What are HDDs and SDDs, and how are these types of storage similar and different?

What is a hard disk drive (HDD)?

A hard drive or hard disk drive (HDD) is a type of data storage device that is used in laptops and desktop computers. An HDD is a “non-volatile” storage drive, which means it can retain the stored data even when no power is supplied to the device. Operating systems (OS) tell the HDD to read and write data as needed by programs. The speed that the drive reads and writes this data is solely dependent on the drive itself.

HDDs started as massive, room-filling devices with a capacity of about 3.75 megabytes. Today, by comparison, an HDD that fits easily in a desktop computer can have upwards of 18 terabytes worth of storage.

How do hard disk drives (HDDs) work?

Anatomy of an HDD

An HDD has disc-like objects that are called “platters.” Platters are where the data is stored using an electrical charge. This electrical charge comes from the actuator arm or “read/write head.” Read/write heads are instructed where to move on the platters by the software in the CPU and motherboard. Each platter has an arm with magnetic heads, and each platter spins and is divided up into sectors. These sectors have thousands of subdivisions (called bits) that can all accept an electric charge. The bits of the sector and their corresponding charges are read by the read/write head and can be translated into binary as 1s or 0s.

Longitudinal recording

Over the years of HDD development, there has been a change in sector layout on the platter. The original design of hard drives included longitudinal recording that aligned the sectors horizontally to the drive’s spinning platter. This horizontal alignment became a problem when increasing the HDD capacity by shrinking the sectors. At such a small scale, the bits would flip their charge randomly depending on temperature, causing data corruption.

Perpendicular recording

“Perpendicular recording” is a method created to combat issues found in longitudinal recording. This method stacks the sectors on their ends and creates more than three times the storage capacity of longitudinal recording. However, the tradeoff is the increased sensitivity to magnetic fields, which required more accurate read/write arms to be designed.

Disk fragmentation

When a CPU writes data onto the HDD, it uses a portion of a sector or sectors, depending on the size of the file. When an update occurs to the data, the CPU will instruct the HDD to write it in the next available sector. The distance from the first sector to this new sector will add time to how quickly the data can be read. While the time is measured in milliseconds, more instances of data separation can cause a significant slowdown. This data separation is called “disk fragmentation,” and most OSs have a built-in program that defragments the disk, rearranging the data so that information for a program is in one place.

Benefits of hard disk drives

Traditional hard disk drives (HDDs) are known as a legacy technology that has existed longer than SSDs. Age comes with its advantages, however, giving ample opportunity to make advances in all aspects of the technology.

The purpose of an HDD is the reading, writing and storing of data. They are reliable devices for backups as well as normal computer processes. HDD technology has been refined significantly, lowering their cost while raising their overall capacity.


HDDs have grown in capacity over the years and now are shipping commercially with 20 terabytes of storage. Many of today’s laptop and desktop PCs come standard with 250GB of storage.


Performance is typically measured in the speed and reliability of the device. The rate at which HDDs process data has grown significantly over the years and fits their purpose well.

The physical components in HDDs create more limitations than other storage devices, though. A precise arm loses accuracy if the disk moves too quickly, and a disk can only spin so fast before it starts to warp or even break. Speeding up the platter to achieve the optimal rate takes time, and results in slower boot-up time.


HDDs are reliable at storing data for long periods of time without being supplied power and are a preferred method of storage for backups. The longevity under constant use for an internal hard drive is three to five years. The lifespan can be longer if the device is an external hard drive and stored in a controlled space. Regular wear and tear on the device is common, especially due to writing and rewriting data over the same sectors of a platter. Long-term storage for multiple drives can be as easy as using an external hard drive. Another way to access these backup files from anywhere is to use a Network Attached Storage (NAS) system. A NAS is a centralized storage location that allows storage and retrieval of data for authorized network users.


External portable hard drives perform the same basic functions of an internal HDD and can be used with laptop or desktop computers. External drives are sold with their own external power supplies. Internal computer hard drives are “portable” — meaning they can be moved from one device to another easily — but they are less compatible with all devices and require more effort to be moved.


HDDs are the most affordable storage type because they have the most efficient cost per gigabyte. As storage capacity increases, the price of smaller HDDs decreases. For example, HDDs with 500 gigabytes capacities sell for less than $40.

What is a solid state drive (SSD)?

A core component of computers, solid state drives (SSDs) feature swift read, write and boot times on modern machines that is unparalleled by traditional hard drives.

A solid state drive is non-volatile memory (NVM) computer hardware that stores data without moving parts. Whereas hard disk drives (HDD) use a spinning magnetic disk and a mechanical write head to manipulate data, SSDs use charge in semiconductors.

Internal SSDs are installed within computers, while external SSDs are plugged in like external HDDs — frequently to USB 3.0 ports — and serve similar purposes. An SSD is a memory storage device that implements integrated circuits rather than mechanical components for storage. The integrated circuits reduce their overall size and make them silent when working. For example, an Apple product like a MacBook has an SSD for a hard drive, giving the Mac a slim profile.

Non-volatile memory express (NVMe) is a logical-device interface protocol for accessing a computer’s non-volatile storage media. NVMe is a standard specification used on SSD drives so that each manufacturer does not have a unique device driver. NVMe SSDs utilize Peripheral component interconnect express (PCIe or PCI express), which can handle the multiple back-and-forth requests from OS to SSD. PCIe is a common high-speed connection interface on the motherboard.

How do solid state drives (SSDs) work?

Solid state drives work by using electronic circuits to store and retrieve data. Data is stored in “blocks,” and these blocks can only be written fully once. To keep sequential data together and response times low, the block must be completely erased and rewritten on a different block. Unfortunately, the blocks are not durable and are damaged in the process of erasing. The writing/erasing is how wear occurs on an SSD and is why most SSDs come with integrated “wear-leveling” technology, which evenly distributes the wear out and extends the lifespan of the device.

Some of the electronic circuits in an SSD are NAND (“Not AND” logic gate) flash memory that consists of non-volatile NAND transistors. Non-volatile NAND transistors store data as a charge in semiconductors on silicon memory chips arrayed and sometimes stacked on circuit boards. The stacks are called 3D NAND and boast far greater storage capacities because memory cells are stacked on top of one another. Single-level cells (SLC) are the most expensive — but most durable — variety of SSD technology. Adding an additional bit of storage space per cell reduces costs accordingly and every additional bit stored is denoted differently, starting with multi-level cells (MLC), triple-level cells (TLC) and finally quad-level cells (QLC).

Controllers manage all the flash memory cells by telling them what memory to access or manipulate. Additionally, they are responsible for even data distribution and handling garbage collection.

Common form factor-dependent practices are for SSDs to cache requested data with quicker response times, similar to RAM modules. The quicker response time is more desirable when compared to caching hot requests from HDDs that would otherwise have low response times.

SSDs have less power consumption requirements than HDDs because they have no moving components. SSDs also rely on the constant power from the operating device to function. While unpowered SSDs lose data when they are not powered, most SSDs come with a built-in battery which allows the device to idle and maintain data integrity.

Hard disk drives vs. solid state drives: A comparison

Each type of storage has benefits and drawbacks. Therefore, a comparison of hard disk drives (HDDs) and solid state drives (SSDs) is needed to determine the best fit for a workload.


A key difference in storage space is that SSDs use flash memory instead of magnetic platters. Newer SSDs have commonly used capacities like 128GB, 256GB, 512GB, 1TB and 2TB. The integrated circuits that reduce the size of the device also increase the storage density.

For the average consumer, the largest SSD to be found is around 8 terabytes. In 2018, Samsung and Toshiba introduced to market 30.72 TB SSDs using the same 2.5-inch form factor but with a 3.5-inch drive thickness using a SAS interface. To show the capabilities of SSDs, Nimbus Data announced and shipped high-capacity 100 TB drives using a SATA interface. SSD technology is constantly being expanded and refined, leaving seemingly endless possibilities.

HDDs have been around longer, allowing them to grow sigificantly in capacity over the years and now are shipping commercially with 20 terabytes of storage. Many of today’s laptop and desktop PCs come standard with 250GB of storage.


The speed at which an SSD accesses data is much higher than an HDD speed. While an HDD can process 500 MB/s, most SSDs can process at 7000 MB/s. These faster speeds allow for instantaneous startup and less latency when logging in to a device or load times on apps. Additionally, file transferring and copying are significantly faster on an SSD. Because of their battery life, power consumption is around a fourth to a third less than an HDD.


HDDs are a better long-term storage device. SDDs tend to be less reliable for long-term storage because of data leaks that begin after a year of being unpowered. Additionally, as they approach their maximum terabytes written (TBW), their effectiveness steadily decreases until they reach an unusable state. The TBW of an SSD is the total amount of data that can be stored and erased from the device


Similarities arise between SSDs and HDDs when it comes to portability. An external version of an SSD is a more portable SSD than its stationary internal counterpart. SSDs are especially useful in data centers where large amounts of data need to be transferred from system to system quickly. An external HDD is more portable than its internal counterpart, but it’s used more for long-term storage than fast data transfer.


For smaller capacity drives in conjunction with frequently used data, SSDs offer the best performance for the price. The larger the capacity, the more beneficial HDDs become. SSD prices are on track to one day be just as cost efficient per gigabyte as any HDD. A 500 Gigabyte SSD currently sells for about $55, while a 500 Gigabyte HDD is roughly $24 (at time of writing).


SSDs are used primarily for fast data retrieval and constant use on a laptop or desktop due to their low power consumption and size. They are used for everyday processes and should not be used for longer storage like HDDs. SSDs are a preferred device when it comes to moving large files quickly and easily.

HDDs, SSDs and IBM

Data storage solutions

IBM offers on-premises cloud, hybrid, and flash memory data storage solutions that seamlessly integrate into your business needs while reducing costs. Transform and enhance your business with a comprehensive storage solution that integrates and refreshes your existing IT infrastructure, while reducing costs.

Discover data storage solutions.

Hybrid cloud solutions

The new generation of hybrid cloud storage solutions provide a common platform across all your cloud, on-premises and edge environments. That means you can skill once, build once and manage from a single pane of glass. IBM provides you with the most comprehensive and consistent approach to development, security and operations across hybrid environments.

In fact, our hybrid cloud approach can offer up to 2.5x more value than a public cloud-only approach. With our hybrid cloud value calculator, you can determine the value that a hybrid cloud approach can bring to your business.

Estimate your hybrid cloud advantage here.

More from Cloud

Clients can strengthen defenses for their data with IBM Storage Defender, now generally available

2 min read - We are excited to inform our clients and partners that IBM Storage Defender, part of our IBM Storage for Data Resilience portfolio, is now generally available. Enterprise clients worldwide continue to grapple with a threat landscape that is constantly evolving. Bad actors are moving faster than ever and are causing more lasting damage to data. According to an IBM report, cyberattacks like ransomware that used to take months to fully deploy can now take as little as four days. Cybercriminals…

2 min read

Integrating data center support: Lower costs and decrease downtime with your support strategy

3 min read - As organizations and their data centers embrace hybrid cloud deployments, they have a rapidly growing number of vendors and workloads in their IT environments. The proliferation of these vendors leads to numerous issues and challenges that overburden IT staff, impede clients’ core business innovations and development, and complicate the support and operation of these environments.  Couple that with the CIO’s priorities to improve IT environment availability, security and privacy posture, performance, and the TCO, and you now have a challenge…

3 min read

Using advanced scan settings in the IBM Cloud Security and Compliance Center

5 min read - Customers and users want the ability to schedule scans at the timing of their choice and receive alerts when issues arise, and we’re happy to make a few announcements in this area today: Scan frequency: Until recently, the IBM Cloud® Security and Compliance Center would scan resources every 24 hours, by default, on all of the attachments in an account. With this release, users can continue to run daily scans—which is the recommended option—but they also have the option for…

5 min read

Modernizing child support enforcement with IBM and AWS

7 min read - With 68% of child support enforcement (CSE) systems aging, most state agencies are currently modernizing them or preparing to modernize. More than 20% of families and children are supported by these systems, and with the current constituents of these systems becoming more consumer technology-centric, the use of antiquated technology systems is archaic and unsustainable. At this point, families expect state agencies to have a modern, efficient child support system. The following are some factors driving these states to pursue modernization:…

7 min read