From a5e2bdff47d7079d022ebfb218edc597ccc03058 Mon Sep 17 00:00:00 2001
From: Kai Krakow <kai@kaishome.de>
Date: Tue, 12 Sep 2017 02:09:22 +0200
Subject: [PATCH] Skip nocow files to speed up processing

If you have a lot of or a few big nocow files (like vm images) which
contain a lot of potential deduplication candidates, bees becomes
incredibly slow running through a lot "invalid operation" exceptions.

Let's just skip over such files to get more bang for the buck. I did no
regression testing as this patch seems trivial (and I cannot imagine any
pitfalls either). The process progresses much faster for me now.
---
 include/crucible/fd.h | 6 ++++++
 lib/fd.cc             | 8 ++++++++
 src/bees-roots.cc     | 8 ++++++++
 3 files changed, 22 insertions(+)

diff --git a/include/crucible/fd.h b/include/crucible/fd.h
index 8492846..9818819 100644
--- a/include/crucible/fd.h
+++ b/include/crucible/fd.h
@@ -13,6 +13,10 @@
 #include <sys/stat.h>
 #include <fcntl.h>
 
+// ioctl
+#include <sys/ioctl.h>
+#include <linux/fs.h>
+
 // socket
 #include <sys/socket.h>
 
@@ -141,6 +145,8 @@ namespace crucible {
 		Stat &lstat(const string &filename);
 	};
 
+	int ioctl_iflags_get(int fd);
+
 	string st_mode_ntoa(mode_t mode);
 
 	// Because it's not trivial to do correctly
diff --git a/lib/fd.cc b/lib/fd.cc
index e0735a9..931167f 100644
--- a/lib/fd.cc
+++ b/lib/fd.cc
@@ -488,6 +488,14 @@ namespace crucible {
 		lstat(filename);
 	}
 
+	int
+	ioctl_iflags_get(int fd)
+	{
+		int attr = 0;
+		DIE_IF_MINUS_ONE(ioctl(fd, FS_IOC_GETFLAGS, &attr));
+		return attr;
+	}
+
 	string
 	readlink_or_die(const string &path)
 	{
diff --git a/src/bees-roots.cc b/src/bees-roots.cc
index 921132c..e99dc66 100644
--- a/src/bees-roots.cc
+++ b/src/bees-roots.cc
@@ -576,6 +576,14 @@ BeesRoots::open_root_ino_nocache(uint64_t root, uint64_t ino)
 			break;
 		}
 
+		int attr = ioctl_iflags_get(rv);
+		if (attr & FS_NOCOW_FL) {
+			BEESLOG("Opening " << name_fd(root_fd) << "/" << file_path << " found incompatible flags " << attr << " (FS_NOCOW_FL)");
+			rv = Fd();
+			BEESCOUNT(open_wrong_flags);
+			break;
+		}
+
 		// Correct root?
 		auto file_root = btrfs_get_root_id(rv);
 		if (file_root != root) {