Optimization of OpenNebula VMs for Higher Performance - Boyan Krosnov
2 likes3,003 views
The document discusses optimizing KVM virtual machines for performance by focusing on compute resources like CPU and memory, storage, and networking. It provides recommendations for hardware configuration including processors, RAM, and network interfaces, as well as software optimizations in the host OS, hypervisor, guest OS, and device drivers. Finally, it lists some good references for further information on virtual machine performance tuning.
Optimization of OpenNebula VMs for Higher Performance - Boyan Krosnov
- 1. Optimizing KVM virtual machines for performance Boyan Krosnov Chief of Product StorPool Storage
- 2. ● Better application performance -- e.g. time to load a page, time to rebuild, time to execute specific query ● Happier customers (in cloud / multi-tenant environments) ● Lower cost per delivered resource (per VM) ○ through higher density Why optimize
- 3. ● Compute - CPU and memory ● Storage ● Network ● Do you optimize for throughput or for latency? Where: ● VM, guest OS, drivers, etc. ● Host OS and hypervisor ● Host hardware ● Network ● Storage system What
- 4. Typically 2x 10GE per hypervisor for storage traffic Same or separate 2x 10GE for internet and inter-VM traffic Typical cluster has just 2 switches. Up to 96x 10GE ports at low cost. We are starting to see 40/56 GigE clusters and we expect many 25 GigE networks in the next year. VLANs, Jumbo frames, flow control. RDMA A word on networks
- 5. Typically - 2x E5-2697v3 -- 28 cores, 56 threads, @3.1GHz all-cores turbo - 256-384-512 GB RAM - 10/40 GigE NICs with RDMA - - firmware versions and BIOS settings matter - Understand power management -- esp. C-states and P-states - Think of rack level optimization - how do we get the lowest total cost per delivered resource. A word on host hardware
- 6. RHEL7 Virtualization_Tuning_and_Optimization_Guide Also https://pve.proxmox.com/wiki/Performance_Tweaks http://events.linuxfoundation.org/sites/events/files/slides/CloudOpen2013_Khoa_Huynh_v3.pdf http://www.linux-kvm.org/images/f/f9/2012-forum-virtio-blk-performance-improvement.pdf http://www.slideshare.net/janghoonsim/kvm-performance-optimization-for-ubuntu … but don’t trust everything you read. Perform your own benchmarking! Good references
- 7. Recent Linux kernel, KVM and QEMU … but beware of the bleeding edge E.g. qemu-kvm-ev from RHEV (repackaged by CentOS) tuned-adm virtual-host tuned-adm virtual-guest Host OS, guest OS
- 8. ● Use virtio-net driver ● regular virtio vs vhost_net ● SR-IOV (PCIe pass-through) Networking
- 9. ● cache=none -- direct IO, bypass host buffer cache ● io=native -- use Linux Native AIO, not POSIX AIO (threads) ● ● virtio-blk -> dataplane ● virtio-scsi -> multiqueue ● ● in guest virtio_blk.queue_depth 128 -> 256 Block I/O
- 10. - balloon - KSM (RAM dedup) - huge pages, THP - NUMA - use local-node memory if you can - route IRQs of network and storage adapters to a core on the node they are on Compute - Memory
- 12. Demo
- 13. Boyan Krosnov b k @ storool.com @bkrosnov https://storpool.com/