[Xen-changelog] [xen-unstable] tmem: reclaim minimal memory proactively

[Xen patchbot-unstable <patchbot-unstable@xxxxxxxxxxxxxxxxxxx>]

# HG changeset patch
# User Keir Fraser <keir.fraser@xxxxxxxxxx>
# Date 1260355496 0
# Node ID 18342df0f9dcf3a0a5a7ce05ea0218cf94335157
# Parent  2c6a04fdf8fb00a26aec125952a710de6cc8439c
tmem: reclaim minimal memory proactively

When a single domain is using most/all of tmem memory
for ephemeral pages belonging to the same object, e.g.
when copying a single huge file larger than ephemeral
memory, long lists are traversed looking for a page to
evict that doesn't belong to this object (as pages in
the object for which a page is currently being inserted
are locked and cannot be evicted).  This is essentially
a livelock.

Avoid this by proactively ensuring there is a margin
of available memory (1MB) before locks are taken on
the object.

Signed-off-by: Dan Magenheimer <dan.magenheimer@xxxxxxxxxx>
---
 xen/common/tmem.c          |   20 ++++++++++++++++++++
 xen/include/xen/tmem_xen.h |    5 +++++
 2 files changed, 25 insertions(+)

diff -r 2c6a04fdf8fb -r 18342df0f9dc xen/common/tmem.c
--- a/xen/common/tmem.c Wed Dec 09 10:44:11 2009 +0000
+++ b/xen/common/tmem.c Wed Dec 09 10:44:56 2009 +0000
@@ -1091,6 +1091,24 @@ static unsigned long tmem_relinquish_npa
     if ( avail_pages )
         tmh_release_avail_pages_to_host();
     return avail_pages;
+}
+
+/* Under certain conditions (e.g. if each client is putting pages for exactly
+ * one object), once locks are held, freeing up memory may
+ * result in livelocks and very long "put" times, so we try to ensure there
+ * is a minimum amount of memory (1MB) available BEFORE any data structure
+ * locks are held */
+static inline void tmem_ensure_avail_pages(void)
+{
+    int failed_evict = 10;
+
+    while ( !tmh_free_mb() )
+    {
+        if ( tmem_evict() )
+            continue;
+        else if ( failed_evict-- <= 0 )
+            break;
+    }
 }
 
 /************ TMEM CORE OPERATIONS ************************************/
@@ -2315,10 +2333,12 @@ EXPORT long do_tmem_op(tmem_cli_op_t uop
                               op.u.new.uuid[0], op.u.new.uuid[1]);
         break;
     case TMEM_NEW_PAGE:
+        tmem_ensure_avail_pages();
         rc = do_tmem_put(pool, op.u.gen.object,
                          op.u.gen.index, op.u.gen.cmfn, 0, 0, 0, NULL);
         break;
     case TMEM_PUT_PAGE:
+        tmem_ensure_avail_pages();
         rc = do_tmem_put(pool, op.u.gen.object,
                     op.u.gen.index, op.u.gen.cmfn, 0, 0, PAGE_SIZE, NULL);
         if (rc == 1) succ_put = 1;
diff -r 2c6a04fdf8fb -r 18342df0f9dc xen/include/xen/tmem_xen.h
--- a/xen/include/xen/tmem_xen.h        Wed Dec 09 10:44:11 2009 +0000
+++ b/xen/include/xen/tmem_xen.h        Wed Dec 09 10:44:56 2009 +0000
@@ -250,6 +250,11 @@ static inline unsigned long tmh_freeable
 {
     return (tmh_avail_pages() + _atomic_read(freeable_page_count)) >>
             (20 - PAGE_SHIFT);
+}
+
+static inline unsigned long tmh_free_mb(void)
+{
+    return (tmh_avail_pages() + total_free_pages()) >> (20 - PAGE_SHIFT);
 }
 
 /*

_______________________________________________
Xen-changelog mailing list
Xen-changelog@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-changelog