Re: [pve-devel] less cores more iops / speed
Adding this to ceph.conf on kvm host adds another 2000 iops (20.000 iop/s with one VM). I'm sure most of them are useless on a client kvm / rbd host but i don't know which one makes sense ;-) [global] debug ms = 0/0 debug rbd = 0/0 debug lockdep = 0/0 debug context = 0/0 debug crush = 0/0 debug buffer = 0/0 debug timer = 0/0 debug journaler = 0/0 debug osd = 0/0 debug optracker = 0/0 debug objclass = 0/0 debug filestore = 0/0 debug journal = 0/0 debug ms = 0/0 debug monc = 0/0 debug tp = 0/0 debug auth = 0/0 debug finisher = 0/0 debug heartbeatmap = 0/0 debug perfcounter = 0/0 debug asok = 0/0 debug throttle = 0/0 [client] debug ms = 0/0 debug rbd = 0/0 debug lockdep = 0/0 debug context = 0/0 debug crush = 0/0 debug buffer = 0/0 debug timer = 0/0 debug journaler = 0/0 debug osd = 0/0 debug optracker = 0/0 debug objclass = 0/0 debug filestore = 0/0 debug journal = 0/0 debug ms = 0/0 debug monc = 0/0 debug tp = 0/0 debug auth = 0/0 debug finisher = 0/0 debug heartbeatmap = 0/0 debug perfcounter = 0/0 debug asok = 0/0 debug throttle = 0/0 Stefan Am 12.11.2012 15:35, schrieb Alexandre DERUMIER: Another idea, do you have tried to put debug lockdep = 0/0 debug context = 0/0 debug crush = 0/0 debug buffer = 0/0 debug timer = 0/0 debug journaler = 0/0 debug osd = 0/0 debug optracker = 0/0 debug objclass = 0/0 debug filestore = 0/0 debug journal = 0/0 debug ms = 0/0 debug monc = 0/0 debug tp = 0/0 debug auth = 0/0 debug finisher = 0/0 debug heartbeatmap = 0/0 debug perfcounter = 0/0 debug asok = 0/0 debug throttle = 0/0 in a ceph.conf on your kvm host ? - Mail original - De: Alexandre DERUMIER aderum...@odiso.com À: Stefan Priebe - Profihost AG s.pri...@profihost.ag Cc: pve-de...@pve.proxmox.com Envoyé: Lundi 12 Novembre 2012 15:26:36 Objet: Re: [pve-devel] less cores more iops / speed Maybe some tracing on kvm process could give us clues to find where the cpu is used ? Also another idea, can you try with auth supported=none ? maybe they are some overhead with ceph authenfication ? - Mail original - De: Alexandre DERUMIER aderum...@odiso.com À: Stefan Priebe - Profihost AG s.pri...@profihost.ag Cc: pve-de...@pve.proxmox.com Envoyé: Lundi 12 Novembre 2012 15:20:07 Objet: Re: [pve-devel] less cores more iops / speed Ok thanks. Seem to use a lot of cpu vs nfs,iscsi ... I hope that ceph dev will work on this soon ! - Mail original - De: Stefan Priebe - Profihost AG s.pri...@profihost.ag À: Alexandre DERUMIER aderum...@odiso.com Cc: eric e...@netwalk.com, pve-de...@pve.proxmox.com Envoyé: Lundi 12 Novembre 2012 15:05:08 Objet: Re: [pve-devel] less cores more iops / speed Am 12.11.2012 13:49, schrieb Alexandre DERUMIER: One VM on one Host: 18.000 IOP/s Two VM on one Host: 2x11.000 IOP/s Three VM on one Host: 3x7.000 IOP/s And host cpu is 100% ? No. For three VMs yes. For one and two no. I think librbd / rbd implementation in kvm is the bottleneck here. Stefan - Mail original - De: Stefan Priebe - Profihost AG s.pri...@profihost.ag À: Alexandre DERUMIER aderum...@odiso.com Cc: eric e...@netwalk.com, pve-de...@pve.proxmox.com Envoyé: Lundi 12 Novembre 2012 12:58:35 Objet: Re: [pve-devel] less cores more iops / speed Am 12.11.2012 08:51, schrieb Alexandre DERUMIER: Right now RBD in KVM is limited by CPU speed. Good to known, so it's seem lack of threading, or maybe somes locks. (so faster cpu give more iops). If you lauch parallel fio on same host on different guest, do you get more total iops ? (for me it's scale) One VM on one Host: 18.000 IOP/s Two VM on one Host: 2x11.000 IOP/s Three VM on one Host: 3x7.000 IOP/s if you launch 2 parallel fio, on same guest (on differents disk), do you get more iops ? (for me, it doesn't scale, so raid0 in guest doesn't help). No it doesn't scale. Stefan - Mail original - De: Stefan Priebe s.pri...@profihost.ag À: Alexandre DERUMIER aderum...@odiso.com Cc: eric e...@netwalk.com, pve-de...@pve.proxmox.com Envoyé: Dimanche 11 Novembre 2012 13:07:36 Objet: Re: [pve-devel] less cores more iops / speed Am 11.11.2012 12:12, schrieb Alexandre DERUMIER: If I remember good, stefan can achieve 100.000 iops with iscsi with same kvm host. Correct but this was always with scsi-generic and I/O multipathing on host. rbd does not support scsi-generic ;-( I have checked ceph mailing, stefan seem to have resolved his problem with dual core with bios update ! Correct. So speed on Dual Xeon is now 14.000 IOP/s and 18.000 IOP/s on Single Xeon. But the difference is an issue of the CPU Speed. 3,6Ghz Single Xeon vs
Re: [pve-devel] less cores more iops / speed
On 11/12/2012 07:33 AM, Stefan Priebe - Profihost AG wrote: Adding this to ceph.conf on kvm host adds another 2000 iops (20.000 iop/s with one VM). I'm sure most of them are useless on a client kvm / rbd host but i don't know which one makes sense ;-) [global] debug ms = 0/0 debug rbd = 0/0 debug lockdep = 0/0 debug context = 0/0 debug crush = 0/0 debug buffer = 0/0 debug timer = 0/0 debug journaler = 0/0 debug osd = 0/0 debug optracker = 0/0 debug objclass = 0/0 debug filestore = 0/0 debug journal = 0/0 debug ms = 0/0 debug monc = 0/0 debug tp = 0/0 debug auth = 0/0 debug finisher = 0/0 debug heartbeatmap = 0/0 debug perfcounter = 0/0 debug asok = 0/0 debug throttle = 0/0 [client] For the client side you'd these settings to disable all debug logging: [client] debug lockdep = 0/0 debug context = 0/0 debug crush = 0/0 debug buffer = 0/0 debug timer = 0/0 debug filer = 0/0 debug objecter = 0/0 debug rados = 0/0 debug rbd = 0/0 debug objectcacher = 0/0 debug client = 0/0 debug ms = 0/0 debug monc = 0/0 debug tp = 0/0 debug auth = 0/0 debug finisher = 0/0 debug perfcounter = 0/0 debug asok = 0/0 debug throttle = 0/0 Josh debug ms = 0/0 debug rbd = 0/0 debug lockdep = 0/0 debug context = 0/0 debug crush = 0/0 debug buffer = 0/0 debug timer = 0/0 debug journaler = 0/0 debug osd = 0/0 debug optracker = 0/0 debug objclass = 0/0 debug filestore = 0/0 debug journal = 0/0 debug ms = 0/0 debug monc = 0/0 debug tp = 0/0 debug auth = 0/0 debug finisher = 0/0 debug heartbeatmap = 0/0 debug perfcounter = 0/0 debug asok = 0/0 debug throttle = 0/0 Stefan Am 12.11.2012 15:35, schrieb Alexandre DERUMIER: Another idea, do you have tried to put debug lockdep = 0/0 debug context = 0/0 debug crush = 0/0 debug buffer = 0/0 debug timer = 0/0 debug journaler = 0/0 debug osd = 0/0 debug optracker = 0/0 debug objclass = 0/0 debug filestore = 0/0 debug journal = 0/0 debug ms = 0/0 debug monc = 0/0 debug tp = 0/0 debug auth = 0/0 debug finisher = 0/0 debug heartbeatmap = 0/0 debug perfcounter = 0/0 debug asok = 0/0 debug throttle = 0/0 in a ceph.conf on your kvm host ? - Mail original - De: Alexandre DERUMIER aderum...@odiso.com À: Stefan Priebe - Profihost AG s.pri...@profihost.ag Cc: pve-de...@pve.proxmox.com Envoyé: Lundi 12 Novembre 2012 15:26:36 Objet: Re: [pve-devel] less cores more iops / speed Maybe some tracing on kvm process could give us clues to find where the cpu is used ? Also another idea, can you try with auth supported=none ? maybe they are some overhead with ceph authenfication ? - Mail original - De: Alexandre DERUMIER aderum...@odiso.com À: Stefan Priebe - Profihost AG s.pri...@profihost.ag Cc: pve-de...@pve.proxmox.com Envoyé: Lundi 12 Novembre 2012 15:20:07 Objet: Re: [pve-devel] less cores more iops / speed Ok thanks. Seem to use a lot of cpu vs nfs,iscsi ... I hope that ceph dev will work on this soon ! - Mail original - De: Stefan Priebe - Profihost AG s.pri...@profihost.ag À: Alexandre DERUMIER aderum...@odiso.com Cc: eric e...@netwalk.com, pve-de...@pve.proxmox.com Envoyé: Lundi 12 Novembre 2012 15:05:08 Objet: Re: [pve-devel] less cores more iops / speed Am 12.11.2012 13:49, schrieb Alexandre DERUMIER: One VM on one Host: 18.000 IOP/s Two VM on one Host: 2x11.000 IOP/s Three VM on one Host: 3x7.000 IOP/s And host cpu is 100% ? No. For three VMs yes. For one and two no. I think librbd / rbd implementation in kvm is the bottleneck here. Stefan - Mail original - De: Stefan Priebe - Profihost AG s.pri...@profihost.ag À: Alexandre DERUMIER aderum...@odiso.com Cc: eric e...@netwalk.com, pve-de...@pve.proxmox.com Envoyé: Lundi 12 Novembre 2012 12:58:35 Objet: Re: [pve-devel] less cores more iops / speed Am 12.11.2012 08:51, schrieb Alexandre DERUMIER: Right now RBD in KVM is limited by CPU speed. Good to known, so it's seem lack of threading, or maybe somes locks. (so faster cpu give more iops). If you lauch parallel fio on same host on different guest, do you get more total iops ? (for me it's scale) One VM on one Host: 18.000 IOP/s Two VM on one Host: 2x11.000 IOP/s Three VM on one Host: 3x7.000 IOP/s if you launch 2 parallel fio, on same guest (on differents disk), do you get more iops ? (for me, it doesn't scale, so raid0 in guest doesn't help). No it doesn't scale. Stefan - Mail original - De: Stefan Priebe s.pri...@profihost.ag À: Alexandre DERUMIER aderum...@odiso.com Cc: eric e...@netwalk.com, pve-de...@pve.proxmox.com Envoyé: Dimanche 11 Novembre 2012 13:07:36 Objet: Re: [pve-devel
Re: [pve-devel] less cores more iops / speed
Hi Josh, For the client side you'd these settings to disable all debug logging: ... Thanks! Stefan -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: less cores more iops / speed
Am 08.11.2012 16:53, schrieb Alexandre DERUMIER: So it is a problem of KVM which let's the processes jump between cores a lot. maybe numad from redhat can help ? http://fedoraproject.org/wiki/Features/numad It's try to keep process on same numa node and I think it's also doing some dynamic pinning. numad doesn't help but libvirt seems to support pinning of kvm instances. Maybe pve should support pinning too? Greets Stefan -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: less cores more iops / speed
Am 08.11.2012 01:59, schrieb Mark Nelson: There's also the context switching overhead. It'd be interesting to know how much the writer processes were shifting around on cores. What do you mean by that? I'm talking about the KVM guest not about the ceph nodes. Stefan, what tool were you using to do writes? as always: fio ;-) Stefan -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: less cores more iops / speed
What do you mean by that? I'm talking about the KVM guest not about the ceph nodes. Do you have tried to compare virtio-blk and virtio-scsi ? Do you have tried directly from the host with the rbd kernel module ? - Mail original - De: Stefan Priebe - Profihost AG s.pri...@profihost.ag À: Mark Nelson mark.nel...@inktank.com Cc: Joao Eduardo Luis joao.l...@inktank.com, ceph-devel@vger.kernel.org Envoyé: Jeudi 8 Novembre 2012 09:45:17 Objet: Re: less cores more iops / speed Am 08.11.2012 01:59, schrieb Mark Nelson: There's also the context switching overhead. It'd be interesting to know how much the writer processes were shifting around on cores. What do you mean by that? I'm talking about the KVM guest not about the ceph nodes. Stefan, what tool were you using to do writes? as always: fio ;-) Stefan -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: less cores more iops / speed
Am 08.11.2012 09:58, schrieb Alexandre DERUMIER: What do you mean by that? I'm talking about the KVM guest not about the ceph nodes. Do you have tried to compare virtio-blk and virtio-scsi ? How to change? Right now i'm using the PVE defaults = scsi-hd. Do you have tried directly from the host with the rbd kernel module ? No don't know how to use ;-) Stefan - Mail original - De: Stefan Priebe - Profihost AG s.pri...@profihost.ag À: Mark Nelson mark.nel...@inktank.com Cc: Joao Eduardo Luis joao.l...@inktank.com, ceph-devel@vger.kernel.org Envoyé: Jeudi 8 Novembre 2012 09:45:17 Objet: Re: less cores more iops / speed Am 08.11.2012 01:59, schrieb Mark Nelson: There's also the context switching overhead. It'd be interesting to know how much the writer processes were shifting around on cores. What do you mean by that? I'm talking about the KVM guest not about the ceph nodes. Stefan, what tool were you using to do writes? as always: fio ;-) Stefan -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: less cores more iops / speed
Do you have tried to compare virtio-blk and virtio-scsi ? How to change? Right now i'm using the PVE defaults = scsi-hd. (virtio-blk is classic virtio ;) Do you have tried directly from the host with the rbd kernel module ? No don't know how to use ;-) http://ceph.com/docs/master/rbd/rbd-ko/ #modprobe rbd #sudo rbd map {image-name} --pool {pool-name} --id {user-name} (then you'll have a /dev/rbd1) - Mail original - De: Stefan Priebe - Profihost AG s.pri...@profihost.ag À: Alexandre DERUMIER aderum...@odiso.com Cc: Joao Eduardo Luis joao.l...@inktank.com, ceph-devel@vger.kernel.org, Mark Nelson mark.nel...@inktank.com Envoyé: Jeudi 8 Novembre 2012 10:02:23 Objet: Re: less cores more iops / speed Am 08.11.2012 09:58, schrieb Alexandre DERUMIER: What do you mean by that? I'm talking about the KVM guest not about the ceph nodes. Do you have tried to compare virtio-blk and virtio-scsi ? How to change? Right now i'm using the PVE defaults = scsi-hd. Do you have tried directly from the host with the rbd kernel module ? No don't know how to use ;-) Stefan - Mail original - De: Stefan Priebe - Profihost AG s.pri...@profihost.ag À: Mark Nelson mark.nel...@inktank.com Cc: Joao Eduardo Luis joao.l...@inktank.com, ceph-devel@vger.kernel.org Envoyé: Jeudi 8 Novembre 2012 09:45:17 Objet: Re: less cores more iops / speed Am 08.11.2012 01:59, schrieb Mark Nelson: There's also the context switching overhead. It'd be interesting to know how much the writer processes were shifting around on cores. What do you mean by that? I'm talking about the KVM guest not about the ceph nodes. Stefan, what tool were you using to do writes? as always: fio ;-) Stefan -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: less cores more iops / speed
Am 08.11.2012 10:05, schrieb Alexandre DERUMIER: Do you have tried to compare virtio-blk and virtio-scsi ? How to change? Right now i'm using the PVE defaults = scsi-hd. (virtio-blk is classic virtio ;) Do you have tried directly from the host with the rbd kernel module ? No don't know how to use ;-) http://ceph.com/docs/master/rbd/rbd-ko/ #modprobe rbd #sudo rbd map {image-name} --pool {pool-name} --id {user-name} this gives me also 8000 iops on the host with 3.6 Ghz. So this is the same like in KVM. Stefan -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: less cores more iops / speed
On 11/08/2012 02:45 AM, Stefan Priebe - Profihost AG wrote: Am 08.11.2012 01:59, schrieb Mark Nelson: There's also the context switching overhead. It'd be interesting to know how much the writer processes were shifting around on cores. What do you mean by that? I'm talking about the KVM guest not about the ceph nodes. in this case, is fio bouncing around between cores? Stefan, what tool were you using to do writes? as always: fio ;-) You could try using numactl to pin fio to a specific core. Also, it may be interesting to try multiple concurrent fio processes, and then concurrent fio processes with each pinned. Stefan -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: less cores more iops / speed
Am 08.11.2012 14:19, schrieb Mark Nelson: On 11/08/2012 02:45 AM, Stefan Priebe - Profihost AG wrote: Am 08.11.2012 01:59, schrieb Mark Nelson: There's also the context switching overhead. It'd be interesting to know how much the writer processes were shifting around on cores. What do you mean by that? I'm talking about the KVM guest not about the ceph nodes. in this case, is fio bouncing around between cores? Thanks you're correct. If i bind fio to two cores on a 8 core VM it runs with 16.000 iops. So it is a problem of KVM which let's the processes jump between cores a lot. Greets, Stefan -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: less cores more iops / speed
So it is a problem of KVM which let's the processes jump between cores a lot. maybe numad from redhat can help ? http://fedoraproject.org/wiki/Features/numad It's try to keep process on same numa node and I think it's also doing some dynamic pinning. - Mail original - De: Stefan Priebe - Profihost AG s.pri...@profihost.ag À: Mark Nelson mark.nel...@inktank.com Cc: Joao Eduardo Luis joao.l...@inktank.com, ceph-devel@vger.kernel.org Envoyé: Jeudi 8 Novembre 2012 16:14:32 Objet: Re: less cores more iops / speed Am 08.11.2012 14:19, schrieb Mark Nelson: On 11/08/2012 02:45 AM, Stefan Priebe - Profihost AG wrote: Am 08.11.2012 01:59, schrieb Mark Nelson: There's also the context switching overhead. It'd be interesting to know how much the writer processes were shifting around on cores. What do you mean by that? I'm talking about the KVM guest not about the ceph nodes. in this case, is fio bouncing around between cores? Thanks you're correct. If i bind fio to two cores on a 8 core VM it runs with 16.000 iops. So it is a problem of KVM which let's the processes jump between cores a lot. Greets, Stefan -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: less cores more iops / speed
On Thu, Nov 8, 2012 at 7:53 PM, Alexandre DERUMIER aderum...@odiso.com wrote: So it is a problem of KVM which let's the processes jump between cores a lot. maybe numad from redhat can help ? http://fedoraproject.org/wiki/Features/numad It's try to keep process on same numa node and I think it's also doing some dynamic pinning. Numad keeps only memory chunks on the preferred node, cpu pinning, which is a primary goal there, should be done separately via libvirt or manually for qemu process via cpuset(libvirt does pinning via taskset and seems that it is broken at least in debian wheezy - even affinity mask is set for qemu process, load spreads all over numa node, including cpus outside the set). - Mail original - De: Stefan Priebe - Profihost AG s.pri...@profihost.ag À: Mark Nelson mark.nel...@inktank.com Cc: Joao Eduardo Luis joao.l...@inktank.com, ceph-devel@vger.kernel.org Envoyé: Jeudi 8 Novembre 2012 16:14:32 Objet: Re: less cores more iops / speed Am 08.11.2012 14:19, schrieb Mark Nelson: On 11/08/2012 02:45 AM, Stefan Priebe - Profihost AG wrote: Am 08.11.2012 01:59, schrieb Mark Nelson: There's also the context switching overhead. It'd be interesting to know how much the writer processes were shifting around on cores. What do you mean by that? I'm talking about the KVM guest not about the ceph nodes. in this case, is fio bouncing around between cores? Thanks you're correct. If i bind fio to two cores on a 8 core VM it runs with 16.000 iops. So it is a problem of KVM which let's the processes jump between cores a lot. Greets, Stefan -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
less cores more iops / speed
Hello again, I've noticed something really interesting. I get 5000 iops / VM for rand. 4k writes while assigning 4 cores on a 2.5 Ghz Xeon. When i move this VM to another kvm host with 3.6Ghz i get 8000 iops (still 8 cores) when i then LOWER the assigned cores from 8 to 4 i get 14.500 iops. If i assign only 2 cores i get 16.000 iops... Why does less kvm cores mean more speed? Greets, Stefan -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: less cores more iops / speed
On 11/07/2012 10:02 PM, Stefan Priebe wrote: Hello again, I've noticed something really interesting. I get 5000 iops / VM for rand. 4k writes while assigning 4 cores on a 2.5 Ghz Xeon. When i move this VM to another kvm host with 3.6Ghz i get 8000 iops (still 8 cores) when i then LOWER the assigned cores from 8 to 4 i get 14.500 iops. If i assign only 2 cores i get 16.000 iops... Why does less kvm cores mean more speed? Totally going on a limb here, but might be related to the cache maybe? When you have more cores your threads may bounce around the cores and invalidate cache entries as they go by; will less cores you might end up with some sort of twisted, forced cpu affinity that allows you to take advantage of caching. But I don't know, really. I would be amazed if what I just wrote had an ounce of truth, and would be completely astonished if that was the cause for such a sudden increase on iops. -Joao Greets, Stefan -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: less cores more iops / speed
On 11/07/2012 06:00 PM, Joao Eduardo Luis wrote: On 11/07/2012 10:02 PM, Stefan Priebe wrote: Hello again, I've noticed something really interesting. I get 5000 iops / VM for rand. 4k writes while assigning 4 cores on a 2.5 Ghz Xeon. When i move this VM to another kvm host with 3.6Ghz i get 8000 iops (still 8 cores) when i then LOWER the assigned cores from 8 to 4 i get 14.500 iops. If i assign only 2 cores i get 16.000 iops... Why does less kvm cores mean more speed? Totally going on a limb here, but might be related to the cache maybe? When you have more cores your threads may bounce around the cores and invalidate cache entries as they go by; will less cores you might end up with some sort of twisted, forced cpu affinity that allows you to take advantage of caching. There's also the context switching overhead. It'd be interesting to know how much the writer processes were shifting around on cores. Stefan, what tool were you using to do writes? But I don't know, really. I would be amazed if what I just wrote had an ounce of truth, and would be completely astonished if that was the cause for such a sudden increase on iops. Yeah, it's seems pretty surprising that there would be any significant effect at this level of performance. -Joao Greets, Stefan -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: less cores more iops / speed
On 11/07/2012 06:00 PM, Joao Eduardo Luis wrote: On 11/07/2012 10:02 PM, Stefan Priebe wrote: Hello again, I've noticed something really interesting. I get 5000 iops / VM for rand. 4k writes while assigning 4 cores on a 2.5 Ghz Xeon. When i move this VM to another kvm host with 3.6Ghz i get 8000 iops (still 8 cores) when i then LOWER the assigned cores from 8 to 4 i get 14.500 iops. If i assign only 2 cores i get 16.000 iops... Why does less kvm cores mean more speed? Totally going on a limb here, but might be related to the cache maybe? When you have more cores your threads may bounce around the cores and invalidate cache entries as they go by; will less cores you might end up with some sort of twisted, forced cpu affinity that allows you to take advantage of caching. There's also the context switching overhead. It'd be interesting to know how much the writer processes were shifting around on cores. Stefan, what tool were you using to do writes? But I don't know, really. I would be amazed if what I just wrote had an ounce of truth, and would be completely astonished if that was the cause for such a sudden increase on iops. Yeah, it's seems pretty surprising that there would be any significant effect at this level of performance. -Joao Greets, Stefan -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
RE: less cores more iops / speed
I've noticed something really interesting. I get 5000 iops / VM for rand. 4k writes while assigning 4 cores on a 2.5 Ghz Xeon. When i move this VM to another kvm host with 3.6Ghz i get 8000 iops (still 8 cores) when i then LOWER the assigned cores from 8 to 4 i get 14.500 iops. If i assign only 2 cores i get 16.000 iops... Why does less kvm cores mean more speed? There is a serious bug in the kvm vhost code. Do you use virtio-net with vhost? see: http://lists.nongnu.org/archive/html/qemu-devel/2012- 11/msg00579.html Please test using the e1000 driver instead. Or update the guest kernel (what guest kernel do you use?). AFAIK 3.X kernels does not trigger the bug. -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: less cores more iops / speed
Am 08.11.2012 um 06:42 schrieb Dietmar Maurer diet...@proxmox.com: I've noticed something really interesting. I get 5000 iops / VM for rand. 4k writes while assigning 4 cores on a 2.5 Ghz Xeon. When i move this VM to another kvm host with 3.6Ghz i get 8000 iops (still 8 cores) when i then LOWER the assigned cores from 8 to 4 i get 14.500 iops. If i assign only 2 cores i get 16.000 iops... Why does less kvm cores mean more speed? There is a serious bug in the kvm vhost code. Do you use virtio-net with vhost? see: http://lists.nongnu.org/archive/html/qemu-devel/2012-11/msg00579.html Please test using the e1000 driver instead. Why is vhost net driver involved here at all? Kvm guest only uses ssh here. Stefan -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
RE: less cores more iops / speed
Why is vhost net driver involved here at all? Kvm guest only uses ssh here. I though you are testing things (rdb) which depends on KVM network speed? -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: less cores more iops / speed
Am 08.11.2012 um 06:49 schrieb Dietmar Maurer diet...@proxmox.com: I've noticed something really interesting. I get 5000 iops / VM for rand. 4k writes while assigning 4 cores on a 2.5 Ghz Xeon. When i move this VM to another kvm host with 3.6Ghz i get 8000 iops (still 8 cores) when i then LOWER the assigned cores from 8 to 4 i get 14.500 iops. If i assign only 2 cores i get 16.000 iops... Why does less kvm cores mean more speed? There is a serious bug in the kvm vhost code. Do you use virtio-net with vhost? see: http://lists.nongnu.org/archive/html/qemu-devel/2012- 11/msg00579.html Please test using the e1000 driver instead. Or update the guest kernel (what guest kernel do you use?). AFAIK 3.X kernels does not trigger the bug. Guest and Host habe 3.6.6 installed. -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: less cores more iops / speed
Am 08.11.2012 um 06:54 schrieb Dietmar Maurer diet...@proxmox.com: Why is vhost net driver involved here at all? Kvm guest only uses ssh here. I though you are testing things (rdb) which depends on KVM network speed? Kvm process uses librbd and both are running on host not in guest. Stefan -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html -- To unsubscribe from this list: send the line unsubscribe ceph-devel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html