| commit | 608c1b0d56200a66e4e0a0f9902f0b5103683e60 | [log] [tgz] |
|---|---|---|
| author | Austin Clements <austin@google.com> | Thu Sep 24 14:39:27 2015 -0400 |
| committer | Austin Clements <austin@google.com> | Fri Oct 02 19:55:48 2015 +0000 |
| tree | b8d674f2b4b2e345f7cf1823393128bb8a2eef6f | |
| parent | fbd2660af3042217a4c831e9d4e24a4e97c296cb [diff] |
runtime: scan objects with finalizers concurrently
This reduces pause time by ~25% relative to tip and by ~50% relative
to Go 1.5.1.
Currently one of the steps of STW mark termination is to loop (in
parallel) over all spans to find objects with finalizers in order to
mark all objects reachable from these objects and to treat the
finalizer special as a root. Unfortunately, even if there are no
finalizers at all, this loop takes roughly 1 ms/heap GB/core, so
multi-gigabyte heaps can quickly push our STW time past 10ms.
Fix this by moving this scan from mark termination to concurrent scan,
where it can run in parallel with mutators. The loop itself could also
be optimized, but this cost is small compared to concurrent marking.
Making this scan concurrent introduces two complications:
1) The scan currently walks the specials list of each span without
locking it, which is safe only with the world stopped. We fix this by
speculatively checking if a span has any specials (the vast majority
won't) and then locking the specials list only if there are specials
to check.
2) An object can have a finalizer set after concurrent scan, in which
case it won't have been marked appropriately by concurrent scan. If
the finalizer is a closure and is only reachable from the special, it
could be swept before it is run. Likewise, if the object is not marked
yet when the finalizer is set and then becomes unreachable before it
is marked, other objects reachable only from it may be swept before
the finalizer function is run. We fix this issue by making
addfinalizer ensure the same marking invariants as markroot does.
For multi-gigabyte heaps, this reduces max pause time by 20%–30%
relative to tip (depending on GOMAXPROCS) and by ~50% relative to Go
1.5.1 (where this loop was neither concurrent nor parallel). Here are
the results for the garbage benchmark:
---------------- max pause ----------------
Heap Procs Concurrent scan STW parallel scan 1.5.1
24GB 12 18ms 23ms 37ms
24GB 4 18ms 25ms 37ms
4GB 4 3.8ms 4.9ms 6.9ms
In all cases, 95%ile pause time is similar to the max pause time. This
also improves mean STW time by 10%–30%.
Fixes #11485.
Change-Id: I9359d8c3d120a51d23d924b52bf853a1299b1dfd
Reviewed-on: https://go-review.googlesource.com/14982
Reviewed-by: Rick Hudson <rlh@golang.org>
Run-TryBot: Austin Clements <austin@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Go is an open source programming language that makes it easy to build simple, reliable, and efficient software.
For documentation about how to install and use Go, visit https://golang.org/ or load doc/install-source.html in your web browser.
Our canonical Git repository is located at https://go.googlesource.com/go. There is a mirror of the repository at https://github.com/golang/go.
Go is the work of hundreds of contributors. We appreciate your help!
To contribute, please read the contribution guidelines: https://golang.org/doc/contribute.html
Unless otherwise noted, the Go source files are distributed under the BSD-style license found in the LICENSE file.
If you have just untarred a binary Go distribution, you need to set the environment variable $GOROOT to the full path of the go directory (the one containing this file). You can omit the variable if you unpack it into /usr/local/go, or if you rebuild from sources by running all.bash (see doc/install-source.html). You should also add the Go binary directory $GOROOT/bin to your shell's path.
For example, if you extracted the tar file into $HOME/go, you might put the following in your .profile:
export GOROOT=$HOME/go export PATH=$PATH:$GOROOT/bin
See https://golang.org/doc/install or doc/install.html for more details.