
ASC offers several options that can dramatically increase the performance of your SAN.
ASC's SafeCache option improves the overall performance of ASC-managed disks (virtual and/or service-enabled) by making use of high performance solid state disks as a persistent (non-volatile) read/write cache.
In a centralized storage environment where a large set of database servers share a smaller set of storage devices, data tends to be randomly accessed. Even with a RAID controller that uses cache memory to increase performance and availability, hard disk storage often cannot keep up with application servers' I/O requests.
ASC's SafeCache, working in conjunction with high-speed devices such as solid state disks (SSD) to `front' slower real disks, can significantly improve performance. Since SSDs are 100% immune to random access, ASC's SafeCache can write data blocks sequentially to the cache and then move them to the data disk (random write) as a separate process once the writes have been acknowledged, effectively accelerating the performance of the slower disks.
ASC's SafeCache makes use of external high-speed storage devices that are persistent for caching purposes, a much safer choice than traditional RAM (which can lose data if a system goes down). While SSDs have a built-in power supply to minimize potential downtime, the cache can also be mirrored through ASC for added protection.
The SafeCache is fully compatible with ASC's Failover option, which allows one ASC Server to automatically fail over to another without any data loss and without any cache write coherency problems.
To set up SafeCache for a SAN or NAS Resource you must create a cache resource. You can create a cache resource for a single SAN or NAS Resource or you can use the batch feature to create cache resources for multiple SAN or NAS Resources.
For multiple SAN or NAS Resources, right-click on the SAN Resources or NAS Resources object and select SafeCache --> Enable.
Note that the cache resource cannot be expanded. Therefore, you should allocate enough space for your SAN/NAS resource, taking into account future growth. If you "outgrow" your cache resource, you will need to disable it and then recreate it.
Custom lets you select which physical device(s) to use and lets you designate how much space to allocate from each.
Express automatically creates the cache resource using the criteria you select:
- Select different drive - ASC will look for space on another hard disk.
- Select drives from different adapter/channel - ASC will look for space on another hard disk only if it is on a separate adapter/channel.
- Select any available drive - ASC will look for space on any disk, including the original. This option is useful if you have mapped a device (such as a RAID device) that looks to ASC like a single physical device.
You can now mirror your cache resource by highlighting the SAN or NAS Resource and selecting SafeCache --> Mirror --> Add.
You can see the current status of your cache resource by checking the SafeCache tab for a cached resource.
Unlike a snapshot resource that continues to grow, the cache resource is cleared out after data blocks are moved to the data disk. Therefore, you can see the Usage Percentage decrease, even return to 0% if there is no write activity.
ASC's HotZone option is an intelligent, policy-driven, disk-based staging mechanism that automatically remaps "hot" (frequently used) areas of disks to higher performance storage devices. This results in enhanced read/write performance for the applications accessing the storage. It also allows you to manage your storage network with a minimal number of high performance devices (such as solid state disks) by leveraging their performance capabilities.
To configure HotZone, you must divide your virtual or service enabled disk into "zones" of equal size (e.g., 64 MB). ASC then automatically creates HotZone storage on the specified high performance disk. This HotZone storage is divided into zones equal in size to the zones on the virtual or service-enabled disk (e.g., 64 MB), and is provisioned to the disk.
ASC monitors reads/writes to each zone on the virtual or service enabled disk. Based on the statistics collected, ASC determines the most frequently accessed zones and re-maps the data from these "hot zones" to the HotZone storage (located on the high performance disk) resulting in enhanced read/write performance for the application accessing the storage. Using the continually collected statistics, if ASC determines that the corresponding "hot zone" is no longer "hot", the data from the high performance disk is moved back to its original zone on the virtual or service-enabled disk.
Note that the HotZone cannot be expanded. Therefore, you should allocate enough space for your SAN/NAS resource, taking into account future growth. If you "outgrow" your HotZone, you will need to disable it and then recreate it.
Custom lets you select which physical device(s) to use and lets you designate how much space to allocate from each.
Express automatically creates the HotZone storage using the criteria you select:
- Select different drive - ASC will look for space on another hard disk.
- Select drives from different adapter/channel - ASC will look for space on another hard disk only if it is on a separate adapter/channel.
- Select any available drive - ASC will look for space on any disk, including the original. This option is useful if you have mapped a device (such as a RAID device) that looks to ASC like a single physical device.
If you selected Custom, you can piece together space from one or more disks.
Size of each zone - Indicate how large each zone should be. ASC monitors reads/writes to each zone on the disk. Based on the statistics collected, ASC determines the most frequently accessed zones and re-maps the data from these "hot zones" to the HotZone storage. You should check with your application server to determine how much data is read/written at one time. The block size used by the application should ideally match the size of each zone.
Minimum stay time - Indicate the minimum amount of time data should remain in the HotZone before being moved back to its original zone once ASC determines that the zone is no longer "hot".
Access type - Indicate whether the zone should be monitored for reads, writes, or both.
Access intensity - Indicate how ASC should determine if a zone is "hot". Number of IOs performed at the site uses the amount of data transferred (read/write) as a determining factor for each zone.
You can see the current status of your HotZone by checking the HotZone tab for a configured resource.
You can also see statistics about the zone by checking the HotZone Statistics tab.
The information displayed is initially for the current interval (hour, day, week, or month). You can go backward (and then forward) to see any particular interval. You can also view multiple intervals by moving backward to a previous interval and then clicking the Play button to see everything from that point to the present interval.
Click the Detail View button to see more detail. There you will see the information presented more granularly, for smaller amounts of the disk.
![]() Acer, Inc. www.acer.com |