git: hammer2 - Optimize hammer2 support threads and dispatch

Matthew Dillon dillon at crater.dragonflybsd.org
Sat Sep 28 14:11:00 PDT 2019


commit 6b039a3d8e04f0c0e7b2738495235b6c03b51632
Author: Matthew Dillon <dillon at apollo.backplane.com>
Date:   Sat Sep 28 14:03:06 2019 -0700

    hammer2 - Optimize hammer2 support threads and dispatch
    
    * Refactor the XOP groups in order to be able to queue strategy
      calls, whenever possible, to the same CPU as the issuer.  This
      optimizes several cases and reduces unnecessary IPI traffic between
      cores.  The next best thing to do would be to not queue certain XOPs
      to an H2 support thread at all, but I would like to keep the threads
      intact for later clustering work.
    
      The best scaling case for this is when one has a large number of user
      threads doing I/O.  One instance of a single-threaded program on
      an otherwise idle machine might see a slightly reduction in performance
      but at the same time we completely avoid unnecessarily spamming all
      cores in the system on the behalf of a single program, so overhead is
      also significantly lower.
    
    * This will tend to increase the number of H2 support threads since
      we need a certain degree of multiplication for domain separation.
    
    * This should significantly increase I/O performance for multi-threaded
      workloads.

Summary of changes:
 sys/vfs/hammer2/hammer2.h        |  6 +++---
 sys/vfs/hammer2/hammer2_admin.c  | 32 ++++++++++++++++++++------------
 sys/vfs/hammer2/hammer2_disk.h   |  2 +-
 sys/vfs/hammer2/hammer2_vfsops.c | 28 ++++++++++++++++------------
 4 files changed, 40 insertions(+), 28 deletions(-)

http://gitweb.dragonflybsd.org/dragonfly.git/commitdiff/6b039a3d8e04f0c0e7b2738495235b6c03b51632


-- 
DragonFly BSD source repository



More information about the Commits mailing list