SUMMARY: iostat - 100 in %w

From: <przemolicc_at_poczta.fm>
Date: Fri Jun 11 2010 - 08:21:42 EDT
Hello,

thank you for all answers. General consensus is that
those drives are suspicious (in terms of hardware).
Because their behaviour influenced our workload very
much we managed to reboot this server to check if that helps.
It did:
                    extended device statistics
    r/s    w/s   kr/s   kw/s wait actv wsvc_t asvc_t  %w  %b device
   12.0  116.6   96.0  469.7  0.0  1.0    0.0    7.6   0  74 c1
    3.4   26.4   27.2  113.6  0.0  0.2    0.0    7.6   0  17 c1t4d0
    0.0    4.8    0.0    3.8  0.0  0.0    0.0    4.7   0   2 c1t0d0
    3.0   28.2   24.0  116.8  0.0  0.2    0.0    7.8   0  18 c1t5d0
    3.0   28.2   24.0  107.8  0.0  0.2    0.0    8.0   0  19 c1t1d0
    2.6   29.0   20.8  127.7  0.0  0.2    0.0    7.4   0  18 c1t2d0
   12.0  117.0   96.0  469.9  0.0  0.3    0.0    2.6   0  27 c2
    3.4   26.6   27.2  113.7  0.0  0.0    0.0    1.3   0   4 c2t12d0
    3.0   28.4   24.0  116.9  0.0  0.1    0.0    1.6   0   4 c2t13d0
    0.0    4.8    0.0    3.8  0.0  0.0    0.0    4.5   0   2 c2t8d0
    2.4   28.2   19.2  107.8  0.0  0.0    0.0    1.1   0   3 c2t9d0
    3.2   29.0   25.6  127.7  0.0  0.2    0.0    5.8   0  14 c2t10d0
    0.0    0.2    0.0    1.5  0.0  0.0    0.0    4.0   0   0 d0
    0.0    0.2    0.0    1.5  0.0  0.0    0.0   12.1   0   0 d1
    0.0    0.2    0.0    1.5  0.0  0.0   13.1   12.2   0   0 d2
   24.0  103.8  192.0  465.8  0.0  1.0    0.3    8.1   2  45 d8
   12.0  103.8   96.0  465.8  0.0  0.9    0.0    7.9   0  40 d9
   12.0  103.8   96.0  465.8  0.0  0.3    0.0    2.7   0  22 d10
    0.0    0.2    0.0    0.1  0.0  0.0    0.0   10.9   0   0 d11
    0.0    0.2    0.0    0.1  0.0  0.0    0.0    6.2   0   0 d12
    0.0    0.2    0.0    0.1  0.0  0.0    0.5   10.9   0   0 d14

however:

  ---- errors ---
  s/w h/w trn tot
    0   0   0   0 d0
    0   0   0   0 d1
    0   0   0   0 d2
    0   0   0   0 d3
    0   0   0   0 d4
    0   0   0   0 d5
    0   0   0   0 d8
    0   0   0   0 d9
    0   0   0   0 d10
    0   0   0   0 d11
    0   0   0   0 d12
    0   0   0   0 d14
    2   0   0   2 c0t6d0
    0   0   0   0 c2t12d0
    0   0   0   0 c2t4d0
    0   0   0   0 c1t13d0
    0   0   0   0 c1t12d0
    0   0   0   0 c1t4d0
    1   0   0   1 c2t13d0	<------
    0   0   0   0 c1t8d0
    0   0   0   0 c2t8d0
    0   0   0   0 c1t0d0
    0   0   0   0 c2t0d0
    0   0   0   0 c1t5d0
    0   0   0   0 c2t5d0
    0   0   0   0 c1t1d0
    0   0   0   0 c2t1d0
    0   0   0   0 c1t11d0
    0   0   0   0 c2t11d0
    0   0   0   0 c1t3d0
    0   0   0   0 c2t3d0
    0   0   0   0 c1t9d0
    0   0   0   0 c2t9d0
    0   0   0   0 c2t10d0
    0   0   0   0 c1t10d0
    0   0   0   0 c2t2d0
    0   0   0   0 c1t2d0
 
It seems that those drives will cause problems sooner or later.

Best regards
Przemek


----- Forwarded message from przemolicc@poczta.fm -----

From: przemolicc@poczta.fm
To: sunmanagers@sunmanagers.org
Subject: iostat - 100 in %w
Date: 09 Jun 2010 21:16:12 +0200

Hello,

we have Sparc server with internal FC disks mirrored and striped:
d8 -m d9 d10 1
d9 1 4 c1t1d0s0 c1t2d0s0 c1t4d0s0 c1t5d0s0 -i 32b -h hsp000
d10 1 4 c2t9d0s0 c2t10d0s0 c2t12d0s0 c2t13d0s0 -i 32b -h hsp000

While running 'iostat -xnzC 5' we get:

                    extended device statistics
    r/s    w/s   kr/s   kw/s wait actv wsvc_t asvc_t  %w  %b device
    5.2  105.2   41.6  134.0  0.0  0.5    0.0    4.6   0  48 c1
    1.4   22.8   11.2   32.0  0.0  0.1    0.0    5.5   0  12 c1t4d0
    1.0   29.8    8.0   35.0  0.0  0.1    0.0    3.5   0  10 c1t5d0
    1.4   22.8   11.2   32.0  0.0  0.1    0.0    5.4   0  12 c1t1d0
    1.4   29.8   11.2   35.0  0.0  0.1    0.0    4.5   0  13 c1t2d0
    5.2  104.4   41.6  133.6  2.0  0.2   18.3    1.8   1  19 c2
    1.0   22.8    8.0   32.0  1.0  0.0   42.0    0.9 100   2 c2t12d0
    0.6   29.4    4.8   34.8  1.0  0.0   33.3    0.5 100   2 c2t13d0
    1.2   22.8    9.6   32.0  0.0  0.0    0.0    0.8   0   2 c2t9d0
    2.4   29.4   19.2   34.8  0.0  0.1    0.0    4.4   0  14 c2t10d0
   10.4  102.8   83.2  134.0  0.0  0.6    0.0    5.1   0  34 d8
    5.2  102.8   41.6  134.0  0.0  0.5    0.0    4.7   0  30 d9
    5.2  102.0   41.6  133.6  0.0  0.2    0.0    1.9   0  17 d10

The interesting part is '100%' in %w column for disks: c2t12d0 and c2t13d0.
Could you explain why is that ?

Regards
Przemek














----------------------------------------------------------------------
Wakacyjna przygoda czeka! Zgarnij nagrody za 18 000zl!
Sprawdz >>> http://linkint.pl/f2721
_______________________________________________
sunmanagers mailing list
sunmanagers@sunmanagers.org
http://www.sunmanagers.org/mailman/listinfo/sunmanagers
Received on Fri Jun 11 08:23:04 2010

This archive was generated by hypermail 2.1.8 : Thu Mar 03 2016 - 06:44:16 EST