My server freezed. I restarted, and after running fsck manually, services restarted normally. I'm analyzing /var/log/messages around the time of the fault, and I found these entries:
Nov 29 22:24:27 cloud kernel: ata1: exception Emask 0x10 SAct 0x0 SErr 0x4090000 action 0xe frozen
Nov 29 22:24:27 cloud kernel: ata1: irq_stat 0x00400040, connection status changed
Nov 29 22:24:27 cloud kernel: ata1: SError: { PHYRdyChg 10B8B DevExch }
Nov 29 22:24:27 cloud kernel: ata1: hard resetting link
Nov 29 22:24:34 cloud kernel: ata1: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
Nov 29 22:24:34 cloud kernel: ata1.00: configured for UDMA/133
Nov 29 22:24:34 cloud kernel: ata1: EH complete
This maybe indicating an HDD fault, but I did a SMART long test of the hard disk and this is the output:
smartctl 5.43 2012-06-30 r3573 [x86_64-linux-2.6.32-573.7.1.el6.x86_64] (local build)
Copyright (C) 2002-12 by Bruce Allen, http://smartmontools.sourceforge.net
=== START OF INFORMATION SECTION ===
Model Family: Seagate Constellation ES (SATA 6Gb/s)
Device Model: ST1000NM0011
Serial Number: Z1N2D4JT
LU WWN Device Id: 5 000c50 04e008fb2
Firmware Version: PA07
User Capacity: 1,000,204,886,016 bytes [1.00 TB]
Sector Size: 512 bytes logical/physical
Device is: In smartctl database [for details use: -P show]
ATA Version is: 8
ATA Standard is: ATA-8-ACS revision 4
Local Time is: Mon Nov 30 15:29:22 2015 CET
SMART support is: Available - device has SMART capability.
SMART support is: Enabled
=== START OF READ SMART DATA SECTION ===
SMART overall-health self-assessment test result: PASSED
General SMART Values:
Offline data collection status: (0x82) Offline data collection activity
was completed without error.
Auto Offline Data Collection: Enabled.
Self-test execution status: ( 0) The previous self-test routine completed
without error or no self-test has ever
been run.
Total time to complete Offline
data collection: ( 609) seconds.
Offline data collection
capabilities: (0x7b) SMART execute Offline immediate.
Auto Offline data collection on/off support.
Suspend Offline collection upon new
command.
Offline surface scan supported.
Self-test supported.
Conveyance Self-test supported.
Selective Self-test supported.
SMART capabilities: (0x0003) Saves SMART data before entering
power-saving mode.
Supports SMART auto save timer.
Error logging capability: (0x01) Error logging supported.
General Purpose Logging supported.
Short self-test routine
recommended polling time: ( 2) minutes.
Extended self-test routine
recommended polling time: ( 151) minutes.
Conveyance self-test routine
recommended polling time: ( 3) minutes.
SCT capabilities: (0x10bd) SCT Status supported.
SCT Error Recovery Control supported.
SCT Feature Control supported.
SCT Data Table supported.
SMART Attributes Data Structure revision number: 10
Vendor Specific SMART Attributes with Thresholds:
ID# ATTRIBUTE_NAME FLAG VALUE WORST THRESH TYPE UPDATED WHEN_FAILED RAW_VALUE
1 Raw_Read_Error_Rate 0x000f 069 063 044 Pre-fail Always - 8118850
3 Spin_Up_Time 0x0003 095 095 000 Pre-fail Always - 0
4 Start_Stop_Count 0x0032 100 100 020 Old_age Always - 15
5 Reallocated_Sector_Ct 0x0033 100 100 036 Pre-fail Always - 0
7 Seek_Error_Rate 0x000f 084 060 030 Pre-fail Always - 4627909443
9 Power_On_Hours 0x0032 073 073 000 Old_age Always - 24302
10 Spin_Retry_Count 0x0013 100 100 097 Pre-fail Always - 0
12 Power_Cycle_Count 0x0032 100 100 020 Old_age Always - 21
184 End-to-End_Error 0x0032 100 100 099 Old_age Always - 0
187 Reported_Uncorrect 0x0032 100 100 000 Old_age Always - 0
188 Command_Timeout 0x0032 100 100 000 Old_age Always - 0
189 High_Fly_Writes 0x003a 100 100 000 Old_age Always - 0
190 Airflow_Temperature_Cel 0x0022 075 064 045 Old_age Always - 25 (Min/Max 23/25)
191 G-Sense_Error_Rate 0x0032 100 100 000 Old_age Always - 0
192 Power-Off_Retract_Count 0x0032 100 100 000 Old_age Always - 27
193 Load_Cycle_Count 0x0032 100 100 000 Old_age Always - 29
194 Temperature_Celsius 0x0022 025 040 000 Old_age Always - 25 (0 20 0 0 0)
195 Hardware_ECC_Recovered 0x001a 105 099 000 Old_age Always - 8118850
197 Current_Pending_Sector 0x0012 100 100 000 Old_age Always - 0
198 Offline_Uncorrectable 0x0010 100 100 000 Old_age Offline - 0
199 UDMA_CRC_Error_Count 0x003e 200 200 000 Old_age Always - 0
240 Head_Flying_Hours 0x0000 100 253 000 Old_age Offline - 169642618276709
241 Total_LBAs_Written 0x0000 100 253 000 Old_age Offline - 3860229105
242 Total_LBAs_Read 0x0000 100 253 000 Old_age Offline - 1373595990
SMART Error Log Version: 1
No Errors Logged
SMART Self-test log structure revision number 1
Num Test_Description Status Remaining LifeTime(hours) LBA_of_first_error
# 1 Extended offline Completed without error 00% 24302 -
# 2 Short offline Completed without error 00% 24299 -
# 3 Short offline Completed without error 00% 24298 -
# 4 Short offline Completed without error 00% 4 -
# 5 Extended offline Completed without error 00% 4 -
SMART Selective self-test log data structure revision number 1
SPAN MIN_LBA MAX_LBA CURRENT_TEST_STATUS
1 0 0 Not_testing
2 0 0 Not_testing
3 0 0 Not_testing
4 0 0 Not_testing
5 0 0 Not_testing
Selective self-test flags (0x0):
After scanning selected spans, do NOT read-scan remainder of disk.
If Selective self-test is pending on power-up, resume after 0 minute delay.
HDD was already replaced recently. Kernel version is 2.6.32-573.7.1.el6.x86_64
As Andrey Sapegin pointed out in comments above, this is very likely hardware.
We cannot currently say whether it is the HDD, or the cable - but it is likely that something physical is failing. That they recently replaced the HDD can be ignored, because they didn't replace it with a new one.
They say that the replacement HDD was known to be good because
That is not an argument that convinces me. I have within the past week had a HDD fail such that it became unable to write, but its read performance was excellent. So "we read all the data off the old HDD" says nothing about the old one's health. "We wrote all the data to a new one" says, to my mind, very little more about the health of the replacement; if that is their total testing methodology, their assurances about the replacement HDD may be ignored.
Google's famous paper makes it clear that just because a drive passes a
smartctlhealth check, you cannot know that it is healthy (only that if it fails, you definitely know it's sick).So where does that leave you? You can be sure you have a problem, and fairly sure the problem is in the hardware. So do the professional thing: shotgun both the cable and the drive. HDDs and cables are cheap enough that it is simply not worth your time (or the risk to your data) to trace this error to its source. Buy a new cable and a new HDD and have your hosting company replace both cable and drive.
And never, ever deploy a server without RAID again.