Top 5 Storage Selection Mistakes and How to Avoid Them

Choosing a storage system is one of the most critical decisions in IT infrastructure. A mistake at this stage can lead to overspending, performance degradation, scalability issues, and even downtime for business‑critical applications. We’ve compiled the five most common mistakes companies make when selecting storage, along with practical advice on how to avoid them. This guide will help you save your budget and choose a solution that will perform efficiently for years.

Mistake #1. Overpaying for Unnecessary Features

The problem: Companies often buy top‑tier all‑flash arrays with maximum performance, even though their actual workloads don’t require such power. For example, a file server or archive doesn’t need 0.05 ms latency and hundreds of thousands of IOPS. The result is 2‑3 times overpayment with no real benefit.

How to avoid: Conduct a workload analysis before purchasing. Assess the actual IOPS, throughput, and latency your applications require. For most mid‑sized enterprises, hybrid storage or entry‑level all‑flash models are more than sufficient. For example, Dell PowerVault ME5024 offers an excellent price/performance balance for mixed workloads, while Huawei OceanStor Dorado 3000 is for those who genuinely need minimal latency.

Mistake #2. Choosing the Wrong Access Protocol

The problem: Many choose a protocol based on habit rather than application requirements. For example, using iSCSI for high‑throughput databases where every microsecond counts, when NVMe‑oF or Fibre Channel would deliver significantly better performance. Or vice versa — deploying an expensive FC network for a file server where NAS would be perfectly adequate.

How to avoid: Evaluate the latency and throughput requirements of each application. For OLTP databases and virtualisation with high IOPS, use NVMe‑oF or FC. For file services and archiving, NAS (NFS, SMB) or object storage with S3 access is sufficient. Modern platforms like Dell PowerStore support all popular protocols, providing flexibility for the future.

Mistake #3. Ignoring Scalability

The problem: Companies choose a system without considering data growth. In 2‑3 years, capacity runs out, and expansion options are limited — forcing an expensive and risky migration to a new storage system.

How to avoid: Plan for 3‑5 years of growth. Choose systems that support scaling: horizontal (scale‑out) — adding new nodes, or vertical (scale‑up) — adding disk shelves. Object storage solutions like Huawei OceanStor Pacific 9550 offer virtually unlimited horizontal expansion. For block systems, Dell PowerStore supports both scale‑up and scale‑out, giving maximum flexibility.

Mistake #4. Skimping on Data Protection

The problem: In pursuit of savings, companies skip replication, snapshots, or dedicated backup solutions. As a result, when a drive fails, a human error occurs, or a ransomware attack hits, data recovery becomes expensive and time‑consuming — sometimes impossible.

How to avoid: Include backup and data protection in your budget. Use snapshots, replication between two storage systems or to the cloud. Consider dedicated backup appliances like Dell PowerProtect DD3300, which provide deduplication, immutable backups, and cloud integration. This will protect your business in an emergency.

Mistake #5. Buying Without Considering Future Applications

The problem: Storage is bought for current needs, but a year later the company adopts new software (AI/ML, analytics, containers) with different performance and interface requirements. The old system can’t keep up, and the budget is spent on replacement again.

How to avoid: When selecting storage, consider not only current but also planned workloads. Ensure the system supports modern interfaces (NVMe‑oF, S3, NFS 4.1), has sufficient controller power, and has IOPS headroom. Platforms like Huawei OceanStor Dorado 5000 with AI‑Inside automatically optimise for changing workloads, while Dell PowerStore supports containers and cloud tools out of the box.

How to Avoid Mistakes: A Step‑by‑Step Plan

• Step 1. Workload audit — collect statistics on current IOPS, throughput, latency, and profile (read/write). Use built‑in monitoring tools or conduct load testing.
• Step 2. Define scaling requirements — forecast data growth for 3‑5 years. Choose scale‑up or scale‑out based on your scenario.
• Step 3. Evaluate protocols and interfaces — consider current and future applications. NVMe‑oF provides performance headroom, S3 offers versatility for cloud environments.
• Step 4. Plan data protection — replication, snapshots, backup appliances. Consider hybrid cloud tiering.
• Step 5. Check compatibility — with hypervisors, databases, container platforms. Ensure the system is certified for your stack.
• Step 6. Calculate TCO — compare total cost of ownership across options, including licenses, support, power, and cooling.
• Step 7. Test in a pilot environment — deploy a demo and test real‑world scenarios, especially peak loads.

We offer assistance at every stage — from audit to deployment. Our engineers will conduct a free workload analysis and help you select the optimal storage system, avoiding common mistakes.

Frequently Asked Questions (FAQ)

In the next article, we will cover the fundamentals of backup and data protection. Stay tuned!

What Is Software‑Defined Storage (SDS) and How It Differs from Traditional Storage

Traditional storage systems are monolithic hardware‑software bundles where the vendor provides controllers, drives, and the storage OS as a single unit. Software‑Defined Storage (SDS) takes a different approach: the storage management software is decoupled from the underlying hardware and can run on standard commodity servers. This delivers flexibility, lowers costs, and simplifies scaling. In this article, we explain what SDS is, how it compares to traditional storage arrays, explore popular solutions (Ceph, VMware vSAN), and identify the scenarios where SDS becomes the optimal choice.

1. What Is Software‑Defined Storage?

Software‑Defined Storage (SDS) is an architecture where the software that manages storage services runs on standard, commodity servers and provides a unified interface for storage resources. The core principles of SDS are:

• Separation of software from hardware — the same software platform can run on servers from different vendors.
• Centralised management — all storage resources (drives, nodes) are managed through a single pane of glass or API.
• Automation — thin provisioning, storage policies, rebalancing, replication — all configured programmatically.
• Scalability — adding new nodes linearly increases capacity and performance.

SDS does not require specialised hardware (like FC switches or HBA adapters for SAN) and can run over standard Ethernet networks, significantly reducing deployment costs.

2. SDS vs Traditional Storage: A Comparison

Traditional storage systems like Huawei OceanStor Dorado or Dell PowerStore remain the best choice for high‑throughput transactional systems where every microsecond counts. SDS, in turn, is ideal for cloud environments, Big Data, archives, and virtualisation with moderate latency requirements.

3. Examples of SDS Solutions

The market offers many SDS platforms, both open‑source and commercial. Here are two of the most popular:

Ceph

Ceph is an open‑source distributed storage system that provides object, file (CephFS), and block (RBD) access. Key features:

• Scales to exabytes of data.
• Uses erasure coding and replication for fault tolerance.
• Self‑healing architecture — data is automatically redistributed when nodes fail.
• Ideal for OpenStack, Kubernetes, and cloud environments.

Ceph is often deployed on rack servers with many drives, such as Dell PowerEdge R760 or Huawei FusionServer 2288H V7.

VMware vSAN

VMware vSAN is a hyperconverged SDS solution built directly into the VMware vSphere hypervisor. It pools local drives from vSphere hosts into a single shared datastore for virtual machines. Benefits:

• Simple management through the familiar vCenter interface.
• Supports all‑flash and hybrid configurations.
• Integration with storage policies.
• Optimised for virtualisation environments, especially VDI and small clusters.

vSAN requires servers from the compatibility list, but these are still standard x86 servers, e.g., Dell PowerEdge or Huawei FusionServer.

4. When to Choose SDS vs Traditional Storage

The choice depends on your priorities:

• Choose traditional storage if: you need maximum performance and minimal latency (OLTP, banking, HFT); you have budget for specialised hardware; your workload is predictable and does not require frequent scaling.
• Choose SDS if: you are building a cloud or hybrid infrastructure; you need flexibility in hardware choice; you want to reduce storage costs; your data grows rapidly and unpredictably.

Many enterprises use a combination: traditional storage for critical databases, and SDS for archives, backups, and development environments.

5. Benefits and Challenges of SDS

Benefits of SDS:

• Lower TCO — commodity servers are cheaper than specialised storage arrays.
• Flexibility — you can mix servers of different generations and vendors.
• Scalability — add nodes as you grow, without downtime.
• API‑driven management — integration with cloud orchestrators (Kubernetes, OpenStack, Terraform).
• Fault tolerance — distributed architecture with replication and erasure coding.

Challenges of SDS:

• Performance — SDS rarely matches the peak performance of specialised storage, especially for synchronous writes.
• Setup complexity — especially for open‑source solutions like Ceph, which require experienced engineers.
• Support — with open‑source software, you rely on the community or external integrators.
• Network load — distributed systems generate significant network traffic for replication and rebalancing.

6. How to Choose Servers for SDS

Selecting the right servers is critical for SDS. Consider the following:

• Storage subsystem — for Ceph and vSAN, use NVMe/SSD for journals and cache, and HDD for data. Ensure the server has enough drive bays.
• Network interfaces — require fast networks (10/25/100 GbE) with RDMA support to minimise latency.
• Memory — for caching and metadata. Ceph recommends 1–2 GB RAM per TB of data.
• Processors — not necessarily the fastest, but sufficient to handle I/O and erasure coding calculations.

Our rack servers from Dell, Huawei, and Lenovo are ideal for SDS deployments. For example, Dell PowerEdge R660 with its NVMe‑optimised architecture is an excellent choice for high‑performance SDS clusters.

7. Frequently Asked Questions (FAQ)

In the next article, we will cover the top 5 storage selection mistakes and how to avoid them. Stay tuned!

How to Calculate Storage Performance: IOPS, Throughput, and Latency

Storage system performance is one of the key factors affecting application speed and user satisfaction. But how do you objectively assess whether your storage has enough power? Three key metrics are used: IOPS (Input/Output Operations Per Second), throughput, and latency. In this article, we break down what these metrics mean, how to calculate them, what workload profiles exist, and how to interpret the results to choose the optimal storage system — whether it’s an all‑flash array, a hybrid storage system, or a scale‑out object storage system.

1. What Are IOPS and How to Measure Them

IOPS (Input/Output Operations Per Second) is the number of read or write operations a storage system can perform per second. The higher the IOPS, the more transactions the storage can handle.

IOPS depend on many factors:

• Drive type — NVMe SSDs deliver hundreds of thousands of IOPS, SATA SSDs deliver tens of thousands, HDDs deliver only hundreds.
• Block size — the smaller the block, the higher the IOPS at the same throughput.
• Read/write ratio — reads are usually faster than writes (due to caching).
• Queue depth — the number of parallel requests; increasing depth often improves IOPS up to a certain point.

To calculate required IOPS, you can use a simple formula:

For example, if your application performs 10,000 transactions per second, each transaction generates an average of 3 I/O operations, and you add a 30% safety margin, the required IOPS = 10,000 × 3 × 1.3 = 39,000 IOPS.

2. Throughput

Throughput is the volume of data a system can transfer per unit of time, usually measured in MB/s or GB/s. This metric is critical for streaming workloads: video editing, backup, large analytical queries.

Throughput and IOPS are related through block size:

For example, if a storage system delivers 10,000 IOPS with an 8 KB block size, the throughput is 10,000 × 0.008 = 80 MB/s. With a 1 MB block size, the throughput would be 10,000 × 1 = 10,000 MB/s (10 GB/s). It is important to understand that maximum throughput is limited by interfaces (SAS, FC, Ethernet) and the controller’s internal bus.

3. Latency

Latency is the time from sending a request to receiving a response. It is measured in milliseconds (ms) or microseconds (µs). Low latency is critical for interactive applications (databases, web services).

• HDD latency — 5–10 ms (mechanical heads).
• SATA SSD latency — 0.2–0.5 ms.
• NVMe SSD latency — 0.05–0.1 ms.
• All‑flash array with NVMe‑oF — can deliver latency below 0.05 ms.

Latency consists of controller time, drive access time, network latency (for SAN and NAS), and queuing delays. The higher the storage load, the higher the latency due to resource contention.

4. Workload Profiles: 70/30, 50/50, 80/20

The read/write ratio significantly affects performance. Most enterprise applications have mixed workloads:

• 70% reads / 30% writes (70/30) — typical for OLTP databases, web applications. Read cache works effectively here.
• 50% / 50% — balanced systems, such as file servers with active file exchange.
• 80% reads / 20% writes — analytical systems, reporting storage.
• 90% writes / 10% reads — log collection systems, backup.

When calculating performance, keep in mind that write operations are usually slower than reads due to the need for synchronisation with protected cache and RAID arrays. Vendors provide IOPS figures for each workload profile.

5. Factors Affecting Real‑World Performance

In addition to the three main metrics, storage performance is affected by:

• Block size — small blocks (4–8 KB) give high IOPS but low throughput. Large blocks (1 MB) do the opposite.
• Queue depth — the number of parallel I/O requests. The optimal queue depth depends on the controller and drive type.
• Caching — read cache accelerates repeated reads; write cache groups operations for batch writes to disks.
• RAID level — RAID 10 offers the best performance; RAID 5/6 require additional parity calculations.
• Deduplication and compression — reduce the volume of written data but consume controller resources.
• Network latency — for SAN (FC, iSCSI, NVMe‑oF) and NAS, network latency is an important factor.

6. How to Measure the Performance of an Existing Storage System

For real‑world performance measurement, use synthetic tests (e.g., FIO, IOmeter, Vdbench) or built‑in monitoring tools (iostat, perf). Recommendations:

• Test with different block sizes and queue depths.
• Measure both peak and average performance.
• Simulate the real workload profile (read/write ratio, random or sequential access).
• Conduct tests during peak hours and low‑activity periods to understand capacity headroom.

We can help with load testing your current storage and selecting the optimal configuration for an upgrade.

7. Performance Calculation Example for a Business Case

Suppose you are deploying a database management system (DBMS) with 5,000 users, each performing 10 transactions per minute. That’s 5,000 × 10 / 60 ≈ 833 transactions per second. Each transaction generates 2 read operations and 1 write operation (3 total operations). So 833 × 3 = 2,499 operations per second. With a 30% safety margin, that’s ~3,250 IOPS. The average block size is 8 KB. Throughput: 3,250 × 0.008 = 26 MB/s. Latency should not exceed 5 ms for a comfortable user experience.

This load can be handled by a hybrid array like Lenovo DE4000H or an entry‑level all‑flash solution. For higher requirements (10,000+ IOPS), a professional all‑flash array is needed.

8. Frequently Asked Questions (FAQ)

In the next article, we will explain software‑defined storage (SDS) and how it differs from traditional storage systems. Stay tuned!

Scale‑Out Storage Systems: When You Need Them and How They Work

Data is growing exponentially. Traditional scale‑up storage systems eventually hit performance and capacity ceilings. Scale‑out systems have emerged as the answer, allowing you to add resources linearly by simply adding new nodes to the cluster. In this article, we explain what scale‑out architecture is, how it differs from scale‑up, when it is essential, and how it works using Huawei OceanStor Pacific 9550 — a flagship object storage solution for Big Data and AI/ML.

1. Scale‑Up vs Scale‑Out: What’s the Difference?

To understand the value of scale‑out, let’s compare the two scaling approaches:

• Scale‑up (vertical scaling) — you increase performance and capacity by upgrading controllers to more powerful ones or adding disk shelves to an existing system. This works up to a point: you hit the vendor’s maximum configuration, upgrade costs grow non‑linearly, and a single controller failure can impact the entire system.
• Scale‑out (horizontal scaling) — you add new nodes to the cluster. Each node contains its own processors, memory, and drives. Capacity and performance grow linearly with every new node. A single node failure does not affect the rest — data is replicated or rebuilt from parity fragments.

Scale‑out systems are built on a “pay‑as‑you‑grow” principle and are ideal for environments where data volumes are unpredictable or growing explosively.

2. How Scale‑Out Storage Works

Scale‑out architecture is based on several key principles:

• Distributed file system — data is split into chunks and distributed across all nodes in the cluster. This enables parallel access and high throughput.
• Unified namespace — all nodes appear as a single storage pool. Clients see a single file system or object pool, regardless of which physical node holds the data.
• Automatic rebalancing — when nodes are added or removed, the system automatically redistributes data to maintain even utilisation.
• Fault tolerance — data is replicated (2–3 copies) or protected with erasure coding, allowing the system to survive multiple node failures without data loss.

A prime example: Huawei OceanStor Pacific 9550 uses a distributed architecture with erasure coding and a unified namespace, scaling from a few terabytes to tens of petabytes.

3. When Do You Need Scale‑Out Storage?

Scale‑out storage becomes essential in these scenarios:

• Big Data and analytics — Hadoop, Spark, ClickHouse. Data volumes are measured in petabytes, and workloads are distributed across dozens or hundreds of nodes.
• Artificial intelligence and machine learning — model training requires access to massive datasets. Scale‑out enables parallel data loading and accelerates training. AI servers and GPU clusters work most efficiently with such storage.
• Cloud and container environments — OpenStack, Kubernetes, S3‑compatible storage. Elasticity and scalability are key requirements.
• Archives and backup — long‑term retention with the ability to grow without migrations.
• Media and content — video hosting, streaming services requiring high throughput and low latency for streaming.

If your business handles large volumes of unstructured data and plans for growth, scale‑out is the right choice.

4. Object Storage as a Classic Example of Scale‑Out

Object storage is the most prominent example of scale‑out architecture. Unlike file (NAS) and block (SAN) systems, object storage is designed from the ground up for horizontal scaling. Key features:

• Data is stored as objects with unique IDs and metadata.
• Access via REST API (S3, Swift).
• Replication and erasure coding at the node level.
• Unified namespace at petabyte scale.

Huawei OceanStor Pacific 9550 is an object storage system that combines high throughput, fault tolerance, and ease of management. It supports both object and file access (NFS, SMB), making it a versatile solution for enterprise environments.

5. Scale‑Out vs Traditional Storage: A Comparison

6. How to Deploy a Scale‑Out Storage System

Deploying a scale‑out system typically involves several stages:

• Workload analysis — determine data types (objects, files, block volumes), required throughput, IOPS, and future growth.
• Architecture selection — object, file, or block storage? For most Big Data and AI/ML tasks, object storage with S3 support is ideal.
• Pilot project — deploy 3–4 nodes, test performance, and integration with existing applications.
• Gradual scaling — add nodes as data grows. Thanks to linear scalability, you pay only for what you use.
• Monitoring and management — use built‑in tools to track cluster health and automatic rebalancing.

We assist at every stage — from design to commissioning. We supply both individual nodes and complete storage system clusters.

7. Frequently Asked Questions (FAQ)

In the next article, we will compare Huawei OceanStor Dorado and Dell PowerStore — two flagship all‑flash solutions. Stay tuned!

Hybrid Storage Systems: Balancing Flash Speed and HDD Capacity

Enterprises need both high performance for critical applications and massive capacity for archives and backups. But buying separate all‑flash and HDD systems is expensive and complex to manage. Hybrid storage systems combine fast SSDs/NVMe for hot data and high‑capacity HDDs for cold data in a single platform, automatically moving data between tiers based on access frequency. In this article, we explain how automated tiering (auto‑tiering) works, what algorithms drive it, the cost savings it delivers, and why Lenovo ThinkSystem DE4000H is one of the best hybrid solutions for mid‑sized businesses.

1. What Is a Hybrid Storage System and Why Do You Need It?

A hybrid storage array uses both solid‑state drives (SSD or NVMe) and traditional hard disk drives (HDD) simultaneously. SSDs deliver high performance (low latency, high IOPS), while HDDs provide large capacity at a low cost per terabyte.

The main goal of a hybrid storage system is to automatically place data on the most appropriate tier so that:

• hot (frequently accessed) data always resides on fast flash;
• cold data (archives, backups) stays on inexpensive HDDs;
• migration happens without administrator intervention and without downtime.

This gives an optimal balance of performance and cost, especially for companies with mixed workloads: file servers, databases, virtualisation, and backup.

2. How Auto‑Tiering Works

Auto‑tiering is an intelligent mechanism that analyses I/O activity and moves data between storage tiers. The typical workflow is:

• Monitoring – the system tracks read/write statistics for each data block.
• Classification – data is categorised as hot (frequently accessed), warm (periodically), or cold (rarely).
• Migration – hot blocks are moved to SSDs, cold blocks to HDDs. This happens asynchronously without affecting application performance.
• Adaptation – the system continuously recalculates activity and adjusts placement to changing workload patterns.

Modern hybrid storage systems use policies based on data temperature and access frequency (IOPS/sec). For example, Lenovo ThinkSystem DE4000H employs dynamic tiering with support for multiple levels: NVMe/SSD — HDD (SAS/NL‑SAS) — and even cloud tiering for the coldest data.

3. Data Migration Algorithms and Their Characteristics

Hybrid storage systems use different migration approaches:

• Threshold‑based – data moves when access frequency exceeds a configured threshold. Simple but not always optimal for rapidly changing workloads.
• Predictive – based on historical data and machine learning, the system forecasts future activity and pre‑moves data. This yields better efficiency, especially for unpredictable workloads. Example: Huawei Dorado with AI‑Inside.
• Mixed (hybrid) – combines thresholds and predictions, adapting to real‑world behaviour.

It is crucial that migration occurs at the block level (sub‑LUN) or even individual extents, not whole volumes. This maximises SSD utilisation without over‑provisioning.

4. The Economic Benefits of Hybrid Storage

Adopting hybrid storage delivers measurable ROI through several factors:

• Lower storage cost – HDDs are 5‑10 times cheaper than NVMe per terabyte. If 70‑80% of data is cold, savings are enormous.
• Optimised flash usage – SSDs are not filled with cold data; their endurance is reserved for active operations.
• Reduced power and cooling costs – HDDs consume less energy than SSDs and can be deployed in denser configurations.
• Deferred upgrades – you don’t need to buy expensive all‑flash “for growth”; a hybrid system scales by adding both SSDs and HDDs as needed.

Typical example: a company with 100 TB of data, of which 20 TB is actively used (databases, VMs) and 80 TB is archives and backups. An all‑flash array would cost $X; a hybrid system with 20 TB NVMe and 80 TB HDD costs 2‑3 times less, while delivering all‑flash performance for hot data.

5. Lenovo ThinkSystem DE4000H – The Ideal Hybrid for Mid‑Sized Businesses

Lenovo ThinkSystem DE4000H is a hybrid storage system built for enterprises that need a balance of performance and capacity. Key features:

• Up to 192 drives – mix NVMe/SSD and HDD (SAS, NL‑SAS).
• Block‑level auto‑tiering – automatic distribution across three tiers.
• Performance up to 300,000 IOPS – sufficient for virtualisation, databases, and file services.
• Support for FC, iSCSI, SAS protocols – flexible connectivity to existing infrastructure.
• Cloud integration – ability to tier to AWS, Azure, Google Cloud for archives.

The DE4000H is an excellent choice for companies that want the benefits of all‑flash for hot data but aren’t ready to pay for a full flash array. The system scales easily and is managed via an intuitive web interface.

6. Hybrid vs All‑Flash: A Comparison

7. Frequently Asked Questions (FAQ)

In the next article, we will dive into NVMe‑oF technology and its role in modern high‑performance storage. Stay tuned!

What Is All‑Flash Storage and When Does Your Business Need It?

In a world where data processing speed defines business competitiveness, traditional hard‑disk‑based (HDD) storage systems are increasingly becoming a bottleneck. All‑flash storage — storage systems built entirely on solid‑state drives (SSDs and NVMe) — delivers microsecond latency, high throughput, and dramatically accelerates application performance. In this article, we explain how all‑flash differs from hybrid and HDD‑based systems, when its adoption is justified, and which solutions from Huawei OceanStor Dorado and Dell PowerStore best fit various business needs.

1. All‑Flash vs HDD vs Hybrid: Key Differences

To understand the value of all‑flash, let’s compare the three main storage types across critical parameters:

• HDD arrays — use mechanical drives. Cheap per terabyte, but suffer from high latency (5–10 ms) and limited IOPS (100–200 per drive). Suitable for archives, backups, and cold data.
• Hybrid systems — combine a small number of SSDs for hot data with HDDs for capacity. Use automated tiering to balance performance and cost, but latency is still constrained by HDD when cache misses occur.
• All‑flash arrays — built entirely on flash (SAS SSD, NVMe). Deliver sub‑0.1 ms latency, hundreds of thousands of IOPS, and high throughput. Ideal for transactional systems, virtualisation, AI/ML, and any latency‑sensitive workload.

The key advantage of all‑flash is consistently low latency under any load — crucial for real‑time user applications.

2. Technologies That Drive All‑Flash Performance

Modern all‑flash arrays rely on several core technologies to achieve maximum performance:

• NVMe (Non‑Volatile Memory Express) — a protocol designed specifically for flash memory. Unlike SATA/SAS, NVMe enables parallel command processing, multiple queues, and significantly lower latency.
• Inline deduplication and compression — data is compressed and deduplicated on the fly, dramatically improving effective capacity utilisation, especially for virtual machines and databases.
• Intelligent caching — machine‑learning algorithms pre‑fetch frequently accessed data into cache, further reducing latency.

Examples include Huawei OceanStor Dorado 5000 with AI‑Inside technology and Dell PowerStore 1200T with its built‑in auto‑optimisation engine.

3. When Does Your Business Need All‑Flash Storage?

Moving to all‑flash is justified in these scenarios:

• High‑throughput databases (OLTP, ERP) — banking, retail, online services demand millisecond responses. All‑flash delivers sub‑0.1 ms latency, critical for transaction processing.
• Enterprise virtualisation — VMware vSphere, Microsoft Hyper‑V. Consolidating hundreds of VMs per host requires high IOPS; all‑flash handles load spikes without degradation.
• Artificial intelligence and machine learning — model training demands fast access to large datasets. All‑flash cuts training times dramatically.
• Real‑time analytics — BI dashboards and analytical systems require instant query responses.
• Cloud and container environments — Kubernetes, OpenStack, where elasticity and fast data migration are essential.

If your business faces complaints about slow applications, rising response times, or simply needs high availability — all‑flash is the right move.

4. Comparison of Leading All‑Flash Solutions: Huawei OceanStor Dorado vs Dell PowerStore

5. Myths About All‑Flash — Debunked

• “All‑flash is too expensive” — with inline deduplication and compression, the effective cost per usable GB is often lower than that of HDD arrays, especially for actively used data. Additional savings come from reduced power, cooling, and floor space.
• “Flash wears out quickly” — modern NVMe SSDs have endurance of 5–10 drive writes per day for 5 years, covering most enterprise workloads. Controllers also extend drive life through wear‑leveling and over‑provisioning.
• “Hybrid gives the same performance” — only when hot data fits entirely in cache. Under real mixed workloads, hybrid systems often suffer latency spikes, while all‑flash delivers consistent performance.

6. How to Choose the Right All‑Flash Array for Your Enterprise

When selecting an all‑flash system, consider these factors:

• Performance — assess the IOPS and latency your applications require. For OLTP and banking, latency under 0.1 ms is critical.
• Scalability — support for scale‑up (adding shelves) or scale‑out (adding nodes). For growing companies, scale‑out provides more flexibility.
• Data reduction features — deduplication, compression, thin provisioning. These significantly improve effective capacity.
• Integration — protocol support (FC, iSCSI, NVMe‑oF), compatibility with hypervisors and databases.
• Reliability and warranty — redundant controllers, power supplies, and vendor SLA.

We offer a full range of all‑flash systems — from compact models for mid‑sized businesses to highly scalable platforms for large data centres. All solutions are sourced directly from China with full warranty and engineering support.

In the next article, we’ll explore hybrid storage and auto‑tiering technology — how they balance performance and cost. Stay tuned!

Modern Storage System Architecture: Components and How It Works

Modern storage systems (SAN, NAS, object storage) are sophisticated engineering solutions that combine hardware and software components to deliver high performance, reliability, and scalability. Understanding storage architecture helps IT professionals design infrastructure correctly, select appropriate hardware, and optimise workloads. In this article, we break down the key components of a storage system: controllers, disk shelves, cache, access protocols (FC, iSCSI, NVMe‑oF), and data protection technologies — RAID and erasure coding. We pay special attention to all‑flash arrays, which are becoming the standard for high‑performance environments.

1. Storage Controllers – The Brain of the System

Storage controllers are the central processing modules that manage all I/O operations, distribute data across drives, handle caching, and provide connectivity to servers. Modern storage systems use two or more controllers in an active‑active configuration for high availability.

Controller functions:

• Processing I/O requests from servers.
• Managing read/write cache.
• Implementing RAID or erasure coding.
• Load balancing between disk shelves.
• Ensuring high availability (failover).

Controllers can be hardware‑based (dedicated boards with their own processors) or software‑based (SDS — software‑defined storage). In enterprise all‑flash arrays like Huawei OceanStor Dorado 3000 or Dell PowerStore 1200T, high‑performance controllers with dedicated compression and deduplication chips are used.

2. Disk Shelves and Drives

Disk shelves are modules that house physical drives (HDD, SSD, NVMe). They connect to controllers via SAS, SATA, or NVMe interfaces. Modern shelves support hot‑swap drive replacement without powering down the system.

• HDD – high capacity but slow; used for archives and cold data.
• SSD (SATA/SAS) – fast but more expensive; suitable for mixed workloads.
• NVMe – ultra‑fast with minimal latency; designed for all‑flash arrays.

Examples: Dell PowerVault ME5024 supports up to 24 drives in 2.5″ or 3.5″ form factors, while Lenovo ThinkSystem DE4000H can combine up to 192 drives in a hybrid configuration.

3. Cache Memory

Cache is high‑speed memory (usually DRAM or NVRAM) located on the controllers. It acts as a buffer between fast server requests and slower disk media. Cache is split into:

• Read cache – stores frequently accessed data to accelerate reads.
• Write cache – buffers write operations to smooth out peak loads and reduce latency.

In all‑flash arrays, cache is used to accelerate operations and also for inline deduplication and compression. For example, Huawei Dorado 5000 uses intelligent caching with machine‑learning algorithms for data prefetching.

4. Access Protocols: FC, iSCSI, NVMe‑oF

The choice of protocol determines how servers connect to the storage system and affects performance, latency, and infrastructure cost.

Fibre Channel (FC)

A high‑speed protocol based on dedicated optical networks. Delivers low latency and high throughput (up to 64 Gbit/s). Used in enterprise SANs. Requires FC switches and HBA adapters.

iSCSI

Encapsulates SCSI commands in TCP/IP packets. Operates over standard Ethernet, lowering cost but adding latency due to TCP/IP overhead. Suitable for mid‑sized enterprises with budget constraints.

NVMe‑oF (NVMe over Fabrics)

The most modern protocol, extending NVMe over networks (Ethernet, InfiniBand, FC). Delivers microsecond‑scale latency and throughput comparable to local NVMe. Ideal for all‑flash arrays and high‑performance computing. Requires RDMA‑capable network adapters (RoCE, iWARP).

Our data centre switches, such as Cisco Nexus 9300‑GX2, support high‑speed connections for NVMe‑oF.

5. Data Protection: RAID and Erasure Coding

Both technologies provide data redundancy to protect against drive failures, but they work differently.

RAID (Redundant Array of Independent Disks)

Hardware‑ or software‑based method of combining drives into arrays with various redundancy levels (RAID 0, 1, 5, 6, 10). RAID 5 and 6 use parity to reconstruct data when one or two drives fail. RAID is widely used in DAS, NAS, and entry‑level SAN.

Erasure Coding

A more modern method used in object and distributed storage systems. Data is split into data chunks and parity chunks, which are distributed across different nodes. This allows recovery from multiple node failures simultaneously. Erasure coding provides better storage efficiency compared to replication and is often used in scale‑out systems such as Huawei OceanStor Pacific 9550.

6. Architectural Approaches: Scale‑Up vs Scale‑Out

Understanding these approaches helps choose the right storage system for business growth.

• Scale‑Up (vertical scaling) – increasing capacity and performance by adding disk shelves or more powerful controllers to an existing system. Suitable for predictable workloads. Examples: traditional SAN and NAS.
• Scale‑Out (horizontal scaling) – adding new nodes (controllers with drives) to a cluster, which increases both capacity and performance linearly. Ideal for big data, cloud environments, and unstructured data. Example: Huawei Pacific 9550 and other object storage systems.

7. Modern All‑Flash Architectures

All‑flash arrays are built entirely on SSDs/NVMe. They deliver minimal latency (below 0.1 ms) and high throughput, which is critical for OLTP, virtualisation, and AI workloads. Key features:

• NVMe drives for maximum speed.
• Built‑in deduplication and compression to save space.
• Intelligent caching and automatic optimisation.
• Support for NVMe‑oF for low‑latency network access.

We offer all‑flash storage systems from Huawei and Dell, such as OceanStor Dorado 5000 and PowerStore 1200T, which meet the highest demands.

8. Frequently Asked Questions (FAQ)

In the next article, we will dive deep into all‑flash storage and its business benefits. Stay tuned!

Storage System Types: DAS, NAS, SAN, Object Storage Explained

Storage systems are the backbone of any IT infrastructure. However, the variety of types and architectures often confuses even experienced administrators. In this article, we break down four fundamental storage system types: DAS, NAS, SAN, and Object Storage. You will learn their key features, advantages, disadvantages, and typical use cases. This will help you choose the right solution for your business — whether you run a small office or a large data center.

1. DAS (Direct Attached Storage) – Direct Connection

DAS is storage that connects directly to a single server or workstation via interfaces such as SATA, SAS, USB, or Thunderbolt. Essentially, it is an external drive or disk array that is visible only to the device it is connected to.

Advantages of DAS:

• Simplicity – requires no networking knowledge; it works “out of the box”.
• Low cost – minimal hardware and maintenance expenses.
• High performance – direct connection ensures low latency and high throughput.

Disadvantages of DAS:

• No scalability – resources are available to only one server.
• Difficult sharing – data cannot be easily shared with other servers or users.
• Limited data protection – typically lacks built‑in replication or snapshot mechanisms.

2. NAS (Network Attached Storage) – Network Storage

NAS is a dedicated device that connects to your network (usually Ethernet) and provides file‑level access using protocols such as NFS (Linux/Unix), SMB/CIFS (Windows), and AFP (macOS). In essence, NAS is a specialised file server with its own operating system optimised for storing and serving data.

Advantages of NAS:

• Easy sharing – multiple users and servers can work with the same files simultaneously.
• Simple management – most NAS devices offer a web‑based interface that does not require deep expertise.
• Rich feature set – supports snapshots, replication, built‑in antivirus, media servers, cloud sync, and more.
• Scalability – many models allow adding drives or connecting expansion units.

Disadvantages of NAS:

• Performance – limited by network speed and the NAS processor. For heavy database workloads, NAS may not be fast enough.
• Latency – file protocols introduce additional overhead compared to block‑level access.

3. SAN (Storage Area Network) – Block‑Level Storage Network

SAN is a high‑performance network dedicated solely to transferring block data between servers and storage systems. Unlike NAS, SAN operates at the block level (like a local hard drive) rather than the file level. Servers connect to SAN via dedicated Fibre Channel (FC), iSCSI (over Ethernet), or NVMe‑oF networks.

Advantages of SAN:

• High performance – minimal latency and high throughput, ideal for databases, OLTP, and virtualisation.
• Scalability – you can add disk shelves, controllers, and nodes without downtime.
• Fault tolerance – redundancy of all components (controllers, power supplies, links).
• Clustering support – multiple servers can access the same data simultaneously (e.g., for database clusters or VMware vSphere).

Disadvantages of SAN:

• High cost – requires specialised hardware (FC switches, HBA adapters).
• Complex management – demands skilled SAN administrators.
• Isolation – SAN is a separate network, adding infrastructure complexity.

4. Object Storage

Object storage is an architecture where data is stored as objects, each containing the data itself, metadata, and a unique identifier. Access is provided via REST APIs (usually over HTTP/HTTPS). Object storage is ideal for large volumes of unstructured data: photos, videos, logs, backups, and archives.

Advantages of Object Storage:

• Virtually unlimited scalability – add nodes and get linear capacity and performance growth. These are scale‑out systems.
• Unified namespace – all data is accessible via a single API, regardless of physical location.
• High durability – data is automatically replicated across nodes, ensuring fault tolerance.
• Low storage cost – object storage is often built on commodity servers with large HDDs.

Disadvantages of Object Storage:

• Latency – HTTP access introduces additional delays, making object storage unsuitable for high‑throughput transactional systems.
• Limited functionality – object storage does not support traditional file operations (rename, move) as efficiently as NAS.

5. Comparison Table: DAS vs NAS vs SAN vs Object Storage

6. How to Choose the Right Storage Type for Your Business

The right storage choice depends on your workloads, budget, and growth plans. Here are practical recommendations:

• For a small office or branch – NAS is a great choice. It is easy to set up, offers shared file access, and basic backup features. Consider Lenovo ThinkSystem ST650 V3 tower servers as a powerful NAS platform.
• For virtualisation and databases – you need SAN. Look at Dell PowerStore 1200T or Huawei OceanStor Dorado 5000 – they deliver the required performance and resilience.
• For Big Data, AI/ML, archives – choose object storage. Huawei OceanStor Pacific 9550 lets you scale to petabytes without performance loss.
• For mixed workloads – consider Lenovo ThinkSystem DE4000H hybrid storage, which combines flash speed with HDD capacity.

7. Frequently Asked Questions (FAQ)

In upcoming articles, we will dive deeper into storage architecture, selection criteria, and real‑world deployment case studies. Subscribe to our updates to stay informed!

How to Choose an Enterprise Storage System: Complete Guide

Modern enterprises generate terabytes of data every day. Without a reliable and high‑performance storage system, businesses risk losing not only data but also competitive advantage. In this guide, we explain storage types (DAS, NAS, SAN, object storage), key selection criteria (IOPS, capacity, protocols), and provide practical recommendations for choosing the right solution from leading brands: Huawei OceanStor, Dell PowerStore, and Lenovo ThinkSystem.

1. Types of Storage Systems: DAS, NAS, SAN, Object Storage

DAS (Direct Attached Storage) – storage directly attached to a server. Simple, affordable, but not scalable. Suitable for small offices or as a temporary solution. NAS (Network Attached Storage) – file‑level storage accessible over a network. Convenient for shared folders and backups, but performance is limited by file protocols. SAN (Storage Area Network) – block‑level storage on a dedicated network (Fibre Channel, iSCSI). Ideal for databases, virtualization, and high‑performance applications. Object Storage – scalable solutions for massive unstructured data (objects, files), often used in clouds and for Big Data.

2. Key Criteria for Choosing Enterprise Storage

When selecting a storage system, focus on these parameters:

• Performance (IOPS & latency) – IOPS (input/output operations per second) and response time. OLTP databases and virtualization require high IOPS and sub‑millisecond latency. All‑flash arrays meet these demands.
• Capacity & scalability – current and future (3‑5 years) data volume. Scale‑out systems let you add nodes without downtime, for example object storage.
• Access protocols – FC, iSCSI, NVMe‑oF, NFS, SMB. Choose based on your workload type and existing network infrastructure.
• Reliability & availability – redundant controllers, power supplies, RAID, erasure coding. For mission‑critical systems, fault‑tolerant architecture is mandatory.
• Data reduction features – deduplication, compression, thin provisioning. They dramatically save space, especially on all‑flash systems.

3. Comparison of Huawei, Dell, and Lenovo Solutions

We source equipment directly from China, offering you the best price/performance ratio. Here are popular models for different use cases:

4. Common Storage Selection Mistakes and How to Avoid Them

• Overpaying for unnecessary features – don’t buy an all‑flash array if your workloads work well on hybrid storage. Assess your real IOPS needs.
• Ignoring scalability – choose platforms that can scale vertically or horizontally. Scale‑out storage allows growth without a full replacement.
• Wrong protocol choice – for heavy databases, use FC or NVMe‑oF, not iSCSI.
• Neglecting data protection – always plan for replication, snapshots, backups. Consider dedicated backup appliances.

5. Frequently Asked Questions (FAQ)

In the following articles, we will dive deeper into storage architectures and provide workload‑specific recommendations. Subscribe to our updates to stay informed.