100% iowait + drive faults in dmesg
- by w00t
Hi,
I have a server on which resides a fairly visited web app.
It has a raid1 of 2 HDDs, 64MB Buffer, 7200 RPM.
Today it started throwing out errors like:
kernel: ata2.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x6 frozen
kernel: ata2.00: cmd b0/d0:01:00:4f:c2/00:00:00:00:00/00 tag 0 pio 512 in
kernel: res 40/00:00:00:4f:c2/00:00:00:00:00/00 Emask 0x4 (timeout)
kernel: ata2.00: status: { DRDY }
kernel: ata2: hard resetting link
kernel: ata2: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
kernel: ata2.00: max_sectors limited to 256 for NCQ
kernel: ata2.00: max_sectors limited to 256 for NCQ
kernel: ata2.00: configured for UDMA/133
kernel: sd 1:0:0:0: timing out command, waited 7s
kernel: ata2: EH complete
kernel: SCSI device sda: 976773168 512-byte hdwr sectors (500108 MB)
kernel: sda: Write Protect is off
kernel: SCSI device sda: drive cache: write back
All day long it has been in load higher than 10-15.
I am monitoring it with atop and it gives some bizarre readings:
DSK | sda | busy 100% | read 2 | write 208 | KiB/r 16 | KiB/w 32 | MBr/s 0.00 | MBw/s 0.65 | avq 86.17 | avio 47.6 ms |
DSK | sdb | busy 1% | read 10 | write 117 | KiB/r 17 | KiB/w 5 | MBr/s 0.02 | MBw/s 0.07 | avq 4.86 | avio 1.04 ms |
I frankly don't understand why only sda is taking all the hit. I do have one process that is constantly writing with 1-2megs but what the hell.. 100% iowait?
