The VC-backed storage crew at Kaminario make three types of K2 array: K2-D, which has DRAM modules; K2-H, with both DRAM and flash; and K2-F, which is all-flash and uses Fusion-io flash cards. But despite a market which is somewhat put off by the high cost of all-flash products – and despite a slew of rivals entering the same space – Kaminario is now focusing on the K2-F all-flash product. The K2-H hybrid product and K2-D details can still be found on the site though.
Version 4 of the K2-F array has quintupled the density of its MLC flash: the previous K2-F had 16TB in 18U (0.9TB/U), while the refreshed one has jumped to 84TB in 18U (4.6TB/U). The K2 capacity has climbed from 100TB to 120TB.
The read/write bandwidth is 30GB/sec, around four times more than the original 8GB/sec for this array. The read latency is 280 microsecs, a tad slower than the previous 260 microsecs, but the write latency has improved from 150 to 120 microsecs.
The random IOPS are up to 2.1 million, well above the K2-F’s original 600,000 IOPS.
Other improvements coming with V4.0 of the SPEAR (Scale-out PErformance ARchitecture) OS include:
– Non-disruptive upgrades
– High-availability with guaranteed performance during component failure and recovery, with a maximum of 25 per cent performance impact
– Hot-swap SAS drives – Kaminario has changed from using Fusion-io PCIe flash cards to SSDs
– OpenStack support via a K2 driver for the Folsom release of OpenStack that represents a K2 array as OpenStack block storage
– RESTful API for external third-party software to use when managing and controlling the array
– Virtually instantaneous K-Snaps – snapshots with consistency groups across multiple OS volumes
– VAAI support
Did we say Kaminario has halved the price of its K2 array? It has, although no actual pricing numbers have been supplied. The company hopes that this will bring new, more budget-limited mid-sized customers through its doors.
Kaminario is facing intensifying all-flash array competition. Let’s just review the competition:
IBM -with FlashSystem (acquired TMS RamSan) arrays
Nimbus Data – with its Gemini and E-Series arrays
SolidFire, with a cloud service provider-focused array
Skyera with Skyhawk
Violin Memory and its 6000 series products
Whiptail with INVICTA and ACCELA arrays
This year we expect EMC’s XtremiIO and NetApp’s FlashRay products to debut with HP and HDS products coming, and Dell expected to deliver an all-flash array too. That’s 15 competitors noted in just a quick look. The space between legacy disk drive arrays and all-flash arrays has been shrunk by hybrid flash-disk drive arrays from all the incumbent disk drive array vendors, offering near-flash speed and near-disk array cost, and also startups like Nimble Storage, Tegile and Tintri. The all-flash arrays should have a speed advantage over them but also a cost disadvantage.
Technologies like compression and deduplication can lower the effective cost/GB of a flash array and help offset their cost disadvantage versus the hybrid arrays which offer near-flash array speed at, in the three startup’s case, lower than mainstream vendor array cost. Niche market strategies like Greenbytes and Tintri (VDI) and Solidfire (cloud) differentiate the vendors adopting them. The other, general purpose flash array vendors face strengthening incumbent competition.
A brief summing up says we have 11 general-purpose flash array startups or effective startups – Astute, Huawei, Nexgen, Nimbus, Skyera, Violin and Whiptail – facing six incumbents for customers’ hearts, minds and wallets. There will be blood and not everybody will survive. The brutal prospect is that more than half of the startups will simply fall by the wayside and their survival depends on getting niche, getting big or getting bought by a good Samaritan incumbent. Miss all of those choices and they will have to get out.