[Bugs] [Bug 1439148] New: Parallel readdir on Gluster NFS displays less number of dentries

[bugzilla at redhat.com]

https://bugzilla.redhat.com/show_bug.cgi?id=1439148

            Bug ID: 1439148
           Summary: Parallel readdir on Gluster NFS displays less number
                    of dentries
           Product: GlusterFS
           Version: 3.10
         Component: unclassified
          Assignee: bugs at gluster.org
          Reporter: pgurusid at redhat.com
                CC: bugs at gluster.org
        Depends On: 1436086



+++ This bug was initially created as a clone of Bug #1436086 +++

Description of problem:

    In readdirp fop, op_errno is overloaded to indicate the EOD detection.
    If op_errno contains ENOENT, then it indicates that there are no
    further entries pending read in the directory. Currently NFS uses the
    ENOENT to identify the EOD.

    Issue:
    NFS clients issues a 4K buffer for readdirp, readdir-ahead converts it
    to 128K buffer as its reading ahead. If there are 100 entries in the
    bricks, 128K can get all 100 and store in readdir-ahead, but only 23
    entries that can be fit in 4K will be sent to NFS. Since the whole
    100 entries were read from brick, the op_errno is set to ENOENT, and
    the op_errno is propagated as is when sent to NFS. Hence NFS client
    in reading 23 entries thinks it reached EOD.

Reproducer:
Run the test case with parallel readdir on
./tests/bugs/distribute/bug-1190734.t

Version-Release number of selected component (if applicable):


How reproducible:


Steps to Reproduce:
1.
2.
3.

Actual results:


Expected results:


Additional info:

--- Additional comment from Worker Ant on 2017-03-27 02:39:19 EDT ---

REVIEW: https://review.gluster.org/16953 (reddir-ahead: Fix EOD propagation
problem) posted (#1) for review on master by Poornima G (pgurusid at redhat.com)

--- Additional comment from Worker Ant on 2017-04-05 02:24:36 EDT ---

COMMIT: https://review.gluster.org/16953 committed in master by Raghavendra G
(rgowdapp at redhat.com) 
------
commit 61f76f318faed395660f5bbcfe39616b39c158f0
Author: Poornima G <pgurusid at redhat.com>
Date:   Mon Mar 27 11:38:28 2017 +0530

    reddir-ahead: Fix EOD propagation problem

    In readdirp fop, op_errno is overloaded to indicate the EOD detection.
    If op_errno contains ENOENT, then it indicates that there are no
    further entries pending read in the directory. Currently NFS uses the
    ENOENT to identify the EOD.

    Issue:
    NFS clients issues a 4K buffer for readdirp, readdir-ahead converts it
    to 128K buffer as its reading ahead. If there are 100 entries in the
    bricks, 128K can get all 100 and store in readdir-ahead, but only 23
    entries that can be fit in 4K will be sent to NFS. Since the whole
    100 entries were read from brick, the op_errno is set to ENOENT, and
    the op_errno is propagated as is when sent to NFS. Hence NFS client
    in reading 23 entries thinks it reached EOD.

    Solution:
    Do not propogate ENOENT errno, unless all the entries are read
    from the readdir ahead buffer.

    Change-Id: I4f173a77b21ab9e98ae35e291a45b8fc0cde65bd
    BUG: 1436086
    Signed-off-by: Poornima G <pgurusid at redhat.com>
    Reviewed-on: https://review.gluster.org/16953
    Smoke: Gluster Build System <jenkins at build.gluster.org>
    Reviewed-by: Raghavendra G <rgowdapp at redhat.com>
    NetBSD-regression: NetBSD Build System <jenkins at build.gluster.org>
    CentOS-regression: Gluster Build System <jenkins at build.gluster.org>


Referenced Bugs:

https://bugzilla.redhat.com/show_bug.cgi?id=1436086
[Bug 1436086] Parallel readdir on Gluster NFS displays less number of
dentries
-- 
You are receiving this mail because:
You are on the CC list for the bug.
You are the assignee for the bug.