[Git][ghc/ghc][wip/gc/docs] 40 commits: rts: Non-concurrent mark and sweep

Ben Gamari gitlab at gitlab.haskell.org
Fri May 17 18:28:39 UTC 2019 


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


Commits:
242f9ff8 by Ömer Sinan Ağacan at 2019-05-17T17:00:12Z
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>

- - - - -
24c946a5 by Ben Gamari at 2019-05-17T17:00:12Z
testsuite: Add nonmoving WAY

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

- - - - -
c7bf0b64 by Ben Gamari at 2019-05-17T17:00:40Z
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>

- - - - -
10d798ad by Ben Gamari at 2019-05-17T17:00:40Z
Drop redundant write barrier

- - - - -
fe2b6bb5 by Ben Gamari at 2019-05-17T17:00:40Z
Nonmoving: Disable memory inventory with concurrent collection

- - - - -
a7affe42 by Ben Gamari at 2019-05-17T17:02:09Z
rts: Tracing support for nonmoving collection events

This introduces a few events to mark key points in the nonmoving
garbage collection cycle. These include:

 * `EVENT_CONC_MARK_BEGIN`, denoting the beginning of a round of
   marking. This may happen more than once in a single major collection
   since we the major collector iterates until it hits a fixed point.

 * `EVENT_CONC_MARK_END`, denoting the end of a round of marking.

 * `EVENT_CONC_SYNC_BEGIN`, denoting the beginning of the post-mark
   synchronization phase

 * `EVENT_CONC_UPD_REM_SET_FLUSH`, indicating that a capability has
   flushed its update remembered set.

 * `EVENT_CONC_SYNC_END`, denoting that all mutators have flushed their
   update remembered sets.

 * `EVENT_CONC_SWEEP_BEGIN`, denoting the beginning of the sweep portion
   of the major collection.

 * `EVENT_CONC_SWEEP_END`, denoting the end of the sweep portion of the
   major collection.

- - - - -
25257464 by Ben Gamari at 2019-05-17T17:02:09Z
rts: Introduce non-moving heap census

This introduces a simple census of the non-moving heap (not to be
confused with the heap census used by the heap profiler). This
collects basic heap usage information (number of allocated and free
blocks) which is useful when characterising fragmentation of the
nonmoving heap.

- - - - -
d4e3fdc1 by Ben Gamari at 2019-05-17T17:02:09Z
rts/Eventlog: More descriptive error message

- - - - -
92ef4dab by Ben Gamari at 2019-05-17T17:02:09Z
Allow census without live word count

Otherwise the census is unsafe when mutators are running due to
concurrent mutation.

- - - - -
85a83144 by Ben Gamari at 2019-05-17T17:02:09Z
NonmovingCensus: Emit samples to eventlog

- - - - -
839d8049 by Ben Gamari at 2019-05-17T17:02:09Z
rts: Add helpers for fetching per-thread CPU time

- - - - -
fb15e2a6 by Ben Gamari at 2019-05-17T17:02:09Z
rts/Stats: Track time usage of nonmoving collector

- - - - -
d93b45c3 by Ben Gamari at 2019-05-17T17:02:19Z
testsuite: Don't run T15892 in nonmoving ways

The nonmoving GC doesn't support `+RTS -G1`, which this test insists on.

- - - - -
34d03273 by Ben Gamari at 2019-05-17T17:02:19Z
testsuite: Nonmoving collector doesn't support -G1

- - - - -
1aff336f by Ben Gamari at 2019-05-17T17:02:19Z
testsuite: Add nonmoving_thr_ghc way

This uses the nonmoving collector when compiling the testcases.

- - - - -
18128631 by Ben Gamari at 2019-05-17T17:02:19Z
testsuite: Ensure that threaded tests are run in nonmoving_thr

- - - - -
3238f4a6 by Ben Gamari at 2019-05-17T17:02:20Z
testsuite: bug1010 requires -c, which isn't supported by nonmoving

- - - - -
17968a6a by Ben Gamari at 2019-05-17T17:02:20Z
Omit broken tests

- - - - -
ab0588fd by Ben Gamari at 2019-05-17T17:02:20Z
testsuite: Skip T15892 in nonmoving_thr_ghc

- - - - -
28822cc7 by Ben Gamari at 2019-05-17T17:02:20Z
testsuite: Disable conc016 and conc068 in nonmoving ways

- - - - -
90217fb0 by Ben Gamari at 2019-05-17T17:02:20Z
testsuite: Don't run conc071 in nonmoving_thr_ghc

- - - - -
158a1186 by Ben Gamari at 2019-05-17T17:02:20Z
ghc-heap: Skip heap_all test with debugged RTS

The debugged RTS initializes the heap with 0xaa, which breaks the
(admittedly rather fragile) assumption that uninitialized fields are set
to 0x00:
```
Wrong exit code for heap_all(nonmoving)(expected 0 , actual 1 )
Stderr ( heap_all ):
heap_all: user error (assertClosuresEq: Closures do not match
Expected: FunClosure {info = StgInfoTable {entry = Nothing, ptrs = 0, nptrs = 1, tipe = FUN_0_1, srtlen = 0, code = Nothing}, ptrArgs = [], dataArgs = [0]}
Actual:   FunClosure {info = StgInfoTable {entry = Nothing, ptrs = 0, nptrs = 1, tipe = FUN_0_1, srtlen = 1032832, code = Nothing}, ptrArgs = [], dataArgs = [12297829382473034410]}

CallStack (from HasCallStack):
  assertClosuresEq, called at heap_all.hs:230:9 in main:Main
)
```

- - - - -
82c0235a by Ben Gamari at 2019-05-17T17:02:20Z
Skip ghc_heap_all test in nonmoving ways

- - - - -
56820c4f by Ben Gamari at 2019-05-17T17:02:20Z
testsuite fixes

- - - - -
d0322333 by Ben Gamari at 2019-05-17T17:02:20Z
testsuite: Add nonmoving_thr_ghc way

This uses the nonmoving collector when compiling the testcases.

- - - - -
e0cbedfb by Ben Gamari at 2019-05-17T17:02:20Z
tests

- - - - -
f05efa48 by Ben Gamari at 2019-05-17T17:02:31Z
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

- - - - -
1cde60c7 by Ben Gamari at 2019-05-17T17:02:44Z
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.

- - - - -
fb80532e by Ben Gamari at 2019-05-17T17:02:44Z
Allocate mark queues in larger block groups

- - - - -
19eba5fa by Ben Gamari at 2019-05-17T17:02:44Z
NonMovingMark: Optimize representation of mark queue

This shortens MarkQueueEntry by 30% (one word)

- - - - -
03e87635 by Ben Gamari at 2019-05-17T17:02:44Z
NonMoving: Optimize bitmap search during allocation

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

- - - - -
ac5fdb15 by Ben Gamari at 2019-05-17T17:02:44Z
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.

- - - - -
75d2d8f9 by Ben Gamari at 2019-05-17T17:02:44Z
NonMoving: Inline nonmovingClearAllBitmaps

- - - - -
b9f039be by Ben Gamari at 2019-05-17T17:02:44Z
NonMoving: Fuse sweep preparation into mark prep

- - - - -
9db2eae5 by Ben Gamari at 2019-05-17T17:02:44Z
NonMoving: Pre-fetch during mark

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

- - - - -
40f3b740 by Ben Gamari at 2019-05-17T17:02:44Z
NonMoving: Prefetch segment header

- - - - -
7effa1b1 by Ben Gamari at 2019-05-17T17:05:21Z
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.

- - - - -
f36efd89 by Ben Gamari at 2019-05-17T17:05:23Z
NonMovingMark: Eliminate redundant check_in_nonmoving_heaps

- - - - -
21534a7a by Ben Gamari at 2019-05-17T17:05:41Z
Merge branches 'wip/gc/test' and 'wip/gc/optimize' into wip/gc/everything

- - - - -
11a4cad7 by Ben Gamari at 2019-05-17T18:27:27Z
NonMoving: Add summarizing Note

- - - - -


30 changed files:

- compiler/cmm/CLabel.hs
- compiler/codeGen/StgCmmBind.hs
- compiler/codeGen/StgCmmPrim.hs
- compiler/codeGen/StgCmmUtils.hs
- includes/Cmm.h
- includes/Rts.h
- includes/RtsAPI.h
- includes/rts/EventLogFormat.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/TSO.h
- includes/stg/MiscClosures.h
- libraries/base/GHC/RTS/Flags.hsc
- libraries/base/GHC/Stats.hsc
- libraries/base/tests/all.T
- libraries/ghc-heap/tests/all.T
- rts/Apply.cmm
- rts/Capability.c
- rts/Capability.h
- rts/Exception.cmm
- rts/GetTime.h
- rts/Messages.c
- rts/PrimOps.cmm
- rts/RaiseAsync.c
- rts/RtsFlags.c
- rts/RtsStartup.c
- rts/RtsSymbols.c


The diff was not included because it is too large.


View it on GitLab: https://gitlab.haskell.org/ghc/ghc/compare/9d6139bec39597baacfe8747507d14f00651ceee...11a4cad7b9308d604bc07ee35b2151b57db8e561

-- 
View it on GitLab: https://gitlab.haskell.org/ghc/ghc/compare/9d6139bec39597baacfe8747507d14f00651ceee...11a4cad7b9308d604bc07ee35b2151b57db8e561
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/20190517/91d90934/attachment-0001.html>

More information about the ghc-commits mailing list