[OmniOS-discuss] kernel panic "kernel heap corruption detected" when creating zero eager disks

[wuffers]

I recently created a pair of 25TB LUs for use in my VMware environment to
test out Veeam (and using that space for my repo - yes, yes, backups should
not reside in the same storage, but they will be exported to tape).

So while trying to create a 16TB drive in the vSphere fat client, I got the
value out of range error (
http://kb.vmware.com/selfservice/microsites/search.do?language=en_US&cmd=displayKC&externalId=2054952).
OKed the error, and task seemed to run anyways, but at some point my whole
SAN crashed during the creation of the drive.

As this was during business hours, I did not have time to wait on the dump,
but I was able to reproduce it later trying to create a 10TB drive (again
from the fat vSphere client, not web client) and capture the dump (which
takes 40 minutes.. grr).

Just an quick note on the environment: the VMware hosts are connected to
the head unit via IB and SRP. The largest LUs I had previously created for
VMware were 5TB in size, and largest drive created was 2TB.

fmdump info:

TIME                           UUID
SUNW-MSG-ID
Mar 20 2015 19:35:26.819716000 31ced65f-dca2-ee58-c882-a6daa6b94208
SUNOS-8000-KL

nvlist version: 0
        version = 0x0
        class = list.suspect
        uuid = 31ced65f-dca2-ee58-c882-a6daa6b94208
        code = SUNOS-8000-KL
        diag-time = 1426894526 787544
        de = fmd:///module/software-diagnosis
        fault-list-sz = 0x1
        fault-list = (array of embedded nvlists)
        (start fault-list[0])
        nvlist version: 0
                version = 0x0
                class = defect.sunos.kernel.panic
                certainty = 0x64
                asru =
sw:///:path=/var/crash/unknown/.31ced65f-dca2-ee58-c882-a6daa6b94208
                resource =
sw:///:path=/var/crash/unknown/.31ced65f-dca2-ee58-c882-a6daa6b94208
                savecore-succcess = 1
                dump-dir = /var/crash/unknown
                dump-files = vmdump.0
                os-instance-uuid = 31ced65f-dca2-ee58-c882-a6daa6b94208
                panicstr = kernel heap corruption detected
                panicstack = fffffffffba49114 () |
genunix:kmem_slab_free+c1 () | genunix:kmem_magazine_destroy+6e () |
genunix:kmem_cache_magazine_purge+f0 () |
genunix:kmem_cache_magazine_resize+40 () | genunix:taskq_thread+2d0 () |
unix:thread_start+8 () |
                crashtime = 1426891707
                panic-time = Fri Mar 20 18:48:27 2015 EDT
        (end fault-list[0])

        fault-status = 0x1
        severity = Major
        __ttl = 0x1
        __tod = 0x550caebe 0x30dbdfa0

Crash file:
https://drive.google.com/open?id=0B7mCJnZUzJPKOXl1S3IwYXh4NTg&authuser=0

I couldn't find any interesting comparative posts/reports. Would some kind
soul care to look at the dump and see what is happening here?

(And is this the right spot for a kernel panic report, or is it better to
go to the illumos list?)
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://omniosce.org/ml-archive/attachments/20150324/0842bce9/attachment.html>