Solidigm D5-P5336 122.88TB Enterprise SSD Review - High Capacity = High Efficiency

TweakTown Rating: 98%

Our Verdict

In enterprise scenarios where capacity is king, Solidigm's D5-P5336 122.88TB SSD reigns supreme.

Pros

• Capacity
• Sequential throughput performance
• Random read performance

Cons

• Mixed workload performance

Should you buy it?

AvoidConsiderShortlistBuy

As an Amazon Associate, we earn from qualifying purchases. TweakTown may also earn commissions from other affiliate partners at no extra cost to you.

Introduction and Drive Details

It's no coincidence that the world's highest-capacity SSD is simultaneously the world's most efficient. With the demand for AI compute stretching the limits of energy grids across the globe, datacenters everywhere are looking for every imaginable way possible to maximize available space and power efficiency.

In the never-ending search for datacenter efficiency, one solution rises above them all - storage capacity. And when we are talking about storage capacity, one technology is the clear leader - QLC flash. With QLC (Quad Level Cell) arrays taking the lead on the efficiency front, we are seeing massive efficiency improvements for both footprint and watt per terabyte.

As we reckon things, Solidigm is currently the leading purveyor of the world's most advanced QLC technology, so it comes as no surprise to us that its new 122.88TB SSD is the most efficient high-capacity storage device of its kind currently in circulation. By deploying the world's highest capacity SSD, Solidigm's datacenter partners can now double power efficiency storage and density within the same footprint to a whopping 4-Petabytes per 1U server. Incredible.

32

Storage density matters. Whether it is the size of datasets for AI models doubling every eight months, or more and more unlimited capacity services emerging - massive, efficient storage density is becoming the most important factor for enterprises everywhere, with no end in sight. This is precisely where the world's highest capacity SSD becomes more of a necessity than an option.

So, what about lackluster endurance that's inherent to QLC flash? This is again where capacity is king as Solidigm explains: "It is not easy to wear 122.88TB of Solidigm Storage within the Solidigm Warranty period. Write amplification and the Program/Erase cycle of the drive impact endurance, and we feel that density is the third parameter to consider for endurance."

32

So, what about the lackluster random write performance inherent to QLC flash? Solidigm has a solution here as well called CSAL, which incorporates Solidigm's D7-P5810 caching SSD in front of massive QLC arrays as follows:

32

As we see it, with CSAL augmentation, all drawbacks inherent to QLC arrays are completely erased and you are left with only game changing advantages. Amazing. Now, let's dive in and take a close look at what Solidigm's new Enterprise offering can do for you by the numbers.

Specs/Comparison Products

32

Solidigm D5-P5336 122.88TB PCIe Gen4 x4 U.2 SSD

32

Solidigm's D5-P5336 Series are available at capacity points ranging from 7.68TB -122.88TB across three form factors including U.2, E1L, and E3.S. The drive we have in hand for this review is 122.88TB 15mm U.2, 8-channel controlled and arrayed with Solidigm' own 192L QLC NAND along with 16GB of Hynix DRAM. These SSDs are compatible with major operating systems such as RHEL, SLES, CentOS, Ubuntu, Windows Server, and VMware ESXi.

Test System Specs & Enterprise Testing Methodology

Enterprise SSD Test System

Prior to the AI revolution, datacenter SSDs' normal operating range would typically never exceed QD32. With AI data pipeline storage being directed by GPU, high queue depth performance has become paramount. Queue depths in the thousands are now commonplace, which is why we've changed our test platform, methodology, and operating system. Our charted upper queue depth range has been revised from QD256 to QD4096 for random data and up to QD1024 for sequential testing.

Testing Methodology

TweakTown strictly adheres to industry-accepted Enterprise Solid State Storage testing procedures. Each test we perform repeats the same sequence of the following steps:

1. Secure Erase SSD
2. Write the entire capacity of SSD 2x (2 loops) with 128KB sequential write data, seamlessly transition to the next step (sequential testing skips step 3)
3. Precondition SSD by filling the drive twice with 4K or 8K random writes
4. Run test-specific workload with a 30-second ramp up for 5 minutes at each measured Queue Depth, and record average result

Best Deals: Solidigm D5-P5336 61.44TB SSD

	Today	7 days ago	30 days ago
	$6334.96 USD	$7385.03 USD	-	Buy
	$6334.96 USD	$7385.03 USD	-	Buy
	£7593.28	£7595.20	-	Buy
	$6334.96 USD	$7385.03 USD	-	Buy
* Prices last scanned on 6/15/2025 at 8:21 pm CDT - prices may not be accurate, click links above for the latest price. We may earn an affiliate commission from any sales.

Benchmarks - Sequential

128K Sequential Write/Read

32

We precondition the drive using 100 percent sequential 128K writes at QD256 using 1-thread for 2-drive fills, receiving performance data every second. We plot this data to observe the test subject's descent into steady-state and to verify steady-state is in effect as we seamlessly transition into testing at queue depth. A steady-state is achieved after 1-drive fill. Average steady-state 128K sequential write performance at QD256 is approximately 3,200 MB/s.

32

32

Solidigm specs its 122.88TB SSD as capable of delivering up to 3,000 MB/s 128K sequential write throughput. We are getting up to 3,200MB/s or just slightly less than its 61.44TB sibling. Notably, it's better across the board here than DapuStor's J5060 61.44TB SSD.

32

32

The drive is factory spec'd for up to 7,000 MB/s 128K sequential read throughput. We are hitting up to 7,481 MB/s, so the factory spec here is on the conservative side. Its performance curve, like that of its 61.44TB sibling, is excellent but even better at 122.88TB. Impressive. This is a very important performance metric as it relates to mass QLC storage, and this is where TLC flash has no inherent performance advantage.

Benchmarks - Random

4K Random Write/Read

32

We precondition the drive using 100 percent random 4K writes at QD256 for 2-drive fills, receiving performance data every second. We plot this data to observe the test subject's descent into steady-state and to verify steady-state is in effect as we seamlessly transition into testing at queue depth. A steady-state is achieved after 1-drive fill. Average steady-state 4K random write performance at QD256 is approximately 25K IOPS.

32

32

Solidigm's 122.88TB SSD is rated at up to 19K for 4K random write IOPS. We are seeing up to 28K, which is significantly better. Additionally, we do appreciate how consistently the drive performs across all measured queue depths. Now, please understand that with CSAL in front of the P5336, random writes will not often be encountered and additionally, most workloads even without CSAL are going to be in the 32KB plus range which is much easier for drives of this nature to ingest.

32

32

Factory spec here is up to 900K IOPS at QD256. We are getting 947K IOPS at QD256 with our configuration. This additional 47K IOPS over factory spec is great to see. Surprisingly, the drive's performance curve here is nearly identical to that of its 61.44TB sibling. This is indeed impressive.

4K 7030

32

32

We will point out that workloads of this nature will rarely, if ever, be encountered in the role QLC SSDs play in the storage tier. Results here are to be taken with a grain of salt.

4K 5050

32

32

Again, we will point out that workloads of this nature will rarely, if ever, be encountered in the role QLC SSDs play in the storage tier. Results here are to be taken with a grain of salt.

8K Random Write/Read

32

We precondition the drive using 100 percent random 8K writes at QD256 for 2-drive fills, receiving performance data every second. We plot this data to observe the test subject's descent into steady-state and to verify steady-state is in effect as we seamlessly transition into testing at queue depth. A steady-state is achieved after 1-drive fill. Average steady-state 8K random write performance at QD256 is approximately 25K IOPS.

32

32

We expect 8K random to track pretty much the same as 4K random here, just at a lower IOPS rate because it's moving twice the amount of data. However, our test subject can deliver double the data at the very same IOPS rate as it did at 4K.

32

32

As we see it, 808K IOPS here is very good. It's again right in there with its TLC-arrayed competition, even better than some of them. Serving data to the host quickly is what this SSD is made to do, and as our chart demonstrates, it does so very well.

8K 7030

32

32

8K 7030 is representative of a common database workload. Again, we will point out that workloads of this nature will rarely, if ever, be encountered in the role QLC SSDs play in the storage tier. Results here are to be taken with a grain of salt.

8K 5050

32

32

Everything just stated about its performance at 8K 7030 applies here as well.

Final Thoughts

In scenarios where capacity is king, Solidigm's D5-P5336 122.88TB SSD reigns supreme as simultaneously the highest capacity and most efficient SSD currently in circulation. In read often, rarely written storage tiers, our test subject clearly demonstrates it can deliver performance on par with and often exceeding that of its TLC arrayed counterparts. And if it's implemented for roles where programming speed is a notable factor, that can be completely mitigated with Solidigm's CSAL technology.

32

Because it delivers as advertised and then some, is readily available, supremely efficient, delivers plenty of performance for its intended roles, and is backed by a 134 PBW 5-year warranty. Solidigm's 122.88TB D5-5336 SSD has earned a Must Have Editor's Choice rating.