From 3668d1ab0e2567e0df1b1d26f226a901c57f3707 Mon Sep 17 00:00:00 2001
From: rmorotti <romain.morotti@man.com>
Date: Thu, 21 Mar 2024 15:07:56 +0000
Subject: [PATCH] gh-117151: IO performance improvement, increase
 io.DEFAULT_BUFFER_SIZE to 128k, fix open() to use max(st_blksize,
 io.DEFAULT_BUFFER_SIZE)

---
 Lib/_pyio.py                                                | 6 +++---
 .../2024-04-30-14-03-09.gh-issue-117151.yt2H8c.rst          | 3 +++
 Modules/_io/_iomodule.h                                     | 2 +-
 3 files changed, 7 insertions(+), 4 deletions(-)
 create mode 100644 Misc/NEWS.d/next/Core and Builtins/2024-04-30-14-03-09.gh-issue-117151.yt2H8c.rst

diff --git a/Lib/_pyio.py b/Lib/_pyio.py
index a3fede699218a15..7979d5766668917 100644
--- a/Lib/_pyio.py
+++ b/Lib/_pyio.py
@@ -23,8 +23,8 @@
     valid_seek_flags.add(os.SEEK_HOLE)
     valid_seek_flags.add(os.SEEK_DATA)
 
-# open() uses st_blksize whenever we can
-DEFAULT_BUFFER_SIZE = 8 * 1024  # bytes
+# open() uses max(st_blksize, io.DEFAULT_BUFFER_SIZE) when st_blksize is available
+DEFAULT_BUFFER_SIZE = 128 * 1024  # bytes
 
 # NOTE: Base classes defined here are registered with the "official" ABCs
 # defined in io.py. We don't use real inheritance though, because we don't want
@@ -249,7 +249,7 @@ def open(file, mode="r", buffering=-1, encoding=None, errors=None,
                 pass
             else:
                 if bs > 1:
-                    buffering = bs
+                    buffering = max(bs, DEFAULT_BUFFER_SIZE)
         if buffering < 0:
             raise ValueError("invalid buffering size")
         if buffering == 0:
diff --git a/Misc/NEWS.d/next/Core and Builtins/2024-04-30-14-03-09.gh-issue-117151.yt2H8c.rst b/Misc/NEWS.d/next/Core and Builtins/2024-04-30-14-03-09.gh-issue-117151.yt2H8c.rst
new file mode 100644
index 000000000000000..f0574bbc16c37d0
--- /dev/null
+++ b/Misc/NEWS.d/next/Core and Builtins/2024-04-30-14-03-09.gh-issue-117151.yt2H8c.rst	
@@ -0,0 +1,3 @@
+increase io.DEFAULT_BUFFER_SIZE from 4k/8k to 128k. fix open on Linux to use
+max(io.DEFAULT_BUFFER_SIZE, device block size) rather than the device block
+size. improve I/O performance by 3 to 5 times. patch by Romain Morotti.
diff --git a/Modules/_io/_iomodule.h b/Modules/_io/_iomodule.h
index afd638a120ba085..18cf20edf26f7d9 100644
--- a/Modules/_io/_iomodule.h
+++ b/Modules/_io/_iomodule.h
@@ -78,7 +78,7 @@ extern Py_ssize_t _PyIO_find_line_ending(
 */
 extern int _PyIO_trap_eintr(void);
 
-#define DEFAULT_BUFFER_SIZE (8 * 1024)  /* bytes */
+#define DEFAULT_BUFFER_SIZE (128 * 1024)  /* bytes */
 
 /*
  * Offset type for positioning.