hastd fail and panic on MAXPHYS=1m

From: Daisuke Aoyama <jack_at_st.rim.or.jp>
Date: Fri, 8 May 2015 06:02:03 +0900
Hi all,

I have problem with MAXPHYS=1m. (I don't know MAXPHYS=1m works on HAST.)

I put "options MAXPHYS=(1024*1024)" in kernel config.
Then, update primary node to the kernel and world.
If the role back to primary on the machine, writing to the hast device cause an error and panic.

I didn't check carefully, but it seems that geom_gate.ko use MAXPHYS=1m and hastd use 
MAXPHYS=128k.
Of course, secondary is MAXPHYS=128k at this time.

Is it an expected result?

Here is a log while manually mounted test:
[DEBUG][2] [hast1] (primary) ggate_recv: (0x20c4b240) Request received from the kernel: 
READ(163840, 28672).
[DEBUG][2] [hast1] (primary) ggate_recv: (0x20c4b240) Moving request to the send queues.
[DEBUG][2] [hast1] (primary) ggate_recv: Taking free request.
[DEBUG][2] [hast1] (primary) ggate_recv: (0x20c4b1f0) 
Gotg_vfs_done():hast/hast1p1[WRITE(offset=174784512, length=393216)]error = 6
/mnt: got error 6 while accessing filesystem
/mnt: got error 6 while accessing filesystem
/mnt: got error 6 while accessing filesystem
/mnt: got error 6 while accessing filesystem
/mnt: got error 6 while accessing filesystem
/mnt: got error 6 while accessing filesystem
/mnt: got error 6 while accessing filesystem
/mnt: got error 6 while accessing filesystem
/mnt: got error 6 while accessing filesystem
/mnt: got error 6 while accessing filesystem
/mnt: got error 6 while accessing filesystem
/mnt: got error 6 while accessing filesystem
 free request.
[DEBUG][2] [hast1] (primary) ggate_recv: (0x20c4b1f0) Waiting for request from the kernel.
[DEBUG][2] [hast1] (primary) local_send: (0x20c4b240) Got request.
[DEBUG][2] [hast1] (primary) local_send: (0x20c4b240) Moving request to the done queue.
[DEBUG][2] [hast1] (primary) [DEBUG][2] [hast1] (primary) ggate_send: (0x20c4b240) Got request.
local_send: Taking request.
[DEBUG][2] [hast1] (primary) ggate_send: (0x20c4b240) Moving request to the free queue.
[DEBUG][2] [hast1] (primary) ggate_send: Taking request.
[ERROR] [hast1] (primary) G_GATE_CMD_START failed: Cannot allocate memory.
[DEBUG][1] Unable to receive event header: Socket is not connected.
softdep_deallocate_dependencies: got error 6 while accessing filesystem
/dev: got error 6 while accessing filesystem
panic: brelvp: Buffer 0xb33129d0 not on queue.
cpuid = 3
KDB: enter: panic

-- 
Daisuke Aoyama
 
Received on Thu May 07 2015 - 19:07:43 UTC

This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:40:57 UTC