mirror of
https://github.com/status-im/nimbus-eth2.git
synced 2025-01-10 22:36:01 +00:00
1a9e9fc398
* use LTO in release builds
This significantly (40%) speeds up block replay and hashing - for example replaying first 1000
blocks, without/with LTO:
```
[arnetheduck@tempus ncli]$ ../env.sh nim c -d:release ncli_db
[arnetheduck@tempus ncli]$ ./ncli_db bench --db:db --network:medalla --slots:1000
Loaded 215006 blocks, head slot 307400
All time are ms
Average, StdDev, Min, Max, Samples, Test
Validation is turned off meaning that no BLS operations are performed
25468.481, 0.000, 25468.481, 25468.481, 1, Initialize DB
0.297, 0.516, 0.053, 13.645, 721, Load block from database
26.458, 0.000, 26.458, 26.458, 1, Load state from database
20.737, 8.288, 11.096, 199.325, 690, Apply block
333.069, 62.798, 45.225, 429.452, 31, Apply epoch block
0.000, 0.000, 0.000, 0.000, 0, Database block store
```
```
[arnetheduck@tempus ncli]$ ../env.sh nim c -d:release --passc:-flto --passl:-flto --stacktrace:off ncli_db
[arnetheduck@tempus ncli]$ ./ncli_db bench --db:db --network:medalla --slots:1000
Loaded 215006 blocks, head slot 307400
All time are ms
Average, StdDev, Min, Max, Samples, Test
Validation is turned off meaning that no BLS operations are performed
23903.006, 0.000, 23903.006, 23903.006, 1, Initialize DB
0.253, 0.122, 0.047, 0.731, 721, Load block from database
24.455, 0.000, 24.455, 24.455, 1, Load state from database
18.734, 7.062, 10.346, 167.397, 690, Apply block
194.869, 33.175, 29.311, 226.981, 31, Apply epoch block
```
Epoch processing is heavy on both arithmetics and hash caching, both of which get a
significant boost here.
This makes sense: nim creates lots of small functions spread out over many C files. A much
worse solution is to try to annotate code with `inline` - it copies functions to multiple
C files but still doesn't do intermodule optimizations significantly limiting the
compilers' ability to reason about the code, causing bloat and misrepresenting the usefulness
of a function to the call frequency analysis that drives actual (C-compiler) inlining and many
other optimizations.
In particular, many nim functions are part of `system` or the `C` backend - stack tracing,
memory allocation etc - nim's inlining system is pretty incomplete in that it does not deal
with these and many other cases.
* windows workaround
* skip LTO on windows for now
99 lines
3.7 KiB
Nim
99 lines
3.7 KiB
Nim
if defined(release):
|
|
switch("nimcache", "nimcache/release/$projectName")
|
|
else:
|
|
switch("nimcache", "nimcache/debug/$projectName")
|
|
|
|
# `-flto` gives a significant improvement in processing speed, specially hash tree and state transition (basically any CPU-bound code implemented in nim)
|
|
# With LTO enabled, optimization flags should be passed to both compiler and linker!
|
|
if defined(release):
|
|
if defined(macosx): # Clang
|
|
switch("passC", "-flto=thin")
|
|
switch("passL", "-flto=thin")
|
|
elif defined(linux):
|
|
switch("passC", "-flto=auto")
|
|
switch("passL", "-flto=auto")
|
|
else:
|
|
# On windows, LTO needs more love and attention so the right linkers
|
|
# are used
|
|
discard
|
|
|
|
if defined(windows):
|
|
# disable timestamps in Windows PE headers - https://wiki.debian.org/ReproducibleBuilds/TimestampsInPEBinaries
|
|
switch("passL", "-Wl,--no-insert-timestamp")
|
|
# increase stack size
|
|
switch("passL", "-Wl,--stack,8388608")
|
|
# https://github.com/nim-lang/Nim/issues/4057
|
|
--tlsEmulation:off
|
|
if defined(i386):
|
|
# set the IMAGE_FILE_LARGE_ADDRESS_AWARE flag so we can use PAE, if enabled, and access more than 2 GiB of RAM
|
|
switch("passL", "-Wl,--large-address-aware")
|
|
|
|
# The dynamic Chronicles output currently prevents us from using colors on Windows
|
|
# because these require direct manipulations of the stdout File object.
|
|
switch("define", "chronicles_colors=off")
|
|
|
|
# This helps especially for 32-bit x86, which sans SSE2 and newer instructions
|
|
# requires quite roundabout code generation for cryptography, and other 64-bit
|
|
# and larger arithmetic use cases, along with register starvation issues. When
|
|
# engineering a more portable binary release, this should be tweaked but still
|
|
# use at least -msse2 or -msse3.
|
|
if defined(disableMarchNative):
|
|
switch("passC", "-msse3")
|
|
switch("passL", "-msse3")
|
|
else:
|
|
switch("passC", "-march=native")
|
|
switch("passL", "-march=native")
|
|
if defined(windows):
|
|
# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65782
|
|
# ("-fno-asynchronous-unwind-tables" breaks Nim's exception raising, sometimes)
|
|
switch("passC", "-mno-avx512f")
|
|
switch("passL", "-mno-avx512f")
|
|
|
|
--threads:on
|
|
--opt:speed
|
|
--excessiveStackTrace:on
|
|
# enable metric collection
|
|
--define:metrics
|
|
--define:chronicles_line_numbers
|
|
# for heap-usage-by-instance-type metrics and object base-type strings
|
|
--define:nimTypeNames
|
|
|
|
# switch("define", "snappy_implementation=libp2p")
|
|
|
|
const currentDir = currentSourcePath()[0 .. ^(len("config.nims") + 1)]
|
|
switch("define", "nim_compiler_path=" & currentDir & "env.sh nim")
|
|
|
|
switch("import", "testutils/moduletests")
|
|
|
|
const useLibStackTrace = not defined(macosx) and
|
|
not defined(windows) and
|
|
not defined(disable_libbacktrace)
|
|
|
|
when useLibStackTrace:
|
|
--define:nimStackTraceOverride
|
|
switch("import", "libbacktrace")
|
|
else:
|
|
--stacktrace:on
|
|
--linetrace:on
|
|
|
|
# the default open files limit is too low on macOS (512), breaking the
|
|
# "--debugger:native" build. It can be increased with `ulimit -n 1024`.
|
|
if not defined(macosx):
|
|
# add debugging symbols and original files and line numbers
|
|
--debugger:native
|
|
|
|
--define:nimOldCaseObjects # https://github.com/status-im/nim-confutils/issues/9
|
|
|
|
# `switch("warning[CaseTransition]", "off")` fails with "Error: invalid command line option: '--warning[CaseTransition]'"
|
|
switch("warning", "CaseTransition:off")
|
|
|
|
# The compiler doth protest too much, methinks, about all these cases where it can't
|
|
# do its (N)RVO pass: https://github.com/nim-lang/RFCs/issues/230
|
|
switch("warning", "ObservableStores:off")
|
|
|
|
# Too many false positives for "Warning: method has lock level <unknown>, but another method has 0 [LockLevel]"
|
|
switch("warning", "LockLevel:off")
|
|
|
|
# Useful for Chronos metrics.
|
|
#--define:chronosFutureTracking
|