Change the management of cached pages (PQ_CACHE) in two fundamental

ways:

(1) Cached pages are no longer kept in the object's resident page
splay tree and memq.  Instead, they are kept in a separate per-object
splay tree of cached pages.  However, access to this new per-object
splay tree is synchronized by the _free_ page queues lock, not to be
confused with the heavily contended page queues lock.  Consequently, a
cached page can be reclaimed by vm_page_alloc(9) without acquiring the
object's lock or the page queues lock.

This solves a problem independently reported by tegge@ and Isilon.
Specifically, they observed the page daemon consuming a great deal of
CPU time because of pages bouncing back and forth between the cache
queue (PQ_CACHE) and the inactive queue (PQ_INACTIVE).  The source of
this problem turned out to be a deadlock avoidance strategy employed
when selecting a cached page to reclaim in vm_page_select_cache().
However, the root cause was really that reclaiming a cached page
required the acquisition of an object lock while the page queues lock
was already held.  Thus, this change addresses the problem at its
root, by eliminating the need to acquire the object's lock.

Moreover, keeping cached pages in the object's primary splay tree and
memq was, in effect, optimizing for the uncommon case.  Cached pages
are reclaimed far, far more often than they are reactivated.  Instead,
this change makes reclamation cheaper, especially in terms of
synchronization overhead, and reactivation more expensive, because
reactivated pages will have to be reentered into the object's primary
splay tree and memq.

(2) Cached pages are now stored alongside free pages in the physical
memory allocator's buddy queues, increasing the likelihood that large
allocations of contiguous physical memory (i.e., superpages) will
succeed.

Finally, as a result of this change long-standing restrictions on when
and where a cached page can be reclaimed and returned by
vm_page_alloc(9) are eliminated.  Specifically, calls to
vm_page_alloc(9) specifying VM_ALLOC_INTERRUPT can now reclaim and
return a formerly cached page.  Consequently, a call to malloc(9)
specifying M_NOWAIT is less likely to fail.

Discussed with: many over the course of the summer, including jeff@,
   Justin Husted @ Isilon, peter@, tegge@
Tested by: an earlier version by kris@
Approved by: re (kensmith)

1 files changed, 2 insertions, 2 deletions

diff --git a/sys/sys/vmmeter.h b/sys/sys/vmmeter.h
index bdd1964..2b4794a 100644
--- a/sys/sys/vmmeter.h
+++ b/sys/sys/vmmeter.h
@@ -68,7 +68,7 @@ struct vmmeter {
 	u_int v_vnodepgsin;	/* (p) vnode_pager pages paged in */
 	u_int v_vnodepgsout;	/* (p) vnode pager pages paged out */
 	u_int v_intrans;	/* (p) intransit blocking page faults */
-	u_int v_reactivated;	/* (q) pages reactivated from free list */
+	u_int v_reactivated;	/* (f) pages reactivated from free list */
 	u_int v_pdwakeups;	/* (f) times daemon has awaken from sleep */
 	u_int v_pdpages;	/* (q) pages analyzed by daemon */
 
@@ -89,7 +89,7 @@ struct vmmeter {
 	u_int v_active_count;	/* (q) pages active */
 	u_int v_inactive_target; /* (c) pages desired inactive */
 	u_int v_inactive_count;	/* (q) pages inactive */
-	u_int v_cache_count;	/* (q) pages on buffer cache queue */
+	u_int v_cache_count;	/* (f) pages on buffer cache queue */
 	u_int v_cache_min;	/* (c) min pages desired on cache queue */
 	u_int v_cache_max;	/* (c) max pages in cached obj */
 	u_int v_pageout_free_min;   /* (c) min pages reserved for kernel */