Re: [PATCH v3] mm: Proactive compaction

On Tue, 10 Mar 2020 15:25:39 -0700 Nitin Gupta [off-list ref] wrote:

For some applications we need to allocate almost all memory as
hugepages. However, on a running system, higher order allocations can
fail if the memory is fragmented. Linux kernel currently does on-demand
compaction as we request more hugepages but this style of compaction
incurs very high latency. Experiments with one-time full memory
compaction (followed by hugepage allocations) shows that kernel is able
to restore a highly fragmented memory state to a fairly compacted memory
state within <1 sec for a 32G system. Such data suggests that a more
proactive compaction can help us allocate a large fraction of memory as
hugepages keeping allocation latencies low.

hn, there was plenty of feedback for earlier versions, but then
everyone went quiet.  I guess it's time for a refresh and resend,
please.

With some code comments, please!  Is the code really so self-evident
that this:

+/* Compact all zones within a node according to proactiveness */

is the only thing which needs to be said about it?  How is the reader
to know what proactive compaction actually *is*?

What does extfrag_for_order() do and what does its return value mean?

Please document /sys/kernel/mm/compaction/proactiveness in the
appropriate place under Documentation/