0

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

  • 1
    Before anything else, do a long test. The short test is primarily a check that the drive hasn't already died; it doesn't have much to say about whether the drive is likely to die. Also, you say the drive has recently been replaced, but this one's been powered on for 24,000 hours, ie nearly 3 years. Either you didn't replace it recently, or you didn't replace it with a new HDD. Which is it? – MadHatter Nov 30 '15 at 9:57
  • @MadHatter The datacenter never said a new HDD was used. Replacement was made one month ago. I'll run a SMART long test, but the server will be read-only or unreachable during the test? – Marco Marsala Nov 30 '15 at 10:00
  • 1
    The server will continue to run, but accesses to the drive may be slightly slower during the test. – Michael Hampton Nov 30 '15 at 10:19
  • 1
    No; read the linked answer, the long test is also (reasonably) service-transparent unless -C is used. Why was the HDD replaced last time, and are these discs mirrored? – MadHatter Nov 30 '15 at 10:20
  • @MadHatter The first time the HDD was replaced because we experienced this issue: unix.stackexchange.com/questions/239193/… As we never understood the cause, and the destination server was rent since only one month, we thought about an hardware fault and asked the farm to replace the disk. They cloned the old disk on a new one (used but tested), and confirmed both old and new disks was 100% ok because no errors arised while cloning. – Marco Marsala Nov 30 '15 at 11:13
1

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

They cloned the old disk on a new one (used but tested), and confirmed both old and new disks was 100% ok because no errors arised while cloning.

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 smartctl health 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.

  • I replaced HDD, cables and motherboard (the controller is integrated in the MB). A server without RAID is acceptable in my case, because we have daily offsite backups, the application is not mission critical and we can tolerate some hours of downtime in the case of an hardware fault while replacing fallen pieces. Or there is something I'm missing? – Marco Marsala Dec 2 '15 at 13:01
  • Have you seen this error since replacing the cables, HDD and mobo? And I can't agree about not having RAID. Very few mobos and cases can't take a second drive, and HDDs are cheap enough that anything that isn't a laptop should have RAID, to my mind. – MadHatter Dec 2 '15 at 13:03
  • I have that server since a month only and I saw that error only one time before replacing parts. So I will know if the problem is solved only in the next months. The mobo supports a second disk but my hosting provider allow only 1 TB disk with this low cost plan (14€/ month), or two small 160GB SSD disks (with software raid). I need more space, and to have two bigger disks, they oblige me to choose an higher plan (from 59€/ month) – Marco Marsala Dec 2 '15 at 13:27
  • 1
    Hey, good call on the replacing - that's not an error you want to see twice. Also good call on the watching brief: as you say, it will take some time to have confidence that the error's gone. I just wanted to be sure that you had not yet seen the error recur, which I now am. I also accept your provider's insane; that might be a good reason to pick a different provider in future, because you've already wasted many months of €(59-14) in terms of wasted time dealing with this issue. – MadHatter Dec 2 '15 at 13:36

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.