----- Original Message -----
> From: "Kazunori INOUE" <inouek...@intellilink.co.jp>
> To: "pacemaker@oss" <pacemaker@oss.clusterlabs.org>
> Cc: shimaza...@intellilink.co.jp
> Sent: Monday, July 30, 2012 5:15:26 AM
> Subject: [Pacemaker] Among monitor of STONITH resource, monitor of other
> resources is not performed
>
> Hi,
>
> I am using Pacemaker-1.1.
> - glue (2012 Jul 16) 2719:18489f275f75
> - libqb (2012 Jul 19) 11b20e19beff7f1b6003be0b4c73da8ecf936442
> - corosync (2012 Jul 19) b9eb19e623d2b69c86cf78f1fa50a004c804ac20
> - pacemaker (2012 Jul 29) 33119da31c235710195c783e5c9a32c6e95b3efc
>
> The monitor operation of other resources is not performed during the
> monitor of STONITH resource.
Looking at the code I can see this is true. How important is it for the
stonith monitors to be able to be performed in parallel with the other resource
monitors? I would expect the stonith monitor interval to be quite large
compared to all the other monitors, meaning that it only executes once every
hour or so.
-- Vossel
> 1. service corosync start ; service pacemaker start
> 2. cibadmin -U -x test.xml
> (STONITH resource + Dummy resource are started on the same node)
> 3. After libvirt (STONITH resource) started, sleep was added to
> status()
> of libvirt.
>
> [root@dev1 external]# diff -u libvirt.ORG libvirt
> --- libvirt.ORG 2012-07-17 13:10:01.000000000 +0900
> +++ libvirt 2012-07-30 13:36:19.661431208 +0900
> @@ -221,6 +221,7 @@
> ;;
>
> status)
> + sleep 3600
> libvirt_check_config
> libvirt_status
> exit $?
>
> [root@dev1 ~]# ps -ef|egrep
> "UID|corosync|pacemaker|stonith|fence|sleep"
> UID PID PPID C STIME TTY TIME CMD
> root 18567 1 0 18:47 ? 00:00:02 corosync
> root 18585 1 0 18:47 ? 00:00:00 pacemakerd
> 496 18587 18585 0 18:47 ? 00:00:00 /usr/libexec/pacemaker/cib
> root 18588 18585 0 18:47 ? 00:00:00
> /usr/libexec/pacemaker/stonithd
> root 18589 18585 76 18:47 ? 00:05:27 /usr/libexec/pacemaker/lrmd
> 496 18590 18585 0 18:47 ? 00:00:00
> /usr/libexec/pacemaker/attrd
> 496 18591 18585 0 18:47 ? 00:00:00
> /usr/libexec/pacemaker/pengine
> 496 18592 18585 0 18:47 ? 00:00:00 /usr/libexec/pacemaker/crmd
> root 18767 18588 0 18:48 ? 00:00:00 /usr/bin/perl
> /usr/sbin/fence_legacy
> root 18768 18767 0 18:48 ? 00:00:00 stonith -t external/libvirt
> -E -S
> root 18778 18768 0 18:48 ? 00:00:00 /bin/sh
> /usr/lib64/stonith/plugins/external/libvirt status
> root 18792 18778 0 18:48 ? 00:00:00 sleep 3600
>
> 4. Then monitor of Dummy resource is not performed.
>
> The following is behavior of lrmd at that time.
>
> # gdb /usr/libexec/pacemaker/lrmd `pgrep lrmd`
> (gdb) bt
> #0 0x0000003f808e83e2 in recv () from /lib64/libc.so.6
> #1 0x00007f0de3820062 in qb_ipc_us_recv_at_most (one_way=0x1118ee8,
> msg=0x111f390,
> len=20480, timeout=500) at ipc_us.c:299
> #2 0x00007f0de381a28e in qb_ipcc_recv (c=0x1118ba0,
> msg_ptr=0x111f390, msg_len=
> 20480, ms_timeout=500) at ipcc.c:249
> #3 0x00007f0de42bc5fb in crm_ipc_send (client=0x111b580,
> message=0x111d860, reply=
> 0x7fffc8ec4c60, ms_timeout=61060000) at ipc.c:517
> #4 0x00007f0de3c97e29 in stonith_send_command (stonith=0x111a6c0,
> op=
> 0x7f0de3c998dd "st_execute", data=0x1119170, output_data=0x0,
> call_options=4096,
> timeout=61000) at st_client.c:1676
> #5 0x00007f0de3c94bd1 in stonith_api_call (stonith=0x111a6c0,
> call_options=4096,
> id=0x1129860 "f-2", action=0x7f0de3c998f7 "monitor", victim=0x0,
> timeout=61000,
> output=0x0) at st_client.c:951
> #6 0x00007f0de3c94d31 in stonith_api_monitor (stonith=0x111a6c0,
> call_options=4096,
> id=0x1129860 "f-2", timeout=61000) at st_client.c:985
> #7 0x00000000004044e2 in lrmd_rsc_execute_stonith (rsc=0x111f130,
> cmd=0x1129660) at
> lrmd.c:522
> #8 0x0000000000404cd6 in lrmd_rsc_execute (rsc=0x111f130) at
> lrmd.c:667
> #9 0x0000000000404d2d in lrmd_rsc_dispatch (user_data=0x111f130) at
> lrmd.c:678
> #10 0x00007f0de42dcd00 in crm_trigger_dispatch (source=0x111f300,
> callback=
> 0x404d06 <lrmd_rsc_dispatch>, userdata=0x111f300) at
> mainloop.c:105
> #11 0x0000003642638f0e in g_main_context_dispatch () from
> /lib64/libglib-2.0.so.0
> #12 0x000000364263c938 in ?? () from /lib64/libglib-2.0.so.0
> #13 0x000000364263cd55 in g_main_loop_run () from
> /lib64/libglib-2.0.so.0
> #14 0x0000000000402d3f in main (argc=1, argv=0x7fffc8ec5188) at
> main.c:285
> (gdb) fin
> Run till exit from #0 0x0000003f808e83e2 in recv () from
> /lib64/libc.so.6
> 0x00007f0de3820062 in qb_ipc_us_recv_at_most (one_way=0x1118ee8,
> msg=0x111f390,
> len=20480, timeout=500) at ipc_us.c:299
> 299 result = recv(one_way->u.us.sock, &data[processed],
> to_recv,
> (gdb) fin
> Run till exit from #0 0x00007f0de3820062 in qb_ipc_us_recv_at_most
> (one_way=
> 0x1118ee8, msg=0x111f390, len=20480, timeout=500) at ipc_us.c:299
> 0x00007f0de381a28e in qb_ipcc_recv (c=0x1118ba0, msg_ptr=0x111f390,
> msg_len=20480,
> ms_timeout=500) at ipcc.c:249
> 249 res = c->funcs.recv(&c->response, msg_ptr, msg_len,
> ms_timeout);
> Value returned is $1 = -11
> (gdb) fin
> Run till exit from #0 0x00007f0de381a28e in qb_ipcc_recv
> (c=0x1118ba0, msg_ptr=
> 0x111f390, msg_len=20480, ms_timeout=500) at ipcc.c:249
> 0x00007f0de42bc5fb in crm_ipc_send (client=0x111b580,
> message=0x111d860, reply=
> 0x7fffc8ec4c60, ms_timeout=61060000) at ipc.c:517
> 517 rc = qb_ipcc_recv(client->ipc, client->buffer,
> client->buf_size, 500);
> Value returned is $2 = -11
> (gdb) n
> 518 if(rc > 0 || crm_ipc_connected(client) == FALSE)
> {
> (gdb) p rc
> $3 = -11
> (gdb) n
> 522 } while(time(NULL) < timeout);
> (gdb) n
> 517 rc = qb_ipcc_recv(client->ipc, client->buffer,
> client->buf_size, 500);
> (gdb) n
> 518 if(rc > 0 || crm_ipc_connected(client) == FALSE)
> {
> (gdb) p rc
> $4 = -11
> (gdb) n
> 522 } while(time(NULL) < timeout);
> (gdb) n
> 517 rc = qb_ipcc_recv(client->ipc, client->buffer,
> client->buf_size, 500);
> (gdb) n
> 518 if(rc > 0 || crm_ipc_connected(client) == FALSE)
> {
> (gdb) p rc
> $5 = -11
> (gdb) n
> 522 } while(time(NULL) < timeout);
> (gdb) n
> 517 rc = qb_ipcc_recv(client->ipc, client->buffer,
> client->buf_size, 500);
> (gdb) n
> 518 if(rc > 0 || crm_ipc_connected(client) == FALSE)
> {
> (gdb) p rc
> $6 = -11
> (gdb)
>
> It seems that lrmd has repeated the reply reception from stonithd
> out of the g_main_loop. Therefore, monitor of Dummy is not performed.
>
> [root@dev1 ~]# top -bn1
> top - 18:53:31 up 5 days, 8:56, 4 users, load average: 0.98, 0.63,
> 0.44
> Tasks: 198 total, 2 running, 196 sleeping, 0 stopped, 0 zombie
> Cpu(s): 0.9%us, 1.2%sy, 0.0%ni, 97.9%id, 0.0%wa, 0.0%hi,
> 0.0%si, 0.0%st
> Mem: 5089052k total, 2417444k used, 2671608k free, 266660k
> buffers
> Swap: 1048568k total, 0k used, 1048568k free, 1724616k
> cached
>
> PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
> 18589 root 20 0 83932 3448 2548 R 98.2 0.1 4:15.89 lrmd
> 1 root 20 0 19348 1520 1212 S 0.0 0.0 0:00.78 init
> 2 root 20 0 0 0 0 S 0.0 0.0 0:00.00 kthreadd
> 3 root RT 0 0 0 0 S 0.0 0.0 0:06.93
> migration/0
> 4 root 20 0 0 0 0 S 0.0 0.0 15:23.59
> ksoftirqd/0
> 5 root RT 0 0 0 0 S 0.0 0.0 0:00.10
> migration/0
>
> Best Regards,
> Kazunori INOUE
>
> _______________________________________________
> Pacemaker mailing list: Pacemaker@oss.clusterlabs.org
> http://oss.clusterlabs.org/mailman/listinfo/pacemaker
>
> Project Home: http://www.clusterlabs.org
> Getting started:
> http://www.clusterlabs.org/doc/Cluster_from_Scratch.pdf
> Bugs: http://bugs.clusterlabs.org
>
_______________________________________________
Pacemaker mailing list: Pacemaker@oss.clusterlabs.org
http://oss.clusterlabs.org/mailman/listinfo/pacemaker
Project Home: http://www.clusterlabs.org
Getting started: http://www.clusterlabs.org/doc/Cluster_from_Scratch.pdf
Bugs: http://bugs.clusterlabs.org
