Bad news, issue remains:
BAD TRAP: type=e (#pf Page fault) rp=ff000fb16970 addr=2e occurred in
module "zfs" due to a NULL pointer dereference
sched:
#pf Page fault
Bad kernel fault at addr=0x2e
pid=0, pc=0xf7d4a1a5, sp=0xff000fb16a60, eflags=0x10246
cr0: 8005003b cr4: 6f8
cr2: 2
…tency
Reviewed by: Dan Kimmel
Reviewed by: John Kennedy
Work by Stephen Blinick.
Nightly performance runs typically consist of two levels of concurrency;
and both are fairly high.
Since the IO runs are to a ZFS filesystem, within a zpool, which is
based on some variable number of vdev's, the
removing the l2arc device indeed gets me a step further, I can no longer
produce crashes using send/receive.
But now I can reproduce a different error when trying to access a zvol (booting
a kvm machine):
panic[cpu3]/thread=ff003d40ec40:
Invalid dnode block MAC
ff003d40e370 zfs:zfs_nfs
On OsX I added a `cache device` to the crypt test, and I got:
```
panic(cpu 0 caller 0xff8027ec8132): Kernel trap at 0xff7fab62a0cc, type
14=page fault, registers:
0xff8087a43d60 : 0xff8027cfc200 mach_kernel : trap_from_kernel + 0x26
0xff8087a43d80 : 0xff7fab62a0cc net.lun
No crash over (I ran `cp -r /etc` though)
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/openzfs/openzfs/pull/489#issuecomment-367891692
--
openzfs-developer
Archive
