はてなブックマーク

Optimizing erasure-coded storage for latency and cost by Robin Harris | Friday, September 12, 2014 | Architecture, Cloud computing & storage, Object storage | 6 comments Erasure coded (EC) storage has achieved remarkable gains over current RAID arrays in fault-tolerance and storage efficiency, but the knock against it is performance. Sure, it’s highly available and cheap, but it’s slo-o-w. Advance

Crossbar founder finds metals move – in a solid by Robin Harris | Friday, June 27, 2014 | Future Tech, SSD/Flash/NVRAM | 0 comments NVRAM maker Crossbar’s co-founder and professor at U Michigan Wei Lu has published a paper describing a never-before-seen phenomena: metal nanoparticles moving in a solid. Crossbar is pushing RRAM – Resistance RAM – but there is a problem with most RRAM implementation

Crossbar shows ultra-dense RRAM architecture by Robin Harris | Monday, June 30, 2014 | Future Tech, SSD/Flash/NVRAM | 0 comments Crossbar, the resistance RAM (RRAM) startup, opened the kimono a little wider today with the announcement of their “1TnR” architecture, which they have implemented on pre-production test chips. Unpacking 1TnR: 1 Transistor drives n number of RRAM cells. How many? They re

Open vStorage by Robin Harris | Thursday, June 5, 2014 | Cloud computing & storage, Clusters, NAS, IP, iSCSI, Object storage, Virtualization | 4 comments Open vStorage is a new virtual storage system coming out of stealth mode. Designed to enable virtual machines to run directly from object storage, it is a layer between the hypervisor and the object store with the goal of turning object storage –

Disks: how hot is too hot? by Robin Harris | Friday, May 30, 2014 | Disk, Enterprise | 0 comments This is a StorageMojo summary of technical research. The effect of temperature on disk drives: shorten their life or not? Most studies say no – including a new one – but Microsoft/UVA researchers seem to disagree. Backblaze published a detailed blog post on observed effects of temperature on disk driv

EMC’s DSSD FUD by Robin Harris | Friday, May 23, 2014 | Architecture, Clusters, Disk, SAN, FC, SSD/Flash/NVRAM | 3 comments Tired of Fibre Channel? Bored with Ethernet? Infiniband not enough? EMC has a new idea: a PCIe SAN. PCIe is part of their DSSD plan. A good question is: will customers buy it? A better question is: what is EMC talking about? EMC‘s head of product operations, Jeremy Burton,

Amazon’s Glacier secret: BDXL by Robin Harris | Friday, April 25, 2014 | Backup, Cloud computing & storage | 24 comments Remember when Amazon Web Services (AWS) announced Glacier, a data archiving service, almost 2 years ago? Long-term, slow-retrieval (3-5 hours) storage for 1¢/GB while maintaining several copies across geographies. Pretty amazing. Less amazing now that disk prices are reaching 3

Is software’s free ride over? by Robin Harris | Thursday, March 27, 2014 | Architecture, Future Tech | 3 comments It’s been a rule of thumb for the last 30+ years that any functionality implemented in hardware will surely migrate to software. But that is starting to change. At the beginning of a new application – say RAID controllers – the volumes are low and the trade-offs poorly understood. Perf

Extending block storage to cloud scale by Robin Harris | Tuesday, October 15, 2013 | Architecture, Cloud computing & storage, Clusters, Disk, Future Tech, SAN, FC, SSD/Flash/NVRAM | 4 comments Block I/O has been a stalwart of SCSI, IDE and SATA interfaces for over 30 years. But sharing those devices hasn’t been easy and certainly has only rarely, if ever, made it into enterprise production systems

The death of disks by Robin Harris | Tuesday, June 25, 2013 | Architecture, Backup, Cloud computing & storage, Disk, Enterprise | 12 comments A forecast says PC shipments with disk drives will drop by a third between now and 2017. IBM is pushing the all-flash datacenter. SSD start ups are claiming that flash is really as cheap as disk with much better performance. Is it the beginning of the end fo

Facebook’s advanced erasure codes by Robin Harris | Friday, June 21, 2013 | Architecture, Clusters, Information Management | 4 comments We want our data protected from device failures. When there is a failure we want to get our data back quickly. And we want to pay as little as possible for the protection and the restore. How? Recent research by hyper-scale system managers – mostly Microsoft and F

Long-term storage at Storage Visions 2013 by Robin Harris | Friday, January 18, 2013 | Backup, Future Tech, Information Management | 2 comments No CES for me this year, but did attend Storage Visions 2013. Some cool stuff there. Panasonic’s Blu-ray RAID archive robot Panasonic has a Blu-ray-based storage system that looks interesting. Imagine 12 Blu-ray discs in the striped RAID configuration. The

The SSD write cliff in real life by Robin Harris | Thursday, June 7, 2012 | Architecture, SSD/Flash/NVRAM | 9 comments Flash drives are known to have latency issues. The requirement to erase and program large blocks – even for small writes – means that if the drive runs out of free blocks a 50+ ms delay is possible while garbage collection works to provide one. Since free blocks are used up in wri

Google’s Disk Failure Experience by Robin Harris | Monday, February 19, 2007 | Clusters, Enterprise, SOHO/SMB | 34 comments Google released a fascinating research paper titled Failure Trends in a Large Disk Drive Population (pdf) at this years File and Storage Technologies (FAST ’07) conference. Google collected data on a population of 100,000 disk drives, analyzed it, and wrote it up for our de

Google File Systems v2, part 1 by Robin Harris | Monday, August 17, 2009 | Architecture, Cloud computing & storage, Clusters | 1 comment A couple of years ago at the first Seattle Conference on Scalability, Google’s Jeffrey Dean remarked that the company wanted 100x more scalability. Unsurprising given the rapid growth of the web. But there was more to it than that: GFS – the Google File System wa

Everything You Know About Disks Is Wrong by Robin Harris | Tuesday, February 20, 2007 | Clusters, Enterprise | 87 comments Update II: NetApp has responded. I’m hoping other vendors will as well. Which do you believe? Costly FC and SCSI drives are more reliable than cheap SATA drives. RAID 5 is safe because the odds of two drives failing in the same RAID set are so low. After infant mortality, driv

GFS: Fundamental Paradigm Shift or One-off Oddity? As regular readers know, I believe that the current model of enterprise storage is badly broken. When I see something that blows that model away I like to learn more. In particular, I assess the marketability of the innovation. So a cool technology, like GFS or backup compression, makes me wonder if and how customers would buy it. This article off