[Liste-clx] FreeBSD / FreeNAS / IO

Olivier Duquesne (DaffyDuke) daffyduke at lautre.net
Ven 1 Juin 00:43:57 CEST 2018


Hello,

Mon NAS est hyper lent depuis quelques jours.
Des transferts de quelques kb/s confirmé par un iperf.
Je n'ai pas encore corrélé mon problème de débit avec cette erreur en terme
de timing :
Jun  1 00:18:42 freenas ahcich3: Timeout on slot 16 port 0
Jun  1 00:18:42 freenas ahcich3: is 00000000 cs 00030000 ss 00000000 rs
00030000 tfd d0 serr 00000000 cmd 0000f017
Jun  1 00:18:42 freenas (ada3:ahcich3:0:0:0): READ_DMA48. ACB: 25 00 a8 a1
bf 40 64 00 00 00 00 01
Jun  1 00:18:42 freenas (ada3:ahcich3:0:0:0): CAM status: Command timeout
Jun  1 00:18:42 freenas (ada3:ahcich3:0:0:0): Retrying command

Est-ce que les lenteurs ont commencé avec çà .... ?
Ca veut dire qu'un disque est en train de mourir non ?

Côté réseau, ma carte dit çà :
bge0: flags=8943<UP,BROADCAST,RUNNING,PROMISC,SIMPLEX,MULTICAST> metric 0
mtu 1500

options=c0099<RXCSUM,VLAN_MTU,VLAN_HWTAGGING,VLAN_HWCSUM,VLAN_HWTSO,LINKSTATE>
        ether 28:92:4a:2b:02:73
        inet 192.168.1.26 netmask 0xffffff00 broadcast 192.168.1.255
        nd6 options=9<PERFORMNUD,IFDISABLED>
        media: Ethernet autoselect (1000baseT <full-duplex,master>)
        status: active

Or ça, c'est un rsync --progress de backup en cours ....
      1,955,391   0%   39.91kB/s   32:39:08

32 heures pour un fichier de même pas 2 Go. Bon je suis pas pressé mais ....


Mon tests smart dit çà :

=== START OF INFORMATION SECTION ===
Model Family:     Toshiba 3.5" DT01ACA... Desktop HDD
Device Model:     TOSHIBA DT01ACA200
Serial Number:    Z2872MBAS
LU WWN Device Id: 5 000039 ff3c33873
Firmware Version: MX4OABB0
User Capacity:    2,000,398,934,016 bytes [2.00 TB]
Sector Sizes:     512 bytes logical, 4096 bytes physical
Rotation Rate:    7200 rpm
Form Factor:      3.5 inches
Device is:        In smartctl database [for details use: -P show]
ATA Version is:   ATA8-ACS T13/1699-D revision 4
SATA Version is:  SATA 3.0, 6.0 Gb/s (current: 3.0 Gb/s)
Local Time is:    Fri Jun  1 00:28:11 2018 CEST
SMART support is: Available - device has SMART capability.
SMART support is: Enabled
[....]
ID# ATTRIBUTE_NAME          FLAG     VALUE WORST THRESH TYPE      UPDATED
WHEN_FAILED RAW_VALUE
[....]
  5 Reallocated_Sector_Ct   0x0033   001   001   005    Pre-fail  Always
 FAILING_NOW 1996
[....]
Error 1284 occurred at disk power-on lifetime: 42413 hours (1767 days + 5
hours)
  When the command that caused the error occurred, the device was active or
idle.

  After command completion occurred, registers were:
  ER ST SC SN CL CH DH
  -- -- -- -- -- -- --
  40 51 58 c8 2d 80 06  Error: UNC at LBA = 0x06802dc8 = 109063624

  Commands leading to the command that caused the error were:
  CR FR SC SN CL CH DH DC   Powered_Up_Time  Command/Feature_Name
  -- -- -- -- -- -- -- --  ----------------  --------------------
  60 08 30 10 7b 95 40 00   3d+21:33:19.249  READ FPDMA QUEUED
  60 80 28 20 2e 80 40 00   3d+21:33:19.249  READ FPDMA QUEUED
  60 00 20 20 2d 80 40 00   3d+21:33:19.249  READ FPDMA QUEUED
  2f 00 01 10 00 00 00 00   3d+21:33:19.248  READ LOG EXT
  60 08 10 10 7b 95 40 00   3d+21:33:05.812  READ FPDMA QUEUED

Error 1283 occurred at disk power-on lifetime: 42413 hours (1767 days + 5
hours)
  When the command that caused the error occurred, the device was active or
idle.
[.....]
#18  Short offline       Completed without error       00%     13320
 -
#19  Short offline       Completed without error       00%     13296
 -
#20  Short offline       Completed without error       00%     13272
 -
#21  Short offline       Completed without error       00%     13248
 -

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.

Le temps d'un iostat "pour voir" => reboot : panic ?

2 questions :
- est-ce grave ?
- est-ce que ça peut dégrader à ce point les débit réseaux ?


-- 

Oliver Duquesne aka DaffyDuke
http://www.coincoin.fr.eu.org

Excusez les éventuelles erreurs, ce message
a été envoyé depuis un mobile.
-------------- section suivante --------------
Une pièce jointe HTML a été nettoyée...
URL: </pipermail/liste-clx/attachments/20180601/e8b8b004/attachment.html>


Plus d'informations sur la liste de diffusion Liste-clx