Fujitsu ETERNUS Storage Lineup Update
Fujitsu has been in the market for disk storage systems for over 50 years. Today, its product portfolio contains both hybrid and All-Flash arrays. The Fujitsu storage lineup is regularly updated with interesting new items, in this article we will talk about some of them.
Last summer, the entry-level hybrid storage systems were updated: ETERNUS DX60 S4, ETERNUS DX100 S4 and ETERNUS DX200 S4. This year, the mid-level storage systems received an update: ETERNUS DX500 S4 and ETERNUS DX600 S4, as well as All-Flash arrays ETERNUS AF250 S2 and ETERNUS AF650 S2. First of all, the performance and hardware capabilities of the storage facilities improved. All Fujitsu storage systems are developed by a single development team, this is not an OEM development and it is not associated with the purchase of third-party manufacturers. As a result of this approach, all Fujitsu ETERNUS DX / AF storage systems of different models and generations are compatible with each other, and the transition to new models is easy to implement gradually. You can create replicas and snapshots between different primary, intermediate and senior ETERNUS systems, and directly transfer data between systems of different generations. All ETERNUS storage systems have a single management tool - the ETERNUS Storage Foundation (SF), and the entry-level equipment runs on the free edition of the ETERNUS SF Express.
Almost all vendors claim high performance of their products, supporting these statements with figures from internal tests. However, one should not forget that the results of independent testing enjoy the greatest confidence. Portal Storageperformance.org has tested ETERNUS DX200 S4 with 20 SSDs on board. In the benchmark simulating high-load OLTP databases, the response time of the DX200 was 0.59 milliseconds with 300,056 IOPS. Testing with the same portal model All-Flash ETERNUS AF250 S2 with 24 SSDs installed, showed a result of 0.67 milliseconds at 360,070 IOPS. This is an absolute record in price / performance ratio $ / IIOPS according to the SPC-1 benchmark.
')
Such indicators guarantee the absence of problems during the transition to a single-tier storage model with the creation of a fast storage of large volume.
British IT portal The Register marks a tendency to reduce the cost of IOPS by 22 times in the last 6-7 years. In this case, the record holder at the lowest cost for IOPS , according to the portal, is Fujitsu ETERNUS AF250 S2.
ETERNUS Storage Foundation Express software is used for storage management in entry-level DX models; for All-Flash models, the full version of ETERNUS SF is used. In both cases, the management software is delivered directly “out of the box” with a convenient licensing mechanism. Licensing policy does not depend on the capacity of disk arrays. The amount of data storage can be increased without additional costs for software licenses. For middle and high level hybrid solutions, the control system is provided separately.
What is the practical level of reliability of 99.9999%, which is declared for ETERNUS systems? The allowable downtime of IT infrastructures for modern enterprises is rapidly decreasing. Today, customers allow the possibility of downtime for just a few minutes a year. To achieve such performance, Fujitsu engineers implemented the Storage Cluster mechanism.
This mechanism works "on top" of the synchronous replica. It can be configured both unidirectionally and bidirectionally. In the event of a disk group failure, the entire array fails, or all access paths to one of the Storage Cluster arrays fail, in a fully automatic mode, it switches to the second array. To do this, all links on the primary array are forcibly disconnected, and on the secondary one, links from the same WWN are “raised”. From the point of view of an application, server, OS, or multi-pass driver, such switching looks like a short-term SFP failure on the switch.
This mechanism can work for individual volumes or storage pools. Switching between arrays takes 5 to 8 seconds when using Fiber Channel and a little more when using iSCSI. It can also be enforced by an administrator. Reverse switching is possible both at the command of the administrator, and in fully automatic mode.
Starting with the entry-level storage system ETERNUS DX200, as well as in the entire All-Flash line, several data compression mechanisms are supported: compression, deduplication, as well as both mechanisms simultaneously. The effectiveness of various compression methods depends on the nature of the data. For example, encrypted data or information from surveillance cameras that have already been compressed, it is impractical to re-compress the means of storage. On the other hand, when creating a large number of identical virtual machines, the use of both deduplication and compression will be very effective.
Compared to the first generation, the performance of the ETERNUS AF250 S2 and ETERNUS AF650 S2 arrays increased by 30%. The average IOPS is 430,000 and 810,000, respectively. Higher performance - more features. Now the new ETERNUS AF supports 30% more virtual machines and database transactions, as well as 20% more virtual desktops (VDI).
Business is not interested in abstract figures, it is important the performance of specific applications. Automating the provision of guaranteed service levels (QoS) allows you to efficiently allocate resources for various applications and services. For example, in online retail the level of load on the front-end of the application varies depending on the calendar period and the time of day. In big data analytics, work is distributed across different departments of a company. All this can be done with the help of QoS mechanisms, which allow you to prioritize each application, as well as target the response time at the millisecond level for individual volumes or groups of volumes.
To increase the performance of ETERNUS AF, developers improved the microcode-level read / write process. So, with a long sequential process of reading, the performance increases markedly. With a long sequential recording process, the system interacts directly with the SSD, bypassing caching, which also increases its performance.
The performance of the Garbage Collection procedure, which every SSD is periodically subjected to, has been significantly optimized. At the microcode level, the system recognizes which of the drives is currently running this procedure and, if possible, does not use it. With a significant filling of the SSD data (60-80% and above), the speed of the storage system is also not reduced.
The new models have improved the mechanisms for transferring data to the newly installed storage system. Some ports in the new storage system need to be transferred to the initiator mode, in which case it will be perceived by other systems as a server initiating data transfer. This allows you to significantly simplify the migration process, since the server immediately “sees” all the data through the new storage system, although data copying has not yet been completed.
Rear view expansion shelf
In the latest microcode updates, data migration with zero downtime is available. In this case, switching is performed by sequential reassignment of the identifier of the new volume to a number identical to the old one for each access path. The server, on the other hand, perceives the new volume as old, which became available after the disappearance of one of the ways.
Summarizing, in the new Fujitsu ETERNUS storage systems, not only all the advantages realized in previous generation systems were preserved: universal controls, the lack of licenses related to the volume, but also significantly increased performance. At the same time, the total cost of IOPS in new models can be called one of the most attractive on the market.
Last summer, the entry-level hybrid storage systems were updated: ETERNUS DX60 S4, ETERNUS DX100 S4 and ETERNUS DX200 S4. This year, the mid-level storage systems received an update: ETERNUS DX500 S4 and ETERNUS DX600 S4, as well as All-Flash arrays ETERNUS AF250 S2 and ETERNUS AF650 S2. First of all, the performance and hardware capabilities of the storage facilities improved. All Fujitsu storage systems are developed by a single development team, this is not an OEM development and it is not associated with the purchase of third-party manufacturers. As a result of this approach, all Fujitsu ETERNUS DX / AF storage systems of different models and generations are compatible with each other, and the transition to new models is easy to implement gradually. You can create replicas and snapshots between different primary, intermediate and senior ETERNUS systems, and directly transfer data between systems of different generations. All ETERNUS storage systems have a single management tool - the ETERNUS Storage Foundation (SF), and the entry-level equipment runs on the free edition of the ETERNUS SF Express.
Independent Performance Test Results
Almost all vendors claim high performance of their products, supporting these statements with figures from internal tests. However, one should not forget that the results of independent testing enjoy the greatest confidence. Portal Storageperformance.org has tested ETERNUS DX200 S4 with 20 SSDs on board. In the benchmark simulating high-load OLTP databases, the response time of the DX200 was 0.59 milliseconds with 300,056 IOPS. Testing with the same portal model All-Flash ETERNUS AF250 S2 with 24 SSDs installed, showed a result of 0.67 milliseconds at 360,070 IOPS. This is an absolute record in price / performance ratio $ / IIOPS according to the SPC-1 benchmark.
')
Such indicators guarantee the absence of problems during the transition to a single-tier storage model with the creation of a fast storage of large volume.
British IT portal The Register marks a tendency to reduce the cost of IOPS by 22 times in the last 6-7 years. In this case, the record holder at the lowest cost for IOPS , according to the portal, is Fujitsu ETERNUS AF250 S2.
Unified Management Software
ETERNUS Storage Foundation Express software is used for storage management in entry-level DX models; for All-Flash models, the full version of ETERNUS SF is used. In both cases, the management software is delivered directly “out of the box” with a convenient licensing mechanism. Licensing policy does not depend on the capacity of disk arrays. The amount of data storage can be increased without additional costs for software licenses. For middle and high level hybrid solutions, the control system is provided separately.
Clustering and disaster recovery
What is the practical level of reliability of 99.9999%, which is declared for ETERNUS systems? The allowable downtime of IT infrastructures for modern enterprises is rapidly decreasing. Today, customers allow the possibility of downtime for just a few minutes a year. To achieve such performance, Fujitsu engineers implemented the Storage Cluster mechanism.
This mechanism works "on top" of the synchronous replica. It can be configured both unidirectionally and bidirectionally. In the event of a disk group failure, the entire array fails, or all access paths to one of the Storage Cluster arrays fail, in a fully automatic mode, it switches to the second array. To do this, all links on the primary array are forcibly disconnected, and on the secondary one, links from the same WWN are “raised”. From the point of view of an application, server, OS, or multi-pass driver, such switching looks like a short-term SFP failure on the switch.
This mechanism can work for individual volumes or storage pools. Switching between arrays takes 5 to 8 seconds when using Fiber Channel and a little more when using iSCSI. It can also be enforced by an administrator. Reverse switching is possible both at the command of the administrator, and in fully automatic mode.
Savings without damage
Starting with the entry-level storage system ETERNUS DX200, as well as in the entire All-Flash line, several data compression mechanisms are supported: compression, deduplication, as well as both mechanisms simultaneously. The effectiveness of various compression methods depends on the nature of the data. For example, encrypted data or information from surveillance cameras that have already been compressed, it is impractical to re-compress the means of storage. On the other hand, when creating a large number of identical virtual machines, the use of both deduplication and compression will be very effective.
All-Flash Array Performance
Compared to the first generation, the performance of the ETERNUS AF250 S2 and ETERNUS AF650 S2 arrays increased by 30%. The average IOPS is 430,000 and 810,000, respectively. Higher performance - more features. Now the new ETERNUS AF supports 30% more virtual machines and database transactions, as well as 20% more virtual desktops (VDI).
Additional features
Business is not interested in abstract figures, it is important the performance of specific applications. Automating the provision of guaranteed service levels (QoS) allows you to efficiently allocate resources for various applications and services. For example, in online retail the level of load on the front-end of the application varies depending on the calendar period and the time of day. In big data analytics, work is distributed across different departments of a company. All this can be done with the help of QoS mechanisms, which allow you to prioritize each application, as well as target the response time at the millisecond level for individual volumes or groups of volumes.
To increase the performance of ETERNUS AF, developers improved the microcode-level read / write process. So, with a long sequential process of reading, the performance increases markedly. With a long sequential recording process, the system interacts directly with the SSD, bypassing caching, which also increases its performance.
The performance of the Garbage Collection procedure, which every SSD is periodically subjected to, has been significantly optimized. At the microcode level, the system recognizes which of the drives is currently running this procedure and, if possible, does not use it. With a significant filling of the SSD data (60-80% and above), the speed of the storage system is also not reduced.
The new models have improved the mechanisms for transferring data to the newly installed storage system. Some ports in the new storage system need to be transferred to the initiator mode, in which case it will be perceived by other systems as a server initiating data transfer. This allows you to significantly simplify the migration process, since the server immediately “sees” all the data through the new storage system, although data copying has not yet been completed.
Rear view expansion shelf
In the latest microcode updates, data migration with zero downtime is available. In this case, switching is performed by sequential reassignment of the identifier of the new volume to a number identical to the old one for each access path. The server, on the other hand, perceives the new volume as old, which became available after the disappearance of one of the ways.
Summarizing, in the new Fujitsu ETERNUS storage systems, not only all the advantages realized in previous generation systems were preserved: universal controls, the lack of licenses related to the volume, but also significantly increased performance. At the same time, the total cost of IOPS in new models can be called one of the most attractive on the market.
Source: https://habr.com/ru/post/358636/
All Articles