journald: turn off COW for journal files on btrfs

btrfs' COW logic results in heavily fragment journal files, which is
detrimental for perfomance. Hence, turn off COW for journal files as we
create them.

Turning off COW comes at the cost of data integrity guarantees, but this
should be acceptable, given that we do our own checksumming, and
generally have a pretty conservative write pattern.

Also see discussion on linux-btrfs:

http://www.spinics.net/lists/linux-btrfs/msg41001.html

4 files changed, 66 insertions, 10 deletions

diff --git a/src/journal/journal-file.c b/src/journal/journal-file.c
index c9030c56ad..c20af5d9bf 100644
--- a/src/journal/journal-file.c
+++ b/src/journal/journal-file.c
@@ -26,6 +26,7 @@
 #include <sys/statvfs.h>
 #include <fcntl.h>
 #include <stddef.h>
+#include <linux/fs.h>
 
 #include "btrfs-util.h"
 #include "journal-def.h"
@@ -141,8 +142,17 @@ void journal_file_close(JournalFile *f) {
         if (f->mmap && f->fd >= 0)
                 mmap_cache_close_fd(f->mmap, f->fd);
 
-        if (f->fd >= 0 && f->defrag_on_close)
-                btrfs_defrag_fd(f->fd);
+        if (f->fd >= 0 && f->defrag_on_close) {
+
+                /* Be friendly to btrfs: turn COW back on again now,
+                 * and defragment the file. We won't write to the file
+                 * ever again, hence remove all fragmentation, and
+                 * reenable all the good bits COW usually provides
+                 * (such as data checksumming). */
+
+                (void) chattr_fd(f->fd, false, FS_NOCOW_FL);
+                (void) btrfs_defrag_fd(f->fd);
+        }
 
         safe_close(f->fd);
         free(f->path);
@@ -2591,6 +2601,18 @@ int journal_file_open(
                 goto fail;
 
         if (f->last_stat.st_size == 0 && f->writable) {
+
+                /* Before we write anything, turn off COW logic. Given
+                 * our write pattern that is quite unfriendly to COW
+                 * file systems this should greatly improve
+                 * performance on COW file systems, such as btrfs, at
+                 * the expense of data integrity features (which
+                 * shouldn't be too bad, given that we do our own
+                 * checksumming). */
+                r = chattr_fd(f->fd, true, FS_NOCOW_FL);
+                if (r < 0)
+                        log_warning_errno(errno, "Failed to set file attributes: %m");
+
                 /* Let's attach the creation time to the journal file,
                  * so that the vacuuming code knows the age of this
                  * file even if the file might end up corrupted one
@@ -2808,6 +2830,8 @@ int journal_file_open_reliably(
 
         /* btrfs doesn't cope well with our write pattern and
          * fragments heavily. Let's defrag all files we rotate */
+
+        (void) chattr_path(p, false, FS_NOCOW_FL);
         (void) btrfs_defrag(p);
 
         log_warning("File %s corrupted or uncleanly shut down, renaming and replacing.", fname);
diff --git a/src/journal/journalctl.c b/src/journal/journalctl.c
index 386e3505c0..62931f14c9 100644
--- a/src/journal/journalctl.c
+++ b/src/journal/journalctl.c
@@ -1294,7 +1294,7 @@ static int setup_keys(void) {
         size_t mpk_size, seed_size, state_size, i;
         uint8_t *mpk, *seed, *state;
         ssize_t l;
-        int fd = -1, r, attr = 0;
+        int fd = -1, r;
         sd_id128_t machine, boot;
         char *p = NULL, *k = NULL;
         struct FSSHeader h;
@@ -1389,13 +1389,9 @@ static int setup_keys(void) {
 
         /* Enable secure remove, exclusion from dump, synchronous
          * writing and in-place updating */
-        if (ioctl(fd, FS_IOC_GETFLAGS, &attr) < 0)
-                log_warning_errno(errno, "FS_IOC_GETFLAGS failed: %m");
-
-        attr |= FS_SECRM_FL|FS_NODUMP_FL|FS_SYNC_FL|FS_NOCOW_FL;
-
-        if (ioctl(fd, FS_IOC_SETFLAGS, &attr) < 0)
-                log_warning_errno(errno, "FS_IOC_SETFLAGS failed: %m");
+        r = chattr_fd(fd, true, FS_SECRM_FL|FS_NODUMP_FL|FS_SYNC_FL|FS_NOCOW_FL);
+        if (r < 0)
+                log_warning_errno(errno, "Failed to set file attributes: %m");
 
         zero(h);
         memcpy(h.signature, "KSHHRHLP", 8);
diff --git a/src/shared/util.c b/src/shared/util.c
index 6293e967c8..88fd78ec8d 100644
--- a/src/shared/util.c
+++ b/src/shared/util.c
@@ -62,6 +62,7 @@
 #include <sys/xattr.h>
 #include <libgen.h>
 #include <sys/statvfs.h>
+#include <linux/fs.h>
 #undef basename
 
 #ifdef HAVE_SYS_AUXV_H
@@ -7740,3 +7741,35 @@ int same_fd(int a, int b) {
 
         return fa == fb;
 }
+
+int chattr_fd(int fd, bool b, int mask) {
+        int old_attr, new_attr;
+
+        assert(fd >= 0);
+
+        if (ioctl(fd, FS_IOC_GETFLAGS, &old_attr) < 0)
+                return -errno;
+
+        if (b)
+                new_attr = old_attr | mask;
+        else
+                new_attr = old_attr & ~mask;
+
+        if (new_attr == old_attr)
+                return 0;
+
+        if (ioctl(fd, FS_IOC_SETFLAGS, &new_attr) < 0)
+                return -errno;
+
+        return 0;
+}
+
+int chattr_path(const char *p, bool b, int mask) {
+        _cleanup_close_ int fd = -1;
+
+        fd = open(p, O_RDWR|O_CLOEXEC|O_NOCTTY|O_NOFOLLOW);
+        if (fd < 0)
+                return -errno;
+
+        return chattr_fd(fd, b, mask);
+}
diff --git a/src/shared/util.h b/src/shared/util.h
index 4b7e12e628..31103e957f 100644
--- a/src/shared/util.h
+++ b/src/shared/util.h
@@ -1071,3 +1071,6 @@ int path_getcrtime(const char *p, usec_t *usec);
 int fd_getcrtime_at(int dirfd, const char *name, usec_t *usec, int flags);
 
 int same_fd(int a, int b);
+
+int chattr_fd(int fd, bool b, int mask);
+int chattr_path(const char *p, bool b, int mask);