On 02/02/18 04:18, Daniel Jordan wrote:

On 02/01/2018 10:54 AM, Steven Whitehouse wrote:

On 31/01/18 23:04, daniel.m.jor...@oracle.com wrote:
lru_lock, a per-node* spinlock that protects an LRU list, is one of the
hottest locks in the kernel.  On some workloads on large machines, it
shows up at the top of lock_stat.

One way to improve lru_lock scalability is to introduce an array of locks,
with each lock protecting certain batches of LRU pages.

         *ooooooooooo**ooooooooooo**ooooooooooo**oooo ...
         |           ||           ||           ||
          \ batch 1 /  \ batch 2 /  \ batch 3 /

In this ASCII depiction of an LRU, a page is represented with either '*'
or 'o'.  An asterisk indicates a sentinel page, which is a page at the
edge of a batch.  An 'o' indicates a non-sentinel page.

To remove a non-sentinel LRU page, only one lock from the array is
required.  This allows multiple threads to remove pages from different
batches simultaneously.  A sentinel page requires lru_lock in addition to
a lock from the array.

Full performance numbers appear in the last patch in this series, but this
prototype allows a microbenchmark to do up to 28% more page faults per
second with 16 or more concurrent processes.

This work was developed in collaboration with Steve Sistare.

Note: This is an early prototype.  I'm submitting it now to support my
request to attend LSF/MM, as well as get early feedback on the idea.  Any
comments appreciated.

* lru_lock is actually per-memcg, but without memcg's in the picture it
   becomes per-node.
GFS2 has an lru list for glocks, which can be contended under certain workloads. Work is still ongoing to figure out exactly why, but this looks like it might be a good approach to that issue too. The main purpose of GFS2's lru list is to allow shrinking of the glocks under memory pressure via the gfs2_scan_glock_lru() function, and it looks like this type of approach could be used there to improve the scalability,

Glad to hear that this could help in gfs2 as well.

Hopefully struct gfs2_glock is less space constrained than struct page for storing the few bits of metadata that this approach requires.


We obviously want to keep gfs2_glock small, however within reason then yet we can add some additional fields as required. The use case is pretty much a standard LRU list, so items are added and removed, mostly at the active end of the list, and the inactive end of the list is scanned periodically by gfs2_scan_glock_lru()


Reply via email to