Downloaded 25 times
![Current Developments
‘11 ‘12 ‘13
Finish initial merge Cortex-A15 Support Lightweight version of
(ARM virt extensions) Xen tools
Key Activities
Integration of Xen ARM with mainline (80% completed)
Rebased on the recent xen-unstable.hg
Many parts of the Xen ARM has been rewritten for the integration.
Prototyping of Cortex A15 support using ARM virtualization extensions
We should start to see the next code drops for review and discussion at the end of November
Select reference platform(s) for Xen ARM [likely that we will follow Linaro]](https://image.slidesharecdn.com/xenprojectupdatelinuxconbrv1-0-111117124113-phpapp02/75/Xen-Project-Update-LinuxCon-Brazil-23-2048.jpg)
![Current Developments
‘11 ‘12 ‘13
Finish initial merge Cortex-A15 Support Lightweight version of
(ARM virt extensions) Xen tools
Key Activities
Integration of Xen ARM with mainline (80% completed)
Rebased on the recent xen-unstable.hg
Many parts of the Xen ARM has been rewritten for the integration.
Prototyping of Cortex A15 support using ARM virtualization extensions
We should start to see the next code drops for review and discussion at the end of November
Select reference platform(s) for Xen ARM [likely that we will follow Linaro]](https://crownmelresort.com/image.slidesharecdn.com/xenprojectupdatelinuxconbrv1-0-111117124113-phpapp02/75/Xen-Project-Update-LinuxCon-Brazil-23-2048.jpg)
Uploaded byThe Linux Foundation
Xen Project Update LinuxCon Brazil
Xen.org Project Updates discusses recent developments in several Xen projects: PVOPS has added Dom0 support to Linux 3.0 and ongoing work in 3.1 including new modules. Planned work includes features like HW clock support and 3D graphics. Xen 4.1 was recently released with large system support up to 4TB and 255 CPUs. Security enhancements include CPU pools and memory introspection. The XCP project aims to make the XenAPI toolstack independent of distributions and deliverable via common package managers. This would allow XCP to become the Xen community platform. The Xen ARM project has supported ARM architectures since 2004. Current work focuses on Cortex-A15
More Related Content
Similar to Xen Project Update LinuxCon Brazil
![XPDDS19: [ARM] OP-TEE Mediator in Xen - Volodymyr Babchuk, EPAM Systems](https://cdn.slidesharecdn.com/ss_thumbnails/xendevsummit2019-babchuk-op-tee-190812095541-thumbnail.jpg?width=640&height=640&fit=bounds)
Xen Project Update LinuxCon Brazil
- 1. Xen.org Project Updates: PVOPS, Xen, XCP and Xen ARM Lars Kurth Xen Community Manager lars.kurth@xen.org @lars_kurth @xen_com_mgr
- 2. PVOPS : Xenin Linux 3.x
- 3. Current State Xen Domain 0 Support Added to Linux 3.0 Ongoing work to round out the feature set in Linux 3.1 and onwards
- 4. New in Linux3.1 • Xen-pciback module – Last major backend to be included • Usability improvements – e.g. Auto loading of backend modules – Helps distros to package / deploy • Memory Hotplug • Bug fixes – e.g. VGA text console for dom0 fixed
- 5. Planned for 3.2and beyond • Hwclock support (date -s) • PV Spinlock support • Blkback: • ACPI S3 ”feature-barrier” support • 3D graphics • Blkback/front: • ACPI cpufreq support ”feature-discard” support • Blkback multiring • PCIback: Support for • Netback optimisations multi-segmented (”big”) boxes • Continue to round out the • Kexec/kdump support for feature set, usability, rough PVHVM guests edges
- 6. OK, so Upstreamhas stuff! • So I can just install <favorite distro> and use Xen? – Yes! (when distributions start shipping 3.0+ kernel) – For details visit Dom 0 Kernels for Xen Wiki – Some distros don't enable all backends – please open distro bugs (and let xen-devel know) • Or you can build a v3.0+ Linux kernel with Xen 4.1.1 on existing distro. – Details, explanations, etc: XenParavirtOps Wiki
- 7. How you canhelp • Take Linux 3.1 for a spin with Xen 4.1.2 – or even Linux 3.2-rc1 or newer if adventurous • Run it first without Xen to establish a baseline • Then run it under Xen and see what happens • Please send e-mail to xen-devel with what works and with what does not.
- 8. Architecture Considerations Type 1:Bare metal Hypervisor Type 2: OS ‘Hosted’ A pure Hypervisor that runs directly on the A Hypervisor that runs within a Host OS and hosts hardware and hosts Guest OS’s. Guest OS’s inside of it, using the host OS services to provide the virtual environment. VMn User-level VMM VMn VM1 VM0 VM0 Device User Apps Models Guest OS Guest OS and Apps and Apps Host OS Hypervisor Device Ring-0 VM Monitor Device Drivers / Models Drivers “Kernel” Scheduler MMU Host HW Host HW Memory CPUs I/O Memory CPUs I/O Provides partition isolation + reliability, Low cost, no additional drivers higher security
- 9. Architectural Advantage ofXen Thin hypervisor VMn Domain 0 • Open source VM1 High-level Monitor VM0 • Proprietary code in guests Device Guest OS Use Linux in upstream Models and Apps Linux • Take full advantage of PV • PV on HVM Device Models Xen Hypervisor (Timer, Interrupt) • No additional device drivers Host HW (Linux 3.x dom0) I/O Memory CPUs Hybrid Architecture Use hardware assistance for unmodified guests 9
- 10.
- 11. Xen 4.1 Release:21 March 2011 • Very large system support – 4 TB; >255 CPUs – Reliability, Availability, Scalability enhancements • CPU Pools for system partitioning • Page sharing enhancements • Hypervisor emergency paging / compression • New “xl” lightweight control stack • Memory Introspection API • Enhanced SR-IOV support • Software-implemented Hardware Fault Tolerance
- 12. Security will drivethe Next Wave of Virtualization • Security is key requirement for Cloud • Security is the primary goal of virtualization on the Client – Desktop, Laptops, Smart Phones, etc • Maintaining isolation between VMs is critical – Spatial and Temporal isolation – Run multiple VMs with policy controlled information flow • E.g. Personal VM; Corporate VM; VM for web browsing; VM for banking
- 13. Disaggregation • Functionality ofXen’s control VM (Dom0) – Disaggregated into specific classes of service VMs • Each contains a specific set of control logic – See: ”Breaking up is hard to do” @ xenpapers • Unique benefit of the Xen architecture – Security: Minimum privilege; Narrow interfaces – Performance: lightweight, e.g. minios directly on hypervisor – Reliability: Able to be safely restarted
- 14. Isolated Driver VMsfor HA • Detect failure e.g. 350 300 – Illegal access 250 – Timeout 200 • Kill domain, restart 150 100 – E.g. Just 275ms outage from 50 failed Ethernet driver 0 0 5 10 15 20 25 30 35 40 • New work uses restarts to time (s) enhance security
- 15. Qubes OS /XenClient XT • First products configured to take advantage of the security benefits of Xen’s architecture • Isolated Driver Domains • Virtual hardware Emulation Domains • Service VMs (global and per-guest) • Xen Security Modules / SElinux • Measured Launch (TXT)
- 16.
- 17. XCP Today Vertical stack for server virtualization Distributed as a closed appliance with CentOS 5.5 Dom0, misc DomU’s, network & storage support and Xen API Really: an open source distribution of XenServer
- 18. Project Kronos • Makethe XAPI toolstack independent of CentOS 5.5 • Extend the delivery model – Deliver Xen, XAPI and everything in between (storage manager, network support, OCaml libs, etc.) via your favorite Linux distro “apt-get install xapi” or “yum install xapi” • The Plan: – Initially Debian and Ubuntu (12.04) – Later any major Linux distro (Fedora, etc.)
- 19. XCP Vision XCP is the configuration of choice for clouds – Optimized for cloud use-cases – Optimized for how usage patterns in cloud projects – XenAPI toolstack is more easily consumable XCP becomes the Xen Community Platform – XCP becomes XenServer “unstable” – Track unstable Xen hypervisor and Linux kernels – Fully open development model (build & test capability)
- 20.
- 21. Xen ARM History ‘04 ‘08 ‘09 ‘10 ‘11 x86 Xen Hypervisor Xen ARM 1st Xen ARM 2nd Xen ARM 3rd Xen ARM 4th Xen ARM 5th Release Release: ARM9 Release: Release: Release: Release: Cortex-A9 (Cambridge Xen Hypervisor, Paravirtualized ARM11MPCore Performance MPCore Support University) Mini-OS Linux kernel Support Optimization (Samsung) (Samsung) (v2.6.24), Xen tool (Samsung) (Samsung) (Samsung) More information: – wiki.xen.org/wiki/XenARM & xen-arm mailing list – Good overview in slides and papers links section
- 22. From Servers toLaptops to Mobiles • ARM based Servers: ARM v7 & v8 • Client Virtualization: Qubes OS / XenClient / XenClient XT • Smart Phones – HW Consolidation: AP(Application Processor) and BP(Baseband Processor) can share multicore ARM CPU SoC in order to run both Linux and Real-time OS efficiently – OS Isolation: important call services can be effectively separated from downloaded third party applications by Xen ARM combined with access control – Rich User Experience: multiple OS domains can run concurrently on a single smartphone
- 23. Current Developments ‘11 ‘12 ‘13 Finish initial merge Cortex-A15 Support Lightweight version of (ARM virt extensions) Xen tools Key Activities Integration of Xen ARM with mainline (80% completed) Rebased on the recent xen-unstable.hg Many parts of the Xen ARM has been rewritten for the integration. Prototyping of Cortex A15 support using ARM virtualization extensions We should start to see the next code drops for review and discussion at the end of November Select reference platform(s) for Xen ARM [likely that we will follow Linaro]
- 24.
- 25. 2011 Contribution Statistics By Change Sets *) By KLOC **) ***) 5000.0 1% 4500.0 3% 5% 4000.0 6% 28% Citrix XCP 3500.0 Citrix HV 3000.0 Samsung* XenARM** 11% 2500.0 Novell PVOPS Oracle 2000.0 XCP AMD 1500.0 Xen HV Individual 13% Intel 1000.0 18% Misc 500.0 0.0 15% *) End of Sept 2011 *) Activity on Development branch (not yet in xen-unstable) **) Activity on Development branch (not yet in xen-unstable) **) Includes PVOPS ***) Until Sept 2011
- 26. How to Contribute& Engage • Developers: same process as for Linux Kernel – Same license: GPLv2 – Same roles: Developers, Maintainers, Committers – Contributions by patches + sign-off (Developer Certificate of Origin) – Details @ xen.org/projects/governance.html • Users – IRC: ##xen @ FREENODE – Mailing List: xen-users, but also groups.google.com/group/xen-br – New wiki: wiki.xen.org, but also wiki.xen-br.org
- 27. Shameless Marketing Vendors inthe Xen community are hiring! Vendors in the Xen community are hiring! Vendors in the Xen community are hiring! xen.org/community/jobs.html
- 28.
Editor's Notes
- #3 PVOPS is the Kernel Infrastructure to run a PV Hypervisor on top of Linux
- #4 Where are we?1) Linux 3 contains everything needed to run Xen on a Vanilla Kernel, both as Dom0 and DomU2) That’s of course a little bit of an old hat now3) But it is worth mentioning that it only took 5 years to upstream that PVOPS into the kernel
- #5 Let’s have a quick look at what’s new in the kernelMainly usability improvementsThe most significant addition is the PCI back module which enables the kernel to pass PCI/PCIe devices to Xen guests
- #6 Quite a lot of features are planned to go into Linux 3.2 and beyond. I will just explain a few. For the rest, do talk to me afterwards3.2 Feature Discard: Tells the HW that disk sectors are unusedThis is good for Solid State DrivesBut it is also good for filers doing thin provisioning3.3 PV Spinlocks: Better performance under contention ACPI S3: Which gives us Suspend to RAM, which is good for Xen on Laptop Use casesThe key is that all this is about optimization and rounding out of features------------------3.2: hwclock -s: Makes time (i.e. wallclock, RTC time) handling work as expected for the dom0 administrator. "feature-barrier": Required for correctness by certain guests (SLES10, I think). AIUI various filesystem implementations rely on barriers to Yup (and Oracle's guests applicance thingies) actually do something for correctness. Without this there coudl be corruption (I wouldn't necessarily stand on stage and say that out loud though) Some form of it can appear if you unplug the machine right as it is writting data out. But I am not entirely sure how to reproduce that 100%.. But yes - barries and flushes provide a mechanism to do 'write meta data NOW', and then the normal data can be written. So that in case of power failure you can go back to the meta data and figure stuff out. So yes. corruption averted! "feature-discard": Used to indicate to h/w that disk sectors are unused. This is good for SSDs and also for filers which do thin provisioning since it improves wear-levelling and allows the space to be recovered respectively. <nods> Not sure what there is to say about the others. 3.3: PV spinlocks: PV spinlocks improve performance under contention by allowing lock takers to sleep/yield instead of spinning wasting scheduling quanta. The current PV spinlock replaces the entire spinlock algorithm/datastructure. The new work simply adds a PV slow path but keeps the core "ticket lock" algorithm. This is beneficial in terms of sharing more code (and hence perf analysis etc) with native. The benefit is that during high contention (so more guests using VCPUs that there are physical CPUS - think four guests, each using 2 VCPU, and the box only has four physical) we can schedule the guests appropiately instead of spinning uselessly wasting CPU resources. ACPI S3: Suspend to RAM. Useful for Xen on laptop type scenarios. Yeah, that one is taking longer than I thought. Got some feedback and will post a new set shortly. 3D graphics: THe RAM used by graphics cards has various constraints on the RAM which they use which we need to work with in order to make those cards work correctly It pretty much is in. Another graphics guy picked up the patches, reworked them even further and they are definitly in for 3.3. ACPU cpufreq: Power management, useful in servers etc. I suspect this also improves performance in some cases by allowing access to faster states. Still a bit behind sadly. The patches are "nicer" but still not sure how to make them even more nicer for Len. Will have to post them at some point. Maybe I shoudl do it on Dec 24th
- #7 So what does all that mean?Firstly, you can just Download the latest Linux distro, get the Xen package and you can get startedOf course that requires distros which have the Linux 3 kernel in itDebian Squeeze, Fedora 16, Ubuntu 10.10
- #8 Why should you help?There are lots of HW variants and our developers cant possibly test all of themSo if you do wangt to help ...If you see any issues: and that may mean bugs, unexpected behavior, unexpected performance: let is know such that we can fix it.
- #9 At this point I want to make a quick detour into the different hypervisor architectures. Partly b ecause some of it is relevant to PVOPS, partly because we need it a little later.Let’s look at type 1 hypervisor:Basically a very simple architecture, where the Hypervisor replaces the kernelThe architecture is significantly simpler that a Type 2 hypervisor, because it does not need to provide rich “process” semantics, like “user”, filesystems, etc.BUT: the trade-off is that all the device drivers need to be rewritten for each hardware platformType 2 is hosted- The hypervisor is just a driver that typically works with user-level monitor.- HW access is interecpted by the ring 0- VM monitor passed to the User level Virtual Monitor, which passes requests to the kernel
- #10 Xen is actually a hybrid hypervisor, which combines the robustness of bare metal with the flexibility & ease of use of a type 2 hypervisor.That comes in its own with the PVOPS project, with Xen support in upstream => go to point 2
- #12 Earlier this year, we released Xen 4.1I just put up the feature list, but I wont go through it in detail. I did want to point out that the focus of this release was onSupport for large systems and easier management of large systems with CPU poolksAs well as on securityAnd that is starting a trend to optimize the hypervisor for cloud use cases
- #13 So for a hypervisor, as Xen which is powering 80% of the public cloud – rackspace, AWS and many other VPS providers use Xen and with cloud computing becoming mainstream, furthering security is really importantAccording to many surveys, security is actually the main reason which makes or breaks cloud adoptionBetter security means more adoptionConcerns about security means slowed adoptionOne of the key things there is isolation between VMs, but also simplicity as I pointed out earlierBut there are also a number of advanced features in Xen, which are not that widely know. So I wanted to give you a short overview of two of them
- #14 Example: XOARSelf-destructing VMs (destroyed after initialization): PCIBack = virtualize access to PCI Bus configRestartable VMs (periodic restarts): NetBack (Physical network driver exposed to guest) = restarted on timerBuilder (instantiate other VMs) = Restarted on each request
- #16 This is not pie in the sky: these features are actually in use already for desktop virtualization.I wanted to point out Qubes OS which is an OSS project in its second betaAnd a commercial Citrix product which makes use of these featuresIn the last 6 months there has been lots of talk in the community, how these features can be adopted for Server virtualization and I expect that we see adoption of these in XCP and commercial Xen products.But of course this is not easy: there are challenges around Configuartion and Usability
- #23 The key point here isXen ARM has a long historyUses paravirtualizationAnd supports a wide range of ARM processor featuresAs Kiko pointed out, there are quite few challenges in the ARM space such as complexity and Linux ports and that also affects XenSo for example to build Xen ARM, it was necessary to modify the ARM Linux kernel and we are facing questions such as a) do we try and upstream, or do we go for a clean start with newer ARM architectures
- #24 This slide is all about pointing out that there is pull for the ARM architectureCALXEDA| HP
- #25 Goals:Mobile, Client and Server for ARM Realtime capabilityMake sure that we have an architecturally clean start moving forward