Messages in this thread | | | Subject | RE: [PATCH] reduce stack in cpqarray.c::ida_ioctl() | Date | Thu, 3 Apr 2003 15:35:07 -0600 | From | "Cameron, Steve" <> |
| |
> Well, my questions were along those lines, like: > . allocate a buffer per hba or per disk?
I don't think the number of concurrent ioctls apps might try to send is governed by number of hba's or number of disks (which are virtualized) or number of physical disks (which the driver doesn't know.) It's whatever the apps want to try to send down.
> . how much is ida_ioctl() [passthru] used?
Not much by most people, I expect. It's not in the main i/o path, definitely.
it's used by things like our online Array Config Utility (for configuring new volumes after adding new hardware such as hot plugging some disks into a storage box...)
Also used by Compaq Insight Manager agents for monitoring.
Flashing HBA firmware...
> . it's not on a normal(!?!) read path, is it?
no.
> if so, using kmalloc() that could fail would be a bad idea.
-- ~Randy - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |