Page allocation failures were observed for Dell open manage services

Solution In Progress - Updated -

Issue

  • Page allocation failures were observed for Dell open manager services on Dell EMC PowerEdge R6525, plugged in with Broadcom 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 8.3 system:
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 dmesg at 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.

Current Customers and Partners

Log in for full access

Log In

New to Red Hat?

Learn more about Red Hat subscriptions

Using a Red Hat product through a public cloud?

How to access this content