Shulou(Shulou.com)06/01 Report--

This article introduces the relevant knowledge of "how to solve the typical fault problem of server disk array". In the operation process of actual cases, many people will encounter such difficulties. Next, let Xiaobian lead you to learn how to deal with these situations! I hope you can read carefully and learn something!

Some common issues are encountered during disk array online support. The typical issues are analyzed as follows

1. Error (such as I/0 error, read/write delay failure, etc.) when the server writes or reads data to the disk array, or fails to write data, or errors occur during the writing process

1)Check SCSI cable and SCSI card for looseness.

2)Determine the disk array model: if it is SCSI interface type disk array, the first idea is to check whether the host channel interface of the disk array is connected incorrectly. If the SCSI cable is connected to the out port, this fault phenomenon is easy to occur. At this time, the user must be reminded to shut down the server first, then shut down the disk array. Wait a moment, and immediately switch the SCSI cable to the in port after the static discharge is completed.

3)View channel speed:

Under normal circumstances, the channel frequency of our company's disk array is 160MHZ(corresponding to the transmission rate of 320MB/s). If the disk channel frequency is 80 or lower, it is recommended to check each component on the SCSI link one by one (SCSI card, SCSI cable, connectivity of disk array channel). If necessary, verify your judgment by replacing the host channel and SCSI card.

2. The server is slow to write or read data to or from the disk array

1)Check the physical connection, such as SCSI cable, SCSI card is loose, SCSI cable is not recommended to be too long, so as not to affect I/0 speed

2)Ask about SCSI card model. If a 160MB/s SCSI card is used to connect a 320MB/s disk array, the server may not be able to access the disk array or the read/write rate may be very slow.

3)Check the channel rate. If someone changes the channel frequency or it shows 80 or lower frequency, it will cause the rate to be very slow. Try to modify it to 160MHz.

4)View parameter settings:

such as read-write strategy

There are two write strategies in the infrotrend array;write back and write through, default is write back, when using the write back write strategy, if the server writes data to the array, the controller will first write the data to the cache, and then write it to the hard disk periodically. Since the cache I/O rate is much higher than the hard disk I/O rate, it will improve performance. Using write through causes the controller to write data directly to the hard disk without caching, which can be improved by modifying the write policy

There are read and write strategies in the promise array

Read cache,read ahead,no cache, default read ahead,no cache is read data do not pass cache, read cache is read data do not read from the hard disk, but first to read the data into the cache, read ahead is to read the data and the next time may be read together into the cache, read performance is better

Writing strategies is similar to infrotrend

5) Strip Size Settings

The controller writes data to and reads data from the disk array in stripes ranging from

(8KB-1MB Take promise as an example, different manufacturers may not be able to), for different applications, different stripe settings can use performance has a big difference

There are two typical types of applications:

a) Multimedia or video-on-demand system: data I/O times should not be too many, and the data volume of one I/O should be large, otherwise there will be multiple pauses at the user end. Therefore, the stripe size should be set to 64K or larger, otherwise the performance will be affected.

b) Database file access: frequent access times, but the amount of data per I/O is not large, generally a table or a few field modifications, then the stripe is required to be relatively small, generally set to 8K or less is appropriate

Another common problem encountered in the online support of common disk array problems is that the server does not recognize the disk array. The general analysis idea is as follows:

As a hardware device, the disk array is recognized by the server at two levels,

The first is that the HBA card scans hardware devices at server boot time, regardless of the operating system, which is not yet booted

The second is whether the disk array can be identified in the system after the operating system is started.

Therefore, the server cannot recognize the disk array, and it is necessary to locate which level it is.

1. If it is at server startup, the disk array is not recognized in the HBA card

1) Check whether the disk array mapping is done well

2) Check the physical connection, HBA card and fiber optic cable, SFP or SCSI card installation, whether there is any problem with the connection, if it is a fiber optic card, check whether the indicator light status of the fiber optic card is normal.

3) The physical connection is normal but the disk array cannot be identified. It needs to be confirmed.

a) Compatibility of HBA cards with disk arrays

For example, adaptec SCSI card is not compatible with SCSI disk array. For details, please refer to the relevant compatibility list.

b)SCSI cable or optical fiber cable, SFP is damaged, if the route through the optical fiber switch, check whether the corresponding port indicator is normal

4) The disk array is strictly tested before being sold, and the possibility of failure is generally small. Only when the above points are confirmed to be normal will the disk array be considered:

If one channel of the panel array is blocked, replace it with another channel to test whether it is normal. If the other channel is normal, it may be the controller channel fault. At this time, you can visually inspect whether there is any artificial damage trace at the channel port, such as bent needle.

2. If the HBA card can identify the disk array when the server is started, but cannot identify the disk array after entering the system

1)First check whether the driver is installed, and if necessary, reinstall the driver

2)If the device array is recognized but the partition is not, typically on a windows system, see if you can activate the disk or rescan the hardware changes

3)When fiber optic disk array is connected to the server, it sometimes happens that the hard disk cannot identify a partition after replacement or restart. At this time, you can restart the server and disk array. If you pass through the fiber optic switch halfway, restart the switch.

"How to solve the typical fault problem of server disk array" is introduced here. Thank you for reading it. If you want to know more about industry-related knowledge, you can pay attention to the website. Xiaobian will output more high-quality practical articles for everyone!

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.