Your current filters are…
by Matt Ahrens
The performance of the file system, or disks, is often the target of blame, especially in multi-tenant cloud environments. At Joyent we deploy a public cloud on ZFS-based systems, and frequently investigate performance with a wide variety of applications in growing environments. This talk is about ZFS performance observability, showing the tools and approaches we use to quickly show what ZFS is doing. This includes observing ZFS I/O throttling, an enhancement added to illumos-ZFS to isolate performance between neighbouring tenants, and the use of DTrace and heat maps to examine latency distributions and locate outliers.
The ZFS hybrid storage pool model is very flexible and allows many different combinations of storage technology to be used. This presents a dilemma to the systems architect: what is the best way to build and configure a pool to meet business requirements? We’ll discuss modeling ZFS systems and hybrid storage pools at a datacenter scale. The models consider space, performance, dependability, and cost of the storage devices and any interconnecting networks (including SANs). We will also discuss methods for measuring the performance of the system.
In 2008, the ZFS Storage Appliance (nee the Sun Storage 7000) was one of the first architectures to add flash SSDs between the existing tiers of disk and memory. The Hybrid Storage Pool (HSP) offered completely new economies, but with both known and unknown idiosyncrasies. Adam Leventhal, the inventor of the HSP, will talk about their functionality and utility, pitfalls and shortcomings, as well as the next steps for ZFS amidst an ever changing landscape of technologies and economics.
For over 30 years, hard drives have designated the smallest storage location as 512 bytes. In January 2011, all major hard drive manufactures began shipping their hard drive platforms using a new standard called Advanced Format. To aid in the transition, these new hard drives provide a 512 byte emulation mode that allows the drives to advertise themselves as a 512 byte addressable devices. This can severely impact write performance resulting in the need for read-modify-write operations for any misaligned or partial writes that are issued.
The problem is not limited to just physical hardware. Other storage platforms may also provide LUNs (logical unit number) that presents themselves as a 512 byte addressable devices when, in fact, they use a 4K sector size internally. Although ZFS has built-in support for 4K sectors, it has no automatic way of dealing with the lies that the storage devices tell. This talk will focus on the methods that have been developed to work around the lies that hard drive storage platforms tell and will discuss the challenges and drawbacks that come with using 4K sectors.
1st–2nd October 2012