FreeBSD 8.2-p5 and Perc6/i

[Davide D'Amico]

Hi all,
I've a couple of dell r410 servers (smtp1 and smtp2) in production with 
the same hw config:

# mfiutil show firmware
mfi0 Firmware Package Version: 6.3.0-0001
mfi0 Firmware Images:
Name  Version            Date         Time      Status
APP   1.22.12-0952       Jul 27 2010  16:44:00  active
BIOS  2.04.00                                   active
BCON  1.1-46-e_15-Rel    Mar  2 2008  14:06:08  active
CTLR  1.02-015B          Jan 27 2009  12:02:58  active
PCLI  01.00-023:#%00006  Nov 25 2008  17:21:50  active
BTBL  1.00.00.01-0011    Nov 27 2007  18:29:20  active
# mfiutil show volumes
mfi0 Volumes:
   Id     Size    Level   Stripe  State   Cache   Name
  mfid0 (  279G) RAID-1      64K OPTIMAL Enabled  <BASE>
# mfiutil show drives
mfi0 Physical Drives:
(  279G) ONLINE <SEAGATE ST3300657SS ES64 serial=3SJ2YR74> SAS 
enclosure 1, slot 0
(  279G) ONLINE <SEAGATE ST3300657SS ES64 serial=3SJ301ZH> SAS 
enclosure 1, slot 1
# mfiutil show volumes
mfi0 Volumes:
   Id     Size    Level   Stripe  State   Cache   Name
  mfid0 (  279G) RAID-1      64K OPTIMAL Enabled  <BASE>
# uname -a
FreeBSD smtp2 8.2-RELEASE-p6 FreeBSD 8.2-RELEASE-p6 #1: Mon Feb 27 
11:17:40 CET 2012     root at smtp2:/usr/obj/usr/src/sys/R410  amd64
#

smtp1 has no problem on its perc controller, but smtp2 sometimes (1 or 
2 times every day) freezes up and I find in user.log (I use syslog-ng):

Mar  2 22:29:59.056 smtp2 mfi0: COMMAND 0xffffff80009aa7f8 TIMEOUT 
AFTER 1784 SECONDS
Mar  2 22:30:29.056 smtp2 mfi0: COMMAND 0xffffff80009aa7f8 TIMEOUT 
AFTER 1814 SECONDS
Mar  2 22:30:59.056 smtp2 mfi0: COMMAND 0xffffff80009aa7f8 TIMEOUT 
AFTER 1844 SECONDS
Mar  2 22:31:29.056 smtp2 mfi0: COMMAND 0xffffff80009aa7f8 TIMEOUT 
AFTER 1874 SECONDS
Mar  2 22:31:59.056 smtp2 mfi0: COMMAND 0xffffff80009aa7f8 TIMEOUT 
AFTER 1904 SECONDS
Mar  2 22:32:29.056 smtp2 mfi0: COMMAND 0xffffff80009aa7f8 TIMEOUT 
AFTER 1934 SECONDS
Mar  2 22:32:59.056 smtp2 mfi0: COMMAND 0xffffff80009aa7f8 TIMEOUT 
AFTER 1964 SECONDS
Mar  2 22:33:29.056 smtp2 mfi0: COMMAND 0xffffff80009aa7f8 TIMEOUT 
AFTER 1994 SECONDS
Mar  2 22:33:59.056 smtp2 mfi0: COMMAND 0xffffff80009aa7f8 TIMEOUT 
AFTER 2024 SECONDS
Mar  2 22:34:29.056 smtp2 mfi0: COMMAND 0xffffff80009aa7f8 TIMEOUT 
AFTER 2054 SECONDS
Mar  2 22:34:59.056 smtp2 mfi0: COMMAND 0xffffff80009aa7f8 TIMEOUT 
AFTER 2084 SECONDS
Mar  2 22:35:29.056 smtp2 mfi0: COMMAND 0xffffff80009aa7f8 TIMEOUT 
AFTER 2114 SECONDS
Mar  2 22:35:59.056 smtp2 mfi0: COMMAND 0xffffff80009aa7f8 TIMEOUT 
AFTER 2144 SECONDS

During these periods, the server becomes unresponsive and this is bad.

smtp2 isn't very "load":

     1 users    Load  0.00  0.00  0.00                  Mar  3 09:57

Mem:KB    REAL            VIRTUAL                       VN PAGER   SWAP 
PAGER
         Tot   Share      Tot    Share    Free           in   out     in 
  out
Act  388136    6276  2322812     7796  14973k  count
All  522452    7448 1076201k    19580          pages
Proc:                                                            
Interrupts
   r   p   d   s   w   Csw  Trp  Sys  Int  Sof  Flt        cow   32010 
total
             147       467    3  203   10  167             zfod        
atkbd0 1
                                                           ozfod       
irq0:
  0.0%Sys   0.0%Intr  0.0%User  0.0%Nice  100%Idle        %ozfod       
stray irq0
|    |    |    |    |    |    |    |    |    |    |       daefr     1 
ehci0 19
                                                           prcfr       
uhci2 uhci
                                         10 dtbuf          totfr       
mfi0 irq38
Namei     Name-cache   Dir-cache    333647 desvn          react  2000 
cpu0: time
    Calls    hits   %    hits   %    130182 numvn          pdwak     9 
bce1 257
      155     155 100                 80196 frevn          pdpgs  2000 
cpu1: time
                                                           intrn  2000 
cpu9: time
Disks mfid0                                        891628 wire   2000 
cpu6: time
KB/t   0.00                                        339876 act    2000 
cpu8: time
tps       0                                         35168 inact  2000 
cpu5: time
MB/s   0.00                                          2420 cache  2000 
cpu14: tim
%busy     0                                      14970588 free   2000 
cpu7: time
                                                   1103136 buf    2000 
cpu11: tim
                                                                  2000 
cpu4: time
                                                                  2000 
cpu15: tim
                                                                  2000 
cpu2: time
                                                                  2000 
cpu10: tim
                                                                  2000 
cpu3: time
                                                                  2000 
cpu12: tim
                                                                  2000 
cpu13: tim

smtp2 hasn't any disk crunching cron job, daemon or service running.

Is it a hw problem on the controller or a compatibility problem? 
Upgrading to 9.0-RELEASE could solve this issue?

Thanks in advance,
d.