Potential data corruption when SATA disk write cache is enabled

Troubleshooting

Problem

The system will not incur any issue. The Operating System (OS) will likely not indicate any event. Data corruption occurs without the users awareness when the active disks write cache is enabled and the disk performs a Read Look Ahead (RLA), which is prematurely ended. Data corruption can occur when cached write data, which has not been committed to disk, is invalidated by a completed disk read operation and then read at a later time.

Resolving The Problem

Source

RETAIN tip: H197382

Symptom

Affected configurations

The system is configured with one or more of the following IBM Options:

1000 GB Dual Port Hot-swap SATA HDD, Option 43W7630, any replacement part number
1000 GB Hot-Swap SATA HDD, Option 43W7626, any replacement part number
2 TB 7200 NL SATA 3.5-inch HS HDD, Option 42D0782, replacement part numbers, any replacement part number, 42D0783
250 GB 7200 RPM SATA Simple-swap HDD, Option 39M4508, any replacement part number
250 GB 7200 RPM SATA Simple-swap HDD, Option 39M4526, any replacement part number
250 GB 7200 RPM Simple-swap SATA HDD, Option 40K6872 replaces 73P8006, any replacement part number
250 GB 7200 RPM Simple-swap SATA HDD, Option 73P8006, any replacement part number
250 GB Hot-Swap SATA II, Option 43W7598, any replacement part number
500 GB 7200 RPM 3.0 GB/sec Hot-swap SATA, Option 39M4530, any replacement part number
500 GB 7200 RPM 3.0 GB/sec Simple-swap SATA HDD, Option 39M4514, any replacement part number
500 GB Dual Port Hot-swap SATA HDD, Option 39M4558, any replacement part number
750 GB 7200 RPM SATA Hot-Swap Hard Drive, Option 43W7584, any replacement part number
750 GB Dual Port Hot-swap SATA HDD, Option 43W7580, any replacement part number
750 GB Hot Swap SATA, Option 43W7576, any replacement part number
750 GB Simple Swap SATA, Option 43W7572, any replacement part number
Express 500 GB Hot-Swap SATA II, Option 41Y8226, any replacement part number
Express 500 GB Simple-Swap SATA II, Option 41Y8218, any replacement part number
Express 750 GB Hot-Swap SATA II HDD, Option 41Y8232, any replacement part number
Express 750 GB Simple-Swap SATA II HDD, Option 41Y8222, any replacement part number

This tip is not system specific.
This tip is not software specific.

The 1.06 HDD update utility is affected.
The BB26 firmware for the 42D0547 is affected.

Solution

This behavior will be corrected in a future release of the Hard Disk Update Program.

The target date for this release is scheduled for third quarter 2010.

The file is or will be available by selecting the appropriate Product Group, Product name, Product machine type, and Operating system on IBM Support's Fix Central web page, at the following URL:

	http://www.ibm.com/support/fixcentral/

Workaround

Disable disk write cache.

Additional information

While performing extended disk test exercises, a latent firmware issue was discovered. Although rare, there is a potential for data corruption with hard disk write cache enabled.

This potential issue results from insufficient overlap checking being performed when the write command is received. If a RLA is allowed to fill the entire cache segment, chances are it will overwrite the complete range with new cached data eliminating the overlapping condition. However, the potential for data corruption occurs when a RLA does not fill the entire cache segment and stale data is read from the uncleared portion.

A firmware Fix was implemented to increase stream overlap range checking on incoming Write commands. In such cases, streaming will now be temporarily stopped to handle the new write command, where as before it could have continued the RLA (reads beyond a given read command range of LBAs as a potential cache hit) operation.

The engineering recommendation is to disable disk write cache and update hard disk firmware during the first available scheduled maintenance.

Document Location

Worldwide

Operating System

System x:Operating system independent / None

[{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HW312","label":"System x->System x3800"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HW313","label":"System x->System x3650 T"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HW314","label":"System x->System x3850"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HW315","label":"System x->System x3950"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU054","label":"Systems w\/TPS"},"Product":{"code":"HW316","label":"System x->System x3950 E"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HW317","label":"System x->System x3500"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HW318","label":"System x->System x3550"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HW319","label":"System x->System x3650"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HW31Q","label":"System x->System x iDataPlex dx320 server"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HW31U","label":"System x->System x iDataPlex dx360 M2 server"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HW31V","label":"System x->System x iDataPlex dx360 server"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HW31Y","label":"System x->System x iDataPlex dx340 server"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HW321","label":"System x->System x3400"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HW322","label":"System x->System x3455"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HW323","label":"System x->System x3655"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HW324","label":"System x->System x3755"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HW328","label":"System x->System x3105"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"LOB26","label":"Storage"}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HW329","label":"System x->System x3200"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HW331","label":"System x->System x3250"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HW332","label":"System x->System x3850 M2"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HW333","label":"System x->System x3950 M2"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HW334","label":"System x->System x3200 M2"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HW335","label":"System x->System x3250 M2"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HW336","label":"System x->System x3350"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HW337","label":"System x->System x3100"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HW338","label":"System x->System x3450"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HW339","label":"System x->System x3610"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HWX10","label":"System x->System x3400 M2"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HWX20","label":"System x->System x3500 M2"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HWX30","label":"System x->System x3550 M2"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HWX40","label":"System x->System x3650 M2"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HWX50","label":"System x->System x3200 M3"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HWX60","label":"System x->System x3250 M3"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HWX70","label":"System x->System x3400 M3"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HWX80","label":"System x->System x3500 M3"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HWX90","label":"System x->System x3550 M3"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HWXA0","label":"System x->System x3650 M3"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HWXA1","label":"System x->System x3650 NAS"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HWXB0","label":"System x->System x3690 X5"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HWXC0","label":"System x->System x3850 X5"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HWXD0","label":"System x->System x3950 X5"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HWXE0","label":"System x->System x3100 M3"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HWXF0","label":"System x->System x iDataPlex dx360 M3 server"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HWXG0","label":"System x->System x3620 M3"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HWXH0","label":"System x->System x3630 M3"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}},{"Type":"HW","Business Unit":{"code":"BU016","label":"Multiple Vendor Support"},"Product":{"code":"HWXJ0","label":"System x->System x3755 M3"},"Platform":[{"code":"PF025","label":"Platform Independent"}],"Line of Business":{"code":"","label":""}}]

Tips

Potential data corruption when SATA disk write cache is enabled - IBM System x