X Settled on what should happen after writeout for wcfs case

bigfile/virtmem.c

@@ -425,18 +425,53 @@ int fileh_dirty_writeout(BigFileH *fileh, enum WriteoutFlags flags)
                 goto out;
         }
 
-        /* page.state -> PAGE_LOADED and correct mappings RW -> R */
-        // XXX wcfs: just remmap base file? (but it does not yet have stored changes)
-        // XXX       -> vma_remove_readonly_overlay()?
+        /* wcfs:  remmap RW pages to base layer
+         * !wcfs: page.state -> PAGE_LOADED and correct mappings RW -> R
+         *
+         * NOTE for transaction storage (ZODB and ZBigFile) storeblk creates
+         * new transaction on database side, but does not update current DB
+         * connection to view that transaction. Thus if loadblk will be loaded
+         * with not-yet-resynced DB connection, it will return old - not stored
+         * - data. For !wcfs case this is partly mitigated by the fact that
+         * stored pages are kept as PAGE_LOADED in ram, but it cannot be
+         * relied as ram_reclaim can drop those pages and read access to them
+         * will trigger loadblk from database which will return old data.
+         * For wcfs case remapping to base layer will always return old data
+         * until wcfs mapping is updated to view database at newer state.
+         *
+         * In general it is a bug to access data pages in between transactions,
+         * so we accept those corner case difference in between wcfs and !wcfs.
+         */
         if (flags & WRITEOUT_MARKSTORED) {
             page->state = PAGE_LOADED;
             list_del_init(&page->in_dirty);
 
             list_for_each(hmmap, &fileh->mmaps) {
                 VMA *vma = list_entry(hmmap, typeof(*vma), same_fileh);
+                if (vma->mmap_overlay) {
+                    /* wcfs:  RW -> base layer */
+                    vma_page_ensure_unmapped(vma, page);
+                } else {
+                    /* !wcfs: RW -> R*/
                     vma_page_ensure_notmappedrw(vma, page);
                 }
             }
+
+            // XXX just relying on page->refcnt==0 is wrong - for !wcfs case
+            // when there are no mappings it will unnecessarily drop fileh cache.
+            // -> move mmap_overlay from vma to fileh and check:
+            // if (fileh->mmap_overlay) {
+            //  ASSERT(page->refcnt == 0);
+            //  page_drop(page);
+            // }
+#if 0
+            /* if noone is using the page (ex all vmas use base layer) - drop
+             * it completely without unnecessarily growing RSS and relying on reclaim. */
+            if (page->refcnt == 0) {
+
+            }
+#endif
+        }
     }
 
 

include/wendelin/bigfile/virtmem.h

@@ -29,6 +29,8 @@
  * Read access to mapped pages cause their on-demand loading, and write access
  * marks modified pages as dirty. Dirty pages then can be on request either
  * written out back to file or discarded.
+ *
+ * XXX update for wcfs.
  */
 
 #include <stdint.h>
@@ -205,8 +207,9 @@ enum WriteoutFlags {
 
     /* mark dirty pages as stored to file ok
      *
-     * pages state becomes PAGE_LOADED and all mmaps are updated to map pages as
-     * R/O to track further writes.
+     * wcfs:  all mmaps are updated to map read-only to base layer.
+     * !wcfs: pages state becomes PAGE_LOADED and all mmaps are updated to map
+     *        pages as R/O to track further writes.
      */
     WRITEOUT_MARKSTORED     = 1 << 1,
 };