Large amount of kmalloc-32 slab cache usage leading to OOM issue.

Solution Unverified - Updated -

Issue

  • Continuous growth of UN-reclaimable slab usage of kmalloc-32 object upon starting the cohesity application.

$ grep -A2 ^Sl proc/meminfo Slab: 18358632 kB SReclaimable: 669856 kB SUnreclaim: 17688776 kB $ cat proc/slabinfo |awk '{printf "%7i MiB : %s\n",$6*$(NF-1)/256,$1}'|sort -nk 1 -r|head -5 15881 MiB : kmalloc-32 487 MiB : kmalloc-4k 316 MiB : kmalloc-2k 203 MiB : ext4_inode_cache 149 MiB : mnt_cache
  • At the time of OOM event, the kmalloc-32 usage is very high and leading to OOM.
NAME                                TOTAL OBJSIZE
kmalloc-32                     84740940 K      32   <<<----

Environment

  • Red Hat Enterprise Linux 8.10
  • kmalloc-32
  • autofs

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