ODA IOCALIBRATE Shows a Very Slow Performing Disk at 1/2 of IO other Disks but Still Shows No Errors : oakcli validate -c DiskCalibration

Asset ID:	1-72-2275132.1
Update Date:	2017-07-11
Keywords:

Solution Type Problem Resolution Sure

Solution 2275132.1 : ODA IOCALIBRATE Shows a Very Slow Performing Disk at 1/2 of IO other Disks but Still Shows No Errors : oakcli validate -c DiskCalibration

Applies to:

Oracle Database Appliance X3-2 - Version All Versions to All Versions [Release All Releases]
Oracle Database Appliance - Version All Versions to All Versions [Release All Releases]
Oracle Database Appliance X4-2 - Version All Versions to All Versions [Release All Releases]
Information in this document applies to any platform.

Symptoms

After re-deployed the ODA, running 'oakcli validate -c DiskCalibration' detected a substandard performing disk

'oakcli validate -c DiskCalibration'

shows one SAS disk having just over half the MB/s as the rest:

RESULT: Random read throughput of HDD_E0_S15_376391396 is 234 IOPS 147 MBPS
RESULT: Random read throughput of HDD_E0_S17_376391424 is 238 IOPS 153 MBPS
RESULT: Random read throughput of HDD_E0_S07_376390852 is 235 IOPS 148 MBPS
RESULT: Random read throughput of HDD_E0_S04_376390396 is 227 IOPS 147 MBPS
RESULT: Random read throughput of HDD_E0_S01_376391436 is 238 IOPS 151 MBPS
RESULT: Random read throughput of HDD_E0_S05_376762192 is 237 IOPS 147 MBPS
RESULT: Random read throughput of HDD_E0_S10_376762548 is 204 IOPS 130 MBPS
RESULT: Random read throughput of HDD_E0_S09_376718004 is 230 IOPS 144 MBPS
RESULT: Random read throughput of HDD_E0_S12_376762224 is 234 IOPS 152 MBPS
RESULT: Random read throughput of HDD_E0_S18_376762524 is 237 IOPS 148 MBPS
RESULT: Random read throughput of HDD_E0_S14_376762520 is 236 IOPS 150 MBPS
RESULT: Random read throughput of HDD_E0_S00_376391324 is 232 IOPS 145 MBPS
RESULT: Random read throughput of HDD_E0_S13_376515908 is 234 IOPS 149 MBPS
RESULT: Random read throughput of HDD_E0_S06_376762276 is 238 IOPS 149 MBPS
RESULT: Random read throughput of HDD_E0_S03_376516984 is 235 IOPS 148 MBPS
RESULT: Random read throughput of HDD_E0_S19_376391432 is 231 IOPS 151 MBPS
RESULT: Random read throughput of HDD_E0_S16_376391480 is 224 IOPS 82 MBPS <RESULT: Random read throughput of HDD_E0_S08_376390936 is 229 IOPS 146 MBPS
RESULT: Random read throughput of HDD_E0_S11_376390800 is 232 IOPS 147 MBPS
RESULT: Random read throughput of HDD_E0_S02_376391428 is 233 IOPS 149 MBPS

# oakcli stordiag e0_pd_16 --> No issues

# smartctl --all /dev/sdao --> No issues

No direct errors was seen for the disk

smartctl --all /dev/sdao
smartctl 5.43 2012-06-30 r3573 [x86_64-linux-2.6.39-400.290.1.el6uek.x86_64] (local build)
Copyright (C) 2002-12 by Bruce ................

Vendor: HITACHI
Product: H109090SESUN900G
Revision: A72A
User Capacity: 900,185,481,216 bytes [900 GB]
Logical block size: 512 bytes
Logical Unit id: 0x5000cca0166f4738
Serial number: 0013........................
Device type: disk
Transport protocol: SAS
Local Time is: Thu May 11 09:32:14 2017 EDT
Device supports SMART and is Enabled
Temperature Warning Enabled
SMART Health Status: OK

Current Drive Temperature: 25 C
Drive Trip Temperature: 85 C
Manufactured in week 18 of year 2013
Specified cycle count over device lifetime: 50000
Accumulated start-stop cycles: 4
Specified load-unload count over device lifetime: 600000
Accumulated load-unload cycles: 794
Elements in grown defect list: 21
Vendor (Seagate) cache information
Blocks sent to initiator = 23079895957504

Error counter log:
Errors Corrected by Total Correction Gigabytes Total
ECC rereads/ errors algorithm processed uncorrected
fast | delayed rewrites corrected invocations [10^9 bytes] errors
read: 0 0 0 0 266512 474.117 0
write: 0 5221 0 5221 2740 468.773 0
verify: 0 0 0 0 57662 0.000 0

Non-medium error count: 0
No self-tests have been logged
Long (extended) Self Test duration: 7308 seconds [121.8 minutes]

This is a clean test with no evidence of a problem

Changes

None: This was an older ODA that was deployed for the first time after sitting on the shelf a few years.

Cause

The disk need replaced.

Solution

1. Replace the disk

2. Run calibration

References

<NOTE:2268148.1> - Disk reporting low IOPS and MBPS - ODA

Attachments

This solution has no attachment