You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
BugLink: https://bugs.launchpad.net/bugs/1879711
This option seems to introduce failures when resuming from hibernation
on Xen t2 instance types, especially those with a small amount of memory
(e.g., t2.nano and t2.small).
With this option enabled device drivers are allowed to use the
Contiguous Memory Allocator (CMA) for DMA operations. So, drivers can
allocate large physically-contiguous blocks of memory, instead of
relying on the I/O map or scatter-gather support.
However, on resume, the memory used by DMA needs to be re-initialized /
re-allocated, but it may fail to allocate large chunks of contiguous
memory due to the fact that we also need to restore the hibernation
image, using more memory and causing a system hang during the resume
process.
Such failures are more likely to happen in systems with a small amount
of memory (e.g., t2.nano and t2.small) that were showing a significant
higher rate of failures.
Make sure to disable this option for now on amd64 and re-align the
config and annotations file with the master kernel.
NOTE #1: this option has been disabled in the generic kernel because,
according to the associated bug link (LP: #1362261), it seemed to
introduce performance regressions on amd64, so there is no reason to do
differently in the aws kernel.
NOTE #2: this also disables the module 'etnaviv' (that is really not
needed in the aws kernel); update the modules list accordingly.
Signed-off-by: Andrea Righi <andrea.righi@canonical.com>
Acked-by: Stefan Bader <stefan.bader@canonical.com>
Acked-by: Kleber Souza <kleber.souza@canonical.com>
Signed-off-by: Khalid Elmously <khalid.elmously@canonical.com>
0 commit comments