Joshua Baker-LePain wrote:
Can anyone summarize the current status of XFS and 4K stacks? There was
recently a thread[1] on the nahant (RHEL4) mailing list where it was
stated[2] that one reason for the exclusion of XFS in RHEL4 is the stack
size issue. I'd love to see XFS in Red Hat, although of course I have no
idea if they'd turn it on even if the stack size issues went away
tomorrow. I'm just wondering what the view of this is from the SGI side.
Thanks.
[1] https://www.redhat.com/archives/nahant-list/2005-June/msg00280.html
[2] https://www.redhat.com/archives/nahant-list/2005-June/msg00304.html
I have my suspicions that they could find another reason if this one was
not present - code is too complex, they have no expertise for support....
Ask them if they support NFS V4 on top of ext3 on top of multipathing on top
of network block device with a 4K stack under low memory conditions..... they
have all the component parts in their kernel.
Sorry about the attitude, but the whole fixed size stack and the continual
addition of layers of code is a little silly. Wait until iscsi initiators
make it into the picture, and throw in a crypto layer for good measure.
As for XFS and a 4K stack, I think it still boils down to a few edge cases,
I have not seen one in years, I am doing all my builds via nfs v3 with
tcp/ip to an XFS filesystem.
The only stack overflow I have seen recently has been attempting to get
device mapper multipath to work, I can make that overflow the stack just
trying to configure it.
Steve (who has an attitude problem this morning)
|