Don't fflush(stdout) when it's not helpful

This patch arose from a discussion started by Jim Meyering's patch
whose intention was to provide better diagnostics for failed writes.
Linus proposed a better way to do things, which also had the added
benefit that adding a fflush() to git-log-* operations and incremental
git-blame operations could improve interactive respose time feel, at
the cost of making things a bit slower when we aren't piping the
output to a downstream program.

This patch skips the fflush() calls when stdout is a regular file, or
if the environment variable GIT_FLUSH is set to "0".  This latter can
speed up a command such as:

GIT_FLUSH=0 strace -c -f -e write time git-rev-list HEAD | wc -l

a tiny amount.

Signed-off-by: "Theodore Ts'o" <[email protected]>
Acked-by: Linus Torvalds <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Documentation/git.txt

@@ -396,6 +396,16 @@ other
 'GIT_PAGER'::
 	This environment variable overrides `$PAGER`.
 
+'GIT_FLUSH'::
+	If this environment variable is set to "1", then commands such
+	as git-blame (in incremental mode), git-rev-list, git-log,
+	git-whatchanged, etc., will force a flush of the output stream
+	after each commit-oriented record have been flushed.   If this
+	variable is set to "0", the output of these commands will be done
+	using completely buffered I/O.   If this environment variable is
+	not set, git will choose buffered or record-oriented flushing
+	based on whether stdout appears to be redirected to a file or not.
+
 'GIT_TRACE'::
 	If this variable is set to "1", "2" or "true" (comparison
 	is case insensitive), git will print `trace:` messages on

builtin-blame.c

@@ -1459,6 +1459,7 @@ static void found_guilty_entry(struct blame_entry *ent)
 				printf("boundary\n");
 		}
 		write_filename_info(suspect->path);
+		maybe_flush_or_die(stdout, "stdout");
 	}
 }
 

builtin-rev-list.c

@@ -100,7 +100,7 @@ static void show_commit(struct commit *commit)
 		printf("%s%c", buf, hdr_termination);
 		free(buf);
 	}
-	fflush(stdout);
+	maybe_flush_or_die(stdout, "stdout");
 	if (commit->parents) {
 		free_commit_list(commit->parents);
 		commit->parents = NULL;

cache.h

@@ -532,6 +532,8 @@ extern char git_default_name[MAX_GITNAME];
 extern const char *git_commit_encoding;
 extern const char *git_log_output_encoding;
 
+/* IO helper functions */
+extern void maybe_flush_or_die(FILE *, const char *);
 extern int copy_fd(int ifd, int ofd);
 extern int read_in_full(int fd, void *buf, size_t count);
 extern int write_in_full(int fd, const void *buf, size_t count);

log-tree.c

@@ -408,5 +408,6 @@ int log_tree_commit(struct rev_info *opt, struct commit *commit)
 		shown = 1;
 	}
 	opt->loginfo = NULL;
+	maybe_flush_or_die(stdout, "stdout");
 	return shown;
 }

write_or_die.c

@@ -1,5 +1,45 @@
 #include "cache.h"
 
+/*
+ * Some cases use stdio, but want to flush after the write
+ * to get error handling (and to get better interactive
+ * behaviour - not buffering excessively).
+ *
+ * Of course, if the flush happened within the write itself,
+ * we've already lost the error code, and cannot report it any
+ * more. So we just ignore that case instead (and hope we get
+ * the right error code on the flush).
+ *
+ * If the file handle is stdout, and stdout is a file, then skip the
+ * flush entirely since it's not needed.
+ */
+void maybe_flush_or_die(FILE *f, const char *desc)
+{
+	static int skip_stdout_flush = -1;
+	struct stat st;
+	char *cp;
+
+	if (f == stdout) {
+		if (skip_stdout_flush < 0) {
+			cp = getenv("GIT_FLUSH");
+			if (cp)
+				skip_stdout_flush = (atoi(cp) == 0);
+			else if ((fstat(fileno(stdout), &st) == 0) &&
+				 S_ISREG(st.st_mode))
+				skip_stdout_flush = 1;
+			else
+				skip_stdout_flush = 0;
+		}
+		if (skip_stdout_flush && !ferror(f))
+			return;
+	}
+	if (fflush(f)) {
+		if (errno == EPIPE)
+			exit(0);
+		die("write failure on %s: %s", desc, strerror(errno));
+	}
+}
+
 int read_in_full(int fd, void *buf, size_t count)
 {
 	char *p = buf;