Back to bug 1304300

Who When What Removed Added
Red Hat Bugzilla Rules Engine 2016-02-03 09:45:46 UTC Flags testing_ack? planning_ack?
Michal Skrivanek 2016-02-03 14:21:57 UTC Blocks 1284775
Michal Skrivanek 2016-02-03 14:30:02 UTC Depends On 1304346
Doc Text large guests have a significant overhead on the host which is not accounted for when scheduling the VM
1/128th of the VM memory size is required to be available on host as a consecutive non-swapped block of memory.
End-user effect is that "sometimes" VMs do not run despite the memory on host seems to be sufficient.
Target Milestone --- ovirt-3.6.4
Doc Type Bug Fix Known Issue
Flags ovirt-3.6.z?
Hanns-Joachim Uhl 2016-02-03 14:53:51 UTC CC hannsj_uhl
Hanns-Joachim Uhl 2016-02-03 14:54:49 UTC Blocks 1201513
Yaniv Kaul 2016-02-04 17:58:33 UTC CC michal.skrivanek
Flags needinfo?(michal.skrivanek)
Michal Skrivanek 2016-02-08 12:30:08 UTC Depends On 1282833
Target Milestone ovirt-3.6.4 ovirt-4.0.0
Flags needinfo?(michal.skrivanek) ovirt-3.6.z? ovirt-4.0.0?
Michal Skrivanek 2016-02-08 12:38:43 UTC Blocks 1305498
Bronce McClain 2016-02-15 15:37:31 UTC Blocks 1308609
Hanns-Joachim Uhl 2016-02-18 16:18:16 UTC Blocks 1201513
Moran Goldboim 2016-03-24 08:32:04 UTC CC mgoldboi
Target Milestone ovirt-4.0.0 ovirt-4.1.0
Flags ovirt-4.0.0? ovirt-4.1.0?
Ilanit Stein 2016-06-22 06:36:31 UTC QA Contact istein mavital
Bronce McClain 2016-07-25 14:18:29 UTC Blocks 1359843
Hanns-Joachim Uhl 2016-07-27 19:15:41 UTC Blocks 1308609
Yaniv Kaul 2016-11-29 21:07:50 UTC Target Milestone ovirt-4.1.0-alpha ovirt-4.2.0
Flags ovirt-4.1? ovirt-4.2?
Hanns-Joachim Uhl 2017-05-11 13:54:16 UTC Blocks 1359843 1444027
Michal Skrivanek 2017-08-22 07:55:58 UTC Priority unspecified medium
Target Milestone ovirt-4.2.0 ovirt-4.3.0
Flags ovirt-4.2? ovirt-4.3?
meital avital 2018-06-06 06:28:00 UTC QA Contact mavital ipinto
meital avital 2018-09-16 12:45:42 UTC CC mavital
QA Contact ipinto lrotenbe
Michal Skrivanek 2018-09-18 12:47:46 UTC Status NEW CLOSED
Resolution --- CURRENTRELEASE
Last Closed 2018-09-18 08:47:46 UTC
Rolfe Dlugy-Hegwer 2019-01-17 22:36:22 UTC CC rdlugyhe
Docs Contact rdlugyhe
Doc Text large guests have a significant overhead on the host which is not accounted for when scheduling the VM
1/128th of the VM memory size is required to be available on host as a consecutive non-swapped block of memory.
End-user effect is that "sometimes" VMs do not run despite the memory on host seems to be sufficient.
Large guest operating systems have a significant overhead on the host. This overhead is not accounted for when scheduling the virtual machine. The host requires a consecutive non-swapped block of memory that is 1/128th of the virtual machine's memory size. If this memory requirement is not satisfied, the virtual machine may fail to start with an error message similar to this one: "libvirtError: internal error: process exited while connecting to monitor: ... qemu-kvm: Failed to allocate HTAB of requested size, try with smaller maxmem"
Rolfe Dlugy-Hegwer 2019-01-21 18:03:47 UTC Doc Text Large guest operating systems have a significant overhead on the host. This overhead is not accounted for when scheduling the virtual machine. The host requires a consecutive non-swapped block of memory that is 1/128th of the virtual machine's memory size. If this memory requirement is not satisfied, the virtual machine may fail to start with an error message similar to this one: "libvirtError: internal error: process exited while connecting to monitor: ... qemu-kvm: Failed to allocate HTAB of requested size, try with smaller maxmem" Large guest operating systems have a significant overhead on the host. The host requires a consecutive non-swapped block of memory that is 1/128th of the virtual machine's memory size. Previously, this overhead was not accounted for when scheduling the virtual machine. If the memory requirement was not satisfied, the virtual machine failed to start with an error message similar to this one: "libvirtError: internal error: process exited while connecting to monitor: ... qemu-kvm: Failed to allocate HTAB of requested size, try with smaller maxmem"

The current release fixes this issue by accounting for the overhead when scheduling a virtual machine that has a large guest operating system.
Doc Type Known Issue Release Note
Flags needinfo?(michal.skrivanek)
Michal Skrivanek 2019-01-22 12:44:02 UTC Flags needinfo?(michal.skrivanek)
Rolfe Dlugy-Hegwer 2019-01-22 14:57:01 UTC Doc Text Large guest operating systems have a significant overhead on the host. The host requires a consecutive non-swapped block of memory that is 1/128th of the virtual machine's memory size. Previously, this overhead was not accounted for when scheduling the virtual machine. If the memory requirement was not satisfied, the virtual machine failed to start with an error message similar to this one: "libvirtError: internal error: process exited while connecting to monitor: ... qemu-kvm: Failed to allocate HTAB of requested size, try with smaller maxmem"

The current release fixes this issue by accounting for the overhead when scheduling a virtual machine that has a large guest operating system.
Large guest operating systems have a significant overhead on the host. The host requires a consecutive non-swapped block of memory that is 1/128th of the virtual machine's memory size. Previously, this overhead was not accounted for when scheduling the virtual machine. If the memory requirement was not satisfied, the virtual machine failed to start with an error message similar to this one: "libvirtError: internal error: process exited while connecting to monitor: ... qemu-kvm: Failed to allocate HTAB of requested size, try with smaller maxmem"

The current release fixes this issue by using dynamic hash page table resizing.

Back to bug 1304300