Storage Linux Reviews & Articles

There have been 191 Linux hardware reviews and benchmark articles on Phoronix for storage. Separately, check out our news section for related product news.

Earlier in the Linux 4.12 cycle I delivered a number of I/O scheduler benchmarks from a solid-state drive while for this article are some fresh I/O scheduler tests using a slower SSD as well as a conventional HDD. Schedulers tested were CFQ, Noop, deadline, MQ None, MQ Kyber, MQ BFQ, and MQ Deadline.

Needing to replace a failed hard drive in one of our server room benchmark systems, I decided to try out the ADATA SU800 as something new. It's an affordable SATA 3.0 SSD and in not trying out an ADATA SSD in a while, I decided to purchase this one and run some benchmarks on it prior to commissioning it to its new home.

I picked up a Corsair Force MP500 NVMe M.2 solid-state drive for one of the new test systems in the Phoronix lab and so I ran some benchmarks on this high-performance drive compared to a few other SSDs.

With Btrfs RAID 5/6 seeing fixes in Linux 4.12, if you are re-evaluating the setup of a Btrfs native RAID array, here are some fresh benchmarks using four solid-state drives.

Given the big changes of the Linux 4.12 kernel and a lot of that being block/file-system-related work, here are some fresh benchmarks of the Btrfs, EXT4, F2FS, and XFS file-systems compared to their performance on past kernel releases when using a solid-state drive.

Here are some of my initial tests of trying out an Intel Optane memory module under Ubuntu Linux with a Kabylake system.

Among the many new features for Linux 4.12 are two new I/O schedulers in mainline: the long-standing BFQ (Budget Fair Queueing) and Kyber, a new I/O scheduler developed at Facebook. Here are some initial benchmarks of these I/O schedulers on the Linux Git code as of this past week.

Last week I posted benchmarks showing off F2FS performance with its multi-drive feature that isn't formal RAID but can still yield better I/O performance. For additional context, here are some results on that same system and with the Linux 4.11 kernel when using Btrfs with its native RAID capabilities.

Late last year F2FS picked up multiple device support for this Flash-Friendly File-System. This F2FS multi-drive capability isn't native RAID support like Btrfs but just allows a single F2FS file-system to span multiple devices. But it's more than that in that block allocation and the garbage collection policy is modified to boost I/O performance by taking advantage of the multiple SSD/flash devices.

With the Linux 4.11 kernel potentially being released as soon as today, here are some fresh benchmarks of Btrfs / EXT4 / F2FS / XFS on a solid-state drive and comparing the performance of 4.11 Git back to Linux 4.9 and 4.10.

While I have already posted some single-disk file-system benchmarks on Linux 4.10, for some benchmarking fun this weekend I decided to run some fresh tests of Btrfs RAID capabilities using four solid-state drives (SSDs).

Given all the changes with the Linux 4.10 kernel, including a fair amount of work on file-systems and block / I/O code, here are some fresh benchmarks of the EXT4, F2FS, Btrfs, and XFS file-systems atop a solid-state drive when comparing the early post-RC1 Linux 4.10 kernel benchmarks to that of the 4.6/4.7/4.8/4.9 stable kernels.

While the Samsung 960 EVO NVMe SSD was promising at first, after its quick failure I decided to try out the Toshiba/OCZ RD400 NVMe M.2 SSD. For the 256GB model (RVD400-M22280-256G) this high-performance solid-state drive will set you back just $149 USD.

Following last week's Btrfs / EXT4 / XFS / F2FS benchmarks using the Linux 4.6 through 4.9 kernels, some requests came in for doing some fresh Btrfs mount option comparison benchmarks. Thus for your viewing pleasure ahead of the holidays are some Btrfs mount option tests with the Linux 4.9 kernel.

For those curious how various Linux file-systems have evolved since Linux 4.6, here are some fresh benchmarks of the Btrfs, EXT4, F2FS, and XFS file-systems being tested on Linux 4.6 vs. 4.7 vs. 4.8 vs. 4.9 with a solid-state drive for looking at any performance changes.

As of this week the Samsung 960 EVO NVMe M.2 SSDs have begun shipping for those interested in high-performance solid-state storage. For our benchmarking fun today I am looking at the Samsung 960 EVO 250GB NVM Express M.2 SSD (MZ-V6E25) with tests under Ubuntu 16.04 while using the Linux 4.9 kernel.

This week I was shopping for a solid state drive to replace a hard drive on one of my backup/archival systems and ended up settling for the Crucial MX300 in getting 525GB of storage for just $120 USD. Here are some benchmarks of the Crucial CT525MX300SSD1 compared to some other SSDs on Linux for those curious.

It has been over one year since last testing the mainline Linux kernel's BCache support for this block cache that allows solid-state drives to act as a cache for slower hard disk drives. Here are some fresh benchmarks of a SATA 3.0 SSD+HDD with BCache from the Linux 4.8 Git kernel.

Last month Intel introduced the 600P Series solid-state drives as the most competitively-priced NVMe SSDs launched to date. Here are a few Linux comparison benchmarks from my initial testing of the SSDPEKKW256G7X1 M.2 SSD on Linux.

Up until running the tests for today's article, I can't remember the last time I touched a hard drive... It's been many months ago at least. Nearly all of our tests at Phoronix are from solid state storage, but I decided to pick up a new HDD for running some Linux file-system tests on a conventional hard drive for those not having an SSD.

Earlier this month I carried out some 4-disk Btrfs RAID benchmarks using four SATA 3.0 SSDs. Those tests were done using the Btrfs built-in RAID capabilities while today are some comparison tests against those numbers when using the Linux Software RAID setup via mdadm.

Going along with the recent Linux 4.7 file-system benchmarks, here are some tests of Btrfs' built-in RAID functionality when tested on the Linux 4.7 kernel across four SATA SSDs.

I've been a bit behind on my file-system benchmarking the past few months but for your viewing pleasure today are some EXT4 vs. Btrfs vs. F2FS file-system tests on an NVMe SSD when testing the Linux 4.4, 4.5, 4.6, and 4.7 kernels.

The latest piece of hardware I've been playing around with at Phoronix is Samsung's V-NAND SSD 950 PRO M.2 NVM Express SSD. Assuming you are running a modern Linux distribution, this M.2 PCI-E NVMe SSD can offer blazing fast performance.

With having some new Corsair USB 3.0 Flash Voyager flash drives around, I decided to run some fresh Linux file-system benchmarks on them to see how various file-systems are performing on low-cost USB flash drives.

The Trion 150 has been generating a fair amount of buzz since its release back in January as being a nice budget solid-state drive ideal for first-time SSD buyers. The Trion 150 is a true budget SSD with the 480GB SATA 3.0 drive retailing for just $140 USD, or about 30 cents per GB. Tests and results of the OCZ Trion 150 under Windows have been rather favorable so I figured it would be interesting to test out this drive under Ubuntu Linux.

With the falling prices of solid-state storage, it's becoming increasingly affordable to build a RAID array of SSDs. I have delivered many Btrfs RAID benchmarks on Phoronix over the years while today I have some fresh RAID0 and RAID1 numbers for Btrfs atop the latest Linux 4.5 development kernel when using two low-cost SSDs that retail for just around $40 USD a piece.

If you are thinking of buying a low-capacity, affordable solid-state drive (SSD) as a stocking stuffer this holiday season or just looking for a new SSD without breaking the bank, here are benchmarks from eight different low-cost solid-state drives done on Ubuntu Linux with the EXT4 file-system.

The latest Linux disk testing fun at Phoronix has been stressing two Samsung 850 EVO solid-state drives on the Linux 4.4 kernel when using the native RAID capabilities built into the Btrfs file-system.

Last week I posted some initial Kingston HyperX Predator M.2 SSD Linux benchmarks. Since those results, which were rather disappointing when factoring in the cost of this solid-state storage, I've run some more tests. While the performance has improved with a newer Skylake Linux system, the results are still not as great as advertised and I'm just returning the darn drive.