[Git][ghc/ghc][wip/gc/segment-header-to-bdescr] 56 commits: rts/BlockAlloc: Allow aligned allocation requests

Ben Gamari gitlab at gitlab.haskell.org
Wed Jun 19 00:40:05 UTC 2019 


Ben Gamari pushed to branch wip/gc/segment-header-to-bdescr at Glasgow Haskell Compiler / GHC


Commits:
80a5d3e1 by Ömer Sinan Ağacan at 2019-06-19T00:30:19Z
rts/BlockAlloc: Allow aligned allocation requests

This implements support for block group allocations which are aligned to
an integral number of blocks.

This will be used by the nonmoving garbage collector, which uses the
block allocator to allocate the segments which back its heap. These
segments are a fixed number of blocks in size, with each segment being
aligned to the segment size boundary. This allows us to easily find the
segment metadata stored at the beginning of the segment.

- - - - -
530e6824 by Ben Gamari at 2019-06-19T00:30:19Z
testsuite/testblockalloc: A bit of refactoring

- - - - -
7c0652b3 by Ben Gamari at 2019-06-19T00:30:19Z
testsuite/testblockalloc: Test aligned block group allocation

- - - - -
ac705426 by Ben Gamari at 2019-06-19T00:30:20Z
rts/BlockAlloc: Wibbles

- - - - -
8788c063 by Ben Gamari at 2019-06-19T00:30:20Z
rts/BlockAlloc: Use allocLargeChunk in aligned block allocation

- - - - -
f3191083 by Ömer Sinan Ağacan at 2019-06-19T00:32:01Z
Disallow allocating megablocks, update tests

- - - - -
67cbec4a by Ömer Sinan Ağacan at 2019-06-19T00:32:01Z
Fix lint errors

- - - - -
59d32a99 by Ömer Sinan Ağacan at 2019-06-19T00:32:01Z
Use allocLargeChunkOnNode to reduce splitting

- - - - -
ead67e40 by Ömer Sinan Ağacan at 2019-06-19T00:32:01Z
Allow allocating megablocks in allocAlignedGroupOnNode

This is currently broken because freeGroup assumes integral number of
megablocks when freeing megablocks but we try to split the megablocks
returned by allocLargeChunkOnNode to smaller groups and free the rest.

- - - - -
5fab1847 by Ben Gamari at 2019-06-19T00:32:46Z
Merge branches 'wip/gc/misc-rts' and 'wip/gc/aligned-block-allocation' into wip/gc/preparation

- - - - -
7cb5b05c by Ömer Sinan Ağacan at 2019-06-19T00:33:55Z
rts/StableName: Expose FOR_EACH_STABLE_NAME, freeSnEntry, SNT_size

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

- - - - -
98c601f2 by Ben Gamari at 2019-06-19T00:33:55Z
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.

- - - - -
225afe49 by Ömer Sinan Ağacan at 2019-06-19T00:33:55Z
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.

- - - - -
babf1fb8 by Ben Gamari at 2019-06-19T00:33:55Z
rts: Introduce flag to enable the nonmoving old generation

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

- - - - -
f1639975 by Ben Gamari at 2019-06-19T00:33:55Z
rts: Introduce debug flag for non-moving GC

- - - - -
85a47315 by Ömer Sinan Ağacan at 2019-06-19T00:33:55Z
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>

- - - - -
044531d5 by Ben Gamari at 2019-06-19T00:33:55Z
testsuite: Add nonmoving WAY

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

- - - - -
d468f6f1 by Ben Gamari at 2019-06-19T00:34:36Z
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>

- - - - -
364e2b37 by Ben Gamari at 2019-06-19T00:34:36Z
Nonmoving: Disable memory inventory with concurrent collection

- - - - -
e0b2d7a2 by Ben Gamari at 2019-06-19T00:37:24Z
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.

- - - - -
616f9a4f by Ben Gamari at 2019-06-19T00:37:24Z
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.

- - - - -
602c6a20 by Ben Gamari at 2019-06-19T00:37:24Z
rts/Eventlog: More descriptive error message

- - - - -
c68097f4 by Ben Gamari at 2019-06-19T00:37:24Z
Allow census without live word count

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

- - - - -
937d3390 by Ben Gamari at 2019-06-19T00:37:24Z
NonmovingCensus: Emit samples to eventlog

- - - - -
aaa908ac by Ben Gamari at 2019-06-19T00:37:24Z
rts: Add GetMyThreadCPUTime helper

- - - - -
596c7834 by Ben Gamari at 2019-06-19T00:37:24Z
rts/Stats: Track time usage of nonmoving collector

- - - - -
f69b4bb9 by Ben Gamari at 2019-06-19T00:37:37Z
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

- - - - -
5be201a0 by Ben Gamari at 2019-06-19T00:37:37Z
Disable aging when doing deadlock detection GC

- - - - -
17b02eff by Ben Gamari at 2019-06-19T00:37:37Z
More comments for aging

- - - - -
8ddbef21 by Ben Gamari at 2019-06-19T00:37:45Z
testsuite: Add nonmoving_thr way

- - - - -
ab9746a2 by Ben Gamari at 2019-06-19T00:37:45Z
testsuite: Add nonmoving_thr_ghc way

This uses the nonmoving collector when compiling the testcases.

- - - - -
af1714c0 by Ben Gamari at 2019-06-19T00:37:45Z
testsuite: Don't run T15892 in nonmoving ways

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

- - - - -
1a3ccea6 by Ben Gamari at 2019-06-19T00:37:45Z
testsuite: Nonmoving collector doesn't support -G1

- - - - -
84bb9d66 by Ben Gamari at 2019-06-19T00:37:45Z
testsuite: Ensure that threaded tests are run in nonmoving_thr

- - - - -
dced7dd7 by Ben Gamari at 2019-06-19T00:37:46Z
testsuite: bug1010 requires -c, which isn't supported by nonmoving

- - - - -
2d1a0845 by Ben Gamari at 2019-06-19T00:37:46Z
testsuite: Skip T15892 in nonmoving_thr_ghc

- - - - -
56efaa98 by Ben Gamari at 2019-06-19T00:37:46Z
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
)
```

- - - - -
0de09bda by Ben Gamari at 2019-06-19T00:37:46Z
Skip ghc_heap_all test in nonmoving ways

- - - - -
088bb5f5 by Ben Gamari at 2019-06-19T00:37:53Z
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.

- - - - -
400a7d28 by Ben Gamari at 2019-06-19T00:37:53Z
Allocate mark queues in larger block groups

- - - - -
5210b6ff by Ben Gamari at 2019-06-19T00:37:54Z
NonMovingMark: Optimize representation of mark queue

This shortens MarkQueueEntry by 30% (one word)

- - - - -
09955ec6 by Ben Gamari at 2019-06-19T00:37:54Z
NonMoving: Optimize bitmap search during allocation

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

- - - - -
bac136c5 by Ben Gamari at 2019-06-19T00:37:54Z
rts: Add prefetch macros

- - - - -
b18d87b7 by Ben Gamari at 2019-06-19T00:37:54Z
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.

- - - - -
ed8df894 by Ben Gamari at 2019-06-19T00:37:54Z
NonMoving: Inline nonmovingClearAllBitmaps

- - - - -
1f057f5e by Ben Gamari at 2019-06-19T00:37:54Z
NonMoving: Fuse sweep preparation into mark prep

- - - - -
3825b722 by Ben Gamari at 2019-06-19T00:37:54Z
NonMoving: Pre-fetch during mark

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

- - - - -
00e38e6c by Ben Gamari at 2019-06-19T00:37:54Z
NonMoving: Prefetch segment header

- - - - -
8cb178eb by Ben Gamari at 2019-06-19T00:37:54Z
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.

- - - - -
8dd9a22e by Ben Gamari at 2019-06-19T00:37:54Z
NonMovingMark: Eliminate redundant check_in_nonmoving_heaps

- - - - -
4715302d by Ben Gamari at 2019-06-19T00:37:54Z
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.

- - - - -
87fb2d0c by Ben Gamari at 2019-06-19T00:37:54Z
Nonmoving: Ensure write barrier vanishes in non-threaded RTS

- - - - -
667b3c33 by Ben Gamari at 2019-06-19T00:38:08Z
Merge branches 'wip/gc/optimize' and 'wip/gc/test' into wip/gc/everything

- - - - -
957c3cdd by Ben Gamari at 2019-06-19T00:38:53Z
NonMoving: Introduce nonmovingSegmentLogBlockSize acccessor

This will allow us to easily move the block size elsewhere.

- - - - -
62176135 by Ben Gamari at 2019-06-19T00:38:53Z
NonMoving: Move block size to block descriptor

- - - - -
71ccd6dc by Ben Gamari at 2019-06-19T00:38:53Z
NonMoving: Move next_free_snap to block descriptor

- - - - -


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/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/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/8031fcee6a0e89ab8cb4ee9f30f55b7649e637a5...71ccd6dc6a0109990ba5955ca91a465c7b0ba079

-- 
View it on GitLab: https://gitlab.haskell.org/ghc/ghc/compare/8031fcee6a0e89ab8cb4ee9f30f55b7649e637a5...71ccd6dc6a0109990ba5955ca91a465c7b0ba079
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/20190618/88db15f1/attachment-0001.html>

More information about the ghc-commits mailing list