[Git][ghc/ghc][wip/gc/optimize] 36 commits: rts/GC: Add an obvious assertion during block initialization

Ben Gamari gitlab at gitlab.haskell.org
Wed Jun 19 18:28:04 UTC 2019



Ben Gamari pushed to branch wip/gc/optimize at Glasgow Haskell Compiler / GHC


Commits:
673a0e41 by Ömer Sinan Ağacan at 2019-06-19T18:17:47Z
rts/GC: Add an obvious assertion during block initialization

Namely ensure that block descriptors are initialized with valid
generation numbers.

Co-Authored-By: Ben Gamari <ben at well-typed.com>

- - - - -
1baa6967 by Ben Gamari at 2019-06-19T18:17:48Z
rts: Add Note explaining applicability of selector optimisation depth limit

This was slightly non-obvious so a note seems deserved.

- - - - -
4c866b4f by Ben Gamari at 2019-06-19T18:17:48Z
rts/Capability: A few documentation comments

- - - - -
d930ba9b by Ben Gamari at 2019-06-19T18:17:48Z
rts: Give stack flags proper macros

This were previously quite unclear and will change a bit under the
non-moving collector so let's clear this up now.

- - - - -
5f8f04b7 by Ben Gamari at 2019-06-19T18:17:48Z
rts/GC: Refactor gcCAFs

- - - - -
c8ee5c5f by Ben Gamari at 2019-06-19T18:17:48Z
rts: Fix macro parenthesisation

- - - - -
4f65be60 by Ben Gamari at 2019-06-19T18:17:48Z
rts: Fix CPP linter issues

- - - - -
ada2e65e by Ömer Sinan Ağacan at 2019-06-19T18:19:53Z
Disallow allocating megablocks, again

- - - - -
7f6f49e0 by Ömer Sinan Ağacan at 2019-06-19T18:20:02Z
Comments

- - - - -
64cf96a3 by Ben Gamari at 2019-06-19T18:20:36Z
Merge branches 'wip/gc/misc-rts' and 'wip/gc/aligned-block-allocation' into wip/gc/preparation

- - - - -
2413f243 by Ömer Sinan Ağacan at 2019-06-19T18:21:20Z
rts/StableName: Expose FOR_EACH_STABLE_NAME, freeSnEntry, SNT_size

These will be needed when we implement sweeping in the nonmoving
collector.

- - - - -
a5767c98 by Ben Gamari at 2019-06-19T18:21:20Z
rts: Disable aggregate-return warnings from gcc

This warning is a bit of a relic; there is little reason to avoid
aggregate return values in 2019.

- - - - -
17d23113 by Ömer Sinan Ağacan at 2019-06-19T18:21:21Z
rts/Scav: Expose scavenging functions

To keep the non-moving collector nicely separated from the moving
collector its scavenging phase will live in another file,
`NonMovingScav.c`. However, it will need to use these functions so
let's expose them.

- - - - -
437933b8 by Ben Gamari at 2019-06-19T18:21:21Z
rts: Introduce flag to enable the nonmoving old generation

This flag will enable the use of a non-moving oldest generation.

- - - - -
8d190c83 by Ben Gamari at 2019-06-19T18:21:21Z
rts: Introduce debug flag for non-moving GC

- - - - -
3f9bd459 by Ömer Sinan Ağacan at 2019-06-19T18:22:09Z
rts: Non-concurrent mark and sweep

This implements the core heap structure and a serial mark/sweep
collector which can be used to manage the oldest-generation heap.
This is the first step towards a concurrent mark-and-sweep collector
aimed at low-latency applications.

The full design of the collector implemented here is described in detail
in a technical note

    B. Gamari. "A Concurrent Garbage Collector For the Glasgow Haskell
    Compiler" (2018)

The basic heap structure used in this design is heavily inspired by

    K. Ueno & A. Ohori. "A fully concurrent garbage collector for
    functional programs on multicore processors." /ACM SIGPLAN Notices/
    Vol. 51. No. 9 (presented by ICFP 2016)

This design is intended to allow both marking and sweeping
concurrent to execution of a multi-core mutator. Unlike the Ueno design,
which requires no global synchronization pauses, the collector
introduced here requires a stop-the-world pause at the beginning and end
of the mark phase.

To avoid heap fragmentation, the allocator consists of a number of
fixed-size /sub-allocators/. Each of these sub-allocators allocators into
its own set of /segments/, themselves allocated from the block
allocator. Each segment is broken into a set of fixed-size allocation
blocks (which back allocations) in addition to a bitmap (used to track
the liveness of blocks) and some additional metadata (used also used
to track liveness).

This heap structure enables collection via mark-and-sweep, which can be
performed concurrently via a snapshot-at-the-beginning scheme (although
concurrent collection is not implemented in this patch).

The mark queue is a fairly straightforward chunked-array structure.
The representation is a bit more verbose than a typical mark queue to
accomodate a combination of two features:

 * a mark FIFO, which improves the locality of marking, reducing one of
   the major overheads seen in mark/sweep allocators (see [1] for
   details)

 * the selector optimization and indirection shortcutting, which
   requires that we track where we found each reference to an object
   in case we need to update the reference at a later point (e.g. when
   we find that it is an indirection). See Note [Origin references in
   the nonmoving collector] (in `NonMovingMark.h`) for details.

Beyond this the mark/sweep is fairly run-of-the-mill.

[1] R. Garner, S.M. Blackburn, D. Frampton. "Effective Prefetch for
    Mark-Sweep Garbage Collection." ISMM 2007.

Co-Authored-By: Ben Gamari <ben at well-typed.com>

- - - - -
439e50c3 by Ben Gamari at 2019-06-19T18:22:09Z
testsuite: Add nonmoving WAY

This simply runs the compile_and_run tests with `-xn`, enabling the
nonmoving oldest generation.

- - - - -
36e2d624 by Ben Gamari at 2019-06-19T18:23:11Z
rts: Implement concurrent collection in the nonmoving collector

This extends the non-moving collector to allow concurrent collection.

The full design of the collector implemented here is described in detail
in a technical note

    B. Gamari. "A Concurrent Garbage Collector For the Glasgow Haskell
    Compiler" (2018)

This extension involves the introduction of a capability-local
remembered set, known as the /update remembered set/, which tracks
objects which may no longer be visible to the collector due to mutation.
To maintain this remembered set we introduce a write barrier on
mutations which is enabled while a concurrent mark is underway.

The update remembered set representation is similar to that of the
nonmoving mark queue, being a chunked array of `MarkEntry`s. Each
`Capability` maintains a single accumulator chunk, which it flushed
when it (a) is filled, or (b) when the nonmoving collector enters its
post-mark synchronization phase.

While the write barrier touches a significant amount of code it is
conceptually straightforward: the mutator must ensure that the referee
of any pointer it overwrites is added to the update remembered set.
However, there are a few details:

 * In the case of objects with a dirty flag (e.g. `MVar`s) we can
   exploit the fact that only the *first* mutation requires a write
   barrier.

 * Weak references, as usual, complicate things. In particular, we must
   ensure that the referee of a weak object is marked if dereferenced by
   the mutator. For this we (unfortunately) must introduce a read
   barrier, as described in Note [Concurrent read barrier on deRefWeak#]
   (in `NonMovingMark.c`).

 * Stable names are also a bit tricky as described in Note [Sweeping
   stable names in the concurrent collector] (`NonMovingSweep.c`).

We take quite some pains to ensure that the high thread count often seen
in parallel Haskell applications doesn't affect pause times. To this end
we allow thread stacks to be marked either by the thread itself (when it
is executed or stack-underflows) or the concurrent mark thread (if the
thread owning the stack is never scheduled). There is a non-trivial
handshake to ensure that this happens without racing which is described
in Note [StgStack dirtiness flags and concurrent marking].

Co-Authored-by: Ömer Sinan Ağacan <omer at well-typed.com>

- - - - -
45297273 by Ben Gamari at 2019-06-19T18:23:14Z
Nonmoving: Disable memory inventory with concurrent collection

- - - - -
e6294bc1 by Ben Gamari at 2019-06-19T18:24:39Z
Nonmoving: Allow aging and refactor static objects logic

This commit does two things:

 * Allow aging of objects during the preparatory minor GC
 * Refactor handling of static objects to avoid the use of a hashtable

- - - - -
43aa973c by Ben Gamari at 2019-06-19T18:24:39Z
Disable aging when doing deadlock detection GC

- - - - -
9327c542 by Ben Gamari at 2019-06-19T18:24:39Z
More comments for aging

- - - - -
f0ee73d5 by Ben Gamari at 2019-06-19T18:25:06Z
NonMoving: Eliminate integer division in nonmovingBlockCount

Perf showed that the this single div was capturing up to 10% of samples
in nonmovingMark. However, the overwhelming majority of cases is looking
at small block sizes. These cases we can easily compute explicitly,
allowing the compiler to turn the division into a significantly more
efficient division-by-constant.

While the increase in source code looks scary, this all optimises down
to very nice looking assembler. At this point the only remaining
hotspots in nonmovingBlockCount are due to memory access.

- - - - -
28b23a9e by Ben Gamari at 2019-06-19T18:25:06Z
Allocate mark queues in larger block groups

- - - - -
068d89ca by Ben Gamari at 2019-06-19T18:25:06Z
NonMovingMark: Optimize representation of mark queue

This shortens MarkQueueEntry by 30% (one word)

- - - - -
d8eaaadb by Ben Gamari at 2019-06-19T18:25:07Z
NonMoving: Optimize bitmap search during allocation

Use memchr instead of a open-coded loop. This is nearly twice as fast in
a synthetic benchmark.

- - - - -
06983d00 by Ben Gamari at 2019-06-19T18:25:07Z
rts: Add prefetch macros

- - - - -
a5be4a42 by Ben Gamari at 2019-06-19T18:25:07Z
NonMoving: Prefetch when clearing bitmaps

Ensure that the bitmap of the segmentt that we will clear next is in
cache by the time we reach it.

- - - - -
b48113b8 by Ben Gamari at 2019-06-19T18:25:07Z
NonMoving: Inline nonmovingClearAllBitmaps

- - - - -
9054a554 by Ben Gamari at 2019-06-19T18:25:07Z
NonMoving: Fuse sweep preparation into mark prep

- - - - -
79f5bec7 by Ben Gamari at 2019-06-19T18:25:07Z
NonMoving: Pre-fetch during mark

This improved overall runtime on nofib's constraints test by nearly 10%.

- - - - -
7750c1dc by Ben Gamari at 2019-06-19T18:25:07Z
NonMoving: Prefetch segment header

- - - - -
cbb9fb1b by Ben Gamari at 2019-06-19T18:25:07Z
NonMoving: Optimise allocator cache behavior

Previously we would look at the segment header to determine the block
size despite the fact that we already had the block size at hand.

- - - - -
ba2ba681 by Ben Gamari at 2019-06-19T18:25:07Z
NonMovingMark: Eliminate redundant check_in_nonmoving_heaps

- - - - -
3bec13fc by Ben Gamari at 2019-06-19T18:25:07Z
NonMoving: Don't do major GC if one is already running

Previously we would perform a preparatory moving collection, resulting
in many things being added to the mark queue. When we finished with this
we would realize in nonmovingCollect that there was already a collection
running, in which case we would simply not run the nonmoving collector.

However, it was very easy to end up in a "treadmilling" situation: all
subsequent GC following the first failed major GC would be scheduled as
major GCs. Consequently we would continuously feed the concurrent
collector with more mark queue entries and it would never finish.

This patch aborts the major collection far earlier, meaning that we
avoid adding nonmoving objects to the mark queue and allowing the
concurrent collector to finish.

- - - - -
8ac9db2c by Ben Gamari at 2019-06-19T18:25:08Z
Nonmoving: Ensure write barrier vanishes in non-threaded RTS

- - - - -


30 changed files:

- compiler/cmm/CLabel.hs
- compiler/codeGen/StgCmmBind.hs
- compiler/codeGen/StgCmmPrim.hs
- compiler/codeGen/StgCmmUtils.hs
- docs/users_guide/runtime_control.rst
- includes/Cmm.h
- includes/Rts.h
- includes/rts/Flags.h
- + includes/rts/NonMoving.h
- includes/rts/storage/Block.h
- includes/rts/storage/ClosureMacros.h
- includes/rts/storage/GC.h
- includes/rts/storage/InfoTables.h
- includes/rts/storage/TSO.h
- includes/stg/MiscClosures.h
- libraries/base/GHC/RTS/Flags.hsc
- rts/Apply.cmm
- rts/Capability.c
- rts/Capability.h
- rts/Exception.cmm
- rts/Messages.c
- rts/PrimOps.cmm
- rts/RaiseAsync.c
- rts/RtsFlags.c
- rts/RtsStartup.c
- rts/RtsSymbols.c
- rts/STM.c
- rts/Schedule.c
- rts/Schedule.h
- rts/StableName.c


The diff was not included because it is too large.


View it on GitLab: https://gitlab.haskell.org/ghc/ghc/compare/b1c0e77701efa7507dd5f4179cfa9d1edc78c71a...8ac9db2cf8e57e1c21ebb45b96ee6887558f69dd

-- 
View it on GitLab: https://gitlab.haskell.org/ghc/ghc/compare/b1c0e77701efa7507dd5f4179cfa9d1edc78c71a...8ac9db2cf8e57e1c21ebb45b96ee6887558f69dd
You're receiving this email because of your account on gitlab.haskell.org.


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.haskell.org/pipermail/ghc-commits/attachments/20190619/7d207595/attachment-0001.html>


More information about the ghc-commits mailing list