Tag Archives: msst

SMORE: A Cold Data Object Store for SMR Drives

Peter Macko, Xiongzi Ge, James Kelley, David Slik, Keith A. Smith and Maxim G. Smith, NetApp, Inc.; John Haskins Jr., Qualcomm

33rd International Conference on Massive Storage Systems and Technology (MSST 2017)
May 15 – May 19, 2017 Santa Clara, CA

Shingled magnetic recording (SMR) increases the capacity of magnetic hard drives, but it requires that each zone of a disk be written sequentially and erased in bulk. This makes SMR a good fit for workloads dominated by large data objects with limited churn. To explore this possibility, we have developed SMORE, an object storage system designed to reliably and efficiently store large, seldom changing data objects on an array of host-managed or host-aware SMR disks.

SMORE uses a log-structured approach to accommodate the constraint that all writes to an SMR drive must be sequential within large shingled zones. It stripes data across zones on separate disks, using erasure coding to protect against drive failure. A separate garbage collection thread reclaims space by migrating live data out of the emptiest zones so that they can be trimmed and reused. An index stored on flash and backed up to the SMR drives maps object identifiers to on-disk locations. SMORE interleaves log records with object data within SMR zones to enable index recovery after a system crash (or failure of the flash device) without any additional logging mechanism.

SMORE achieves full disk bandwidth when ingesting data— with a variety of object sizes—and when reading large objects. Read performance declines for smaller object sizes where inter- object seek time dominates. With a worst-case pattern of random deletions, SMORE has a write amplification (not counting RAID parity) of less than 2.0 at 80% occupancy. By taking an index snapshot every two hours, SMORE recovers from crashes in less than a minute. More frequent snapshots allow faster recovery.

Resources

A Deduplication Study for Host-side Caches in Virtualized Data Center Environments

msst.gifJingxin Feng and Jiri Schindler.

This paper explores the effectiveness of content deduplication in large (typically hundreds of GB) flash memory-based caches inside VM hypervisors.

Flash memory-based caches inside VM hypervisors can reduce I/O latencies and offload much of the I/O traffic from network-attached storage systems deployed in virtualized data centers. This paper explores the effectiveness of content deduplication in these large (typically 100s of GB) host-side caches. Previous deduplication studies focused on data mostly at rest in backup and archive applications. This study focuses on cached data and dynamic workloads within the shared VM infrastructure. We analyze I/O traces from six virtual desktop infrastructure (VDI) I/O storms and two long-term CIFS studies and show that deduplication can reduce the data footprint inside host-side caches by as much as 67%. This in turn allows for caching a larger portion of the data set and improves the effective cache hit rate. More importantly, such increased caching efficiency can alleviate load from networked storage systems during I/O storms when most VM instances perform the same operation such as virus scans, OS patch installs, and reboots.

In Proceedings of the IEEE Symposium on Massive Storage Systems and Technologies 2013 (MSST ’13).

Resources

  • The author’s version of this paper is attached to this posting. Please observe the following copyright:

© 2013 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Host-Side-Cache-Deduplication.pdf

Paragone: What’s next in block I/O trace modeling

msst.gifRukma Talwadker and Kaladhar Voruganti.

In this paper, we present Paragone, an algorithm that helps designers fundamentally rethink how I/O traces should be modeled and replayed.

Designers of storage and file systems use I/O traces to emulate application workloads while designing new algorithms and for testing bug fixes. However, since traces are large, they are hard to store and moreover inflexible to manipulate. Thus, researchers have proposed techniques to create trace models in order to alleviate these concerns. However, the prior trace modeling approaches are limited with respect to 1) number of trace parameters they can model, and hence, the accuracy of the model and 2) with respect to manipulating the trace model in both temporal and spatial domains (that is, changing the burstiness of a workload, or scaling the size of the data supporting the workload). In this paper we present a new algorithm/tool called Paragone that addresses the above mentioned problems by fundamentally re-thinking how traces should be modeled and replayed.

In Proceedings of the IEEE Symposium on Massive Storage Systems and Technologies 2013 (MSST ’13).

Resources

  • The author’s version of this paper is attached to this posting. Please observe the following copyright:

© 2013 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Paragone.pdf

SLO-aware Hybrid Store

msst-whitebg.pngPriya Sehgal, Kaladhar Voruganti, and Rajesh Sundaram.

In this paper we present an SLO based resource management algorithm that controls the amount of SSD given to a particular workload.

In the past storage vendors used different types of storage depending upon the type of workload. For example, they used Solid State Drives (SSDs) or FC hard disks (HDD) for online transaction, while SATA for archival type workloads. However, recently many storage vendors are designing hybrid SSD/HDD based systems that can satisfy multiple service level objectives (SLOs) of different workloads all placed together in one storage box, at better cost points. The combination is achieved by using SSDs as a read-write cache while HDD as a permanent store. In this paper we present an SLO based resource management algorithm that controls the amount of SSD given to a particular workload. This algorithm solves following problems: 1) it ensures that workloads do not interfere with each other 2) it ensure that we do not overprovision (cost wise) the amount of SSD allocated to a workload to satisfy its SLO (latency requirement) and 3) dynamically adjust SSD allocated in light of changing workload characteristics (i.e., provide only required amount of SSD). We have implemented our algorithm in a prototype Hybrid Store, and have tested its efficacy using many real workloads. Our algorithm satisfies latency SLOs almost always by utilizing close to optimal amount of SSD and saving 6-50% of SSD space compared to the naïve algorithm

In Proceedings of the IEEE Conference on Mass Storage Systems and Technologies 2012 (MSST’12)

Resources

  • The author’s version of the paper is attached to this posting, please observe the following copyright:

© 2012 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

 
msst-SLOAware.pdf