diff mbox series

lib/sstatesig: use the SHA256 fastpath in bitbake/utils.py

Message ID 20260626134221.1556950-1-ross.burton@arm.com
State Under Review
Headers show
Series lib/sstatesig: use the SHA256 fastpath in bitbake/utils.py | expand

Commit Message

Ross Burton June 26, 2026, 1:42 p.m. UTC 
Instead of iterating through a file by hand to hash it, call into the
hashing code in bitbake's utils.py.  This uses mmap() instead of plain
file operations which is ~30% faster in benchmarks[1], and will speed
up hash calculations when writing sstate.

[1] On my build machine, hashing a 300MB kernel image 100 times takes
    34s with open() and 26s with mmap()

Signed-off-by: Ross Burton <ross.burton@arm.com>
---
 meta/lib/oe/sstatesig.py | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)
diff mbox series

Patch

diff --git a/meta/lib/oe/sstatesig.py b/meta/lib/oe/sstatesig.py
index af6df60271d..f016fc67704 100644
--- a/meta/lib/oe/sstatesig.py
+++ b/meta/lib/oe/sstatesig.py
@@ -684,10 +684,10 @@  def OEOuthashBasic(path, sigfile, task, d):
                     update_hash(" " * 10)
 
                 update_hash(" ")
-                fh = hashlib.sha256()
                 if stat.S_ISREG(s.st_mode):
                     # Hash file contents
                     if filterfile:
+                        fh = hashlib.sha256()
                         # Need to ignore paths in crossscripts and postinst-useradd files.
                         with open(path, 'rb') as d:
                             chunk = d.read()
@@ -701,13 +701,13 @@  def OEOuthashBasic(path, sigfile, task, d):
                                     else:
                                         chunk = chunk.replace(bytes(r, encoding='utf8'), b'')
                             fh.update(chunk)
+                        update_hash(fh.hexdigest())
                     else:
-                        with open(path, 'rb') as d:
-                            for chunk in iter(lambda: d.read(4096), b""):
-                                fh.update(chunk)
-                    update_hash(fh.hexdigest())
+                        # Plain file that we're not filtering, use the fastpath in bb.utils
+                        update_hash(bb.utils.sha256_file(path))
                 else:
-                    update_hash(" " * len(fh.hexdigest()))
+                    # SHA256 has a 64 character hex digest
+                    update_hash(" " * 64)
 
                 update_hash(" %s" % path)