Error in Power path devices.

[skt_skt]

Red Hat Enterprise Linux Server release 5.1 (Tikanga)
2.6.18-53.1.14.el5 #1 SMP Tue Feb 19 07:18:46 EST 2008 x86_64 x86_64 x86_64 GNU/Linux

# powermt display
Symmetrix logical device count=12
CLARiiON logical device count=6
Hitachi logical device count=0
Invista logical device count=0
HP xp logical device count=0
Ess logical device count=0
HP HSx logical device count=0
==============================================================================
----- Host Bus Adapters --------- ------ I/O Paths ----- ------ Stats ------
### HW Path Summary Total Dead IO/Sec Q-IOs Errors
==============================================================================
3 qla2xxx optimal 24 0 - 0 443
4 qla2xxx optimal 24 0 - 0 0


Also i see the below statistics from the same HBA

"Commands retried with dropped frame(s) = 513"
======
QLogic PCI to Fibre Channel Host Adapter for QLA2460:
Firmware version 4.00.26 [IP] , Driver version 8.01.07.15
ISP: ISP2422
Request Queue = 0x449c00000, Response Queue = 0x44c4d0000
Request Queue count = 4096, Response Queue count = 512
Total number of active commands = 0
Total number of interrupts = 94270
Device queue depth = 0x20
Number of free request entries = 222
Number of mailbox timeouts = 0
Number of ISP aborts = 0
Number of loop resyncs = 0
Number of retries for empty slots = 0
Number of reqs in pending_q= 0, retry_q= 0, done_q= 0, scsi_retry_q= 0
Host adapter:loop state = , flags = 0x1a43
Dpc flags = 0x4000000
MBX flags = 0x0
Link down Timeout = 030
Port down retry = 030
Login retry count = 030
Commands retried with dropped frame(s) = 513
Product ID = 0000 0000 0000 0000
===

Also there are messages about LUN tress passing between primary and alternate paths

whats your openion ? Will it due to defective cable or HBA or ??

[Steven E. Protter]

Shalom,

I would favor an HBA over a cable. A badly seated cable could do this.

I also suspect the fabric switch in this instance.

SEP

[Andrew Cowan]

Santosh,

Have you tried removing one of the cables to cause a path failure to see if the failover etc. works as you expect? These tests could also point to which cable is giving you the problem.

The Powerpath manuals mention many scenarios that generate "trespass" errors and there could be some clues there.

[skt_skt]

the error is coming from one HBA.Being a PROD one we have scheuled a cable/GBIC test soon.