GitLab

A new eventlog event containing 7 spark counters/statistics: sparks
created, dud, overflowed, converted, GC'd, fizzled and remaining.
These are maintained and logged separately for each capability.
We log them at startup, on each GC (minor and major) and on shutdown.

Rather than a separate phase of initSparkPools. It means all the spark
stuff for a capability is initialisaed at the same time, which is then
becomes a good place to stick an initial spark trace event.

The invariant is: created = converted + remaining + gcd + fizzled
Since sparks move between capabilities, we have to aggregate the
counters over all capabilities. This in turn means we can only check
the invariant at stable points where all but one capabilities are
stopped. We can do this at shutdown time and before and after a global
synchronised GC.

When you use `par` to make a spark, if the spark pool on the current
capability is full then the spark is discarded. This represents a
loss of potential parallelism and it also means there are simply a
lot of sparks around. Both are things that might be of concern to a
programmer when tuning a parallel program that uses par.

The "+RTS -s" stats command now reports overflowed sparks, e.g.
SPARKS: 100001 (15521 converted, 84480 overflowed, 0 dud, 0 GC'd, 0 fizzled)

We want to count fizzled sparks accurately. Now tryStealSpark returns
fizzled sparks, and the callers now update the fizzled spark count.

newSpark() checks if the spark is a dud, and if so does not add it to
the spark pool. Previously, newSpark would discard the pointer tag bits
and just check closure_SHOULD_SPARK(p). We can take advantage of the
tag bits which can tell us if the pointer points to a value. If it is,
it's a dud spark and we don't need to add it to the spark pool.

assembly version as part of the fix for #5250, we inadvertently lost
the Windows magic for extending the stack.  Win32 requires that the
stack is extended a page at a time, otherwise you get a segfault.  The
C compiler knows how to do this, so we now call a C stub to ensure
there's enough stack space at each invocation of the scheduler.

When we install the packages, ghc-pkg obeys umask when creating
package.cache, but for everything else we specify the permissions. We
therefore fix the permissions of package.cache afterwards.

Now after, for example, "./sync-all pull", if pulling in one repo fails
then you can restart from that point with "./sync-all --resume pull".

This change gets rid of a debug WARNING; it wasn't
actually making anything go wrong, but it's best to
have the correct in-scope set.

"inplace/bin/ghc-stage1"   -H32m -O    -package-name base-4.4.0.0 -hide-all-packages -i -ilibraries/base/. -ilibraries/base/dist-install/build -ilibraries/base/dist-install/build/autogen -Ilibraries/base/dist-install/build -Ilibraries/base/dist-install/build/autogen -Ilibraries/base/include   -optP-DOPTIMISE_INTEGER_GCD_LCM -optP-include -optPlibraries/base/dist-install/build/autogen/cabal_macros.h -package ghc-prim-0.2.0.0 -package integer-gmp-0.3.0.0 -package rts-1.0 -split-objs -package-name base -XHaskell98 -XCPP -O2 -no-user-package-conf -rtsopts     -odir libraries/base/dist-install/build -hidir libraries/base/dist-install/build -stubdir libraries/base/dist-install/build -hisuf hi -osuf  o -hcsuf hc -c libraries/base/./GHC/Int.hs -o libraries/base/dist-install/build/GHC/Int.o
/usr/lib/gcc/sparc-unknown-linux-gnu/4.5.2/../../../../sparc-unknown-linux-gnu/bin/ld: --relax and -r may not be used together
collect2: ld returned 1 exit status
make[1]: *** [libraries/base/dist-install/build/GHC/Int.o] Error 1

Or with '-v' param:
/usr/bin/gcc -fno-stack-protector -nostdlib -nodefaultlibs -Wl,-r -Wl,--build-id=none -Wl,-x -o libraries/base/dist-install/build/GHC/Int.o /tmp/ghc45126_0/ghc45126_0.ldscript
/usr/lib/gcc/sparc-unknown-linux-gnu/4.5.2/../../../../sparc-unknown-linux-gnu/bin/ld: --relax and -r may not be used together

On SPARC gcc-4.5.2 has -mrelax in it's default specs, so we explicitly pass --no-relax
for ld to make sure gcc's default does not affect us.
Signed-off-by: Sergei Trofimovich <slyfox@gentoo.org>

See #5320 and discussion there.  This patch only removes
a bogus assertion failure and refactors the code slightly.
There's still an underlying delicate point, described in #5320.

We now pass the correct platform in instead

A coercion variable in a term must be wrapped in a coercion!
(Led to lint errors.)

There's now a variant of the Outputable class that knows what
platform we're targetting:

class PlatformOutputable a where
    pprPlatform :: Platform -> a -> SDoc
    pprPlatformPrec :: Platform -> Rational -> a -> SDoc

and various instances have had to be converted to use that class,
and we pass Platform around accordingly.

The -w flag wasn't turning off a few warnings (Opt_WarnMissingImportList,
Opt_WarnMissingLocalSigs, Opt_WarnIdentities). Rather than just adding
them, I've separated the Opt_Warn* contructors off into their own type,
so -w now just sets the list of warning flags to [].

Old versions don't understand -Wno-error=inline

They've been deprecated since GHC 6.12.