From ab6e257b3e4e5b95f3750ed019bed6e89989e41b Mon Sep 17 00:00:00 2001
From: Daan De Meyer <daan.j.demeyer@gmail.com>
Date: Tue, 16 Nov 2021 23:45:58 +0000
Subject: [PATCH] journal: truncate archived journals

Journal files have space allocated in 8MiB-aligned increments. This
can add up to substantial wasted space as many archived journals
accumulate without using all the allocated space. Let's truncate
journal files to their actually used size when archiving them to
reclaim this unused space.

As the mmap cache is not thread-safe, we can't call
journal_file_move_to_object() from the offline thread. Instead,
we use journal_file_read_object() which doesn't rely on the mmap
cache.
---
 src/libsystemd/sd-journal/journal-file.c | 81 ++++++++++++++++++------
 1 file changed, 60 insertions(+), 21 deletions(-)

diff --git a/src/libsystemd/sd-journal/journal-file.c b/src/libsystemd/sd-journal/journal-file.c
index 7068b6bb178..655f9cf7e4d 100644
--- a/src/libsystemd/sd-journal/journal-file.c
+++ b/src/libsystemd/sd-journal/journal-file.c
@@ -91,6 +91,59 @@
 #  pragma GCC diagnostic ignored "-Waddress-of-packed-member"
 #endif
 
+static int journal_file_tail_end(JournalFile *f, uint64_t *ret_offset) {
+        Object tail;
+        uint64_t p;
+        int r;
+
+        assert(f);
+        assert(f->header);
+        assert(ret_offset);
+
+        p = le64toh(f->header->tail_object_offset);
+        if (p == 0)
+                p = le64toh(f->header->header_size);
+        else {
+                uint64_t sz;
+
+                r = journal_file_read_object(f, OBJECT_UNUSED, p, &tail);
+                if (r < 0)
+                        return r;
+
+                sz = le64toh(tail.object.size);
+                if (sz > UINT64_MAX - sizeof(uint64_t) + 1)
+                        return -EBADMSG;
+
+                sz = ALIGN64(sz);
+                if (p > UINT64_MAX - sz)
+                        return -EBADMSG;
+
+                p += sz;
+        }
+
+        *ret_offset = p;
+
+        return 0;
+}
+
+static int journal_file_truncate(JournalFile *f) {
+        uint64_t p;
+        int r;
+
+        /* truncate excess from the end of archives */
+        r = journal_file_tail_end(f, &p);
+        if (r < 0)
+                return log_debug_errno(r, "Failed to determine end of tail object: %m");
+
+        /* arena_size can't exceed the file size, ensure it's updated before truncating */
+        f->header->arena_size = htole64(p - le64toh(f->header->header_size));
+
+        if (ftruncate(f->fd, p) < 0)
+                log_debug_errno(errno, "Failed to truncate %s: %m", f->path);
+
+        return 0;
+}
+
 /* This may be called from a separate thread to prevent blocking the caller for the duration of fsync().
  * As a result we use atomic operations on f->offline_state for inter-thread communications with
  * journal_file_set_offline() and journal_file_set_online(). */
@@ -117,6 +170,9 @@ static void journal_file_set_offline_internal(JournalFile *f) {
                         break;
 
                 case OFFLINE_SYNCING:
+                        if (f->archive)
+                                (void) journal_file_truncate(f);
+
                         (void) fsync(f->fd);
 
                         if (!__sync_bool_compare_and_swap(&f->offline_state, OFFLINE_SYNCING, OFFLINE_OFFLINING))
@@ -1089,7 +1145,7 @@ int journal_file_append_object(
 
         int r;
         uint64_t p;
-        Object *tail, *o;
+        Object *o;
         void *t;
 
         assert(f);
@@ -1101,26 +1157,9 @@ int journal_file_append_object(
         if (r < 0)
                 return r;
 
-        p = le64toh(f->header->tail_object_offset);
-        if (p == 0)
-                p = le64toh(f->header->header_size);
-        else {
-                uint64_t sz;
-
-                r = journal_file_move_to_object(f, OBJECT_UNUSED, p, &tail);
-                if (r < 0)
-                        return r;
-
-                sz = le64toh(READ_NOW(tail->object.size));
-                if (sz > UINT64_MAX - sizeof(uint64_t) + 1)
-                        return -EBADMSG;
-
-                sz = ALIGN64(sz);
-                if (p > UINT64_MAX - sz)
-                        return -EBADMSG;
-
-                p += sz;
-        }
+        r = journal_file_tail_end(f, &p);
+        if (r < 0)
+                return r;
 
         r = journal_file_allocate(f, p, size);
         if (r < 0)
-- 
2.47.3