From: Michael Vrable <mvrable@cs.ucsd.edu>
Date: Fri, 20 Aug 2010 20:51:31 +0000 (-0700)
Subject: Back out dirty reference tracking, as the design was flawed.
X-Git-Url: http://git.vrable.net/?p=bluesky.git;a=commitdiff_plain;h=9b1a8397b18ba54e6ad6cc306e1baaecda6fe1fe

Back out dirty reference tracking, as the design was flawed.

Objects can be written to the journal but not to the cloud--for example, if
a data block is written to the journal but overwritten before the file is
flushed to the cloud.  This write-combining is good, but the old code for
tracking when a journal segment could be reclaimed couldn't handle this.

So, back out that dirty reference tracking code, in preparation for
replacing it with another approach.
---

diff --git a/bluesky/bluesky-private.h b/bluesky/bluesky-private.h
index c527ee6..8601228 100644
--- a/bluesky/bluesky-private.h
+++ b/bluesky/bluesky-private.h
@@ -192,13 +192,6 @@ struct _BlueSkyCloudLog {
     int location_flags;
     int pending_read, pending_write;
 
-    // If the object is not yet flushed to cloud storage but is written to a
-    // journal file locally, a reference to that journal file so that we can
-    // keep the dirty_refs count updated.  When the object is deleted or
-    // becomes clean, decrement the dirty_refs counter of the journal file and
-    // set this pointer to NULL.
-    BlueSkyCacheFile *dirty_journal;
-
     // A stable identifier for the object (only changes when authenticated data
     // is written out, but stays the same when the in-cloud cleaner relocates
     // the object).
@@ -293,11 +286,6 @@ struct _BlueSkyCacheFile {
     BlueSkyLog *log;
     gboolean fetching, ready;   // Cloud data: downloading or ready for use
     int64_t atime;              // Access time, for cache management
-
-    /* Journal: Count of objects which are not yet committed to cloud storage
-     * but need to be; a non-zero value prevents the journal file from being
-     * deleted. */
-    gint dirty_refs;
 };
 
 BlueSkyLog *bluesky_log_new(const char *log_directory);
diff --git a/bluesky/cloudlog.c b/bluesky/cloudlog.c
index 8b88f64..e842fbf 100644
--- a/bluesky/cloudlog.c
+++ b/bluesky/cloudlog.c
@@ -158,8 +158,6 @@ void bluesky_cloudlog_unref(BlueSkyCloudLog *log)
         }
         g_array_unref(log->links);
         bluesky_string_unref(log->data);
-        if (log->dirty_journal != NULL)
-            g_atomic_int_add(&log->dirty_journal->dirty_refs, -1);
         g_free(log);
     }
 }
@@ -300,10 +298,6 @@ static void cloudlog_flush_complete(BlueSkyStoreAsync *async,
             item->pending_write &= ~CLOUDLOG_CLOUD;
             item->location_flags |= CLOUDLOG_CLOUD;
             bluesky_cloudlog_stats_update(item, 1);
-            if (item->dirty_journal != NULL) {
-                g_atomic_int_add(&item->dirty_journal->dirty_refs, -1);
-                item->dirty_journal = NULL;
-            }
             g_mutex_unlock(item->lock);
             bluesky_cloudlog_unref(item);
 
diff --git a/bluesky/debug.c b/bluesky/debug.c
index 0a5f254..207cb7b 100644
--- a/bluesky/debug.c
+++ b/bluesky/debug.c
@@ -56,9 +56,9 @@ static void cache_dump(gpointer key, gpointer value, gpointer user_data)
     BlueSkyCacheFile *cache = (BlueSkyCacheFile *)value;
 
     int64_t age = bluesky_get_current_time() - cache->atime;
-    g_print("%s addr=%p mapcount=%d refcount=%d dirty=%d atime_age=%f",
+    g_print("%s addr=%p mapcount=%d refcount=%d atime_age=%f",
             cache->filename, cache->addr, cache->mapcount, cache->refcount,
-            cache->dirty_refs, age / 1e6);
+            age / 1e6);
     if (cache->fetching)
         g_print(" (fetching)");
     g_print("\n");
diff --git a/bluesky/log.c b/bluesky/log.c
index a904fe1..5fd6e28 100644
--- a/bluesky/log.c
+++ b/bluesky/log.c
@@ -217,15 +217,6 @@ static gpointer log_thread(gpointer d)
 
         offset += sizeof(header) + sizeof(footer) + item->data->len;
 
-        /* Since we have just written a new dirty object to the journal,
-         * increment the count of live dirty objects in that journal file.  The
-         * count will be decremented when objects are deleted or written to the
-         * cloud. */
-        if (!(item->location_flags & CLOUDLOG_CLOUD)) {
-            g_atomic_int_add(&log->current_log->dirty_refs, 1);
-            item->dirty_journal = log->current_log;
-        }
-
         /* Replace the log item's string data with a memory-mapped copy of the
          * data, now that it has been written to the log file.  (Even if it
          * isn't yet on disk, it should at least be in the page cache and so
@@ -522,17 +513,16 @@ void bluesky_cachefile_gc(BlueSkyFS *fs)
          * then we'll just skip the file on this pass. */
         if (g_mutex_trylock(cachefile->lock)) {
             int64_t age = bluesky_get_current_time() - cachefile->atime;
-            g_print("%s addr=%p mapcount=%d refcount=%d dirty=%d atime_age=%f",
+            g_print("%s addr=%p mapcount=%d refcount=%d atime_age=%f",
                     cachefile->filename, cachefile->addr, cachefile->mapcount,
-                    cachefile->refcount, cachefile->dirty_refs, age / 1e6);
+                    cachefile->refcount, age / 1e6);
             if (cachefile->fetching)
                 g_print(" (fetching)");
             g_print("\n");
 
             if (g_atomic_int_get(&fs->log->disk_used) > DISK_CACHE_SIZE_TARGET
                 && g_atomic_int_get(&cachefile->refcount) == 0
-                && g_atomic_int_get(&cachefile->mapcount) == 0
-                && g_atomic_int_get(&cachefile->dirty_refs) == 0)
+                && g_atomic_int_get(&cachefile->mapcount) == 0)
             {
                 g_print("   ...deleting\n");
                 if (unlinkat(fs->log->dirfd, cachefile->filename, 0) < 0) {