X-MimeOLE: Produced By Microsoft Exchange V6.5
Received: by onstor-exch02.onstor.net 
	id <01C889EF.29252902@onstor-exch02.onstor.net>; Wed, 19 Mar 2008 11:29:26 -0700
MIME-Version: 1.0
Content-Type: text/plain;
	charset="us-ascii"
Content-Transfer-Encoding: quoted-printable
Content-class: urn:content-classes:message
Subject: RE: testing status for fb-jong-perf2
Date: Wed, 19 Mar 2008 11:29:25 -0700
Message-ID: <BB375AF679D4A34E9CA8DFA650E2B04E08F02D05@onstor-exch02.onstor.net>
In-Reply-To: <BB375AF679D4A34E9CA8DFA650E2B04E08F02C08@onstor-exch02.onstor.net>
X-MS-Has-Attach: 
X-MS-TNEF-Correlator: 
Thread-Topic: testing status for fb-jong-perf2
Thread-Index: AciJq+Edw+iS9l86QJSR6p3yOW1DqgAKws02AAK93sAAAzToUA==
References: <BB375AF679D4A34E9CA8DFA650E2B04E03B5B6FB@onstor-exch02.onstor.net> <BB375AF679D4A34E9CA8DFA650E2B04E08F02C08@onstor-exch02.onstor.net>
From: "Vikas Saini" <vikas.saini@onstor.com>
To: "Raj Kumar" <raj.kumar@onstor.com>,
	"Jonathan Goldick" <jonathan.goldick@onstor.com>,
	"dl-Cougar" <dl-Cougar@onstor.com>


Looks like we got 22799 with new build. G11r204 FP crashed. Below is the
GDB.=20

Filer info=20
G11r204 (10.2.204.11)
FP0 Crash so telnet 10.2.204.11 61234
from gdb "target pmon 10.2.204.11:61235"

Vikas



-bash-3.1$ /n/build-trees/gdb/gdb64 -nw Build/cg/dbg/Images/fp_cg
GNU gdb 5.1.1
Copyright 2002 Free Software Foundation, Inc.
GDB is free software, covered by the GNU General Public License, and you
are
welcome to change it and/or distribute copies of it under certain
conditions.
Type "show copying" to see the conditions.
There is absolutely no warranty for GDB.  Type "show warranty" for
details.
This GDB was configured as "--host=3Di686-pc-linux-gnu =
--target=3Dmips64"...
The target architecture is assumed to be mips:sb1
Breakpoint 1 at 0xffffffff83030d2c: file Panic.c, line 48.
(gdb) target pmon 10.2.204.11:61235
Remote MIPS debugging using 10.2.204.11:61235
0x832d9e98 in evm_qeltTransmitComplete (qEle=3D0x0) at evm-io.c:656
656       evm_ioQueue_t *queue =3D ((qEle->handle.parts.dataType =3D=3D
EVM_META_DATA_REQ)
(gdb) bt
#0  0x832d9e98 in evm_qeltTransmitComplete (qEle=3D0x0) at evm-io.c:656
#1  0x832da4bc in evm_transmitComplete (edesc=3D0x4003a08f00) at
evm-io.c:761
#2  0x8300ba5c in eee_freePacket (edesc=3D0x4003a08f00) at =
eee-desc.c:1385
#3  0x8349b9d4 in scsi_deallocDesc (sd=3D0x1003864dc8) at scsi.c:1298
#4  0x8348d854 in scsi_process_device_sd_rsp (pdev=3D0x1020028000,
sd=3D0x1003864dc8, ecode=3D0, ra=3D18446744071617098232)
    at scsi-msg.c:7206
#5  0x8348db48 in scsi_processDeviceRsp (pdev=3D0x1020028000,
sd=3D0x1003864dc8) at scsi-msg.c:7276
#6  0x8347b1f8 in scsi_llReceive (sd=3D0x1003864dc8) at scsi-ll.c:391
#7  0x8346dc70 in ispfc_dispose_of_scsi_desc (cb=3D0x1003a16000,
dev=3D0x101ffe5540, sd=3D0x1003864dc8, retry=3D0) at ispfc_scsi.c:302
#8  0x83459afc in ispfc_process_iocb_completions (cb=3D0x1003a16000,
response_throttle=3D16) at ispfc_iocb.c:1647
#9  0x83441a40 in ispfc_completion_handler (cb=3D0x1003a16000,
timer_ref=3D2) at ispfc.c:842
#10 0x8301748c in eee_poll (num_loops=3D14) at eee-poll.c:551
#11 0x8304ee24 in getchar () at serio-api.c:363
#12 0x83043608 in get_line (p=3D0xffffffff86522f08 "", usehist=3D1) at
hist.c:145
#13 0x83043d54 in get_input (p=3D0xffffffff86522f08 "") at hist.c:259
#14 0x83043d8c in get_cmd (p=3D0xffffffff86522f08 "") at hist.c:284
#15 0x8304d77c in runtime_prompt () at test.c:560
#16 0x8304d6a0 in _main () at test.c:543
(gdb)


-----Original Message-----
From: Raj Kumar=20
Sent: Wednesday, March 19, 2008 9:56 AM
To: Vikas Saini; Jonathan Goldick; dl-Cougar
Subject: RE: testing status for fb-jong-perf2

Update:

Backup works. Restore fails. In our ndmp trace I see the following. This
is also a possible DMA issue (very low probability). Lets see if vikas's
restore go through.

Message   : 0x300 (NDMP_TAPE_OPEN)
Timestamp : 1205945527
XSequence : 7
RSequence : 6
Error     : 0 (NDMP_NO_ERR)
        Error : 10 (NDMP_NO_TAPE_LOADED_ERR !!!)

-----Original Message-----
From: Vikas Saini=20
Sent: Wednesday, March 19, 2008 8:36 AM
To: Jonathan Goldick; dl-Cougar
Subject: RE: testing status for fb-jong-perf2

Jonathan,
   Raj and I will verify backup/restore.

Vikas


-----Original Message-----
From: Jonathan Goldick
Sent: Wed 3/19/2008 3:27 AM
To: dl-Cougar
Subject: testing status for fb-jong-perf2
=20
Tim and I have tested the new code drop reasonably well but we need
someone to run a real dump and restore test, preferably one that has
been failing to date.  Vikas, can you or someone you designate do this?

The code in this branch seems to have the I/O stall fixed.  I ran the
*_stress tests that were in the defect until I ran out of disk space so
I think we are good on that.  It would be nice if someone with more disk
space could try this out.  Sandrine, can you do this one for me?

I have made builds for all targets in=20
~jong/src/fb-jong-perf2/Build


Please copy files rather than booting off my directory via NFS, since I
want to be able to change things without impacting you.

Tim and I still run into the Cougar SCSI ASSERT on timers already being
stopped so that bug is still with us.

My branch has dev changelists up through 28399.  I will get it current
later today.


