[Bugs] [Bug 1377193] Poor smallfile read performance on Arbiter volume compared to Replica 3 volume

bugzilla at redhat.com bugzilla at redhat.com
Thu Sep 29 07:10:22 UTC 2016


--- Comment #6 from Worker Ant <bugzilla-bot at gluster.org> ---
COMMIT: http://review.gluster.org/15578 committed in release-3.8 by Pranith
Kumar Karampuri (pkarampu at redhat.com) 
commit 44dbec60a2cd8fe6a68ff30cb6b8a1cf67b717be
Author: Ravishankar N <ravishankar at redhat.com>
Date:   Tue Sep 27 10:39:58 2016 +0530

    afr: Ignore gluster internal (virtual) xattrs in metadata heal check

    Backport of http://review.gluster.org/#/c/15548/

    In arbiter configuration, posix-xlator in the arbiter brick always sets the
    GF_CONTENT_KEY in the response dict with a value 0. If the file size on the
    data bricks is more than quick-read's max-file-size (64kb default), those
    bricks don't set the key. Because of this difference in the no. of dict
    elements, afr triggers metadata heal in lookup code path, in turn leading
    extra lookups+inodelks.

    Changed afr dict comparison logic to ignore all virtual xattrs and the
    ones that we should not be healing.

    Change-Id: I05730bdd39d8fb0b9a49a5fc9c0bb01f0d3bb308
    BUG: 1377193
    Signed-off-by: Ravishankar N <ravishankar at redhat.com>
    Reviewed-on: http://review.gluster.org/15578
    Smoke: Gluster Build System <jenkins at build.gluster.org>
    NetBSD-regression: NetBSD Build System <jenkins at build.gluster.org>
    CentOS-regression: Gluster Build System <jenkins at build.gluster.org>
    Reviewed-by: Pranith Kumar Karampuri <pkarampu at redhat.com>

You are receiving this mail because:
You are on the CC list for the bug.
Unsubscribe from this bug https://bugzilla.redhat.com/token.cgi?t=2K7ncFrIps&a=cc_unsubscribe

More information about the Bugs mailing list