Re: FIXED: mpt Serious performance issues

[buhrow%lothlorien.nfbcal.org@localhost (Brian Buhrow)]

        Hello.  Here's a silly thought.  Can't you determine whether a disk is
in a raid set by looking at the components in a logical volume and
subtracting them from the list of disks on the controller?  Then, only read
and reset the mode pages on those disks which don't appear in any logical
volumes on the controller?


-Brian
On Feb 9, 12:50pm, Stephan wrote:
} Subject: Re: FIXED: mpt Serious performance issues
} > Reset it to a known state.
} 
} Okay.
} 
} 
} > No, but it's just wrong to apply the modes computed for the
} > virtual disk, to a physical disk.
} 
} When the controller operates in RAID mode, is target page 0 still the
} disk page or the page for the RAID volume? I think that=B4s what Eduardo
} said. If it=B4s for the RAID set, should then the mode setting still be
} ignored?
} 
} 
} > for your configuration. I could immagine that not resetting the
} > mode pages could make it non-functionnal in some other
} > configs.
} 
} Maybe yes. But I wonder why I don=B4t see this behaviour in the OpenBSD
} and FreeBSD driver.
} 
} 
} > both x86 I guess, and both with the BIOS enabled.
} 
} Both x86. Did you mean the mainboard BIOS or the MPT BIOS?
} 
} 
} > for FC, tagged queuing should also work AFAIK.
} 
} The driver needs some love regarding FC and SAS. Looking at other
} drivers, special treatment for these devices is needed.
} 
} 
} Making the driver RAID aware, I successfully gathered different types
} of information from the controller. What i don=B4t see at the moment is
} how physical disks can be associated to RAID sets. That would be
} needed in order to determine the disks mode setting should be ignored
} for.
} 
} mpt0: DEBUG: Reading MPI_CONFIG_PAGETYPE_RAID_VOLUME 0 Header
} mpt0: DEBUG: Secussfully read MPI_CONFIG_PAGETYPE_RAID_VOLUME 0 Header
} mpt0: DEBUG: Reading scsi page 0
} mpt0: DEBUG: Successfully read raid page 0
} mpt0: DEBUG: Volume ID: 0
} mpt0: DEBUG: Write Cache: 1
} mpt0: DEBUG: AUTO_CONFIGURE: 4
} mpt0: DEBUG: PRIORITY_RESYNC: 0
} mpt0: DEBUG: USE_DEFAULTS: 0
} mpt0: DEBUG: ENABLED: 1
} mpt0: DEBUG: QUIESCED: 0
} mpt0: DEBUG: RESYNC: 0
} mpt0: DEBUG: OPTIMAL: 0 (This should be 1)
} mpt0: DEBUG: DEGRADED: 0
} mpt0: DEBUG: FAILED: 0
} mpt0: DEBUG: Reading MPI_CONFIG_PAGETYPE_IOC 2 Header
} mpt0: DEBUG: Secussfully read MPI_CONFIG_PAGETYPE_IOC 2 Header
} mpt0: DEBUG: Reading ioc page 2
} mpt0: DEBUG: Successfully read ioc page 2
} mpt0: DEBUG: Active Vols: 1
} mpt0: DEBUG: Max Vols: 1
} mpt0: DEBUG: Actice Phys Disks: 2
} mpt0: DEBUG: Max Phys Disks: 6
} mpt0: DEBUG: Volume 0: Type 2 (IM, RAID-1)
} mpt0: DEBUG: Volume 0: Page Number: 0
>-- End of excerpt from Stephan