Launching soon: The world's first vendor agnostic bug scrubLearn more & join waitlist
OPERATIONAL DEFECT DATABASE
...
...
IMPORTANT : HPE strongly recommends performing the firmware upgrade (below) at the customer's earliest opportunity and to complete the additional steps in the Resolution section. Neglecting to perform the recommended resolution could result in subsequent media errors and potentially unavailable data. Certain HPE NVMe SSD drive models may report an excessive number of media errors. These errors may be the result of data written incorrectly when the NVMe drive is in idle power mode. NOTE : Customer Bulletin a00113342en_us identifies the same HPE NVMe drives for Linux, MS Windows and VMware platforms, BUT the procedure should NOT be followed for Cohesity servers impacted by this drive firmware update. Determine if Your Cohesity System Is Impacted by Media Errors The media errors may not be reported in the logs for AHS, IML, or iLO. Instead, the errors will be observed as the following: SSD failure Media errors on SSDs High capacity where clean-up does not appear to be working as expected Scribe instability or timeouts Capacity not coming down during garbage collection
Any Cohesity Data Platform software running on HPE ProLiant DL380, ProLiant DL360, Apollo 4200, Apollo 2000 or Apollo 4510 servers with the following HPE Cohesity SKUs: R4R12A R0R04B R0R05B R3R77B R3R76B R0R04A R0R05A R3R77A R3R76A R0Q30B R0Q31B R0Q30A R0Q31A R7C08A R7C09A Drives Impacted Affected NVMe drive models include Add In Cards (AIC - PCIe boards) and large capacity Small From Factor U.3 (SFF) drives. AIC - firmware versions prior to EPK75H3Q are affected: 1.6TB MZPLJ1T6HBJR-000 3.2TB MZPLJ3T2HBJR-000 6.4TB MZPLJ6T4HALA-000 U.3 SFF drives - firmware versions prior to MPK75H5Q are affected: 12TB MZXL512THALA-000 15TB MZXL515THALA-000 Note : Only the large capacity U.3 drives for 12TB and 15TB models are affected. Option Kit Description Raw Drive PN P26934-B21 P26934-H21 P26934-K21 HPE 1.6TB PCIe x8 MU HH DS Card P27023-001 P26936-B21 P26936-H21 P26936-K21 HPE 3.2TB PCIe x8 MU HH DS Card P27023-002 P26938-B21 P26938-H21 P26938-K21 HPE 6.4TB PCIe x8 MU HH DS Card P27023-003
IMPORTANT : For Cohesity systems, follow the process in this Customer Bulletin to ensure the issue is properly addressed. Do NOT follow the information in Customer Bulletin a00113342en_us for Cohesity servers impacted by the firmware update for NVMe drives. For the Cohesity SKUs listed above, contact HPE Support and/or Cohesity to have the following steps performed. Click the following URL to locate the HPE Customer Support phone number in your country: TECHNICAL SUPPORT PHONE NUMBERS HPE Support and/or Cohesity strongly recommend performing ALL the steps in the order given. NOTE : If the drive fails at any point during this resolution process, contact HPE Customer Support for a drive replacement. Step 1: Update Firmware HPE will provide a Custom SPP ISO that will include the upgrade firmware files. HPE and Cohesity will jointly apply the firmware update without impacting service to the Cohesity cluster. Step 2: Evaluate Drive Integrity HPE and Cohesity will jointly evaluate the drive integrity and use this as a basis for further remediation. If the evaluation indicates the following results: A drive with media errors, " Step 3: Format the Drive " will be performed next. A drive with a media error count greater than 200, but no current media errors, the next step, " Step 4: Reset Error Counter " should be performed. A drive with media error count less than 200, no current media errors, and additional affected drives remain in the node, the next drive can be evaluated and Step 2 repeated to determine its integrity. When all drives in the node have been evaluated, " Step 5: Verify Node Status " should be performed. Step 3: Format the Drive Cohesity will perform the necessary steps to format the affected drive and clear any remaining media errors. The results of Step 2 above may indicate this drive has the following conditions: More than 200 media errors exist, a Media Error Reset Tool (currently under development) will be available to reset the error counter of the drive as mentioned in " Step 4: Reset Error Counter ". Less than 200 media errors exist, and additional affected drives remain in the node, the next drive will be evaluated as in " Step 2: Evaluate Drive Integrity " above. No additional affected drives remain in the node, then " Step 5: Verify Node Status " can be performed. Step 4: Reset Error Counter HPE and Cohesity will jointly use a Media Error Counter Reset Tool that is currently under development to reset the error counter of the drive. If additional affected drives remain in the node, the next drive can be evaluated as in " Step 2: Evaluate Drive Integrity ". If no additional affected drives remain in the node, then " Step 5: Verify Node Status " will be performed. Step 5: Verify Node Status After successfully completing the steps above, HPE and Cohesity will jointly verify the following items: Drive firmware was updated to EPK75H3Q or later If a reset has been performed, then the drive media error count is reset Cohesity Cluster Services are running on the node If additional nodes with affected drives remain in the cluster, continue to next node and return to "Step 1: Update Firmware". For more information, contact Cohesity Support . RECEIVE PROACTIVE UPDATES : Receive support alerts (such as Customer Advisories), as well as updates on drivers, software, firmware, and customer replaceable components, proactively in your e-mail through HPE Support Alerts. Sign up for Support Alerts at the following URL: Proactive Updates Subscription Form. NAVIGATION TIP: For hints on navigating HPE.com to locate the latest drivers, patches and other support software downloads, refer to the Navigation Tips document. SEARCH TIP: For hints on locating similar documents on HPE.com, refer to the Search Tips document.