Page allocation failures were observed for Dell open manage services
Issue
- Page allocation failures were observed for Dell open manager services on
Dell EMC PowerEdge R6525, plugged in withBroadcom 25G Mezz NIC.(Note: Issue may occur on different combination in hardware specifications as well.) - Messages were noticed post two to three hours after stress is started in the VMs.
- Below is the snippet from
RHEL 8.3system:
Jan 5 04:29:59 localhost kernel: dsm_sa_datamgrd: page allocation failure: order:6, mode:0x6000c0(GFP_KERNEL), nodemask=(null),cpuset=/,mems_allowed=0-1
Jan 5 04:29:59 localhost kernel: CPU: 69 PID: 8110 Comm: dsm_sa_datamgrd Kdump: loaded Tainted: G --------- -t - 4.18.0-240.el8.x86_64 #1
Jan 5 04:29:59 localhost kernel: Hardware name: Dell Inc. PowerEdge R6525/, BIOS 1.7.3 10/05/2020
Jan 5 04:29:59 localhost kernel: Call Trace:
Jan 5 04:29:59 localhost kernel: dump_stack+0x5c/0x80
Jan 5 04:29:59 localhost kernel: warn_alloc.cold.118+0x7b/0x10d
Jan 5 04:29:59 localhost kernel: ? __alloc_pages_direct_compact+0x93/0x130
Jan 5 04:29:59 localhost kernel: __alloc_pages_slowpath+0xcfc/0xd40
Jan 5 04:29:59 localhost kernel: ? __switch_to_asm+0x35/0x70
Jan 5 04:29:59 localhost kernel: ? __switch_to_asm+0x35/0x70
Jan 5 04:29:59 localhost kernel: ? __switch_to_asm+0x41/0x70
Jan 5 04:29:59 localhost kernel: ? __switch_to_asm+0x41/0x70
Jan 5 04:29:59 localhost kernel: ? __switch_to_asm+0x35/0x70
Jan 5 04:29:59 localhost kernel: ? __switch_to_asm+0x41/0x70
Jan 5 04:29:59 localhost kernel: ? __switch_to_asm+0x41/0x70
Jan 5 04:29:59 localhost kernel: ? __switch_to_asm+0x35/0x70
Jan 5 04:29:59 localhost kernel: __alloc_pages_nodemask+0x245/0x280
Jan 5 04:29:59 localhost kernel: __dma_direct_alloc_pages+0x104/0x210
Jan 5 04:29:59 localhost kernel: dma_direct_alloc_pages+0x25/0xf0
Jan 5 04:29:59 localhost kernel: megasas_mgmt_fw_ioctl+0x256/0x800 [megaraid_sas]
Jan 5 04:29:59 localhost kernel: megasas_mgmt_ioctl_fw.isra.30+0x164/0x1d0 [megaraid_sas]
Jan 5 04:29:59 localhost kernel: megasas_mgmt_ioctl+0x24/0x40 [megaraid_sas]
Jan 5 04:29:59 localhost kernel: do_vfs_ioctl+0xa4/0x640
Jan 5 04:29:59 localhost kernel: ksys_ioctl+0x60/0x90
Jan 5 04:29:59 localhost kernel: __x64_sys_ioctl+0x16/0x20
Jan 5 04:29:59 localhost kernel: do_syscall_64+0x5b/0x1a0
Jan 5 04:29:59 localhost kernel: entry_SYSCALL_64_after_hwframe+0x65/0xca
Jan 5 04:29:59 localhost kernel: RIP: 0033:0x7fdda331688b
- Below messages were also noticed in
dmesgat the time of the issue :
[15017.815471] megaraid_sas 0000:01:00.0: Failed to alloc kernel SGL buffer for IOCTL
[15017.856149] megaraid_sas 0000:01:00.0: Failed to alloc kernel SGL buffer for IOCTL
Environment
- Red Hat Enterprise Linux 7
- Red Hat Enterprise Linux 8
- Dell Physical System having multiple virtual machines(KVM) running storage and network IO
Subscriber exclusive content
A Red Hat subscription provides unlimited access to our knowledgebase, tools, and much more.