Newer kernels allocate swap slots in batches to reduce the contention on swap info lock. This results in the max write values defined by swap ratio for fast and slow swap devices multiply by batch size. This causes the longer writes to one particular swap device failing the swap ratio feature. Change-Id: I9bb927b235fbf5b6f8b40bcdeb406ae6c48d9fb0 Signed-off-by: Vinayak Menon <vinmenon@codeaurora.org>tirimbino
parent
e41ce2b892
commit
4dfafa67ea
Loading…
Reference in new issue