Presentazione VMware @ VMUGIT UserCon 2015
0 likes721 views
Virtual SAN is VMware's hyper-converged infrastructure storage solution that is integrated with vSphere. It provides a software-defined, distributed storage platform that offers policy-based placement and management of virtual machine storage. Version 6.1 introduced new features like stretched clusters for disaster recovery between sites, support for high-density flash devices, and health monitoring and troubleshooting tools through integration with vRealize Operations. Future enhancements may include RAID 5 and 6 functionality over the network to improve storage efficiency as well as data deduplication and compression.
Presentazione VMware @ VMUGIT UserCon 2015
- 1. VMware Virtual SAN Duncan Epping Chief Technologist Office of CTO Storage & Availability The story up to version 6.1, and a hint of what is coming
- 2. Agenda 1 Introduction 2 Virtual SAN, what is it? 3 Virtual SAN, a bit of a deeper dive 4 Version 6.1 specifics 5 Virtual SAN, the future 2
- 3. The Software Defined Data Center 3 Compute Networking Storage Management • All infrastructure services virtualized: compute, networking, storage • Control of data center automated by software (management, security) • Unified platform for existing and new apps, delivered to many devices • Any size / scale!
- 6. What is our goal? CHOICESIMPLICITY COST $ 3 PERFORMANCE AND SCALABILITY
- 7. The Hypervisor is the Strategic High Ground 7 Object Storagex86 - HCI SAN/NAS VMware vSphere
- 8. Storage Policy-Based Management – App centric automation 8 Overview • Intelligent placement • Fine control of services at VM level • Automation at scale through policy • Change policy when required • Attach new policy Virtual Machine Storage policy Reserve Capacity 40GB Availability 2 Failures to tolerate Read Cache 50% Stripe Width 6 Storage Policy-Based Management vSphere Virtual SAN Virtual Volumes Virtual Datastore
- 9. Storage Policy Based Management – What does it look like? 9 If the storage can satisfy the VM Storage Policy, the VM Summary tab in the vSphere client will display the VM as compliant. If not, either due to failures, or other reasons, the VM will be shown as non-compliant.
- 10. Virtual SAN, what is it? 10
- 11. Virtual SAN, what is it? 11 Hyper-Converged Infrastructure Distributed, Scale-out Architecture Integrated with vSphere platform Ready for today’s vSphere use cases Software-Defined Storage vSphere & Virtual SAN
- 12. VSAN is the Most Widely Adopted HCI Product Over 2000 customers within 15 months and growing rapidly
- 13. Virtual SAN Use Cases 13 VMware vSphere + Virtual SAN End User Computing Test/Dev ROBOStagingManagementDMZ Business Critical Apps DR / DA
- 14. Hyper-Converged Consumption Models 14 VMware Virtual SAN Software Software-Defined Storage Foundation for Hyper-Converged VMware Hyper-Converged Infrastructure Virtual SAN Ready Nodes • Certified server configuration • 90+ configuration options EVO:RAIL • Pre-integrated and pre- configured appliance • Rapidly deploy and manage EVO SDDC Suite • Pre-integrated and pre- configured data-center • Advanced automation with rapid deployment
- 15. Tiered Hybrid and All-Flash Options 15 All-Flash 90K IOPS per Host + sub-millisecond latency Caching Writes cached first, Reads from capacity tier Capacity Tier Flash Devices Reads go directly to capacity tier SSD PCIe Ultra DIMM Data Persistence Hybrid 40K IOPS per Host Read and Write Cache Capacity Tier SAS / NL-SAS / SATA SSD PCIe Ultra DIMM Virtual SAN
- 16. Production – Typical Design • In production most used is a 2U server platform • 256 / 384GB and 2 x 10 core Intel (v3) CPU • Two disk groups is typical per server • Per disk group: – Disk controller SAS Expander – 400GB SSD for read/write cache – 6 magnetic disks per disk group • Most customers use SAS – Those who use NL-SAS buy more flash! • Note, more than 8 disks? SAS Expander! • 2 x 10GbE 16
- 17. Yes… really simple! Virtual SAN is a cluster level feature similar to: – vSphere DRS – vSphere HA – Virtual SAN Deployed, configured and manage from vCenter through the vSphere Web Client – Radically simple • Configure VMkernel interface for Virtual SAN • Enable Virtual SAN by clicking Turn On 17
- 18. Virtual SAN, a bit of a deeper dive 18
- 19. Virtual SAN, what it is not... and what it is It’s not a distributed file system, it’s an object store! • Object Tree with Branches • Each Object has multiple Components • This allows you to meet availability and performance requirements • You can view it as “Distributed RAID” using 2 techniques: – Striping (RAID-0) – Mirroring (RAID-1) • Data is distributed based on policy 19 RAID-1 Mirror Copy Mirror Copy ESXi Host ESXi Host stripe-1b stripe-1a stripe-2b stripe-2a RAID-0RAID-0 witness VMDK Object
- 20. Define a policy first… Virtual SAN currently surfaces five unique storage capabilities to vCenter Server 20 What If APIs
- 21. Assign it to a new or existing VM When the policy is selected, Virtual SAN uses it to place / distribute the VM to guarantee availability and Performance 21
- 22. Number of Failures to Tolerate • Defines the number of hosts, disk or network failures a storage object can tolerate. • For “n” failures tolerated, “n+1” copies of the object are created and “2n+1” host contributing storage are required! 22 esxi-01 esxi-02 esxi-03 esxi-04 Virtual SAN Policy: “Number of failures to tolerate = 1” vmdk ~50% of I/O vmdk witness ~50% of I/O RAID-1
- 23. Number of Disk Stripes Per Object • The number of HDDs across which each replica of a storage object is distributed. Higher values may result in better performance. 23 esxi-01 esxi-02 esxi-03 esxi-04 VSAN Policy: “Number of failures to tolerate = 1” + “Stripe Width =2” stripe-1a stripe-2a witness RAID-0 RAID-0 stripe-1b stripe-2b RAID-1
- 24. Fault Domains, increasing availability through awareness • Create fault domains to increase availability • Four defined fault domains FD1 = esxi-01, esxi-02 FD3 = esxi-05, esxi-06 FD2 = esxi-03, esxi-04 FD4 = esxi-7, esxi-08 • To protect against one rack failure only 2 replicas are required and a witness across 3 failure domains! 24 FD2 FD3 FD4 vmdk vmdk witness RAID-1 esxi-01 esxi-02 esxi-03 esxi-04 esxi-05 esxi-06 esxi-07 esxi-08 FD1
- 26. 26 VSAN 5.5 March 2014 VSAN 6.0 March 2015 All Flash 64 host Clusters x2 Hybrid Performance VSAN Snapshots VSAN Clones Rack Awareness VSAN 6.1 September 2015 Stretched Cluster + ROBO vROps Management Pack Replication - 5 Minutes RPO Health and Performance Monitoring Root Cause Analysis & Guided Remediation
- 27. New Flash Hardware Devices Supported High Density Flash Devices • NVMe allows for greater parallelism to be utilized by both hardware and software and as a result various performance improvements • ULLtraDIMM™ SSDs connect flash storage to the memory channel via DIMM slots, achieving very low (<5us) write latency 27 Ultra DIMM vSphere & Virtual SAN
- 28. Virtual SAN – Stretched Cluster 28 Active-Active data centers • Virtual SAN cluster split across 2 sites! • Site-level protection with zero data loss and near-instantaneous recovery • Support for up to 5ms RTT latency between data sites – 10Gbps bandwidth expectation • Witness VM can reside anywhere – 200ms RTT latency – 100Mbps bandwidth required at most • Automated failover • Requires Virtual SAN Advanced license witness 5ms RTT, 10GbE Today VMware vSphere & Virtual SAN
- 29. Stretched Clusters, some things you need to know • We introduced the concept of site locality – Latency can be up to 5ms, you don’t want to incur that on every read – In order for reads to come from “site local” cache, define DRS rules! • We support both L2 and L3 for the Virtual SAN network – Keep in mind you need multicast routing for L3 between the data sites – The witness does not require multicast any longer 29
- 30. Virtual SAN – Disaster Recovery 30 Today witness 5ms RTT, 10GbE VMware vSphere & Virtual SAN Site Recovery Manager vSphere & Virtual SAN Site Recovery Manager • Replication between Virtual SAN datastores enables RPO as low as 5 minutes – Exclusively available to Virtual SAN 6.x, leverages vSphere Replication • Leverage Site Recovery Manager for disaster recovery orchestration • Stretched across metro distance, replicated across geo!
- 31. ROBO Deployments • As of VSAN 6.1 we support 2 host clusters for ROBO deployments – Both hosts only used to store “data” • Extension of VSAN Stretched Cluster solution • Each of the nodes will be a Fault Domain (FD) • One witness host needed per VSAN cluster – Witness node can be an ESXi VM – 500ms RTT latency • All sites managed centrally by one vCenter instance • Patching and software upgrades performed centrally through vCenter Server 31 witness witness witness vSphere & VSAN vSphere & Virtual SAN vSphere & VSAN vSphere & VSAN
- 32. Virtual SAN Witness Appliance 32 • Witness appliance: – ONLY supported with Stretched Cluster and ROBO – ONLY stores meta-data NOT customer data – is not able to host any virtual machines – can be re-created in event of failure • Appliance requirements: – at least three VMDK’s – Boot disks for ESXi requires 20GB – Capacity tier requires 16MB per witness component – Caching tier is 10% of capacity tier – Both tiers on witness could be on MDs • The amount of storage on the witness is related to number of components on the witness Witness Appliance vESXi
- 33. Advanced Monitoring and Troubleshooting with VROps 33 • Introduced with Virtual SAN 6.1 • Comprehensive global view across multiple Virtual SAN cluster • Hundred of KPIs simplified to an easy to consume dashboard • Smart alerts deliver insight and information – correlate symptoms across the stack • Supported with VROps Standard!
- 34. Advanced Troubleshooting with VSAN Health Check Plug-in 34 • Cluster Health • Network Health • Data Health • Limits Health • Physical Disk Health
- 36. RAID-5 and RAID-6 over the network • With “FTT=1” availability RAID-5 – 3+1 (4 host minimum) – 1.33x instead of 2x overhead • 20GB disk normally takes 40GB, now just ~27GB 36 RAID-5 ESXi Host parity data data data Beta coming! ESXi Host data parity data data ESXi Host data data parity data ESXi Host data data data parity • With “FTT=2” availability RAID-6 – 4+2 (6 host minimum) – 1.5x instead of 3x overhead • 20GB disk normally takes 60GB, now just ~30GB
- 37. Deduplication and compression for Space Efficiency • Deduplication and compression per disk group level, up to 8x data reduction – Will be called “Space Efficiency” • Space Efficiency enabled on a cluster level • Deduplicated when de-staging from cache tier to capacity tier – Fixed block length deduplication (4KB Blocks) • Compressed after deduplication – 4KB unique becomes 2KB or 1KB – Optimizing still cost vs benefit! 37 BetaBeta coming! esxi-01 esxi-02 esxi-03 vmdk vmdk vSphere & Virtual SAN vmdk
- 38. Serviceability: Performance Monitoring 38Disk Group Level Disk LevelCluster Level Host Level
- 39. VMware Virtual SAN: Generic Object Storage Platform VMware vSphere Virtual SAN VMFS Block File Rest