[LU-9072] Upstream lnet-selftest causing node to crash on load

• Type: Bug
• Resolution: Fixed
• Priority: Critical
• Fix Version/s: Upstream
• Affects Version/s: Upstream
• Severity: 3
• Assignee: Doug Oucharek (Inactive)
• Reporter: Doug Oucharek (Inactive)

Description

The upstream version of lnet-selftest is triggering a node crash when it is loaded.  We know that a kernel developer changed the definition of kiov in both LNet and lnet-selftest.  The crash may be related.  In one run, I saw this log before crashing:

LNet: 16216:0:(framework.c:1712:sfw_startup()) Failed to reserve enough buffers: service debug, 256 needed: -30720

This may be a "hint" we are running out of memory and thereby causing instability in the kernel. It may be the new kiov system is causing memory exhaustion especially when allocating per-CPT.