2

Recently my system is showing high iowait after using it for 1-2 hour even if it stay idle in the mean time.

I have looked into /var/log/syslog and the content is as follows:

Jan  1 00:43:48 bolt kernel: [ 9091.210590] ata1.00: exception Emask 0x0 SAct 0x0 SErr 0x40000 action 0x6 frozen
Jan  1 00:43:48 bolt kernel: [ 9091.210604] ata1: SError: { CommWake }
Jan  1 00:43:48 bolt kernel: [ 9091.210610] ata1.00: failed command: FLUSH CACHE EXT
Jan  1 00:43:48 bolt kernel: [ 9091.210621] ata1.00: cmd ea/00:00:00:00:00/00:00:00:00:00/a0 tag 27
Jan  1 00:43:48 bolt kernel: [ 9091.210621]          res 40/00:ff:80:00:00/00:00:00:00:00/00 Emask 0x4 (timeout)
Jan  1 00:43:48 bolt kernel: [ 9091.210627] ata1.00: status: { DRDY }
Jan  1 00:43:48 bolt kernel: [ 9091.210635] ata1: hard resetting link
Jan  1 00:43:53 bolt kernel: [ 9096.571351] ata1: link is slow to respond, please be patient (ready=0)
Jan  1 00:43:58 bolt kernel: [ 9101.220139] ata1: COMRESET failed (errno=-16)
Jan  1 00:43:58 bolt kernel: [ 9101.220154] ata1: hard resetting link
Jan  1 00:44:03 bolt kernel: [ 9106.585077] ata1: link is slow to respond, please be patient (ready=0)
Jan  1 00:44:04 bolt kernel: [ 9107.145217] ata1: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
Jan  1 00:44:04 bolt kernel: [ 9107.195250] ata1.00: configured for UDMA/100
Jan  1 00:44:04 bolt kernel: [ 9107.195259] ata1.00: retrying FLUSH 0xea Emask 0x4
Jan  1 00:44:04 bolt kernel: [ 9107.195421] ata1: EH complete
Jan  1 00:44:17 bolt kernel: [ 9120.143473] ata1.00: exception Emask 0x0 SAct 0x0 SErr 0x50000 action 0x6 frozen
Jan  1 00:44:17 bolt kernel: [ 9120.143485] ata1: SError: { PHYRdyChg CommWake }
Jan  1 00:44:17 bolt kernel: [ 9120.143491] ata1.00: failed command: IDENTIFY DEVICE
Jan  1 00:44:17 bolt kernel: [ 9120.143500] ata1.00: cmd ec/00:01:00:00:00/00:00:00:00:00/00 tag 17 pio 512 in
Jan  1 00:44:17 bolt kernel: [ 9120.143500]          res 40/00:01:00:00:00/00:00:00:00:00/40 Emask 0x4 (timeout)
Jan  1 00:44:17 bolt kernel: [ 9120.143504] ata1.00: status: { DRDY }
Jan  1 00:44:17 bolt kernel: [ 9120.143512] ata1: hard resetting link
Jan  1 00:44:22 bolt kernel: [ 9125.504263] ata1: link is slow to respond, please be patient (ready=0)
Jan  1 00:44:26 bolt kernel: [ 9129.200981] ata1: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
Jan  1 00:44:26 bolt kernel: [ 9129.248292] ata1.00: configured for UDMA/100
Jan  1 00:44:26 bolt kernel: [ 9129.248459] ata1: EH complete
Jan  1 00:44:39 bolt kernel: [ 9142.131168] ata1.00: exception Emask 0x0 SAct 0x0 SErr 0x40000 action 0x6 frozen
Jan  1 00:44:39 bolt kernel: [ 9142.131181] ata1: SError: { CommWake }
Jan  1 00:44:39 bolt kernel: [ 9142.131187] ata1.00: failed command: CHECK POWER MODE
Jan  1 00:44:39 bolt kernel: [ 9142.131198] ata1.00: cmd e5/00:00:00:00:00/00:00:00:00:00/00 tag 3
Jan  1 00:44:39 bolt kernel: [ 9142.131198]          res 40/00:01:00:00:00/00:00:00:00:00/40 Emask 0x4 (timeout)
Jan  1 00:44:39 bolt kernel: [ 9142.131204] ata1.00: status: { DRDY }
Jan  1 00:44:39 bolt kernel: [ 9142.131213] ata1: hard resetting link
Jan  1 00:44:44 bolt kernel: [ 9147.495976] ata1: link is slow to respond, please be patient (ready=0)
Jan  1 00:44:48 bolt kernel: [ 9151.304687] ata1: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
Jan  1 00:44:48 bolt kernel: [ 9151.351255] ata1.00: configured for UDMA/100
Jan  1 00:44:48 bolt kernel: [ 9151.351413] ata1: EH complete
Jan  1 00:45:01 bolt CRON[7231]: (root) CMD (command -v debian-sa1 > /dev/null && debian-sa1 1 1)
Jan  1 00:47:16 bolt kernel: [ 9299.245699] ata1.00: NCQ disabled due to excessive errors
Jan  1 00:47:16 bolt kernel: [ 9299.245706] ata1.00: exception Emask 0x0 SAct 0x0 SErr 0x40000 action 0x6 frozen
Jan  1 00:47:16 bolt kernel: [ 9299.245711] ata1: SError: { CommWake }
Jan  1 00:47:16 bolt kernel: [ 9299.245714] ata1.00: failed command: FLUSH CACHE EXT
Jan  1 00:47:16 bolt kernel: [ 9299.245721] ata1.00: cmd ea/00:00:00:00:00/00:00:00:00:00/a0 tag 15
Jan  1 00:47:16 bolt kernel: [ 9299.245721]          res 40/00:ff:ff:00:00/00:00:00:00:00/00 Emask 0x4 (timeout)
Jan  1 00:47:16 bolt kernel: [ 9299.245724] ata1.00: status: { DRDY }
Jan  1 00:47:16 bolt kernel: [ 9299.245728] ata1: hard resetting link
Jan  1 00:47:21 bolt kernel: [ 9304.614593] ata1: link is slow to respond, please be patient (ready=0)
Jan  1 00:47:26 bolt kernel: [ 9309.263429] ata1: COMRESET failed (errno=-16)
Jan  1 00:47:26 bolt kernel: [ 9309.263445] ata1: hard resetting link
Jan  1 00:47:31 bolt kernel: [ 9314.624287] ata1: link is slow to respond, please be patient (ready=0)
Jan  1 00:47:32 bolt kernel: [ 9315.576458] ata1: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
Jan  1 00:47:32 bolt kernel: [ 9315.623445] ata1.00: configured for UDMA/100
Jan  1 00:47:32 bolt kernel: [ 9315.623455] ata1.00: retrying FLUSH 0xea Emask 0x4
Jan  1 00:47:32 bolt kernel: [ 9315.623629] ata1: EH complete

I have ran the S.M.A.R.T data and self-test with no failure. So, is my HDD working is fine ?

Are there problem with SATA cable ? How I can confirm without using any other hardware. Please suggest what else I can try or a solution.

I'm using Ubuntu 14.04 on Dell N4110

1
  • After so many years I'm experiencing the same problem (with a newer hardware and system - kernel 5.4.0-126...). Did you find the reason?
    – Hastur
    Sep 30, 2022 at 9:26

2 Answers 2

1

This could be a compatibility issue, but far more likely the hard drive is failing - S.M.A.R.T is not fullproof.

2
  • Why it's happening only after 1-2 hour ? Jan 1, 2016 at 11:12
  • It could be that there is thermal expansion, and it takes 1-2 hours for the disk to get hot. It may well be the case that even when the system is idle, the disk is still spinning.
    – davidgo
    Jan 1, 2016 at 20:16
1

I don't think it is possible to be absolutely sure what's wrong there just by looking at these logs which can be very misleading in this particular case. If this machine is local then just swap the SATA cable first. Yes, they break sometimes or become loose. You could also try connecting the drive to a different SATA port. Please also make sure about the power connector for this drive and replace the power cable as well making sure that it is fitted properly. There also could be a problem with your PSU but that's just a quick thought as i don't know much about your setup for now.

If above steps won't help we can always investigate more into it.

1

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .