From: Austin Clements <austin@google.com>
Date: Sun, 1 Nov 2020 22:48:42 +0000 (-0500)
Subject: runtime: default to MADV_DONTNEED on Linux
X-Git-Tag: go1.16beta1~354
X-Git-Url: http://www.git.cypherpunks.su/?a=commitdiff_plain;h=05e6d28849293266028c0bc9e9b0f8d0da38a2e2;p=gostls13.git

runtime: default to MADV_DONTNEED on Linux

In Go 1.12, we changed the runtime to use MADV_FREE when available on
Linux (falling back to MADV_DONTNEED) in CL 135395 to address issue
 #23687. While MADV_FREE is somewhat faster than MADV_DONTNEED, it
doesn't affect many of the statistics that MADV_DONTNEED does until
the memory is actually reclaimed under OS memory pressure. This
generally leads to poor user experience, like confusing stats in top
and other monitoring tools; and bad integration with management
systems that respond to memory usage.

We've seen numerous issues about this user experience, including
 #41818, #39295, #37585, #33376, and #30904, many questions on Go
mailing lists, and requests for mechanisms to change this behavior at
run-time, such as #40870. There are also issues that may be a result
of this, but root-causing it can be difficult, such as #41444 and
 #39174. And there's some evidence it may even be incompatible with
Android's process management in #37569.

This CL changes the default to prefer MADV_DONTNEED over MADV_FREE, to
favor user-friendliness and minimal surprise over performance. I think
it's become clear that Linux's implementation of MADV_FREE ultimately
doesn't meet our needs. We've also made many improvements to the
scavenger since Go 1.12. In particular, it is now far more prompt and
it is self-paced, so it will simply trickle memory back to the system
a little more slowly with this change. This can still be overridden by
setting GODEBUG=madvdontneed=0.

Fixes #42330 (meta-issue).

Fixes #41818, #39295, #37585, #33376, #30904 (many of which were
already closed as "working as intended").

Change-Id: Ib6aa7f2dc8419b32516cc5a5fc402faf576c92e4
Reviewed-on: https://go-review.googlesource.com/c/go/+/267100
Trust: Austin Clements <austin@google.com>
Reviewed-by: Michael Knyszek <mknyszek@google.com>
---

diff --git a/src/runtime/extern.go b/src/runtime/extern.go
index b75507b8f8..dacdf4f383 100644
--- a/src/runtime/extern.go
+++ b/src/runtime/extern.go
@@ -91,10 +91,10 @@ It is a comma-separated list of name=val pairs setting these named variables:
 		# bytes     memory allocated on the heap
 		# allocs    number of heap allocations
 
-	madvdontneed: setting madvdontneed=1 will use MADV_DONTNEED
-	instead of MADV_FREE on Linux when returning memory to the
-	kernel. This is less efficient, but causes RSS numbers to drop
-	more quickly.
+	madvdontneed: setting madvdontneed=0 will use MADV_FREE
+	instead of MADV_DONTNEED on Linux when returning memory to the
+	kernel. This is more efficient, but means RSS numbers will
+	drop only when the OS is under memory pressure.
 
 	memprofilerate: setting memprofilerate=X will update the value of runtime.MemProfileRate.
 	When set to 0 memory profiling is disabled.  Refer to the description of
diff --git a/src/runtime/runtime1.go b/src/runtime/runtime1.go
index 0f182ac58e..30b7044bff 100644
--- a/src/runtime/runtime1.go
+++ b/src/runtime/runtime1.go
@@ -352,6 +352,17 @@ func parsedebugvars() {
 	// defaults
 	debug.cgocheck = 1
 	debug.invalidptr = 1
+	if GOOS == "linux" {
+		// On Linux, MADV_FREE is faster than MADV_DONTNEED,
+		// but doesn't affect many of the statistics that
+		// MADV_DONTNEED does until the memory is actually
+		// reclaimed. This generally leads to poor user
+		// experience, like confusing stats in top and other
+		// monitoring tools; and bad integration with
+		// management systems that respond to memory usage.
+		// Hence, default to MADV_DONTNEED.
+		debug.madvdontneed = 1
+	}
 
 	for p := gogetenv("GODEBUG"); p != ""; {
 		field := ""