<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML><HEAD>
<META http-equiv=Content-Type content="text/html; charset=us-ascii">
<META content="MSHTML 6.00.2900.3059" name=GENERATOR></HEAD>
<BODY>
<DIV><SPAN class=112310706-10042007><FONT face=Arial size=2>I've been testing
SRP HA and dm_multipath with:</FONT></SPAN></DIV>
<DIV><SPAN class=112310706-10042007><FONT face=Arial size=2>- RHEL4 U3 x86_64,
Cisco FC Gateway, and Sun T4 RAID</FONT></SPAN></DIV>
<DIV><SPAN class=112310706-10042007><FONT face=Arial size=2>- RHEL4 U3 x86_64,
Cisco FC Gateway, and Sun 3510 RAID</FONT></SPAN></DIV>
<DIV><SPAN class=112310706-10042007><FONT face=Arial size=2>- SLES10 x86_64,
Cisco FC Gateway, and 3 JBODs</FONT></SPAN></DIV>
<DIV><SPAN class=112310706-10042007><FONT face=Arial
size=2></FONT></SPAN> </DIV>
<DIV><SPAN class=112310706-10042007><FONT face=Arial size=2>On RHEL4, I edited
/etc/multipath.conf, ran "chkconfig multipathd on", then rebooted. On SLES
10, I ran "chkconfig boot.multipath on" and "chkconfig multipathd on", then
rebooted. </FONT></SPAN><SPAN class=112310706-10042007><FONT face=Arial
size=2>Ishai, I don't seem to need 91-srp.rules, are you using the
boot.multipath and multipathd scripts?</FONT></SPAN></DIV>
<DIV><SPAN class=112310706-10042007><FONT face=Arial
size=2></FONT></SPAN> </DIV>
<DIV><SPAN class=112310706-10042007><FONT face=Arial size=2>On both RHEL4
networks, I get IB port load balancing and failover, on SLES10 I only see
failover. I'm not sure if this is a function of RHEL4-vs-SLES10, or RAID vs
JBOD.</FONT></SPAN></DIV>
<DIV><SPAN class=112310706-10042007><FONT face=Arial
size=2></FONT></SPAN> </DIV>
<DIV><SPAN class=112310706-10042007><FONT face=Arial size=2>Traffic failover is
very slow (a few minutes), what do others see?</FONT></SPAN></DIV>
<DIV><SPAN class=112310706-10042007><FONT face=Arial
size=2></FONT></SPAN> </DIV>
<DIV><SPAN class=112310706-10042007><FONT face=Arial size=2>I will be testing
DDN IB storage, EMC DMX, and RHEL5 soon.</FONT></SPAN></DIV>
<DIV><SPAN class=112310706-10042007><FONT face=Arial
size=2></FONT></SPAN> </DIV>
<DIV><SPAN class=112310706-10042007><FONT face=Arial size=2>I'm getting an Oops
on RHEL4 U3 x86_64 on both test networks:</FONT></SPAN></DIV>
<DIV><SPAN class=112310706-10042007><FONT face=Arial
size=2></FONT></SPAN> </DIV>
<DIV><SPAN class=112310706-10042007><FONT face=Arial size=2>scsi3 (0:0):
rejecting I/O to offline device<BR>scsi3 (0:0): rejecting I/O to offline
device<BR>scsi3 (0:0): rejecting I/O to offline device<BR>scsi3 (0:<4>NMI
Watchdog detected LOCKUP, CPU=1, registers:<BR>CPU 1<BR>Modules linked in:
parport_pc lp parport autofs4 i2c_dev i2c_core nfs lockd nfs_<BR>acl sunrpc
rdma_ucm(U) ib_srp(U) ib_sdp(U) rdma_cm(U) iw_cm(U) ib_addr(U)
ib_loc<BR>al_sa(U) ds yenta_socket pcmcia_core dm_mirror dm_round_robin
dm_multipath dm_mo<BR>d button battery ac ohci_hcd hw_random shpchp ib_mthca(U)
ib_ipoib(U) ib_umad(U)<BR> ib_ucm(U) ib_uverbs(U) ib_cm(U) ib_sa(U)
ib_mad(U) ib_core(U) md5 ipv6 tg3 flop<BR>py sg ext3 jbd mptscsih mptsas mptspi
mptfc mptscsi mptbase sd_mod scsi_mod<BR>Pid: 3990, comm: scsi_eh_3 Not tainted
2.6.9-34.ELsmp<BR>RIP: 0010:[<ffffffff802409bf>]
<ffffffff802409bf>{serial_in+83}<BR>RSP: 0018:000001007f203c10
EFLAGS: 00000002<BR>RAX: 00000000ffffff00 RBX: 0000000000000000 RCX:
0000000000000000<BR>RDX: 00000000000003fd RSI: 0000000000000005 RDI:
ffffffff804b59a0<BR>RBP: ffffffff804b59a0 R08: 000000000000003a R09:
0000000000000000<BR>R10: 0000000000000000 R11: 0000000000000000 R12:
0000000000002706<BR>R13: ffffffff8045afc5 R14: 0000000000000009 R15:
000000000000002d<BR>FS: 0000002a958a07a0(0000) GS:ffffffff804d7b80(0000)
knlGS:0000000000000000<BR>CS: 0010 DS: 0000 ES: 0000 CR0:
000000008005003b<BR>CR2: 00000036ce02e728 CR3: 00000000cff00000 CR4:
00000000000006e0<BR>Process scsi_eh_3 (pid: 3990, threadinfo 000001007f202000,
task 000001007f1957f0<BR>)<BR>Stack: ffffffff80242ab2 0000000d000402dc
ffffffff803f88e0 00000000000402dc<BR>
0000000000040309 0000000000000030 000001017bf79830
000000000000c000<BR> ffffffff8013764c
0000000000040309<BR>Call
Trace:<ffffffff80242ab2>{serial8250_console_write+113}
<ffffffff8013764c>{_<BR>_call_console_drivers+68}<BR>
<ffffffff801378b9>{release_console_sem+276}
<ffffffff80137b44>{vprintk+49<BR>8}<BR>
<ffffffff80137bee>{printk+141}
<ffffffff8013346f>{__wake_up+54}<BR>
<ffffffff802498bc>{freed_request+105}
<ffffffffa01e24e4>{:dm_multipath:mu<BR>ltipath_end_io+0}<BR>
<ffffffffa0007350>{:scsi_mod:scsi_prep_fn+120}
<ffffffff80247f53>{elv_nex<BR>t_request+68}<BR>
<ffffffffa00076c6>{:scsi_mod:scsi_request_fn+66}
<ffffffff8024a107>{blk_i<BR>nsert_request+160}<BR>
<ffffffffa0006d15>{:scsi_mod:scsi_requeue_command+48}<BR>
<ffffffffa000720f>{:scsi_mod:scsi_io_completion+866}<BR>
<ffffffffa00064c7>{:scsi_mod:scsi_error_handler+2809}<BR>
<ffffffff80110e17>{child_rip+8}
<ffffffffa00059ce>{:scsi_mod:scsi_error_h<BR>andler+0}<BR>
<ffffffff80110e0f>{child_rip+0}</FONT></SPAN></DIV>
<DIV> </DIV>
<DIV><SPAN class=112310706-10042007><FONT face=Arial size=2>Code: 0f b6 c0 c3 0f
b6 4f 22 0f b6 47 23 41 89 d0 d3 e6 83 f8 02<BR>Kernel panic - not syncing: nmi
watchdog<BR></FONT></SPAN></DIV>
<DIV> </DIV>
<DIV align=left><FONT face=Arial size=2>Scott Weitzenkamp</FONT></DIV>
<DIV align=left><FONT face=Arial size=2>SQA and Release Manager</FONT></DIV>
<DIV align=left><FONT face=Arial size=2>Server Virtualization Business
Unit</FONT></DIV>
<DIV align=left><FONT face=Arial size=2>Cisco Systems</FONT></DIV>
<DIV> </DIV></BODY></HTML>