Bug 1455872 - [Perf]: 25% regression on sequential reads on EC over SMB3
Summary: [Perf]: 25% regression on sequential reads on EC over SMB3
Keywords:
Status: CLOSED CURRENTRELEASE
Alias: None
Product: GlusterFS
Classification: Community
Component: open-behind
Version: mainline
Hardware: x86_64
OS: Linux
unspecified
high
Target Milestone: ---
Assignee: Milind Changire
QA Contact:
URL:
Whiteboard:
Depends On:
Blocks: 1419807
TreeView+ depends on / blocked
 
Reported: 2017-05-26 10:51 UTC by Milind Changire
Modified: 2018-10-23 15:06 UTC (History)
11 users (show)

Fixed In Version: glusterfs-5.0
Clone Of: 1419807
Environment:
Last Closed: 2018-10-23 15:06:00 UTC
Regression: ---
Mount Type: ---
Documentation: ---
CRM:
Verified Versions:
Embargoed:


Attachments (Terms of Use)

Comment 1 Milind Changire 2017-05-26 10:54:30 UTC
Description:
There is a performance drop for large files if opened with a delay.

Comment 2 Worker Ant 2017-05-26 10:57:15 UTC
REVIEW: https://review.gluster.org/17377 (performance/open-behind: open early for large files) posted (#5) for review on master by Milind Changire (mchangir)

Comment 3 Worker Ant 2018-07-14 13:02:14 UTC
REVIEW: https://review.gluster.org/20511 (performance/open-behind: don't use anonymous fds for reads by default) posted (#1) for review on master by Raghavendra G

Comment 4 Worker Ant 2018-08-03 00:59:20 UTC
COMMIT: https://review.gluster.org/20511 committed in master by "Raghavendra G" <rgowdapp> with a commit message- performance/open-behind: don't use anonymous fds for reads by default

anonymous fds interfere with working of read-ahead as read-ahead won't
be able to store its cache in fd. Also, as seen in bz 1455872,
anonymous fds also affect performance of large file sequential reads
as the cost of opening fd for each read on brick stack is
significant. So, have a proper fd which enables read-ahead to store
its cache and brick stack to reuse the fd during reads.

With this change test
tests/bugs/snapshot/bug-1167580-set-proper-uid-and-gid-during-nfs-access.t
fails consistently. The failure can also be seen with open-behind
off. bz 1611532 has been filed to track the issue with test. Thanks to
Rafi <rkavunga> for assistance provided in debugging test
failure.

Change-Id: Ifa52d8ff017f115e83247f3396b9d27f0295ce3f
Signed-off-by: Raghavendra G <rgowdapp>
Fixes: bz#1455872

Comment 5 Shyamsundar 2018-10-23 15:06:00 UTC
This bug is getting closed because a release has been made available that should address the reported issue. In case the problem is still not fixed with glusterfs-5.0, please open a new bug report.

glusterfs-5.0 has been announced on the Gluster mailinglists [1], packages for several distributions should become available in the near future. Keep an eye on the Gluster Users mailinglist [2] and the update infrastructure for your distribution.

[1] https://lists.gluster.org/pipermail/announce/2018-October/000115.html
[2] https://www.gluster.org/pipermail/gluster-users/


Note You need to log in before you can comment on or make changes to this bug.