Re: Cloustack 4.1.0 + GlusterFS
John, care to write a HOWTO use GlusterFS in the wiki? On 9/11/13 5:27 PM, John Skinner john.skin...@appcore.com wrote: I ran each test independently for each block size. iozone -I -i 0 -i 1 -i 2 -r 4k -s 1G In order: -I to specify direct-IO, -i 0 to specify write/rewrite, -i 1 to specify read/re-read, -i 2 to specify random read/write, -r specify block size, -s to specify file size. The report is pretty thorough. What I put in the email was different, I just took the throughput from each test and put it into a table outside of the full report. - Original Message - From: Rafael Weingartner rafaelweingart...@gmail.com To: users@cloudstack.apache.org Sent: Wednesday, September 11, 2013 4:16:23 PM Subject: Re: Cloustack 4.1.0 + GlusterFS I have never used iozone before, How did you get that report? I tried: iozone -s 1024m -t 1 -R But the report was pretty different from yours. 2013/9/11 John Skinner john.skin...@appcore.com I currently have GlusterFS deployed into an 8 node KVM cluster running on CloudStack 4.1 for primary storage. Gluster is deployed on 28 1TB drives across 2 separate storage appliances using a distributed-replicated volume with the replica set to 2. The storage network is 10Gb copper. These are the options I have configured for the volume in Gluster, most of them are from a Red Hat document on configuring Red Hat Enterprise Storage for VM hosting: performance.io-thread-count: 32 performance.cache-size: 1024MB performance.write-behind-window-size: 5MB performance.write-behind: on network.remote-dio: on cluster.eager-lock: enable performance.stat-prefetch: off performance.io-cache: on performance.read-ahead: on performance.quick-read: on Here are some of the numbers I was getting when benchmarking the storage from the KVM node directly (not a VM) The below table is in KB/s. The test is single stream 1GB file utilizing Direct I/O (no cache). I used iozone to run the benchmark. Write 4k 45729 Read 4k 10189 Random Write 4k 31983 Random Read 4k 9859 Write 16k 182246 Read 16k 37146 Random Write 16k 113026 Random Read 16k 37237 Write 64k 420908 Read 64k 125315 Random Write 64k 383848 Random Read 64k 125218 Write 256k 567501 Read 256k 218413 Random Write 256k 508650 Random Read 256k 229117 In the above results, I have the volume mounted to each KVM host as a FUSE glusterfs file system. They are added to CloudStack as a shared mount point. In the future it would be great to utilize GlusterFS qemu libvirt integration with libgfapi so I could bypass fuse altogether. However, that would require adding that code to CloudStack to support that. I maybe have 15 or so VMs running from the storage now and it is still pretty snappy. Need to do some more testing though and really get it loaded. - Original Message - From: Rafael Weingartner rafaelweingart...@gmail.com To: users@cloudstack.apache.org Sent: Wednesday, September 11, 2013 8:48:07 AM Subject: Re: Cloustack 4.1.0 + GlusterFS Right now I can think in three main reasons: The first reason, performance (I do not know Gluster and its performance and if the read and write speed are satisfactory). Please if you can make a test, post the results. Second consistency, I do not know Gluster, but swift that is also a Distributed File System is not consistency and they make it pretty clear on their page (http://docs.openstack.org/developer/swift/) Swift is a highly available, distributed, eventually consistent object/blob store I would not accept to storage my VMs images on a FS that is eventually consistent. Third, network, I haven't used this kind of FS, but I can image that it uses a lot of bandwidth to keep synchronizing, managing and securing the data. So, managing the networking would be a pain. 2013/9/11 Olivier Mauras oliv...@core-hosting.net Hi, Those thinking that it's not a good idea, do you mind explaining your point of view? GlusterFS seems like the only real alternative to a highly priced SAN for the primary storage... Thanks, Olivier On 2013-09-11 15:08, Rafael Weingartner wrote: I totally agree with Tomasz, I do not think that using a distributed FS as primary storage is a good idea, but as a secondary it sounds interesting. But, off course you can try *;*) 2013/9/11 Shanker Balan shanker.ba...@shapeblue.com On 11-Sep-2013, at 5:14 PM, Tomasz Zięba t.a.zi...@gmail.com [1] wrote: Hi, Some time ago I tried to use GlusterFS as storage for cloudstacka but I noticed that cloudstack uses the default settings for mount command. By default mount command is using the UDP protocol but glusterfs works only using tcp. I think, if cloudstack developers could add -o proto=tcp to code glusterfs should works. For example: /bin/mount -t nfs -o proto=tcp IP:/share /mnt/gluster/ If you
Re: Cloustack 4.1.0 + GlusterFS
Ive been reading that it is not possible to use Cloudstack with glusterfs + VMware hosts? Can anyone confirm this? From: Jake G. dj_dark_jungl...@yahoo.com To: users@cloudstack.apache.org users@cloudstack.apache.org Sent: Tuesday, September 10, 2013 7:26 PM Subject: Cloustack 4.1.0 + GlusterFS Hi all, I have a working Cloudstack environment on Centos 6.4. I also have a working GlusterFS cluster volume working on two other servers. I was able to mount the GlusterFS volume to a folder via CentOS CLI but went trying to add the volume as a primary or secondary storage via the Coudstack GUI it failed. Anyone know how to do this or have any useful links? Thank you in advance! Jake
Re: Cloustack 4.1.0 + GlusterFS
I think that CS will not even know that it is a Distributed FS since you can mount the distributed volume in a folder and export it with NFS. The question should be, is a distributed FS interesting to be used in a cloud environment? Since there is a cost to use this kind of model and it may or may not have performance problems since read and write speed are crucial for the whole system. As and example here we use a RAID controller as the bases for storage of our cloud, we achieved something around 60MB+ of writing and reading speed, which is pretty good. How would be the performance of Gluster in your environment? All of your storage server have gigabyte connections? 2013/9/11 Jake G. dj_dark_jungl...@yahoo.com Ive been reading that it is not possible to use Cloudstack with glusterfs + VMware hosts? Can anyone confirm this? From: Jake G. dj_dark_jungl...@yahoo.com To: users@cloudstack.apache.org users@cloudstack.apache.org Sent: Tuesday, September 10, 2013 7:26 PM Subject: Cloustack 4.1.0 + GlusterFS Hi all, I have a working Cloudstack environment on Centos 6.4. I also have a working GlusterFS cluster volume working on two other servers. I was able to mount the GlusterFS volume to a folder via CentOS CLI but went trying to add the volume as a primary or secondary storage via the Coudstack GUI it failed. Anyone know how to do this or have any useful links? Thank you in advance! Jake -- Rafael Weingartner
Re: Cloustack 4.1.0 + GlusterFS
Hi, Some time ago I tried to use GlusterFS as storage for cloudstacka but I noticed that cloudstack uses the default settings for mount command. By default mount command is using the UDP protocol but glusterfs works only using tcp. I think, if cloudstack developers could add -o proto=tcp to code glusterfs should works. For example: /bin/mount -t nfs -o proto=tcp IP:/share /mnt/gluster/ If you are using CitrixXen you should mount the share and make it as SR. For cloudstacka is clear because you should use the option PreSetup when creating PrimaryStorage. Personally, I doubt that using GlusterFS as a primary storage is a good solution but for secondary storage it should be very usefull. -- Regards, Tomasz Zięba Twitter: @TZieba LinkedIn: pl.linkedin.com/pub/tomasz-zięba-ph-d/3b/7a8/ab6/http://pl.linkedin.com/pub/tomasz-zi%C4%99ba-ph-d/3b/7a8/ab6/ 2013/9/11 Jake G. dj_dark_jungl...@yahoo.com Ive been reading that it is not possible to use Cloudstack with glusterfs + VMware hosts? Can anyone confirm this? From: Jake G. dj_dark_jungl...@yahoo.com To: users@cloudstack.apache.org users@cloudstack.apache.org Sent: Tuesday, September 10, 2013 7:26 PM Subject: Cloustack 4.1.0 + GlusterFS Hi all, I have a working Cloudstack environment on Centos 6.4. I also have a working GlusterFS cluster volume working on two other servers. I was able to mount the GlusterFS volume to a folder via CentOS CLI but went trying to add the volume as a primary or secondary storage via the Coudstack GUI it failed. Anyone know how to do this or have any useful links? Thank you in advance! Jake
Re: Cloustack 4.1.0 + GlusterFS
On 11-Sep-2013, at 5:14 PM, Tomasz Zięba t.a.zi...@gmail.com wrote: Hi, Some time ago I tried to use GlusterFS as storage for cloudstacka but I noticed that cloudstack uses the default settings for mount command. By default mount command is using the UDP protocol but glusterfs works only using tcp. I think, if cloudstack developers could add -o proto=tcp to code glusterfs should works. For example: /bin/mount -t nfs -o proto=tcp IP:/share /mnt/gluster/ If you are using CitrixXen you should mount the share and make it as SR. For cloudstacka is clear because you should use the option PreSetup when creating PrimaryStorage. Personally, I doubt that using GlusterFS as a primary storage is a good solution but for secondary storage it should be very usefull. And maybe as a Swift backend. -- @shankerbalan M: +91 98860 60539 | O: +91 (80) 67935867 shanker.ba...@shapeblue.com | www.shapeblue.com | Twitter:@shapeblue ShapeBlue Services India LLP, 22nd floor, Unit 2201A, World Trade Centre, Bangalore - 560 055 This email and any attachments to it may be confidential and are intended solely for the use of the individual to whom it is addressed. Any views or opinions expressed are solely those of the author and do not necessarily represent those of Shape Blue Ltd or related companies. If you are not the intended recipient of this email, you must neither take any action based upon its contents, nor copy or show it to anyone. Please contact the sender if you believe you have received this email in error. Shape Blue Ltd is a company incorporated in England Wales. ShapeBlue Services India LLP is operated under license from Shape Blue Ltd. ShapeBlue is a registered trademark.
Re: Cloustack 4.1.0 + GlusterFS
I totally agree with Tomasz, I do not think that using a distributed FS as primary storage is a good idea, but as a secondary it sounds interesting. But, off course you can try *;*) 2013/9/11 Shanker Balan shanker.ba...@shapeblue.com On 11-Sep-2013, at 5:14 PM, Tomasz Zięba t.a.zi...@gmail.com wrote: Hi, Some time ago I tried to use GlusterFS as storage for cloudstacka but I noticed that cloudstack uses the default settings for mount command. By default mount command is using the UDP protocol but glusterfs works only using tcp. I think, if cloudstack developers could add -o proto=tcp to code glusterfs should works. For example: /bin/mount -t nfs -o proto=tcp IP:/share /mnt/gluster/ If you are using CitrixXen you should mount the share and make it as SR. For cloudstacka is clear because you should use the option PreSetup when creating PrimaryStorage. Personally, I doubt that using GlusterFS as a primary storage is a good solution but for secondary storage it should be very usefull. And maybe as a Swift backend. -- @shankerbalan M: +91 98860 60539 | O: +91 (80) 67935867 shanker.ba...@shapeblue.com | www.shapeblue.com | Twitter:@shapeblue ShapeBlue Services India LLP, 22nd floor, Unit 2201A, World Trade Centre, Bangalore - 560 055 This email and any attachments to it may be confidential and are intended solely for the use of the individual to whom it is addressed. Any views or opinions expressed are solely those of the author and do not necessarily represent those of Shape Blue Ltd or related companies. If you are not the intended recipient of this email, you must neither take any action based upon its contents, nor copy or show it to anyone. Please contact the sender if you believe you have received this email in error. Shape Blue Ltd is a company incorporated in England Wales. ShapeBlue Services India LLP is operated under license from Shape Blue Ltd. ShapeBlue is a registered trademark. -- Rafael Weingartner
Re: Cloustack 4.1.0 + GlusterFS
Right now I can think in three main reasons: The first reason, performance (I do not know Gluster and its performance and if the read and write speed are satisfactory). Please if you can make a test, post the results. Second consistency, I do not know Gluster, but swift that is also a Distributed File System is not consistency and they make it pretty clear on their page (http://docs.openstack.org/developer/swift/) Swift is a highly available, distributed, eventually consistent object/blob store I would not accept to storage my VMs images on a FS that is eventually consistent. Third, network, I haven't used this kind of FS, but I can image that it uses a lot of bandwidth to keep synchronizing, managing and securing the data. So, managing the networking would be a pain. 2013/9/11 Olivier Mauras oliv...@core-hosting.net Hi, Those thinking that it's not a good idea, do you mind explaining your point of view? GlusterFS seems like the only real alternative to a highly priced SAN for the primary storage... Thanks, Olivier On 2013-09-11 15:08, Rafael Weingartner wrote: I totally agree with Tomasz, I do not think that using a distributed FS as primary storage is a good idea, but as a secondary it sounds interesting. But, off course you can try *;*) 2013/9/11 Shanker Balan shanker.ba...@shapeblue.com On 11-Sep-2013, at 5:14 PM, Tomasz Zięba t.a.zi...@gmail.com [1] wrote: Hi, Some time ago I tried to use GlusterFS as storage for cloudstacka but I noticed that cloudstack uses the default settings for mount command. By default mount command is using the UDP protocol but glusterfs works only using tcp. I think, if cloudstack developers could add -o proto=tcp to code glusterfs should works. For example: /bin/mount -t nfs -o proto=tcp IP:/share /mnt/gluster/ If you are using CitrixXen you should mount the share and make it as SR. For cloudstacka is clear because you should use the option PreSetup when creating PrimaryStorage. Personally, I doubt that using GlusterFS as a primary storage is a good solution but for secondary storage it should be very usefull. And maybe as a Swift backend. -- @shankerbalan M: +91 98860 60539 | O: +91 (80) 67935867 shanker.ba...@shapeblue.com [2] | www.shapeblue.com [3] | Twitter:@shapeblue ShapeBlue Services India LLP, 22nd floor, Unit 2201A, World Trade Centre, Bangalore - 560 055 This email and any attachments to it may be confidential and are intended solely for the use of the individual to whom it is addressed. Any views or opinions expressed are solely those of the author and do not necessarily represent those of Shape Blue Ltd or related companies. If you are not the intended recipient of this email, you must neither take any action based upon its contents, nor copy or show it to anyone. Please contact the sender if you believe you have received this email in error. Shape Blue Ltd is a company incorporated in England Wales. ShapeBlue Services India LLP is operated under license from Shape Blue Ltd. ShapeBlue is a registered trademark. -- Rafael Weingartner Links: -- [1] mailto:t.a.zi...@gmail.com [2] mailto:shanker.ba...@shapeblue.com [3] http://www.shapeblue.com -- Rafael Weingartner
Re: Cloustack 4.1.0 + GlusterFS
I currently have GlusterFS deployed into an 8 node KVM cluster running on CloudStack 4.1 for primary storage. Gluster is deployed on 28 1TB drives across 2 separate storage appliances using a distributed-replicated volume with the replica set to 2. The storage network is 10Gb copper. These are the options I have configured for the volume in Gluster, most of them are from a Red Hat document on configuring Red Hat Enterprise Storage for VM hosting: performance.io-thread-count: 32 performance.cache-size: 1024MB performance.write-behind-window-size: 5MB performance.write-behind: on network.remote-dio: on cluster.eager-lock: enable performance.stat-prefetch: off performance.io-cache: on performance.read-ahead: on performance.quick-read: on Here are some of the numbers I was getting when benchmarking the storage from the KVM node directly (not a VM) The below table is in KB/s. The test is single stream 1GB file utilizing Direct I/O (no cache). I used iozone to run the benchmark. Write 4k45729 Read 4k 10189 Random Write 4k 31983 Random Read 4k 9859 Write 16k 182246 Read 16k37146 Random Write 16k113026 Random Read 16k 37237 Write 64k 420908 Read 64k125315 Random Write 64k383848 Random Read 64k 125218 Write 256k 567501 Read 256k 218413 Random Write 256k 508650 Random Read 256k229117 In the above results, I have the volume mounted to each KVM host as a FUSE glusterfs file system. They are added to CloudStack as a shared mount point. In the future it would be great to utilize GlusterFS qemu libvirt integration with libgfapi so I could bypass fuse altogether. However, that would require adding that code to CloudStack to support that. I maybe have 15 or so VMs running from the storage now and it is still pretty snappy. Need to do some more testing though and really get it loaded. - Original Message - From: Rafael Weingartner rafaelweingart...@gmail.com To: users@cloudstack.apache.org Sent: Wednesday, September 11, 2013 8:48:07 AM Subject: Re: Cloustack 4.1.0 + GlusterFS Right now I can think in three main reasons: The first reason, performance (I do not know Gluster and its performance and if the read and write speed are satisfactory). Please if you can make a test, post the results. Second consistency, I do not know Gluster, but swift that is also a Distributed File System is not consistency and they make it pretty clear on their page (http://docs.openstack.org/developer/swift/) Swift is a highly available, distributed, eventually consistent object/blob store I would not accept to storage my VMs images on a FS that is eventually consistent. Third, network, I haven't used this kind of FS, but I can image that it uses a lot of bandwidth to keep synchronizing, managing and securing the data. So, managing the networking would be a pain. 2013/9/11 Olivier Mauras oliv...@core-hosting.net Hi, Those thinking that it's not a good idea, do you mind explaining your point of view? GlusterFS seems like the only real alternative to a highly priced SAN for the primary storage... Thanks, Olivier On 2013-09-11 15:08, Rafael Weingartner wrote: I totally agree with Tomasz, I do not think that using a distributed FS as primary storage is a good idea, but as a secondary it sounds interesting. But, off course you can try *;*) 2013/9/11 Shanker Balan shanker.ba...@shapeblue.com On 11-Sep-2013, at 5:14 PM, Tomasz Zięba t.a.zi...@gmail.com [1] wrote: Hi, Some time ago I tried to use GlusterFS as storage for cloudstacka but I noticed that cloudstack uses the default settings for mount command. By default mount command is using the UDP protocol but glusterfs works only using tcp. I think, if cloudstack developers could add -o proto=tcp to code glusterfs should works. For example: /bin/mount -t nfs -o proto=tcp IP:/share /mnt/gluster/ If you are using CitrixXen you should mount the share and make it as SR. For cloudstacka is clear because you should use the option PreSetup when creating PrimaryStorage. Personally, I doubt that using GlusterFS as a primary storage is a good solution but for secondary storage it should be very usefull. And maybe as a Swift backend. -- @shankerbalan M: +91 98860 60539 | O: +91 (80) 67935867 shanker.ba...@shapeblue.com [2] | www.shapeblue.com [3] | Twitter:@shapeblue ShapeBlue Services India LLP, 22nd floor, Unit 2201A, World Trade Centre, Bangalore - 560 055 This email and any attachments to it may be confidential and are intended solely for the use of the individual to whom it is addressed. Any views or opinions expressed are solely those of the author and do not necessarily represent those of Shape Blue Ltd or related companies. If you are not the intended recipient of this email, you must
Re: Cloustack 4.1.0 + GlusterFS
I have never used iozone before, How did you get that report? I tried: iozone -s 1024m -t 1 -R But the report was pretty different from yours. 2013/9/11 John Skinner john.skin...@appcore.com I currently have GlusterFS deployed into an 8 node KVM cluster running on CloudStack 4.1 for primary storage. Gluster is deployed on 28 1TB drives across 2 separate storage appliances using a distributed-replicated volume with the replica set to 2. The storage network is 10Gb copper. These are the options I have configured for the volume in Gluster, most of them are from a Red Hat document on configuring Red Hat Enterprise Storage for VM hosting: performance.io-thread-count: 32 performance.cache-size: 1024MB performance.write-behind-window-size: 5MB performance.write-behind: on network.remote-dio: on cluster.eager-lock: enable performance.stat-prefetch: off performance.io-cache: on performance.read-ahead: on performance.quick-read: on Here are some of the numbers I was getting when benchmarking the storage from the KVM node directly (not a VM) The below table is in KB/s. The test is single stream 1GB file utilizing Direct I/O (no cache). I used iozone to run the benchmark. Write 4k45729 Read 4k 10189 Random Write 4k 31983 Random Read 4k 9859 Write 16k 182246 Read 16k37146 Random Write 16k113026 Random Read 16k 37237 Write 64k 420908 Read 64k125315 Random Write 64k383848 Random Read 64k 125218 Write 256k 567501 Read 256k 218413 Random Write 256k 508650 Random Read 256k229117 In the above results, I have the volume mounted to each KVM host as a FUSE glusterfs file system. They are added to CloudStack as a shared mount point. In the future it would be great to utilize GlusterFS qemu libvirt integration with libgfapi so I could bypass fuse altogether. However, that would require adding that code to CloudStack to support that. I maybe have 15 or so VMs running from the storage now and it is still pretty snappy. Need to do some more testing though and really get it loaded. - Original Message - From: Rafael Weingartner rafaelweingart...@gmail.com To: users@cloudstack.apache.org Sent: Wednesday, September 11, 2013 8:48:07 AM Subject: Re: Cloustack 4.1.0 + GlusterFS Right now I can think in three main reasons: The first reason, performance (I do not know Gluster and its performance and if the read and write speed are satisfactory). Please if you can make a test, post the results. Second consistency, I do not know Gluster, but swift that is also a Distributed File System is not consistency and they make it pretty clear on their page (http://docs.openstack.org/developer/swift/) Swift is a highly available, distributed, eventually consistent object/blob store I would not accept to storage my VMs images on a FS that is eventually consistent. Third, network, I haven't used this kind of FS, but I can image that it uses a lot of bandwidth to keep synchronizing, managing and securing the data. So, managing the networking would be a pain. 2013/9/11 Olivier Mauras oliv...@core-hosting.net Hi, Those thinking that it's not a good idea, do you mind explaining your point of view? GlusterFS seems like the only real alternative to a highly priced SAN for the primary storage... Thanks, Olivier On 2013-09-11 15:08, Rafael Weingartner wrote: I totally agree with Tomasz, I do not think that using a distributed FS as primary storage is a good idea, but as a secondary it sounds interesting. But, off course you can try *;*) 2013/9/11 Shanker Balan shanker.ba...@shapeblue.com On 11-Sep-2013, at 5:14 PM, Tomasz Zięba t.a.zi...@gmail.com [1] wrote: Hi, Some time ago I tried to use GlusterFS as storage for cloudstacka but I noticed that cloudstack uses the default settings for mount command. By default mount command is using the UDP protocol but glusterfs works only using tcp. I think, if cloudstack developers could add -o proto=tcp to code glusterfs should works. For example: /bin/mount -t nfs -o proto=tcp IP:/share /mnt/gluster/ If you are using CitrixXen you should mount the share and make it as SR. For cloudstacka is clear because you should use the option PreSetup when creating PrimaryStorage. Personally, I doubt that using GlusterFS as a primary storage is a good solution but for secondary storage it should be very usefull. And maybe as a Swift backend. -- @shankerbalan M: +91 98860 60539 | O: +91 (80) 67935867 shanker.ba...@shapeblue.com [2] | www.shapeblue.com [3] | Twitter:@shapeblue ShapeBlue Services India LLP, 22nd floor, Unit 2201A, World Trade Centre, Bangalore - 560 055 This email and any attachments to it may be confidential and are intended solely for the use of the individual to whom it is addressed. Any views
Re: Cloustack 4.1.0 + GlusterFS
I ran each test independently for each block size. iozone -I -i 0 -i 1 -i 2 -r 4k -s 1G In order: -I to specify direct-IO, -i 0 to specify write/rewrite, -i 1 to specify read/re-read, -i 2 to specify random read/write, -r specify block size, -s to specify file size. The report is pretty thorough. What I put in the email was different, I just took the throughput from each test and put it into a table outside of the full report. - Original Message - From: Rafael Weingartner rafaelweingart...@gmail.com To: users@cloudstack.apache.org Sent: Wednesday, September 11, 2013 4:16:23 PM Subject: Re: Cloustack 4.1.0 + GlusterFS I have never used iozone before, How did you get that report? I tried: iozone -s 1024m -t 1 -R But the report was pretty different from yours. 2013/9/11 John Skinner john.skin...@appcore.com I currently have GlusterFS deployed into an 8 node KVM cluster running on CloudStack 4.1 for primary storage. Gluster is deployed on 28 1TB drives across 2 separate storage appliances using a distributed-replicated volume with the replica set to 2. The storage network is 10Gb copper. These are the options I have configured for the volume in Gluster, most of them are from a Red Hat document on configuring Red Hat Enterprise Storage for VM hosting: performance.io-thread-count: 32 performance.cache-size: 1024MB performance.write-behind-window-size: 5MB performance.write-behind: on network.remote-dio: on cluster.eager-lock: enable performance.stat-prefetch: off performance.io-cache: on performance.read-ahead: on performance.quick-read: on Here are some of the numbers I was getting when benchmarking the storage from the KVM node directly (not a VM) The below table is in KB/s. The test is single stream 1GB file utilizing Direct I/O (no cache). I used iozone to run the benchmark. Write 4k 45729 Read 4k 10189 Random Write 4k 31983 Random Read 4k 9859 Write 16k 182246 Read 16k 37146 Random Write 16k 113026 Random Read 16k 37237 Write 64k 420908 Read 64k 125315 Random Write 64k 383848 Random Read 64k 125218 Write 256k 567501 Read 256k 218413 Random Write 256k 508650 Random Read 256k 229117 In the above results, I have the volume mounted to each KVM host as a FUSE glusterfs file system. They are added to CloudStack as a shared mount point. In the future it would be great to utilize GlusterFS qemu libvirt integration with libgfapi so I could bypass fuse altogether. However, that would require adding that code to CloudStack to support that. I maybe have 15 or so VMs running from the storage now and it is still pretty snappy. Need to do some more testing though and really get it loaded. - Original Message - From: Rafael Weingartner rafaelweingart...@gmail.com To: users@cloudstack.apache.org Sent: Wednesday, September 11, 2013 8:48:07 AM Subject: Re: Cloustack 4.1.0 + GlusterFS Right now I can think in three main reasons: The first reason, performance (I do not know Gluster and its performance and if the read and write speed are satisfactory). Please if you can make a test, post the results. Second consistency, I do not know Gluster, but swift that is also a Distributed File System is not consistency and they make it pretty clear on their page (http://docs.openstack.org/developer/swift/) Swift is a highly available, distributed, eventually consistent object/blob store I would not accept to storage my VMs images on a FS that is eventually consistent. Third, network, I haven't used this kind of FS, but I can image that it uses a lot of bandwidth to keep synchronizing, managing and securing the data. So, managing the networking would be a pain. 2013/9/11 Olivier Mauras oliv...@core-hosting.net Hi, Those thinking that it's not a good idea, do you mind explaining your point of view? GlusterFS seems like the only real alternative to a highly priced SAN for the primary storage... Thanks, Olivier On 2013-09-11 15:08, Rafael Weingartner wrote: I totally agree with Tomasz, I do not think that using a distributed FS as primary storage is a good idea, but as a secondary it sounds interesting. But, off course you can try *;*) 2013/9/11 Shanker Balan shanker.ba...@shapeblue.com On 11-Sep-2013, at 5:14 PM, Tomasz Zięba t.a.zi...@gmail.com [1] wrote: Hi, Some time ago I tried to use GlusterFS as storage for cloudstacka but I noticed that cloudstack uses the default settings for mount command. By default mount command is using the UDP protocol but glusterfs works only using tcp. I think, if cloudstack developers could add -o proto=tcp to code glusterfs should works. For example: /bin/mount -t nfs -o proto=tcp IP:/share /mnt/gluster/ If you are using CitrixXen you should mount the share
Re: Cloustack 4.1.0 + GlusterFS
cool, thanks. 2013/9/11 John Skinner john.skin...@appcore.com I ran each test independently for each block size. iozone -I -i 0 -i 1 -i 2 -r 4k -s 1G In order: -I to specify direct-IO, -i 0 to specify write/rewrite, -i 1 to specify read/re-read, -i 2 to specify random read/write, -r specify block size, -s to specify file size. The report is pretty thorough. What I put in the email was different, I just took the throughput from each test and put it into a table outside of the full report. - Original Message - From: Rafael Weingartner rafaelweingart...@gmail.com To: users@cloudstack.apache.org Sent: Wednesday, September 11, 2013 4:16:23 PM Subject: Re: Cloustack 4.1.0 + GlusterFS I have never used iozone before, How did you get that report? I tried: iozone -s 1024m -t 1 -R But the report was pretty different from yours. 2013/9/11 John Skinner john.skin...@appcore.com I currently have GlusterFS deployed into an 8 node KVM cluster running on CloudStack 4.1 for primary storage. Gluster is deployed on 28 1TB drives across 2 separate storage appliances using a distributed-replicated volume with the replica set to 2. The storage network is 10Gb copper. These are the options I have configured for the volume in Gluster, most of them are from a Red Hat document on configuring Red Hat Enterprise Storage for VM hosting: performance.io-thread-count: 32 performance.cache-size: 1024MB performance.write-behind-window-size: 5MB performance.write-behind: on network.remote-dio: on cluster.eager-lock: enable performance.stat-prefetch: off performance.io-cache: on performance.read-ahead: on performance.quick-read: on Here are some of the numbers I was getting when benchmarking the storage from the KVM node directly (not a VM) The below table is in KB/s. The test is single stream 1GB file utilizing Direct I/O (no cache). I used iozone to run the benchmark. Write 4k 45729 Read 4k 10189 Random Write 4k 31983 Random Read 4k 9859 Write 16k 182246 Read 16k 37146 Random Write 16k 113026 Random Read 16k 37237 Write 64k 420908 Read 64k 125315 Random Write 64k 383848 Random Read 64k 125218 Write 256k 567501 Read 256k 218413 Random Write 256k 508650 Random Read 256k 229117 In the above results, I have the volume mounted to each KVM host as a FUSE glusterfs file system. They are added to CloudStack as a shared mount point. In the future it would be great to utilize GlusterFS qemu libvirt integration with libgfapi so I could bypass fuse altogether. However, that would require adding that code to CloudStack to support that. I maybe have 15 or so VMs running from the storage now and it is still pretty snappy. Need to do some more testing though and really get it loaded. - Original Message - From: Rafael Weingartner rafaelweingart...@gmail.com To: users@cloudstack.apache.org Sent: Wednesday, September 11, 2013 8:48:07 AM Subject: Re: Cloustack 4.1.0 + GlusterFS Right now I can think in three main reasons: The first reason, performance (I do not know Gluster and its performance and if the read and write speed are satisfactory). Please if you can make a test, post the results. Second consistency, I do not know Gluster, but swift that is also a Distributed File System is not consistency and they make it pretty clear on their page (http://docs.openstack.org/developer/swift/) Swift is a highly available, distributed, eventually consistent object/blob store I would not accept to storage my VMs images on a FS that is eventually consistent. Third, network, I haven't used this kind of FS, but I can image that it uses a lot of bandwidth to keep synchronizing, managing and securing the data. So, managing the networking would be a pain. 2013/9/11 Olivier Mauras oliv...@core-hosting.net Hi, Those thinking that it's not a good idea, do you mind explaining your point of view? GlusterFS seems like the only real alternative to a highly priced SAN for the primary storage... Thanks, Olivier On 2013-09-11 15:08, Rafael Weingartner wrote: I totally agree with Tomasz, I do not think that using a distributed FS as primary storage is a good idea, but as a secondary it sounds interesting. But, off course you can try *;*) 2013/9/11 Shanker Balan shanker.ba...@shapeblue.com On 11-Sep-2013, at 5:14 PM, Tomasz Zięba t.a.zi...@gmail.com [1] wrote: Hi, Some time ago I tried to use GlusterFS as storage for cloudstacka but I noticed that cloudstack uses the default settings for mount command. By default mount command is using the UDP protocol but glusterfs works only using tcp. I think, if cloudstack developers could add -o proto=tcp to code glusterfs should works. For example: /bin/mount -t nfs -o proto=tcp IP:/share
Re: Cloustack 4.1.0 + GlusterFS
It's always interesting seeing people advising against a solution without actually having it tested :) Thanks John for sharing your results. I guess that you're using XFS as the underlying FS ? Your write-behind options, clearly show a performance improvement for write speed. Have you tried with VM cache enabled? What about read performances? I also hope that qemu native integration will be soon supported in Cloudstack, performances are definitely boosted :) BTW are you happy with the cloudstack KVM integration? Seems, reading this list, that there's some needed features that doesn't work very well with KVM - HA, VM snapshots,... Cheers, Olivier On 2013-09-11 16:38, John Skinner wrote: I currently have GlusterFS deployed into an 8 node KVM cluster running on CloudStack 4.1 for primary storage. Gluster is deployed on 28 1TB drives across 2 separate storage appliances using a distributed-replicated volume with the replica set to 2. The storage network is 10Gb copper. These are the options I have configured for the volume in Gluster, most of them are from a Red Hat document on configuring Red Hat Enterprise Storage for VM hosting: performance.io-thread-count: 32 performance.cache-size: 1024MB performance.write-behind-window-size: 5MB performance.write-behind: on network.remote-dio: on cluster.eager-lock: enable performance.stat-prefetch: off performance.io-cache: on performance.read-ahead: on performance.quick-read: on Here are some of the numbers I was getting when benchmarking the storage from the KVM node directly (not a VM) The below table is in KB/s. The test is single stream 1GB file utilizing Direct I/O (no cache). I used iozone to run the benchmark. Write 4k 45729 Read 4k 10189 Random Write 4k 31983 Random Read 4k 9859 Write 16k 182246 Read 16k 37146 Random Write 16k 113026 Random Read 16k 37237 Write 64k 420908 Read 64k 125315 Random Write 64k 383848 Random Read 64k 125218 Write 256k 567501 Read 256k 218413 Random Write 256k 508650 Random Read 256k 229117 In the above results, I have the volume mounted to each KVM host as a FUSE glusterfs file system. They are added to CloudStack as a shared mount point. In the future it would be great to utilize GlusterFS qemu libvirt integration with libgfapi so I could bypass fuse altogether. However, that would require adding that code to CloudStack to support that. I maybe have 15 or so VMs running from the storage now and it is still pretty snappy. Need to do some more testing though and really get it loaded. - Original Message - From: Rafael Weingartner rafaelweingart...@gmail.com To: users@cloudstack.apache.org Sent: Wednesday, September 11, 2013 8:48:07 AM Subject: Re: Cloustack 4.1.0 + GlusterFS Right now I can think in three main reasons: The first reason, performance (I do not know Gluster and its performance and if the read and write speed are satisfactory). Please if you can make a test, post the results. Second consistency, I do not know Gluster, but swift that is also a Distributed File System is not consistency and they make it pretty clear on their page (http://docs.openstack.org/developer/swift/) Swift is a highly available, distributed, eventually consistent object/blob store I would not accept to storage my VMs images on a FS that is eventually consistent. Third, network, I haven't used this kind of FS, but I can image that it uses a lot of bandwidth to keep synchronizing, managing and securing the data. So, managing the networking would be a pain. 2013/9/11 Olivier Mauras oliv...@core-hosting.net Hi, Those thinking that it's not a good idea, do you mind explaining your point of view? GlusterFS seems like the only real alternative to a highly priced SAN for the primary storage... Thanks, Olivier On 2013-09-11 15:08, Rafael Weingartner wrote: I totally agree with Tomasz, I do not think that using a distributed FS as primary storage is a good idea, but as a secondary it sounds interesting. And maybe as a Swift backend. -- @shankerbalan M: +91 98860 60539 | O: +91 (80) 67935867 shanker.ba...@shapeblue.com [1] [2] | www.shapeblue.com [2][3] | Twitter:@shapeblue ShapeBlue Services India LLP, 22nd floor, Unit 2201A, World Trade Centre, Bangalore - 560 055 This email and any attachments to it may be confidential and are intended solely for the use of the indivi sarily represent those of Shape Blue Ltd or related companies. If you are not the intended recipient of this email, you must neit action based upon its contents, nor copy or show it to anyone. Please contact the sender if you believe you have received this email in error. Shape Blue Ltd is a company incorporated in England Wales. ShapeBlue Services India LLP is operated under license from Shape Blue Ltd. ShapeBlue is a registered trademark. -- Rafael Weingartner Links: -- [1] mailto:t.a.zi...@gmail.com [3] [2