor list is missing from the wiki?
On 10/17/2012 09:41 AM, Pádraig Brady wrote: I tried to approve a few new CLA signers and noticed that the http://wiki.openstack.org/Contributors page is missing. Trying to restore a previous version resulted in an error. Could someone with appropriate admin rights look into this? The list appears to be back now. Mikal ___ Mailing list: https://launchpad.net/~openstack Post to : openstack@lists.launchpad.net Unsubscribe : https://launchpad.net/~openstack More help : https://help.launchpad.net/ListHelp
Re: [Openstack] ask for comments - Light weight Erasure code framework for swift
Overall I've never been super enthusiastic about erasure codes for swift. Figuring out which blocks are missing then re-assembling them is a lot more difficult and expensive than what we do now. But if you can come up with a good scheme for identifying missing blocks and it doesn't double the amount of code in Swift, I'm sure we all have use cases where we'd trade latency for disk usage. - Michael On Mon, Oct 15, 2012 at 7:36 PM, Duan, Jiangang jiangang.d...@intel.com wrote: Some of our customers are interested in Erasure code than tri-replicate to save disk space. We propose a BP Light weight Erasure code framework for swift, which can be found here https://blueprints.launchpad.net/swift/+spec/swift-ec The general idea is to have some daemon on storage node to do offline scan - select code object with big enough size to do EC. Will glad to hear any feedback on this. -jiangang ___ Mailing list: https://launchpad.net/~openstack Post to : openstack@lists.launchpad.net Unsubscribe : https://launchpad.net/~openstack More help : https://help.launchpad.net/ListHelp ___ Mailing list: https://launchpad.net/~openstack Post to : openstack@lists.launchpad.net Unsubscribe : https://launchpad.net/~openstack More help : https://help.launchpad.net/ListHelp
Re: [Openstack] quantum create_net- creates network for non-existing tenant also.
It seems that you are using quantum cli v1.0, which is not supported in new quantum version v2.0 API. Are u using quantum v1.x, right? On 10/16/2012 10:39 AM, Raja Gajju wrote: Hi All, I am testing the Quantum CLIs in my set up. When I am creating a new network using create_net CLI for an non-existing tenant, it is showing successful creation. It should not do so. It is something unexpected. And again when I am doing list_nets it is showing that network under the specified non-existing tenant. Here is the snippet of the commans and their results : --- ~/devstack$ quantum create_net hjbddsbfikeoqjroijmfgvkmgfv fake_net Created a new Virtual Network with ID: f3b1d829-009d-45b5-9108-01722539135e for Tenant: hjbddsbfikeoqjroijmfgvkmgfv ~/devstack$ quantum list_nets hjbddsbfikeoqjroijmfgvkmgfv Virtual Networks for Tenant hjbddsbfikeoqjroijmfgvkmgfv Network ID: f3b1d829-009d-45b5-9108-01722539135e --- Any effort to explain this inconsistency issue will be highly appreciated. Many thanks in advance. Thanks and Regards, Girija Sharan Singh ___ Mailing list: https://launchpad.net/~openstack Post to : openstack@lists.launchpad.net Unsubscribe : https://launchpad.net/~openstack More help : https://help.launchpad.net/ListHelp ___ Mailing list: https://launchpad.net/~openstack Post to : openstack@lists.launchpad.net Unsubscribe : https://launchpad.net/~openstack More help : https://help.launchpad.net/ListHelp
Re: [Openstack] ask for comments - Light weight Erasure code framework for swift
This requests sound reasonable. This work may be worked together for the replicator-optimization patch. We will work on the patch. Any other feedback? -jiangang -Original Message- From: palr...@gmail.com [mailto:palr...@gmail.com] On Behalf Of Michael Barton Sent: Thursday, October 18, 2012 2:29 AM To: Duan, Jiangang Cc: openstack@lists.launchpad.net; Zhou, Yuan Subject: Re: [Openstack] ask for comments - Light weight Erasure code framework for swift Overall I've never been super enthusiastic about erasure codes for swift. Figuring out which blocks are missing then re-assembling them is a lot more difficult and expensive than what we do now. But if you can come up with a good scheme for identifying missing blocks and it doesn't double the amount of code in Swift, I'm sure we all have use cases where we'd trade latency for disk usage. - Michael On Mon, Oct 15, 2012 at 7:36 PM, Duan, Jiangang jiangang.d...@intel.com wrote: Some of our customers are interested in Erasure code than tri-replicate to save disk space. We propose a BP Light weight Erasure code framework for swift, which can be found here https://blueprints.launchpad.net/swift/+spec/swift-ec The general idea is to have some daemon on storage node to do offline scan - select code object with big enough size to do EC. Will glad to hear any feedback on this. -jiangang ___ Mailing list: https://launchpad.net/~openstack Post to : openstack@lists.launchpad.net Unsubscribe : https://launchpad.net/~openstack More help : https://help.launchpad.net/ListHelp ___ Mailing list: https://launchpad.net/~openstack Post to : openstack@lists.launchpad.net Unsubscribe : https://launchpad.net/~openstack More help : https://help.launchpad.net/ListHelp
Re: [Openstack] ask for comments - Light weight Erasure code framework for swift
On 10/15/12 5:36 PM, Duan, Jiangang wrote: Some of our customers are interested in Erasure code than tri-replicate to save disk space. We propose a BP Light weight Erasure code framework for swift, which can be found here https://blueprints.launchpad.net/swift/+spec/swift-ec The general idea is to have some daemon on storage node to do offline scan - select code object with big enough size to do EC. Will glad to hear any feedback on this. Here, in no particular order, are some thoughts I have. - Object blocks (both data blocks and parity blocks) will need to be marked somehow so that 3 replicas of each block aren't kept. This is a pretty fundamental change to Swift; up until now, all objects are treated the same. It's essentially introducing the notion of tiered storage into Swift. - Who's responsible for ensuring the presence of all the blocks? That is, assume you have an object that's been split into ten data blocks (D1, D2, ..., D10) and 2 parity blocks (P1, P2). The drive with D7 on it dies. Which replicator(s) is(are) responsible for rebuilding D7 and storing it on a handoff node? If you have the replicators on each block's machine checking for failures, then you'll wind up with more people checking each replica. Here, it would be 11 replicators ensuring that each block is present. Compare that to the full-replication case, where there are 2 replicators checking on it. That's going to result in more traffic on the internal network. - There will need to be throttles on the transformation daemons (replica - EC and vice versa), as that's very IO intensive. If a big bunch of data is uploaded at one time and then not accessed (think large backups), then that could be a ticking time bomb for my cluster performance. After those objects become cold, the transformation daemons will thrash my disks and network turning them into EC-type objects. - Does this open up a Swift cluster to a DoS attack? If my objects are stored w/EC, then can someone go through and request a few bytes from each object in my cluster a few times and cause all my objects to get hot? Under the proposed scheme, this would turn my objects from EC-storage to replica-storage, filling up my disks and killing my cluster. To mitigate that, I'd have to keep enough disk around to hold 3 replicas of everything, and at that point, I may as well just keep the 3 replicas. - Another thought for a resource-consumption attack: can someone slowly walk my objects and make a large fraction (say, 5%) of them hot each day? That seems like it would make the transformation daemons run at maximum capacity all the time trying to keep up. - Retrieval of EC-stored objects becomes more failure-prone. With replica-stored objects, 1 out of 3 object servers has to be available for a GET request to work. With EC-stored objects and a 10:2 coding, 10 out of 12 object servers have to be available. That makes network partitions much worse for data availability. - EC-storage is at odds with geographic replication. Of course, Swift supports neither one today. However, with geographic replication, one wants to have a local replica of each each object in each geographic region, which results in more copies for lower latency. With EC-storage, less data is stored. When they're combined, the result is a whole lot of traffic across slow, expensive WAN links. - Recombining EC-stored object chunks is going to chew up a ton more CPU on either the object or proxy servers, depending on which one does it. If the proxy, then it'll add more to an already CPU-heavy workload. If the object server, then it'll make using big storage boxes less practical (like one of the 48-drives-in-4U servers one can buy). - Can one change the EC-coding level? That is, if I'm using 10:2 coding (so each object turns into 10 data blocks and 2 parity blocks), can I change that later? Will that have massive performance impacts on my cluster as more data blocks are computed? It may be that this is like changing the replica count, and the answer is yes, but your cluster will thrash for a long time after you do it. - Where's the original checksum stored? Clearly, each block will have its own checksum for the auditors to use. However, if a client issues a request like HEAD /a/c/o, that'll contain the checksum of the original file. Does that live somewhere, or will the proxy have to read all the bytes and determine the checksum? - I wonder what effect this will have on internal-network traffic. With a replica-stored object, the proxy opens one connection to an object server, sends a request, gets a response, and streams the bytes out to the client. With an EC-stored object, the proxy has to open connections to, say, 10 different object servers. Further, if one of the data blocks is unavailable (say data block 5), then the proxy has to go ahead and re-request all the data blocks plus a parity block so that it can fill in the
Re: [Openstack] ask for comments - Light weight Erasure code framework for swift
Hi Sam, My five cents. Using Fountain codes, which are also a class of EC, one can make all the blocks equivalent in role (no separation into data and parity blocks). http://en.wikipedia.org/wiki/Fountain_code They resolve a few of the issues that you raised, however they may raise others - e.g. it's more difficult to determine how many blocks you need to fetch to reconstruct the data. On Wed, Oct 17, 2012 at 4:24 PM, Samuel Merritt s...@swiftstack.com wrote: On 10/15/12 5:36 PM, Duan, Jiangang wrote: Some of our customers are interested in Erasure code than tri-replicate to save disk space. We propose a BP Light weight Erasure code framework for swift, which can be found here https://blueprints.launchpad.net/swift/+spec/swift-ec The general idea is to have some daemon on storage node to do offline scan - select code object with big enough size to do EC. Will glad to hear any feedback on this. Here, in no particular order, are some thoughts I have. - Object blocks (both data blocks and parity blocks) will need to be marked somehow so that 3 replicas of each block aren't kept. This is a pretty fundamental change to Swift; up until now, all objects are treated the same. It's essentially introducing the notion of tiered storage into Swift. - Who's responsible for ensuring the presence of all the blocks? That is, assume you have an object that's been split into ten data blocks (D1, D2, ..., D10) and 2 parity blocks (P1, P2). The drive with D7 on it dies. Which replicator(s) is(are) responsible for rebuilding D7 and storing it on a handoff node? If you have the replicators on each block's machine checking for failures, then you'll wind up with more people checking each replica. Here, it would be 11 replicators ensuring that each block is present. Compare that to the full-replication case, where there are 2 replicators checking on it. That's going to result in more traffic on the internal network. - There will need to be throttles on the transformation daemons (replica - EC and vice versa), as that's very IO intensive. If a big bunch of data is uploaded at one time and then not accessed (think large backups), then that could be a ticking time bomb for my cluster performance. After those objects become cold, the transformation daemons will thrash my disks and network turning them into EC-type objects. - Does this open up a Swift cluster to a DoS attack? If my objects are stored w/EC, then can someone go through and request a few bytes from each object in my cluster a few times and cause all my objects to get hot? Under the proposed scheme, this would turn my objects from EC-storage to replica-storage, filling up my disks and killing my cluster. To mitigate that, I'd have to keep enough disk around to hold 3 replicas of everything, and at that point, I may as well just keep the 3 replicas. - Another thought for a resource-consumption attack: can someone slowly walk my objects and make a large fraction (say, 5%) of them hot each day? That seems like it would make the transformation daemons run at maximum capacity all the time trying to keep up. - Retrieval of EC-stored objects becomes more failure-prone. With replica-stored objects, 1 out of 3 object servers has to be available for a GET request to work. With EC-stored objects and a 10:2 coding, 10 out of 12 object servers have to be available. That makes network partitions much worse for data availability. - EC-storage is at odds with geographic replication. Of course, Swift supports neither one today. However, with geographic replication, one wants to have a local replica of each each object in each geographic region, which results in more copies for lower latency. With EC-storage, less data is stored. When they're combined, the result is a whole lot of traffic across slow, expensive WAN links. - Recombining EC-stored object chunks is going to chew up a ton more CPU on either the object or proxy servers, depending on which one does it. If the proxy, then it'll add more to an already CPU-heavy workload. If the object server, then it'll make using big storage boxes less practical (like one of the 48-drives-in-4U servers one can buy). - Can one change the EC-coding level? That is, if I'm using 10:2 coding (so each object turns into 10 data blocks and 2 parity blocks), can I change that later? Will that have massive performance impacts on my cluster as more data blocks are computed? It may be that this is like changing the replica count, and the answer is yes, but your cluster will thrash for a long time after you do it. - Where's the original checksum stored? Clearly, each block will have its own checksum for the auditors to use. However, if a client issues a request like HEAD /a/c/o, that'll contain the checksum of the original file. Does that live somewhere, or will the proxy have to read all the bytes and determine the checksum? - I wonder what effect this will have on
Re: [Openstack] ask for comments - Light weight Erasure code framework for swift
Hi Sam, I got some thoughts from your mail. EC is more useful for a centered storage solution but not for a distributed one. It will bring a heavy load on internal network traffic. Actually from network performance's point of view, the 3 copies are also sort of the result of compromise. There should be a way to combine them together and tune the parameters under different scenarios. They, however, would bring different reliability and performance. Regards, Howard On Thu, Oct 18, 2012 at 7:30 AM, Eugene Kirpichov ekirpic...@gmail.comwrote: Hi Sam, My five cents. Using Fountain codes, which are also a class of EC, one can make all the blocks equivalent in role (no separation into data and parity blocks). http://en.wikipedia.org/wiki/Fountain_code They resolve a few of the issues that you raised, however they may raise others - e.g. it's more difficult to determine how many blocks you need to fetch to reconstruct the data. On Wed, Oct 17, 2012 at 4:24 PM, Samuel Merritt s...@swiftstack.com wrote: On 10/15/12 5:36 PM, Duan, Jiangang wrote: Some of our customers are interested in Erasure code than tri-replicate to save disk space. We propose a BP Light weight Erasure code framework for swift, which can be found here https://blueprints.launchpad.net/swift/+spec/swift-ec The general idea is to have some daemon on storage node to do offline scan - select code object with big enough size to do EC. Will glad to hear any feedback on this. Here, in no particular order, are some thoughts I have. - Object blocks (both data blocks and parity blocks) will need to be marked somehow so that 3 replicas of each block aren't kept. This is a pretty fundamental change to Swift; up until now, all objects are treated the same. It's essentially introducing the notion of tiered storage into Swift. - Who's responsible for ensuring the presence of all the blocks? That is, assume you have an object that's been split into ten data blocks (D1, D2, ..., D10) and 2 parity blocks (P1, P2). The drive with D7 on it dies. Which replicator(s) is(are) responsible for rebuilding D7 and storing it on a handoff node? If you have the replicators on each block's machine checking for failures, then you'll wind up with more people checking each replica. Here, it would be 11 replicators ensuring that each block is present. Compare that to the full-replication case, where there are 2 replicators checking on it. That's going to result in more traffic on the internal network. - There will need to be throttles on the transformation daemons (replica - EC and vice versa), as that's very IO intensive. If a big bunch of data is uploaded at one time and then not accessed (think large backups), then that could be a ticking time bomb for my cluster performance. After those objects become cold, the transformation daemons will thrash my disks and network turning them into EC-type objects. - Does this open up a Swift cluster to a DoS attack? If my objects are stored w/EC, then can someone go through and request a few bytes from each object in my cluster a few times and cause all my objects to get hot? Under the proposed scheme, this would turn my objects from EC-storage to replica-storage, filling up my disks and killing my cluster. To mitigate that, I'd have to keep enough disk around to hold 3 replicas of everything, and at that point, I may as well just keep the 3 replicas. - Another thought for a resource-consumption attack: can someone slowly walk my objects and make a large fraction (say, 5%) of them hot each day? That seems like it would make the transformation daemons run at maximum capacity all the time trying to keep up. - Retrieval of EC-stored objects becomes more failure-prone. With replica-stored objects, 1 out of 3 object servers has to be available for a GET request to work. With EC-stored objects and a 10:2 coding, 10 out of 12 object servers have to be available. That makes network partitions much worse for data availability. - EC-storage is at odds with geographic replication. Of course, Swift supports neither one today. However, with geographic replication, one wants to have a local replica of each each object in each geographic region, which results in more copies for lower latency. With EC-storage, less data is stored. When they're combined, the result is a whole lot of traffic across slow, expensive WAN links. - Recombining EC-stored object chunks is going to chew up a ton more CPU on either the object or proxy servers, depending on which one does it. If the proxy, then it'll add more to an already CPU-heavy workload. If the object server, then it'll make using big storage boxes less practical (like one of the 48-drives-in-4U servers one can buy). - Can one change the EC-coding level? That is, if I'm using 10:2 coding (so each object turns into 10 data
Re: [Openstack] Quantum OVS Agent as service
Hi Dan, I am following Folsom Installation guide provided by Emilien Macchi. In that document it is mentioned to create a bridge 'br-int' attached to 'eth1' through ovs. And also it suggests to assign this '*br-int*' bridge as '*integration_bridge*' and '*br-eth1*' as '*bridge_mappings*' in '/etc/quantum/plugins/openvswitch/ovs_quantum_plugin.ini' like the following: *integration_bridge = br-int* *bridge_mappings = default:br-eth1* * * Please clarify me, is it necessary to enable 'bridge_mappings' field. * * Regards, Srikanth. On Wed, Oct 17, 2012 at 10:13 PM, Dan Wendlandt d...@nicira.com wrote: It sounds like your config file is saying that you have an OVS bridge named br-eth1, but it looks like you do not. Did you intend to do this, or is this a config copied from somewhere else? If you actually intended to use VLANs that send traffic out eth1, you can do the following: # create bridge ovs-vsctl add-br br-eth1 # add eth1 as a port on this bridge ovs-vsctl add-port br-eth1 eth1 dan On Wed, Oct 17, 2012 at 1:53 AM, Srikanth Kumar Lingala srikanthkumar.ling...@gmail.com wrote: Hi all, If we run Quantum OVS Agent as a service ... 'service quantum-plugin-openvswitch-agent start', it is unable to start the agent. It is throwing the following error to '/var/log/quantum/agent-ovs.log' Stderr: 'Device br-eth1 does not exist.\n' 2012-10-16 12:48:10ERROR [quantum.plugins.openvswitch.agent.ovs_quantum_agent] Bridge br-eth1 for physical network default does not exist if we run the agent manually like the following command, it is able to start: /usr/bin/quantum-openvswitch-agent -- --config-file=/etc/quantum/plugins/openvswitch/ovs_quantum_plugin.ini --log-file=/var/log/quantum/agent-ovs.log --config-file=/etc/quantum/quantum.conf Please suggest. -- Srikanth. ___ Mailing list: https://launchpad.net/~openstack Post to : openstack@lists.launchpad.net Unsubscribe : https://launchpad.net/~openstack More help : https://help.launchpad.net/ListHelp -- ~~~ Dan Wendlandt Nicira, Inc: www.nicira.com twitter: danwendlandt ~~~ ___ Mailing list: https://launchpad.net/~openstack Post to : openstack@lists.launchpad.net Unsubscribe : https://launchpad.net/~openstack More help : https://help.launchpad.net/ListHelp
[Openstack-qa-team] Blueprint for Compute Admin API tests
Hi everyone, After our discussions earlier today about being more vocal about what's being worked on, I wanted to raise awareness of what I'm currently working to avoid duplication of efforts. This is the first blueprint I've submitted, so if there's any additional detail that I'm missing, I'm always glad to get feedback. https://blueprints.launchpad.net/tempest/+spec/add-compute-admin-tests Daryl -- Mailing list: https://launchpad.net/~openstack-qa-team Post to : openstack-qa-team@lists.launchpad.net Unsubscribe : https://launchpad.net/~openstack-qa-team More help : https://help.launchpad.net/ListHelp