Samsung PM853T SSD Review

Samsung PM853T SSD Review

Here at Teknophiles, we don’t believe in a once-size-fits-all approach to selecting hard drives for our lab servers. We prefer to adhere to the rule of specificity, where drives have a defined purpose and drive selection is based on several criteria that suit that purpose. In no particular order, we evaluate capacity, cost, reliability, performance and form factor when selecting a drive for a particular role.

Looking at this list of attributes, it’s easy to reach the conclusion that simply selecting the fastest drive would be a no-brainer for all applications. But fast drives come at an expense – both literal expense, as well as capacity expense. And, frankly, there are times where you just don’t need the the capacity or even the raw performance that some drives offer. One example, as detailed in our Silicon Power S60 60GB SSD Review, are server OS drives. On nearly every server we build, any serious workload is going to be performed on a dedicated array or SAN LUN, where IOPS and throughput are known quantities that are appropriately sized. As such, dedicated operating system drives typically experience low I/O and are approximately 75-80% read operation. You just won’t see much benefit by spending extra cash on a blazing fast SSD for your OS. And when you further consider that we nearly always configure our OS drives in RAID-1, even relatively “slow” SSDs will yield perfectly usable read speeds for a typical operating system. Heck, reliability even takes somewhat of a back seat when using cheaper drives in a RAID-1 configuration – by simply by keeping an extra $30 drive or two on hand as spares, you’ll still come out ahead financially, with no little down time waiting on a new drive to arrive.

Have Your Cake and Eat It Too

But what about those times where you do need speed, capacity, and reliability? It’s sorta like that old muscle car adage: cheap, fast, reliable – pick any two. The same premise generally holds true for computer components, including hard drives. Simply put, if you want fast and cheap, it likely won’t be reliable. Reliable and cheap? It’s not gonna be fast. You want all three? Unfortunately, you’re going to have to pay for it.

Or are you?

Perhaps there’s a happy medium – as long as you understand what it is you’re looking for. You see, performance is relative. There are certainly applications that require an abundance of IOPS. Others require significant write endurance. Others yet are heavily read biased. For each of these use cases, there are drives that fit the specific profile. For us, we needed some reliable, reasonably fast drives that will be 80% read-biased, but not break the bank. We’ve think we’ve found the sweet spot with the Samsung PM853T.

The Samsung PM853T

The Samsung PM853T series drives were mass produced around 2014-2016, so all the drives floating around out there are data center pulls, some with low hours, and in some cases, even New Old-Stock (NOS). Still, these are a great deal and can be had for as low as $0.10 per GB. Keep in mind that many of these drives are OEM drives that were sold bundled with servers, and thus will carry no warranty from the drive manufacturer even if they had a recent manufacture date. At this price point, however, having a cold-spare on hand is certainly achievable, and is highly recommended.

Samsung considers these drives to be a mixed workload drive with high sustained performance, which is perfect for our purposes. Note that the PM853T is an TLC SATA III 6 Gb/s drive, so like other SATA SSDs, it’s limited to a theoretical 600 MB/s. In our case, this is mostly irrelevant, however, as we’ll be using these in RAID-1/0 arrays as the disk subsystem for Hyper-V clusters. Given a minimum of 4 disks in an array (and possibly many more), this configuration can easily saturate the 2000 MB/s maximum throughput of a single 4-lane SFF-808x connector on an older SAS2 HBA like the LSI-Avago SAS 9210-8i.

Attributes

Samsung offered the PM853T in 240 / 480 / 960 GB sizes, and the drive offers many features not found on Samsung’s consumer drives.

Samsung PM853T – Specifications
Form factor 2.5 inches
Capacity 240 / 480 / 960 GB
Host Interface SATA3 – 6 Gb/s
Encryption AES 256-bit Hardware Encryption
Mean time 2.0 million hours
Uncorrectable bit 1 in 10^17
Power consumption Active Read/Write : 2.7 Watt/3.8 Watt, Idle : 1.2 Watt
TBW – 240 GB : 150 TBW
– 480 GB : 300 TBW
– 960 GB : 600 TBW
Cache power protection Supported
Sequential R/W (MB/s) Up to 530 / 420 MB/s
Random R/W (IOPs) Up to 90,000 / 14,000
Physical dimensions 100mm x 70mm x 7mm
Weight 63g

Among the features, Samsung lists the following:

    Consistent high-quality performance. Delivers consistent performance under diverse workloads to meet various data center demands.
    Advanced Error-Correcting Code (ECC) engine. Corrects read failures to greatly improve the reliability of the data stored in the memory for higher error correction and endurance than the BCH code can deliver alone.
    End-to-end protection. Extends error detection to cover the entire path, from the host interface to the NAND flash memory in the SSD for superior data integrity.
    Power-loss protection. Ensures no data loss during unexpected power failures by using the power supply of tantalum capacitors to borrow enough time to store all cached data to flash memory.
    SMART technology. Anticipates failures and warns users of impending drive failure, enabling time to replace the ailing drive to avoid data loss and system failure malfunctions.
    Thermal throttling. Regulates the temperature of the hardware components automatically to protect them from overheating by managing its performance level to prevent data loss.

Performance

So how does it perform? Samsung provides an enormous amount of data in their product brief on the PM853T, but here are some highlights of tests conducted in Samsung’s data lab using a PM853T 480 GB drive against a competitor’s product. Samsung uses the following tools to generate this data: Fio 2.1.3, Jetstress, and IOMeter.

Sustained Performance Tests

In this test, Samsung pitted the PM853T against an competitor’s MLC SSD drive during an 11 hour workload. The results indicate that the Samsung drive shows much lower latency with less standard deviation (more consistency). Overall the Samsung drive also had overall higher average IOPS.

Read/Write Tests

Additionally, the Samsung drive outperformed it’s competitor in both sustained random, as well as sequential read/write tests, achieving nearly 160000 IOPS at 100% random read in RAID-5 configurations, and 30000 IOPS at 100% random write in RAID-1 configurations.

In the sequential read tests throughput reached approximately 1500 MB/s in RAID-1 and over 1200 MB/s write in RAID-5 and outperforms its competitor as much as 29%, depending on RAID configuration and queue depth.

In mixed workloads it’s a similar story – the PM853T performs outperforms its competitor at all queue depths, in both non-RAID and RAID configurations, achieving more than 60,000 IOPs in RAID-1 at a RW ratio of 75:25, which is similar to typical virtual environment workloads.

Latency

In terms of average and maximum latency, the PM853T again performs admirably against a competitor.

Application Workloads

Finally, in both virtual environments using multiple VMs, as well in as various real-world application workloads, the PM853T again outperforms its competitor across the board.

In our own much simpler tests, we used a Samsung PM853T 960 GB drive. This drive was a server pull that, as you can see, had very low hours.

We saw read/write performance very much in line with Samsung’s official claims and consistently saw over sequential reads over 550 MB/s read and sequential writes over 420 MB/s.

Limitations

All this said, these drives do have certain limitations that should be at least touched upon:

    Form Factor. These drives are 2.5″, so they may not fit in your existing NAS, at least not without an adapter. Though at 7 mm z-height these will easily fit in all 2.5″ drive locations.
    SATA III. The PM853T is SATA III, not SAS or PCI-E, so if you need the raw performance of PCI-E or the expanded feature set of SAS such as multiple initiators, full duplex speeds or multipath I/O, then these drives are not for you.
    Write Speed. Being a read-biased drive, one would expect write performance to take a bit of a hit. These drives certainly do not display write speeds as fast as modern PCI-E/NVMe based drives. That said, they’re no slouch either, especially in RAID arrays. And at $0.10 per GB, you can actually afford to build an array with them.
    Endurance. Again, being a read-centric TLC SSD, the PM853T is only rated at 0.3 drive writes per day (DWPD). SLC drives can typically handle as many as 10x the number of write cycles that MLC or TLC drives can. This translates to nearly 300 GB in drive writes daily for 5 years. Unless you have some atypical use case, these drives should last a very long time in a typical 80%/20% R/W virtualization scenario.

Conclusion

So how exactly are we using these drives at Teknophiles? We’re currently running nearly 30 virtual machines on a single 1.8TB RAID-1/0 volume (4 x 960GB Samsung PM853T) and these drives don’t break a sweat. Even when hammering the environment with Windows Updates, mass live migrations or boot storms, these drives hold up well. The PM853T’s random IO performance and low latency makes it quite suitable to meet the demands of the mixed workloads that virtual machines place on the disk subsystem. Additionally, with numerous 853T drives currently in play (4 x 960 GB and 2 x 480 GB), we’ve not had a single failure in more than 10k hours use – these seem to be quite reliable drives. Simply put, for a home Hyper-V or ESX lab, it’s hard to imagine a better drive for the money. Factor in the quite excellent IO and throughput per watt of power consumption these drives produce, and you have a clear winner with the PM853T.

Choosing the Right Hard Drive for Your Lab

Choosing the Right Hard Drive for Your Lab

At Teknophiles, we run a fairly large number of hard drives in our lab servers. These drives fulfill several different duties, but typically fall into three primary categories. Over the years, we’ve tried a bunch of combinations, been through several iterations, and found some setups that worked well and others that didn’t. We’ll walk through our criteria for each type of drive, and hopefully help you choose the right drive for the application at hand.

Performance Drives

First, let’s talk about performance drives. We typically use 2.5″ enterprise SATA solid state drives, designed for high IOPS and long service lives. Similar in performance to high-end consumer drives, these typically have additional  features such as power-loss protection, higher write endurance, a greater number of spare blocks, and better error correction. These drives are great for arrays housing virtual machines, databases, or other high workload operations. What you get in performance, however, is offset by a much higher price per GB compared to other types of drives. You’re likely not going to put your media collection on these drives, unless of course you’ve got really deep pockets! For these drives, look for used, low-hour enterprise SSDs. These can typically be found with much of their useful service life left after retirement from a data center.

Storage Drives

The 4TB Seagate STDR4000100 is an excellent candidate for shucking

Second, we have storage drives. These drives comprise the SATA arrays that contain mostly static data, and typically fall into the write once/read many (WORM) category of service. With these drives, we’re not so much concerned with raw performance, nor ultra-high reliability. In a lab environment, we’re looking for three primary attributes with our storage drives: 1) low price per GB, 2) storage density (TB per rack unit) and 3) low watts per TB. Since it takes a significant number of drives to assemble a 30, 50, or 100 TB array, meeting these criteria keeps the overall costs of drives down, takes up less space in the rack and requires lower energy costs to operate. Individually, these drives may be quite slow – even 5400 RPM spindles will suffice, but in the proper configuration can still saturate 1Gbps or even 10Gbps links. And since we’ll be employing a number of these drives in a single array, we’ll be assuming a, “strength in numbers” approach, both from a performance and reliability standpoint. A popular, low-cost strategy for sourcing 2.5″ or 3.5″ HDDs is shucking external USB drives from several different vendors. A bit of research will reveal which drives are housed in each external drive model. But be careful! Not all external USB drives use a standard SATA connector internally, and you’re also sacrificing your warranty by doing this. It’s best to thoroughly check the drive for errors before disassembling the USB enclosure, and make a warranty claim if necessary. However, because you can save tens of dollars per drive by adopting this strategy, you can save enough to essentially “self-warranty” the drives by using the savings to keep a spare drive around, with the added benefit of limiting downtime in the event of a failure.

Archive & Backup Drives

A third category of drive is the archive or backup drive. These drives are typically not configured into RAID arrays, though they can be if one so chooses. In our lab environment, we choose to use individual backup disks grouped into a large storage pool. This gives us the benefit of a single, large backup target, but without the added cost and complexity of RAID groups. We have redundancy in our primary storage arrays, so if a single backup disk fails, the next backup job will simply copy that data back to the pool. Like storage drives, the backup drives are large, inexpensive, relatively slow disks. We typically use 4TB-6TB or larger 3.5″ disks for this purpose. Again like storage drives, many people choose to shuck drives like the WD My Book external drives and adopt a self-warranty strategy.



OS Drives

The final category we’d like to mention is server OS drives. Why do we consider OS drives to fall into their own category? Simple – efficient use of disk space. With many drives, whether SSD or spindle HDDs, you’ll likely find that after installing your OS to a RAID1 array, you have much more space than you’ll ever need. Unless you’re purposing servers for multiple duties, you’ll find that most Windows Server OSes use less than 20 GB of disk space, and even applications like WSUS which employ the Windows Internal Database (WID) will use less than 40 GB of space for the C: drive. Thus, it makes little sense to use drives that are terabytes, or even only a few hundred gigabytes, since the majority of that space will just be wasted. And though not paramount, some reasonable amount of performance is desirable for these drives, as it speeds reboot times and increases overall responsiveness of the server. To that end, small, consumer SSDs fit the bill perfectly for these drives. They’re inexpensive (sometimes, under $40 each), reasonably fast, mostly reliable, and we don’t have to worry much about write cycles, since a typical OS workload is primarily read (75-80% in our tests in Enterprise environments). While there aren’t a huge number of drives that fit these criteria, there are still a reasonable number of 50-60 GB drives available and plenty of affordable 120 GB options out there as well.

One note if you choose to use a small SSD for your OS drives.  In most cases it won’t be an issue, but do exercise caution if you use a relatively small drive for a hypervisor with a significant amount of RAM.  Since a Windows managed paged file can grow quite large (as much as 3x RAM!), you can see how the page file could easily fill a 60 GB drive. Consider a system with as 64 GB of RAM.  When performing a complete system crash dump, a full 1x RAM is required to write out the dump to either the page file or dedicated dump file.  This would quickly overwhelm the drive, even though a page file likely wouldn’t be needed at all during normal operation, assuming the system’s memory was well managed.  Given this potential issue, some Admins choose to manually set the page file to a specific value to prevent the drive from filling.  This comes with the tradeoff of not being able to perform the full system dump, however.  Check here for more information on Microsoft’s recommendations for calculating page file sizes.

TIP

If you have multiple servers, try to stick with the same drive, or at least a drive of the same capacity. This way, you can stockpile one extra drive to serve as a cold spare for all of your servers.

Other Drives

You might have noticed that we neglected to mention Enterprise SAS and ultra high-end SSDs. These drives certainly have value in specific applications, but a home lab environment is probably not the best use case. SAS drives can be expensive, power-hungry, require SAS controllers, and are finicky about mixed-use with SATA drives. And while you might have one in your high-end gaming rig, it’s not likely you’re going to fill your home lab with a dozen or more PCIe or NVMe drives, due to cost alone. We find it’s best to keep things relatively simple when it comes to your home lab, and we hope these tips will help you select a storage strategy that will serve you well into the future.