[PATCH v2 08/10] csum-file: introduce `hashfd_ext()`

From

Patrick Steinhardt <ps@pks.im>

Date

Mar 3, 2026, 15:00 UTC

Message-ID

<20260303-pks-upload-pack-write-contention-v2-8-7321830f08fe@pks.im>

In-Reply-To

<20260303-pks-upload-pack-write-contention-v2-0-7321830f08fe@pks.im>

Signed-off-by: Patrick Steinhardt <ps@pks.im>
---
 csum-file.c | 22 +++++++++++++---------
 csum-file.h | 14 ++++++++++++++
 2 files changed, 27 insertions(+), 9 deletions(-)

diff --git a/csum-file.c b/csum-file.c
index 6e21e3cac8..a50416247e 100644
--- a/csum-file.c
+++ b/csum-file.c
@@ -161,17 +161,16 @@ struct hashfile *hashfd_check(const struct git_hash_algo *algop,
 	return f;
 }
 
-static struct hashfile *hashfd_internal(const struct git_hash_algo *algop,
-					int fd, const char *name,
-					struct progress *tp,
-					size_t buffer_len)
+struct hashfile *hashfd_ext(const struct git_hash_algo *algop,
+			    int fd, const char *name,
+			    const struct hashfd_options *opts)
 {
 	struct hashfile *f = xmalloc(sizeof(*f));
 	f->fd = fd;
 	f->check_fd = -1;
 	f->offset = 0;
 	f->total = 0;
-	f->tp = tp;
+	f->tp = opts->progress;
 	f->name = name;
 	f->do_crc = 0;
 	f->skip_hash = 0;
@@ -179,8 +178,8 @@ static struct hashfile *hashfd_internal(const struct git_hash_algo *algop,
 	f->algop = unsafe_hash_algo(algop);
 	f->algop->init_fn(&f->ctx);
 
-	f->buffer_len = buffer_len;
-	f->buffer = xmalloc(buffer_len);
+	f->buffer_len = opts->buffer_len ? opts->buffer_len : 128 * 1024;
+	f->buffer = xmalloc(f->buffer_len);
 	f->check_buffer = NULL;
 
 	return f;
@@ -194,7 +193,8 @@ struct hashfile *hashfd(const struct git_hash_algo *algop,
 	 * measure the rate of data passing through this hashfile,
 	 * use a larger buffer size to reduce fsync() calls.
 	 */
-	return hashfd_internal(algop, fd, name, NULL, 128 * 1024);
+	struct hashfd_options opts = { 0 };
+	return hashfd_ext(algop, fd, name, &opts);
 }
 
 struct hashfile *hashfd_throughput(const struct git_hash_algo *algop,
@@ -206,7 +206,11 @@ struct hashfile *hashfd_throughput(const struct git_hash_algo *algop,
 	 * size so the progress indicators arrive at a more
 	 * frequent rate.
 	 */
-	return hashfd_internal(algop, fd, name, tp, 8 * 1024);
+	struct hashfd_options opts = {
+		.progress = tp,
+		.buffer_len = 8 * 1024,
+	};
+	return hashfd_ext(algop, fd, name, &opts);
 }
 
 void hashfile_checkpoint_init(struct hashfile *f,
diff --git a/csum-file.h b/csum-file.h
index 07ae11024a..a03b60120d 100644
--- a/csum-file.h
+++ b/csum-file.h
@@ -45,6 +45,20 @@ int hashfile_truncate(struct hashfile *, struct hashfile_checkpoint *);
 #define CSUM_FSYNC		2
 #define CSUM_HASH_IN_STREAM	4
 
+struct hashfd_options {
+	/*
+	 * Throughput progress that counts the number of bytes that have been
+	 * hashed.
+	 */
+	struct progress *progress;
+
+	/* The length of the buffer that shall be used read read data. */
+	size_t buffer_len;
+};
+
+struct hashfile *hashfd_ext(const struct git_hash_algo *algop,
+			    int fd, const char *name,
+			    const struct hashfd_options *opts);
 struct hashfile *hashfd(const struct git_hash_algo *algop,
 			int fd, const char *name);
 struct hashfile *hashfd_check(const struct git_hash_algo *algop,

-- 
2.53.0.697.g625c4fb2da.dirty