Bug 1897815

Summary: [ppc64le] segfault happened. multipathd[77038]: unhandled signal 11 at 0000000000000000 nip 00007fff807f8148 lr 00007fff80820f70 code 1
Product: Red Hat Enterprise Linux 8 Reporter: Lin Li <lilin>
Component: device-mapper-multipathAssignee: Ben Marzinski <bmarzins>
Status: CLOSED ERRATA QA Contact: Lin Li <lilin>
Severity: high Docs Contact:
Priority: high    
Version: 8.4CC: agk, bmarzins, bugproxy, chetjain, hannsj_uhl, heinzm, iranna.ankad, jbrassow, msnitzer, prajnoha, zkabelac
Target Milestone: rcKeywords: Triaged
Target Release: 8.4Flags: pm-rhel: mirror+
Hardware: ppc64le   
OS: Linux   
Whiteboard:
Fixed In Version: device-mapper-multipath-0.8.4-6.el8 Doc Type: Bug Fix
Doc Text:
Cause: Multipath allowed multipaths section configurations that didn't include a WWID, and when printing the configuration, attempted to dereference the missing WWID Consequence: If multipaths sections with no WWID were included in /etc/multipath.conf, multipathd would crash when running the "show config local" command. Fix: Since a multipaths section without a WWID will never be used, multipath now ignores them. Result: Multipathd no longer crashes when running the show config local" command.
Story Points: ---
Clone Of: Environment:
Last Closed: 2021-05-18 15:06:46 UTC Type: Bug
Regression: --- Mount Type: ---
Documentation: --- CRM:
Verified Versions: Category: ---
oVirt Team: --- RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: --- Target Upstream Version:
Embargoed:
Bug Depends On:    
Bug Blocks: 1796871    

Description Lin Li 2020-11-14 19:10:06 UTC
Description of problem:
[ppc64le] "error -5 receiving packet" is getting reported while running "multipathd show config local"

Version-Release number of selected component (if applicable):
device-mapper-multipath-0.8.4-5.el8.ppc64le


How reproducible:
always

Steps to Reproduce:
1.[root@ibm-p9z-20-lp15 ~]# rpm -qa | grep multipath
device-mapper-multipath-libs-0.8.4-5.el8.ppc64le
device-mapper-multipath-0.8.4-5.el8.ppc64le

2,[root@ibm-p9z-20-lp15 ~]# multipathd show config local
defaults {
	verbosity 2
	polling_interval 5
	max_polling_interval 20
	reassign_maps "no"
	multipath_dir "/lib64/multipath"
	path_selector "service-time 0"
	path_grouping_policy "failover"
	uid_attribute "ID_SERIAL"
	prio "const"
	prio_args ""
	features "0"
	path_checker "tur"
	alias_prefix "mpath"
	failback "manual"
	rr_min_io 1000
	rr_min_io_rq 1
	max_fds "max"
	rr_weight "uniform"
	queue_without_daemon "no"
	flush_on_last_del "no"
	user_friendly_names "yes"
	fast_io_fail_tmo 5
	bindings_file "/etc/multipath/bindings"
	wwids_file "/etc/multipath/wwids"
	prkeys_file "/etc/multipath/prkeys"
	log_checker_err always
	all_tg_pt "no"
	retain_attached_hw_handler "yes"
	detect_prio "yes"
	detect_checker "yes"
	force_sync "no"
	strict_timing "no"
	deferred_remove "no"
	config_dir "/etc/multipath/conf.d"
	delay_watch_checks "no"
	delay_wait_checks "no"
	san_path_err_threshold "no"
	san_path_err_forget_rate "no"
	san_path_err_recovery_time "no"
	marginal_path_err_sample_time "no"
	marginal_path_err_rate_threshold "no"
	marginal_path_err_recheck_gap_time "no"
	marginal_path_double_failed_time "no"
	find_multipaths "smart"
	uxsock_timeout 4000
	retrigger_tries 3
	retrigger_delay 10
	missing_uev_wait_timeout 30
	skip_kpartx "no"
	disable_changed_wwids ignored
	remove_retries 0
	ghost_delay "no"
	find_multipaths_timeout -10
	enable_foreign ""
	marginal_pathgroups "no"
}
blacklist {
	devnode "!^(sd[a-z]|dasd[a-z]|nvme[0-9])"
	device {
		vendor "SGI"
		product "Universal Xport"
	}
	device {
		vendor "^DGC"
		product "LUNZ"
	}
	device {
		vendor "EMC"
		product "LUNZ"
	}
	device {
		vendor "DELL"
		product "Universal Xport"
	}
	device {
		vendor "IBM"
		product "Universal Xport"
	}
	device {
		vendor "IBM"
		product "S/390"
	}
	device {
		vendor "LENOVO"
		product "Universal Xport"
	}
	device {
		vendor "(NETAPP|LSI|ENGENIO)"
		product "Universal Xport"
	}
	device {
		vendor "STK"
		product "Universal Xport"
	}
	device {
		vendor "SUN"
		product "Universal Xport"
	}
	device {
		vendor "(Intel|INTEL)"
		product "VTrak V-LUN"
	}
	device {
		vendor "Promise"
		product "VTrak V-LUN"
	}
	device {
		vendor "Promise"
		product "Vess V-LUN"
	}
}
blacklist_exceptions {
}
devices {
	device {
		vendor "AIX"
		product "VDASD"
		path_grouping_policy "multibus"
		no_path_retry 60
	}
	device {
		vendor "^DGC"
		product "^(RAID|DISK|VRAID)"
		product_blacklist "LUNZ"
		path_grouping_policy "group_by_prio"
		path_checker "emc_clariion"
		hardware_handler "1 emc"
		prio "emc"
		failback "immediate"
		no_path_retry 60
	}
}
overrides {
}
multipaths {
	multipath {
		wwid "3600601605e203f008e22d0221f07eb11"
		# alias "mpatha"
	}
}



blacklist {
}

multipaths {
	multipath {
#		wwid 3600601605e203f008e22d0221f07eb11
		# alias "mpatha"
#		path_grouping_policy failover
	}
}


3.edit /etc/multipath.conf 
[root@ibm-p9z-20-lp15 ~]# cat /etc/multipath.conf 
defaults {
#	find_multipaths yes
	find_multipaths smart
	user_friendly_names yes
}


blacklist {
}

multipaths {
	multipath {
#		wwid 3600601605e203f008e22d0221f07eb11
		# alias "mpatha"
#		path_grouping_policy failover
	}
}

4.[root@ibm-p9z-20-lp15 ~]# service multipathd reload
Redirecting to /bin/systemctl reload multipathd.service

5,[root@ibm-p9z-20-lp15 ~]# multipathd show config local
error -5 receiving packet   <---------------------------------

6,[root@ibm-p9z-20-lp15 ~]# dmesg
[43777.894648] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[85754.079808] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[86124.403868] device-mapper: multipath: 253:0: Failing path 8:64.
[86349.466824] device-mapper: multipath: 253:0: Failing path 8:32.
[86429.649835] device-mapper: multipath: 253:0: Reinstating path 8:64.
[86429.649858] device-mapper: multipath: 253:0: Reinstating path 8:32.
[86434.490220] device-mapper: multipath: 253:0: Failing path 8:64.
[86434.490345] device-mapper: multipath: 253:0: Failing path 8:32.
[86448.331408] sd 1:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[86448.332638] sd 1:0:0:0: alua: port group 01 state A non-preferred supports tolUsNA
[86448.332819] sd 2:0:0:0: Asymmetric access state changed
[86448.351293] sd 2:0:0:0: alua: port group 01 state A non-preferred supports tolUsNA
[86449.601476] device-mapper: multipath: 253:0: Failing path 8:64.
[86449.601510] device-mapper: multipath: 253:0: Failing path 8:32.
[86449.621486] sd 1:0:0:0: alua: port group 01 state A non-preferred supports tolUsNA
[87174.811626] sd 1:0:1:0: Asymmetric access state changed
[87174.827678] sd 1:0:1:0: alua: port group 02 state N preferred supports tolUsNA
[87175.812971] device-mapper: multipath: 253:0: Reinstating path 8:64.
[87175.827756] sd 1:0:1:0: alua: port group 02 state N preferred supports tolUsNA
[87175.829838] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[87175.987654] device-mapper: multipath: 253:0: Failing path 8:32.
[87176.027711] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[87181.078300] device-mapper: multipath: 253:0: Failing path 8:32.
[87181.108448] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[87185.079431] sd 1:0:0:0: Asymmetric access state changed
[87185.099216] sd 1:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[87192.083034] sd 2:0:0:0: Asymmetric access state changed
[87192.100047] sd 2:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[87205.087235] sd 2:0:1:0: Asymmetric access state changed
[87205.101872] sd 2:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[87206.088908] device-mapper: multipath: 253:0: Reinstating path 8:32.
[87206.102090] sd 2:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[87347.772774] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[87538.178847] sd 1:0:0:0: Asymmetric access state changed
[87538.190558] sd 1:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[87543.181785] sd 2:0:0:0: Asymmetric access state changed
[87543.211398] sd 2:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[88198.354326] device-mapper: multipath: 253:0: Failing path 8:64.
[88268.307365] sd 2:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[88503.438820] device-mapper: multipath: 253:0: Failing path 8:32.
[88546.188097] sd 1:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[88546.189172] sd 1:0:0:0: alua: port group 01 state A non-preferred supports tolUsNA
[88564.455412] sd 2:0:0:0: Asymmetric access state changed
[88564.470559] sd 2:0:0:0: alua: port group 01 state A non-preferred supports tolUsNA
[88739.505812] device-mapper: multipath: 253:0: Failing path 8:48.
[88753.118183] sd 2:0:0:0: alua: port group 01 state A non-preferred supports tolUsNA
[88925.562271] device-mapper: multipath: 253:0: Failing path 8:16.
[89098.928348] INFO: task dd:73103 blocked for more than 120 seconds.
[89098.928357]       Not tainted 4.18.0-247.el8.ppc64le #1
[89098.928359] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[89098.928362] dd              D    0 73103  44566 0x00040080
[89098.928366] Call Trace:
[89098.928369] [c000000146457660] [c00000014436bc80] 0xc00000014436bc80 (unreliable)
[89098.928375] [c000000146457830] [c000000000020650] __switch_to+0x2e0/0x4f0
[89098.928378] [c000000146457890] [c000000000e4f834] __schedule+0x2d4/0x9b0
[89098.928382] [c000000146457960] [c000000000e4ff78] schedule+0x68/0x130
[89098.928385] [c000000146457990] [c000000000e5049c] io_schedule+0x5c/0x90
[89098.928388] [c0000001464579c0] [c000000000e50ca8] bit_wait_io+0x28/0x80
[89098.928391] [c0000001464579f0] [c000000000e51004] out_of_line_wait_on_bit+0x104/0x1b0
[89098.928395] [c000000146457a80] [c0000000005a8bf0] __block_write_begin_int+0x2e0/0x750
[89098.928399] [c000000146457b50] [c0000000005a90ec] block_write_begin+0x6c/0x160
[89098.928402] [c000000146457ba0] [c0000000005ab880] blkdev_write_begin+0x40/0x60
[89098.928406] [c000000146457bc0] [c0000000003edc80] generic_perform_write+0x100/0x2a0
[89098.928410] [c000000146457c60] [c0000000003f2184] __generic_file_write_iter+0x104/0x2b0
[89098.928413] [c000000146457cc0] [c0000000005ac658] blkdev_write_iter+0xb8/0x180
[89098.928417] [c000000146457d30] [c0000000005284e8] new_sync_write+0x148/0x1d0
[89098.928420] [c000000146457dd0] [c00000000052e350] sys_write+0x2c0/0x3a0
[89098.928424] [c000000146457e30] [c00000000000b408] system_call+0x5c/0x70
[89221.826303] INFO: task dd:73103 blocked for more than 120 seconds.
[89221.826312]       Not tainted 4.18.0-247.el8.ppc64le #1
[89221.826315] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[89221.826318] dd              D    0 73103  44566 0x00040082
[89221.826321] Call Trace:
[89221.826324] [c000000146457660] [c00000014436bc80] 0xc00000014436bc80 (unreliable)
[89221.826330] [c000000146457830] [c000000000020650] __switch_to+0x2e0/0x4f0
[89221.826334] [c000000146457890] [c000000000e4f834] __schedule+0x2d4/0x9b0
[89221.826337] [c000000146457960] [c000000000e4ff78] schedule+0x68/0x130
[89221.826341] [c000000146457990] [c000000000e5049c] io_schedule+0x5c/0x90
[89221.826344] [c0000001464579c0] [c000000000e50ca8] bit_wait_io+0x28/0x80
[89221.826347] [c0000001464579f0] [c000000000e51004] out_of_line_wait_on_bit+0x104/0x1b0
[89221.826352] [c000000146457a80] [c0000000005a8bf0] __block_write_begin_int+0x2e0/0x750
[89221.826355] [c000000146457b50] [c0000000005a90ec] block_write_begin+0x6c/0x160
[89221.826359] [c000000146457ba0] [c0000000005ab880] blkdev_write_begin+0x40/0x60
[89221.826363] [c000000146457bc0] [c0000000003edc80] generic_perform_write+0x100/0x2a0
[89221.826367] [c000000146457c60] [c0000000003f2184] __generic_file_write_iter+0x104/0x2b0
[89221.826370] [c000000146457cc0] [c0000000005ac658] blkdev_write_iter+0xb8/0x180
[89221.826374] [c000000146457d30] [c0000000005284e8] new_sync_write+0x148/0x1d0
[89221.826378] [c000000146457dd0] [c00000000052e350] sys_write+0x2c0/0x3a0
[89221.826382] [c000000146457e30] [c00000000000b408] system_call+0x5c/0x70
[89225.647980] blk_update_request: I/O error, dev dm-0, sector 1152 op 0x0:(READ) flags 0x0 phys_seg 1 prio class 0
[89225.647994] blk_update_request: I/O error, dev dm-0, sector 0 op 0x1:(WRITE) flags 0x100000 phys_seg 9 prio class 0
[89225.647999] Buffer I/O error on dev dm-0, logical block 0, lost async page write
[89225.648006] Buffer I/O error on dev dm-0, logical block 1, lost async page write
[89225.648009] Buffer I/O error on dev dm-0, logical block 2, lost async page write
[89225.648013] Buffer I/O error on dev dm-0, logical block 3, lost async page write
[89225.648016] Buffer I/O error on dev dm-0, logical block 4, lost async page write
[89225.648020] Buffer I/O error on dev dm-0, logical block 5, lost async page write
[89225.648023] Buffer I/O error on dev dm-0, logical block 6, lost async page write
[89225.648027] Buffer I/O error on dev dm-0, logical block 7, lost async page write
[89225.648030] Buffer I/O error on dev dm-0, logical block 8, lost async page write
[89318.677007] sd 1:0:1:0: Asymmetric access state changed
[89318.690765] sd 1:0:1:0: alua: port group 02 state N preferred supports tolUsNA
[89319.678547] device-mapper: multipath: 253:0: Reinstating path 8:64.
[89319.711023] sd 1:0:1:0: alua: port group 02 state N preferred supports tolUsNA
[89319.712106] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[89324.680086] sd 1:0:0:0: Asymmetric access state changed
[89324.691811] sd 1:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[89325.681743] device-mapper: multipath: 253:0: Reinstating path 8:48.
[89335.685261] sd 2:0:0:0: Asymmetric access state changed
[89335.703340] sd 2:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[89336.686532] device-mapper: multipath: 253:0: Reinstating path 8:16.
[89338.687357] sd 2:0:1:0: Asymmetric access state changed
[89338.703695] sd 2:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[89339.688595] device-mapper: multipath: 253:0: Reinstating path 8:32.
[89425.346405] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[89425.346549] sd 1:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[89425.347641] sd 1:0:0:0: alua: port group 01 state A non-preferred supports tolUsNA
[89425.347765] sd 1:0:1:0: Asymmetric access state changed
[89425.366557] sd 2:0:0:0: Asymmetric access state changed
[89425.376510] sd 1:0:1:0: alua: port group 02 state N preferred supports tolUsNA
[89425.386343] sd 2:0:0:0: alua: port group 01 state A non-preferred supports tolUsNA
[89425.387980] sd 2:0:1:0: Asymmetric access state changed
[89425.416501] sd 2:0:1:0: alua: port group 02 state N preferred supports tolUsNA
[89720.788614] device-mapper: multipath: 253:0: Failing path 8:32.
[89940.847053] device-mapper: multipath: 253:0: Failing path 8:16.
[91034.911516] device-mapper: multipath: 253:0: Failing path 8:16.
[91034.911554] device-mapper: multipath: 253:0: Failing path 8:32.
[91034.951613] sd 1:0:0:0: alua: port group 01 state A non-preferred supports tolUsNA
[91034.951696] sd 1:0:1:0: alua: port group 02 state N preferred supports tolUsNA
[91034.953025] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[91034.953522] sd 1:0:0:0: Asymmetric access state changed
[91034.971609] sd 1:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[91180.184737] sd 2:0:0:0: Asymmetric access state changed
[91180.204350] sd 2:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[91181.204581] device-mapper: multipath: 253:0: Reinstating path 8:16.
[91181.233121] sd 2:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[91181.234309] sd 2:0:0:0: alua: port group 01 state A non-preferred supports tolUsNA
[91185.205844] sd 1:0:0:0: Asymmetric access state changed
[91185.206916] sd 1:0:1:0: Asymmetric access state changed
[91185.233634] sd 1:0:0:0: alua: port group 01 state A non-preferred supports tolUsNA
[91185.233737] sd 1:0:1:0: alua: port group 02 state N preferred supports tolUsNA
[91190.211311] sd 2:0:1:0: Asymmetric access state changed
[91190.236149] sd 2:0:1:0: alua: port group 02 state N preferred supports tolUsNA
[91191.235781] device-mapper: multipath: 253:0: Reinstating path 8:32.
[91191.254644] sd 2:0:1:0: alua: port group 02 state N preferred supports tolUsNA
[91191.255827] sd 2:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[91196.237244] sd 2:0:0:0: Asymmetric access state changed
[91196.255324] sd 2:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[91197.625052] sd 1:0:0:0: Asymmetric access state changed
[91197.645521] sd 1:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[91197.649414] sd 1:0:1:0: Asymmetric access state changed
[91197.665243] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[91602.504518] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[91652.988479] multipathd[949]: unhandled signal 11 at 0000000000000000 nip 00007fffb58f8148 lr 00007fffb5920f70 code 1
[91698.003836] multipathd[74929]: unhandled signal 11 at 0000000000000000 nip 00007fff865c8148 lr 00007fff865f0f70 code 1
[91769.205724] multipathd[75033]: unhandled signal 11 at 0000000000000000 nip 00007fffa6148148 lr 00007fffa6170f70 code 1
[91769.248861] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[root@ibm-p9z-20-lp15 ~]# vim /var/log/messages 
[root@ibm-p9z-20-lp15 ~]# dmesg
[43777.894648] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[85754.079808] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[86124.403868] device-mapper: multipath: 253:0: Failing path 8:64.
[86349.466824] device-mapper: multipath: 253:0: Failing path 8:32.
[86429.649835] device-mapper: multipath: 253:0: Reinstating path 8:64.
[86429.649858] device-mapper: multipath: 253:0: Reinstating path 8:32.
[86434.490220] device-mapper: multipath: 253:0: Failing path 8:64.
[86434.490345] device-mapper: multipath: 253:0: Failing path 8:32.
[86448.331408] sd 1:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[86448.332638] sd 1:0:0:0: alua: port group 01 state A non-preferred supports tolUsNA
[86448.332819] sd 2:0:0:0: Asymmetric access state changed
[86448.351293] sd 2:0:0:0: alua: port group 01 state A non-preferred supports tolUsNA
[86449.601476] device-mapper: multipath: 253:0: Failing path 8:64.
[86449.601510] device-mapper: multipath: 253:0: Failing path 8:32.
[86449.621486] sd 1:0:0:0: alua: port group 01 state A non-preferred supports tolUsNA
[87174.811626] sd 1:0:1:0: Asymmetric access state changed
[87174.827678] sd 1:0:1:0: alua: port group 02 state N preferred supports tolUsNA
[87175.812971] device-mapper: multipath: 253:0: Reinstating path 8:64.
[87175.827756] sd 1:0:1:0: alua: port group 02 state N preferred supports tolUsNA
[87175.829838] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[87175.987654] device-mapper: multipath: 253:0: Failing path 8:32.
[87176.027711] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[87181.078300] device-mapper: multipath: 253:0: Failing path 8:32.
[87181.108448] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[87185.079431] sd 1:0:0:0: Asymmetric access state changed
[87185.099216] sd 1:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[87192.083034] sd 2:0:0:0: Asymmetric access state changed
[87192.100047] sd 2:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[87205.087235] sd 2:0:1:0: Asymmetric access state changed
[87205.101872] sd 2:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[87206.088908] device-mapper: multipath: 253:0: Reinstating path 8:32.
[87206.102090] sd 2:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[87347.772774] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[87538.178847] sd 1:0:0:0: Asymmetric access state changed
[87538.190558] sd 1:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[87543.181785] sd 2:0:0:0: Asymmetric access state changed
[87543.211398] sd 2:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[88198.354326] device-mapper: multipath: 253:0: Failing path 8:64.
[88268.307365] sd 2:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[88503.438820] device-mapper: multipath: 253:0: Failing path 8:32.
[88546.188097] sd 1:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[88546.189172] sd 1:0:0:0: alua: port group 01 state A non-preferred supports tolUsNA
[88564.455412] sd 2:0:0:0: Asymmetric access state changed
[88564.470559] sd 2:0:0:0: alua: port group 01 state A non-preferred supports tolUsNA
[88739.505812] device-mapper: multipath: 253:0: Failing path 8:48.
[88753.118183] sd 2:0:0:0: alua: port group 01 state A non-preferred supports tolUsNA
[88925.562271] device-mapper: multipath: 253:0: Failing path 8:16.
[89098.928348] INFO: task dd:73103 blocked for more than 120 seconds.
[89098.928357]       Not tainted 4.18.0-247.el8.ppc64le #1
[89098.928359] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[89098.928362] dd              D    0 73103  44566 0x00040080
[89098.928366] Call Trace:
[89098.928369] [c000000146457660] [c00000014436bc80] 0xc00000014436bc80 (unreliable)
[89098.928375] [c000000146457830] [c000000000020650] __switch_to+0x2e0/0x4f0
[89098.928378] [c000000146457890] [c000000000e4f834] __schedule+0x2d4/0x9b0
[89098.928382] [c000000146457960] [c000000000e4ff78] schedule+0x68/0x130
[89098.928385] [c000000146457990] [c000000000e5049c] io_schedule+0x5c/0x90
[89098.928388] [c0000001464579c0] [c000000000e50ca8] bit_wait_io+0x28/0x80
[89098.928391] [c0000001464579f0] [c000000000e51004] out_of_line_wait_on_bit+0x104/0x1b0
[89098.928395] [c000000146457a80] [c0000000005a8bf0] __block_write_begin_int+0x2e0/0x750
[89098.928399] [c000000146457b50] [c0000000005a90ec] block_write_begin+0x6c/0x160
[89098.928402] [c000000146457ba0] [c0000000005ab880] blkdev_write_begin+0x40/0x60
[89098.928406] [c000000146457bc0] [c0000000003edc80] generic_perform_write+0x100/0x2a0
[89098.928410] [c000000146457c60] [c0000000003f2184] __generic_file_write_iter+0x104/0x2b0
[89098.928413] [c000000146457cc0] [c0000000005ac658] blkdev_write_iter+0xb8/0x180
[89098.928417] [c000000146457d30] [c0000000005284e8] new_sync_write+0x148/0x1d0
[89098.928420] [c000000146457dd0] [c00000000052e350] sys_write+0x2c0/0x3a0
[89098.928424] [c000000146457e30] [c00000000000b408] system_call+0x5c/0x70
[89221.826303] INFO: task dd:73103 blocked for more than 120 seconds.
[89221.826312]       Not tainted 4.18.0-247.el8.ppc64le #1
[89221.826315] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[89221.826318] dd              D    0 73103  44566 0x00040082
[89221.826321] Call Trace:
[89221.826324] [c000000146457660] [c00000014436bc80] 0xc00000014436bc80 (unreliable)
[89221.826330] [c000000146457830] [c000000000020650] __switch_to+0x2e0/0x4f0
[89221.826334] [c000000146457890] [c000000000e4f834] __schedule+0x2d4/0x9b0
[89221.826337] [c000000146457960] [c000000000e4ff78] schedule+0x68/0x130
[89221.826341] [c000000146457990] [c000000000e5049c] io_schedule+0x5c/0x90
[89221.826344] [c0000001464579c0] [c000000000e50ca8] bit_wait_io+0x28/0x80
[89221.826347] [c0000001464579f0] [c000000000e51004] out_of_line_wait_on_bit+0x104/0x1b0
[89221.826352] [c000000146457a80] [c0000000005a8bf0] __block_write_begin_int+0x2e0/0x750
[89221.826355] [c000000146457b50] [c0000000005a90ec] block_write_begin+0x6c/0x160
[89221.826359] [c000000146457ba0] [c0000000005ab880] blkdev_write_begin+0x40/0x60
[89221.826363] [c000000146457bc0] [c0000000003edc80] generic_perform_write+0x100/0x2a0
[89221.826367] [c000000146457c60] [c0000000003f2184] __generic_file_write_iter+0x104/0x2b0
[89221.826370] [c000000146457cc0] [c0000000005ac658] blkdev_write_iter+0xb8/0x180
[89221.826374] [c000000146457d30] [c0000000005284e8] new_sync_write+0x148/0x1d0
[89221.826378] [c000000146457dd0] [c00000000052e350] sys_write+0x2c0/0x3a0
[89221.826382] [c000000146457e30] [c00000000000b408] system_call+0x5c/0x70
[89225.647980] blk_update_request: I/O error, dev dm-0, sector 1152 op 0x0:(READ) flags 0x0 phys_seg 1 prio class 0
[89225.647994] blk_update_request: I/O error, dev dm-0, sector 0 op 0x1:(WRITE) flags 0x100000 phys_seg 9 prio class 0
[89225.647999] Buffer I/O error on dev dm-0, logical block 0, lost async page write
[89225.648006] Buffer I/O error on dev dm-0, logical block 1, lost async page write
[89225.648009] Buffer I/O error on dev dm-0, logical block 2, lost async page write
[89225.648013] Buffer I/O error on dev dm-0, logical block 3, lost async page write
[89225.648016] Buffer I/O error on dev dm-0, logical block 4, lost async page write
[89225.648020] Buffer I/O error on dev dm-0, logical block 5, lost async page write
[89225.648023] Buffer I/O error on dev dm-0, logical block 6, lost async page write
[89225.648027] Buffer I/O error on dev dm-0, logical block 7, lost async page write
[89225.648030] Buffer I/O error on dev dm-0, logical block 8, lost async page write
[89318.677007] sd 1:0:1:0: Asymmetric access state changed
[89318.690765] sd 1:0:1:0: alua: port group 02 state N preferred supports tolUsNA
[89319.678547] device-mapper: multipath: 253:0: Reinstating path 8:64.
[89319.711023] sd 1:0:1:0: alua: port group 02 state N preferred supports tolUsNA
[89319.712106] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[89324.680086] sd 1:0:0:0: Asymmetric access state changed
[89324.691811] sd 1:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[89325.681743] device-mapper: multipath: 253:0: Reinstating path 8:48.
[89335.685261] sd 2:0:0:0: Asymmetric access state changed
[89335.703340] sd 2:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[89336.686532] device-mapper: multipath: 253:0: Reinstating path 8:16.
[89338.687357] sd 2:0:1:0: Asymmetric access state changed
[89338.703695] sd 2:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[89339.688595] device-mapper: multipath: 253:0: Reinstating path 8:32.
[89425.346405] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[89425.346549] sd 1:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[89425.347641] sd 1:0:0:0: alua: port group 01 state A non-preferred supports tolUsNA
[89425.347765] sd 1:0:1:0: Asymmetric access state changed
[89425.366557] sd 2:0:0:0: Asymmetric access state changed
[89425.376510] sd 1:0:1:0: alua: port group 02 state N preferred supports tolUsNA
[89425.386343] sd 2:0:0:0: alua: port group 01 state A non-preferred supports tolUsNA
[89425.387980] sd 2:0:1:0: Asymmetric access state changed
[89425.416501] sd 2:0:1:0: alua: port group 02 state N preferred supports tolUsNA
[89720.788614] device-mapper: multipath: 253:0: Failing path 8:32.
[89940.847053] device-mapper: multipath: 253:0: Failing path 8:16.
[91034.911516] device-mapper: multipath: 253:0: Failing path 8:16.
[91034.911554] device-mapper: multipath: 253:0: Failing path 8:32.
[91034.951613] sd 1:0:0:0: alua: port group 01 state A non-preferred supports tolUsNA
[91034.951696] sd 1:0:1:0: alua: port group 02 state N preferred supports tolUsNA
[91034.953025] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[91034.953522] sd 1:0:0:0: Asymmetric access state changed
[91034.971609] sd 1:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[91180.184737] sd 2:0:0:0: Asymmetric access state changed
[91180.204350] sd 2:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[91181.204581] device-mapper: multipath: 253:0: Reinstating path 8:16.
[91181.233121] sd 2:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[91181.234309] sd 2:0:0:0: alua: port group 01 state A non-preferred supports tolUsNA
[91185.205844] sd 1:0:0:0: Asymmetric access state changed
[91185.206916] sd 1:0:1:0: Asymmetric access state changed
[91185.233634] sd 1:0:0:0: alua: port group 01 state A non-preferred supports tolUsNA
[91185.233737] sd 1:0:1:0: alua: port group 02 state N preferred supports tolUsNA
[91190.211311] sd 2:0:1:0: Asymmetric access state changed
[91190.236149] sd 2:0:1:0: alua: port group 02 state N preferred supports tolUsNA
[91191.235781] device-mapper: multipath: 253:0: Reinstating path 8:32.
[91191.254644] sd 2:0:1:0: alua: port group 02 state N preferred supports tolUsNA
[91191.255827] sd 2:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[91196.237244] sd 2:0:0:0: Asymmetric access state changed
[91196.255324] sd 2:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[91197.625052] sd 1:0:0:0: Asymmetric access state changed
[91197.645521] sd 1:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[91197.649414] sd 1:0:1:0: Asymmetric access state changed
[91197.665243] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[91602.504518] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[91652.988479] multipathd[949]: unhandled signal 11 at 0000000000000000 nip 00007fffb58f8148 lr 00007fffb5920f70 code 1
[91698.003836] multipathd[74929]: unhandled signal 11 at 0000000000000000 nip 00007fff865c8148 lr 00007fff865f0f70 code 1
[91769.205724] multipathd[75033]: unhandled signal 11 at 0000000000000000 nip 00007fffa6148148 lr 00007fffa6170f70 code 1
[91769.248861] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[92369.076509] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[92594.409442] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[93050.296087] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[93158.431936] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[93183.245174] multipathd[75308]: unhandled signal 11 at 0000000000000000 nip 00007fffa83a8148 lr 00007fffa83d0f70 code 1
[93289.061270] multipathd[76077]: unhandled signal 11 at 0000000000000000 nip 00007fffacd08148 lr 00007fffacd30f70 code 1
[93299.852564] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[93509.790665] multipathd[76192]: unhandled signal 11 at 0000000000000000 nip 00007fffb45a8148 lr 00007fffb45d0f70 code 1
[93984.147103] multipathd[76553]: unhandled signal 11 at 0000000000000000 nip 00007fffb0df8148 lr 00007fffb0e20f70 code 1
[93984.202661] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[94084.707436] sd 1:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[94084.709016] sd 1:0:0:0: alua: port group 01 state A non-preferred supports tolUsNA
[94084.709177] sd 2:0:0:0: Asymmetric access state changed
[94084.727331] sd 2:0:0:0: alua: port group 01 state A non-preferred supports tolUsNA
[94085.297809] sd 1:0:1:0: Asymmetric access state changed
[94085.299389] sd 2:0:1:0: Asymmetric access state changed
[94085.327613] sd 1:0:1:0: alua: port group 02 state N preferred supports tolUsNA
[94085.367813] sd 1:0:1:0: alua: port group 02 state N preferred supports tolUsNA
[94085.368784] sd 2:0:1:0: Asymmetric access state changed
[94085.368971] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[94085.370441] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[94086.427664] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[94090.378883] sd 1:0:0:0: Asymmetric access state changed
[94090.398165] sd 1:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[94095.381254] sd 2:0:0:0: Asymmetric access state changed
[94095.399009] sd 2:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[94100.781568] multipathd[76622]: unhandled signal 11 at 0000000000000000 nip 00007fff85e48148 lr 00007fff85e70f70 code 1
[94321.512047] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[94354.316742] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[95031.505824] sd 1:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[95031.507429] sd 1:0:0:0: alua: port group 01 state A non-preferred supports tolUsNA
[95031.507583] sd 2:0:0:0: Asymmetric access state changed
[95031.535728] sd 2:0:0:0: alua: port group 01 state A non-preferred supports tolUsNA
[95031.816092] sd 1:0:1:0: Asymmetric access state changed
[95031.817717] sd 2:0:1:0: Asymmetric access state changed
[95031.846238] sd 1:0:1:0: alua: port group 02 state N preferred supports tolUsNA
[95031.865929] sd 1:0:1:0: alua: port group 02 state N preferred supports tolUsNA
[95031.867619] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[95031.867798] sd 2:0:1:0: Asymmetric access state changed
[95031.886045] sd 2:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[95032.956013] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[95036.907431] sd 1:0:0:0: Asymmetric access state changed
[95036.926760] sd 1:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[95038.166327] sd 2:0:0:0: Asymmetric access state changed
[95038.176948] sd 2:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[95321.248205] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[95327.569198] sd 1:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[95327.570392] sd 1:0:0:0: alua: port group 01 state A non-preferred supports tolUsNA
[95327.570546] sd 2:0:0:0: Asymmetric access state changed
[95327.589097] sd 2:0:0:0: alua: port group 01 state A non-preferred supports tolUsNA
[95328.279336] sd 1:0:1:0: Asymmetric access state changed
[95328.281062] sd 2:0:1:0: Asymmetric access state changed
[95328.309208] sd 1:0:1:0: alua: port group 02 state N preferred supports tolUsNA
[95328.359329] sd 1:0:1:0: alua: port group 02 state N preferred supports tolUsNA
[95328.360830] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[95328.361012] sd 2:0:1:0: Asymmetric access state changed
[95328.389238] sd 2:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[95329.409412] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
[95333.360576] sd 1:0:0:0: Asymmetric access state changed
[95333.390161] sd 1:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[95338.362986] sd 2:0:0:0: Asymmetric access state changed
[95338.391093] sd 2:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
[95354.519712] multipathd[77038]: unhandled signal 11 at 0000000000000000 nip 00007fff807f8148 lr 00007fff80820f70 code 1
[95374.466019] sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA



7,[root@ibm-p9z-20-lp15 ~]# tail -n 100 /var/log/messages 
Nov 14 13:53:25 ibm-p9z-20-lp15 multipathd[77037]: 8:48: reinstated
Nov 14 13:53:25 ibm-p9z-20-lp15 multipathd[77037]: mpatha: queue_if_no_path enabled
Nov 14 13:53:25 ibm-p9z-20-lp15 multipathd[77037]: mpatha: Recovered to normal mode
Nov 14 13:53:25 ibm-p9z-20-lp15 multipathd[77037]: mpatha: remaining active paths: 1
Nov 14 13:53:25 ibm-p9z-20-lp15 multipathd[77037]: mpatha: load table [0 16777216 multipath 1 queue_if_no_path 1 alua 2 2 service-time 0 2 1 8:48 1 8:16 1 service-time 0 2 1 8:64 1 8:32 1]
Nov 14 13:53:25 ibm-p9z-20-lp15 kernel: sd 1:0:1:0: Asymmetric access state changed
Nov 14 13:53:25 ibm-p9z-20-lp15 kernel: sd 2:0:1:0: Asymmetric access state changed
Nov 14 13:53:25 ibm-p9z-20-lp15 kernel: sd 1:0:1:0: alua: port group 02 state N preferred supports tolUsNA
Nov 14 13:53:25 ibm-p9z-20-lp15 kernel: sd 1:0:1:0: alua: port group 02 state N preferred supports tolUsNA
Nov 14 13:53:25 ibm-p9z-20-lp15 kernel: sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
Nov 14 13:53:25 ibm-p9z-20-lp15 kernel: sd 2:0:1:0: Asymmetric access state changed
Nov 14 13:53:25 ibm-p9z-20-lp15 kernel: sd 2:0:1:0: alua: port group 02 state A preferred supports tolUsNA
Nov 14 13:53:26 ibm-p9z-20-lp15 multipathd[77037]: mpatha: load table [0 16777216 multipath 1 queue_if_no_path 1 alua 2 1 service-time 0 2 1 8:64 1 8:32 1 service-time 0 2 1 8:48 1 8:16 1]
Nov 14 13:53:26 ibm-p9z-20-lp15 kernel: sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
Nov 14 13:53:30 ibm-p9z-20-lp15 kernel: sd 1:0:0:0: Asymmetric access state changed
Nov 14 13:53:30 ibm-p9z-20-lp15 kernel: sd 1:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
Nov 14 13:53:31 ibm-p9z-20-lp15 kernel: sd 2:0:0:0: Asymmetric access state changed
Nov 14 13:53:31 ibm-p9z-20-lp15 kernel: sd 2:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
Nov 14 13:56:42 ibm-p9z-20-lp15 multipathd[77037]: Multipath configuration updated.
Nov 14 13:56:42 ibm-p9z-20-lp15 multipathd[77037]: Reload multipathd for changes to take effect
Nov 14 13:58:14 ibm-p9z-20-lp15 systemd[1]: Reloading Device-Mapper Multipath Device Controller.
Nov 14 13:58:14 ibm-p9z-20-lp15 multipathd[77037]: reconfigure (operator)
Nov 14 13:58:14 ibm-p9z-20-lp15 multipathd[77850]: ok
Nov 14 13:58:14 ibm-p9z-20-lp15 systemd[1]: Reloaded Device-Mapper Multipath Device Controller.
Nov 14 13:58:14 ibm-p9z-20-lp15 multipathd[77037]: mpatha: setting up map with 4/4 path checkers pending
Nov 14 13:58:14 ibm-p9z-20-lp15 multipathd[77037]: mpatha: load table [0 16777216 multipath 1 queue_if_no_path 1 alua 2 1 service-time 0 2 1 8:48 1 8:16 1 service-time 0 2 1 8:64 1 8:32 1]
Nov 14 13:58:14 ibm-p9z-20-lp15 multipathd[77037]: mpatha: Entering recovery mode: max_retries=60
Nov 14 13:58:14 ibm-p9z-20-lp15 multipathd[77037]: mpatha: sdd - tur checker reports path is up
Nov 14 13:58:14 ibm-p9z-20-lp15 multipathd[77037]: 8:48: reinstated
Nov 14 13:58:14 ibm-p9z-20-lp15 multipathd[77037]: mpatha: queue_if_no_path enabled
Nov 14 13:58:14 ibm-p9z-20-lp15 multipathd[77037]: mpatha: Recovered to normal mode
Nov 14 13:58:14 ibm-p9z-20-lp15 multipathd[77037]: mpatha: remaining active paths: 1
Nov 14 13:58:14 ibm-p9z-20-lp15 multipathd[77037]: mpatha: sde - tur checker reports path is up
Nov 14 13:58:14 ibm-p9z-20-lp15 multipathd[77037]: 8:64: reinstated
Nov 14 13:58:14 ibm-p9z-20-lp15 multipathd[77037]: mpatha: remaining active paths: 2
Nov 14 13:58:14 ibm-p9z-20-lp15 multipathd[77037]: mpatha: switch to path group #2
Nov 14 13:58:14 ibm-p9z-20-lp15 multipathd[77037]: mpatha: sdb - tur checker reports path is up
Nov 14 13:58:14 ibm-p9z-20-lp15 multipathd[77037]: 8:16: reinstated
Nov 14 13:58:14 ibm-p9z-20-lp15 multipathd[77037]: mpatha: remaining active paths: 3
Nov 14 13:58:14 ibm-p9z-20-lp15 multipathd[77037]: mpatha: sdc - tur checker reports path is up
Nov 14 13:58:14 ibm-p9z-20-lp15 multipathd[77037]: 8:32: reinstated
Nov 14 13:58:14 ibm-p9z-20-lp15 multipathd[77037]: mpatha: remaining active paths: 4
Nov 14 13:58:15 ibm-p9z-20-lp15 kernel: sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
Nov 14 13:58:20 ibm-p9z-20-lp15 systemd[1]: Reloading Device-Mapper Multipath Device Controller.
Nov 14 13:58:21 ibm-p9z-20-lp15 multipathd[77037]: reconfigure (operator)
Nov 14 13:58:21 ibm-p9z-20-lp15 multipathd[77885]: ok
Nov 14 13:58:21 ibm-p9z-20-lp15 systemd[1]: Reloaded Device-Mapper Multipath Device Controller.
Nov 14 13:58:21 ibm-p9z-20-lp15 multipathd[77037]: mpatha: setting up map with 4/4 path checkers pending
Nov 14 13:58:21 ibm-p9z-20-lp15 multipathd[77037]: mpatha: load table [0 16777216 multipath 1 queue_if_no_path 1 alua 2 1 service-time 0 2 1 8:48 1 8:16 1 service-time 0 2 1 8:64 1 8:32 1]
Nov 14 13:58:21 ibm-p9z-20-lp15 multipathd[77037]: mpatha: Entering recovery mode: max_retries=60
Nov 14 13:58:21 ibm-p9z-20-lp15 kernel: sd 1:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
Nov 14 13:58:21 ibm-p9z-20-lp15 kernel: sd 1:0:0:0: alua: port group 01 state A non-preferred supports tolUsNA
Nov 14 13:58:21 ibm-p9z-20-lp15 kernel: sd 2:0:0:0: Asymmetric access state changed
Nov 14 13:58:21 ibm-p9z-20-lp15 kernel: sd 2:0:0:0: alua: port group 01 state A non-preferred supports tolUsNA
Nov 14 13:58:21 ibm-p9z-20-lp15 multipathd[77037]: mpatha: sdd - tur checker reports path is up
Nov 14 13:58:21 ibm-p9z-20-lp15 multipathd[77037]: 8:48: reinstated
Nov 14 13:58:21 ibm-p9z-20-lp15 multipathd[77037]: mpatha: queue_if_no_path enabled
Nov 14 13:58:21 ibm-p9z-20-lp15 multipathd[77037]: mpatha: Recovered to normal mode
Nov 14 13:58:21 ibm-p9z-20-lp15 multipathd[77037]: mpatha: remaining active paths: 1
Nov 14 13:58:22 ibm-p9z-20-lp15 multipathd[77037]: mpatha: load table [0 16777216 multipath 1 queue_if_no_path 1 alua 2 2 service-time 0 2 1 8:48 1 8:16 1 service-time 0 2 1 8:64 1 8:32 1]
Nov 14 13:58:22 ibm-p9z-20-lp15 kernel: sd 1:0:1:0: Asymmetric access state changed
Nov 14 13:58:22 ibm-p9z-20-lp15 kernel: sd 2:0:1:0: Asymmetric access state changed
Nov 14 13:58:22 ibm-p9z-20-lp15 kernel: sd 1:0:1:0: alua: port group 02 state N preferred supports tolUsNA
Nov 14 13:58:22 ibm-p9z-20-lp15 kernel: sd 1:0:1:0: alua: port group 02 state N preferred supports tolUsNA
Nov 14 13:58:22 ibm-p9z-20-lp15 kernel: sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
Nov 14 13:58:22 ibm-p9z-20-lp15 kernel: sd 2:0:1:0: Asymmetric access state changed
Nov 14 13:58:22 ibm-p9z-20-lp15 kernel: sd 2:0:1:0: alua: port group 02 state A preferred supports tolUsNA
Nov 14 13:58:23 ibm-p9z-20-lp15 multipathd[77037]: mpatha: load table [0 16777216 multipath 1 queue_if_no_path 1 alua 2 1 service-time 0 2 1 8:64 1 8:32 1 service-time 0 2 1 8:48 1 8:16 1]
Nov 14 13:58:23 ibm-p9z-20-lp15 kernel: sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
Nov 14 13:58:27 ibm-p9z-20-lp15 kernel: sd 1:0:0:0: Asymmetric access state changed
Nov 14 13:58:27 ibm-p9z-20-lp15 kernel: sd 1:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
Nov 14 13:58:32 ibm-p9z-20-lp15 kernel: sd 2:0:0:0: Asymmetric access state changed
Nov 14 13:58:32 ibm-p9z-20-lp15 kernel: sd 2:0:0:0: alua: port group 01 state N non-preferred supports tolUsNA
Nov 14 13:58:48 ibm-p9z-20-lp15 kernel: multipathd[77038]: unhandled signal 11 at 0000000000000000 nip 00007fff807f8148 lr 00007fff80820f70 code 1
Nov 14 13:58:48 ibm-p9z-20-lp15 systemd[1]: Started Process Core Dump (PID 77991/UID 0).
Nov 14 13:58:48 ibm-p9z-20-lp15 systemd[1]: multipathd.service: Main process exited, code=killed, status=11/SEGV
Nov 14 13:58:48 ibm-p9z-20-lp15 systemd[1]: multipathd.service: Failed with result 'signal'.
Nov 14 13:58:48 ibm-p9z-20-lp15 systemd-coredump[77992]: Process 77037 (multipathd) of user 0 dumped core.#012#012Stack trace of thread 77038:#012#0  0x00007fff807f8148 find_mp_by_wwid (libmultipath.so.0)#012#1  0x00007fff80820f70 snprint_config (libmultipath.so.0)#012#2  0x000000010f1043e8 show_config (multipathd)#012#3  0x000000010f105344 cli_list_config_local (multipathd)#012#4  0x000000010f10392c parse_cmd (multipathd)#012#5  0x000000010f0f8fd8 uxsock_trigger (multipathd)#012#6  0x000000010f101794 uxsock_listen (multipathd)#012#7  0x000000010f0fa67c uxlsnrloop (multipathd)#012#8  0x00007fff805d87c8 start_thread (libpthread.so.0)#012#9  0x00007fff801c0158 __clone (libc.so.6)
Nov 14 13:58:49 ibm-p9z-20-lp15 systemd[1]: systemd-coredump: Succeeded.
Nov 14 13:59:07 ibm-p9z-20-lp15 systemd[1]: Starting dnf makecache...
Nov 14 13:59:07 ibm-p9z-20-lp15 systemd[1]: Starting Device-Mapper Multipath Device Controller...
Nov 14 13:59:08 ibm-p9z-20-lp15 multipathd[78016]: --------start up--------
Nov 14 13:59:08 ibm-p9z-20-lp15 multipathd[78016]: read /etc/multipath.conf
Nov 14 13:59:08 ibm-p9z-20-lp15 multipathd[78016]: path checkers start up
Nov 14 13:59:08 ibm-p9z-20-lp15 systemd[1]: Started Device-Mapper Multipath Device Controller.
Nov 14 13:59:08 ibm-p9z-20-lp15 multipathd[78016]: mpatha: switch to path group #2
Nov 14 13:59:08 ibm-p9z-20-lp15 multipathd[78016]: mpatha: sde - tur checker reports path is up
Nov 14 13:59:08 ibm-p9z-20-lp15 multipathd[78016]: 8:64: reinstated
Nov 14 13:59:08 ibm-p9z-20-lp15 multipathd[78016]: mpatha: remaining active paths: 3
Nov 14 13:59:08 ibm-p9z-20-lp15 multipathd[78016]: mpatha: switch to path group #1
Nov 14 13:59:08 ibm-p9z-20-lp15 multipathd[78016]: mpatha: sdc - tur checker reports path is up
Nov 14 13:59:08 ibm-p9z-20-lp15 multipathd[78016]: 8:32: reinstated
Nov 14 13:59:08 ibm-p9z-20-lp15 multipathd[78016]: mpatha: remaining active paths: 4
Nov 14 13:59:08 ibm-p9z-20-lp15 kernel: sd 1:0:1:0: alua: port group 02 state A preferred supports tolUsNA
Nov 14 13:59:08 ibm-p9z-20-lp15 dnf[78010]: Updating Subscription Management repositories.
Nov 14 13:59:08 ibm-p9z-20-lp15 dnf[78010]: Unable to read consumer identity
Nov 14 13:59:08 ibm-p9z-20-lp15 dnf[78010]: This system is not registered to Red Hat Subscription Management. You can use subscription-manager to register.
Nov 14 13:59:08 ibm-p9z-20-lp15 dnf[78010]: Metadata cache refreshed recently.
Nov 14 13:59:08 ibm-p9z-20-lp15 systemd[1]: dnf-makecache.service: Succeeded.
Nov 14 13:59:08 ibm-p9z-20-lp15 systemd[1]: Started dnf makecache.



Actual results:
segfault happened. multipathd[77038]: unhandled signal 11 at 0000000000000000 nip 00007fff807f8148 lr 00007fff80820f70 code 1

Expected results:
No segfault

Additional info:
This is a IBM ppc64le server.
Vendor:DGC
Product:VRAID

[root@ibm-p9z-20-lp15 ~]# multipath -ll
mpatha (3600601605e203f008e22d0221f07eb11) dm-0 DGC,VRAID
size=8.0G features='1 queue_if_no_path' hwhandler='1 alua' wp=rw
|-+- policy='service-time 0' prio=50 status=active
| |- 1:0:1:0 sde 8:64 active ready running
| `- 2:0:1:0 sdc 8:32 active ready running
`-+- policy='service-time 0' prio=10 status=enabled
  |- 1:0:0:0 sdd 8:48 active ready running
  `- 2:0:0:0 sdb 8:16 active ready running

Comment 3 Ben Marzinski 2020-12-08 03:55:46 UTC
Fixed

Comment 6 Lin Li 2020-12-10 07:10:00 UTC
Verified on device-mapper-multipath-0.8.4-6.el8.ppc64le
1,[root@ibm-p9z-20-lp15 ~]# rpm -qa | grep multipath
device-mapper-multipath-libs-0.8.4-6.el8.ppc64le
device-mapper-multipath-0.8.4-6.el8.ppc64le

2,[root@ibm-p9z-20-lp15 ~]# multipathd show config local
defaults {
	verbosity 2
	polling_interval 5
	max_polling_interval 20
	reassign_maps "no"
	multipath_dir "/lib64/multipath"
	path_selector "service-time 0"
	path_grouping_policy "failover"
	uid_attribute "ID_SERIAL"
	prio "const"
	prio_args ""
	features "0"
	path_checker "tur"
	alias_prefix "mpath"
	failback "manual"
	rr_min_io 1000
	rr_min_io_rq 1
	max_fds "max"
	rr_weight "uniform"
	queue_without_daemon "no"
	flush_on_last_del "no"
	user_friendly_names "yes"
	fast_io_fail_tmo 5
	bindings_file "/etc/multipath/bindings"
	wwids_file "/etc/multipath/wwids"
	prkeys_file "/etc/multipath/prkeys"
	log_checker_err always
	all_tg_pt "no"
	retain_attached_hw_handler "yes"
	detect_prio "yes"
	detect_checker "yes"
	force_sync "no"
	strict_timing "no"
	deferred_remove "no"
	config_dir "/etc/multipath/conf.d"
	delay_watch_checks "no"
	delay_wait_checks "no"
	san_path_err_threshold "no"
	san_path_err_forget_rate "no"
	san_path_err_recovery_time "no"
	marginal_path_err_sample_time "no"
	marginal_path_err_rate_threshold "no"
	marginal_path_err_recheck_gap_time "no"
	marginal_path_double_failed_time "no"
	find_multipaths "smart"
	uxsock_timeout 4000
	retrigger_tries 3
	retrigger_delay 10
	missing_uev_wait_timeout 30
	skip_kpartx "no"
	disable_changed_wwids ignored
	remove_retries 0
	ghost_delay "no"
	find_multipaths_timeout -10
	enable_foreign ""
	marginal_pathgroups "no"
}
blacklist {
	devnode "!^(sd[a-z]|dasd[a-z]|nvme[0-9])"
	device {
		vendor "SGI"
		product "Universal Xport"
	}
	device {
		vendor "^DGC"
		product "LUNZ"
	}
	device {
		vendor "EMC"
		product "LUNZ"
	}
	device {
		vendor "DELL"
		product "Universal Xport"
	}
	device {
		vendor "IBM"
		product "Universal Xport"
	}
	device {
		vendor "IBM"
		product "S/390"
	}
	device {
		vendor "LENOVO"
		product "Universal Xport"
	}
	device {
		vendor "(NETAPP|LSI|ENGENIO)"
		product "Universal Xport"
	}
	device {
		vendor "STK"
		product "Universal Xport"
	}
	device {
		vendor "SUN"
		product "Universal Xport"
	}
	device {
		vendor "(Intel|INTEL)"
		product "VTrak V-LUN"
	}
	device {
		vendor "Promise"
		product "VTrak V-LUN"
	}
	device {
		vendor "Promise"
		product "Vess V-LUN"
	}
}
blacklist_exceptions {
}
devices {
	device {
		vendor "AIX"
		product "VDASD"
		path_grouping_policy "multibus"
		no_path_retry 60
	}
	device {
		vendor "^DGC"
		product "^(RAID|DISK|VRAID)"
		product_blacklist "LUNZ"
		path_grouping_policy "group_by_prio"
		path_checker "emc_clariion"
		hardware_handler "1 emc"
		prio "emc"
		failback "immediate"
		no_path_retry 60
	}
}
overrides {
}
multipaths {
	multipath {
		wwid "3600601605e203f008e22d0221f07eb11"
		# alias "mpatha"
	}
}



blacklist {
}

multipaths {
	multipath {
#		wwid 3600601605e203f008e22d0221f07eb11
		# alias "mpatha"
#		path_grouping_policy failover
	}
}


3.edit /etc/multipath.conf 
[root@ibm-p9z-20-lp15 ~]# cat /etc/multipath.conf 
defaults {
#	find_multipaths yes
	find_multipaths smart
	user_friendly_names yes
}


blacklist {
}

multipaths {
	multipath {
#		wwid 3600601605e203f008e22d0221f07eb11
		# alias "mpatha"
#		path_grouping_policy failover
	}
}

4.[root@ibm-p9z-20-lp15 ~]# service multipathd reload
Redirecting to /bin/systemctl reload multipathd.service

5,[root@ibm-p9z-20-lp15 ~]# multipathd show config local
Dec 10 02:03:40 | multipaths config section missing wwid     <----------------------------------------------
defaults {
	verbosity 2
	polling_interval 5
	max_polling_interval 20
	reassign_maps "no"
	multipath_dir "/lib64/multipath"
	path_selector "service-time 0"
	path_grouping_policy "failover"
	uid_attribute "ID_SERIAL"
	prio "const"
	prio_args ""
	features "0"
	path_checker "tur"
	alias_prefix "mpath"
	failback "manual"
	rr_min_io 1000
	rr_min_io_rq 1
	max_fds "max"
	rr_weight "uniform"
	queue_without_daemon "no"
	flush_on_last_del "no"
	user_friendly_names "yes"
	fast_io_fail_tmo 5
	bindings_file "/etc/multipath/bindings"
	wwids_file "/etc/multipath/wwids"
	prkeys_file "/etc/multipath/prkeys"
	log_checker_err always
	all_tg_pt "no"
	retain_attached_hw_handler "yes"
	detect_prio "yes"
	detect_checker "yes"
	force_sync "no"
	strict_timing "no"
	deferred_remove "no"
	config_dir "/etc/multipath/conf.d"
	delay_watch_checks "no"
	delay_wait_checks "no"
	san_path_err_threshold "no"
	san_path_err_forget_rate "no"
	san_path_err_recovery_time "no"
	marginal_path_err_sample_time "no"
	marginal_path_err_rate_threshold "no"
	marginal_path_err_recheck_gap_time "no"
	marginal_path_double_failed_time "no"
	find_multipaths "smart"
	uxsock_timeout 4000
	retrigger_tries 3
	retrigger_delay 10
	missing_uev_wait_timeout 30
	skip_kpartx "no"
	disable_changed_wwids ignored
	remove_retries 0
	ghost_delay "no"
	find_multipaths_timeout -10
	enable_foreign ""
	marginal_pathgroups "no"
}
blacklist {
	devnode "!^(sd[a-z]|dasd[a-z]|nvme[0-9])"
	device {
		vendor "SGI"
		product "Universal Xport"
	}
	device {
		vendor "^DGC"
		product "LUNZ"
	}
	device {
		vendor "EMC"
		product "LUNZ"
	}
	device {
		vendor "DELL"
		product "Universal Xport"
	}
	device {
		vendor "FUJITSU"
		product "Universal Xport"
	}
	device {
		vendor "IBM"
		product "Universal Xport"
	}
	device {
		vendor "IBM"
		product "S/390"
	}
	device {
		vendor "LENOVO"
		product "Universal Xport"
	}
	device {
		vendor "(NETAPP|LSI|ENGENIO)"
		product "Universal Xport"
	}
	device {
		vendor "STK"
		product "Universal Xport"
	}
	device {
		vendor "SUN"
		product "Universal Xport"
	}
	device {
		vendor "(Intel|INTEL)"
		product "VTrak V-LUN"
	}
	device {
		vendor "Promise"
		product "VTrak V-LUN"
	}
	device {
		vendor "Promise"
		product "Vess V-LUN"
	}
}
blacklist_exceptions {
}
devices {
	device {
		vendor "AIX"
		product "VDASD"
		path_grouping_policy "multibus"
		no_path_retry 60
	}
	device {
		vendor "^DGC"
		product "^(RAID|DISK|VRAID)"
		product_blacklist "LUNZ"
		path_grouping_policy "group_by_prio"
		path_checker "emc_clariion"
		hardware_handler "1 emc"
		prio "emc"
		failback "immediate"
		no_path_retry 60
	}
}
overrides {
}
multipaths {
	multipath {
		wwid "3600601605e203f008e22d0221f07eb11"
		# alias "mpatha"
	}
}



Test result: Multipathd no longer crashes when running the show config local" command.

Comment 8 errata-xmlrpc 2021-05-18 15:06:46 UTC
Since the problem described in this bug report should be
resolved in a recent advisory, it has been closed with a
resolution of ERRATA.

For information on the advisory (device-mapper-multipath bug fix and enhancement update), and where to find the updated
files, follow the link below.

If the solution does not work for you, open a new bug report.

https://access.redhat.com/errata/RHEA-2021:1685