RHEL Engineering is moving the tracking of its product development work on RHEL 6 through RHEL 9 to Red Hat Jira (issues.redhat.com). If you're a Red Hat customer, please continue to file support cases via the Red Hat customer portal. If you're not, please head to the "RHEL project" in Red Hat Jira and file new tickets here. Individual Bugzilla bugs in the statuses "NEW", "ASSIGNED", and "POST" are being migrated throughout September 2023. Bugs of Red Hat partners with an assigned Engineering Partner Manager (EPM) are migrated in late September as per pre-agreed dates. Bugs against components "kernel", "kernel-rt", and "kpatch" are only migrated if still in "NEW" or "ASSIGNED". If you cannot log in to RH Jira, please consult article #7032570. That failing, please send an e-mail to the RH Jira admins at rh-issues@redhat.com to troubleshoot your issue as a user management inquiry. The email creates a ServiceNow ticket with Red Hat. Individual Bugzilla bugs that are migrated will be moved to status "CLOSED", resolution "MIGRATED", and set with "MigratedToJIRA" in "Keywords". The link to the successor Jira issue will be found under "Links", have a little "two-footprint" icon next to it, and direct you to the "RHEL project" in Red Hat Jira (issue links are of type "https://issues.redhat.com/browse/RHEL-XXXX", where "X" is a digit). This same link will be available in a blue banner at the top of the page informing you that that bug has been migrated.
Bug 1451449 - fsck.gfs2 is too slow
Summary: fsck.gfs2 is too slow
Keywords:
Status: CLOSED WONTFIX
Alias: None
Product: Red Hat Enterprise Linux 7
Classification: Red Hat
Component: gfs2-utils
Version: 7.4
Hardware: Unspecified
OS: Unspecified
high
unspecified
Target Milestone: rc
: ---
Assignee: Andrew Price
QA Contact: cluster-qe@redhat.com
URL:
Whiteboard:
Depends On: 1721973
Blocks: 1111393 1469559 1497636 1546181
TreeView+ depends on / blocked
 
Reported: 2017-05-16 16:34 UTC by Nate Straz
Modified: 2020-10-06 10:54 UTC (History)
7 users (show)

Fixed In Version:
Doc Type: If docs needed, set a value
Doc Text:
Clone Of:
: 1721973 (view as bug list)
Environment:
Last Closed: 2020-10-06 10:54:33 UTC
Target Upstream Version:
Embargoed:


Attachments (Terms of Use)

Description Nate Straz 2017-05-16 16:34:56 UTC
Description of problem:

Checking a 300TB file system which is 80% full can take a full week with an average throughput of 5-10MB/s.

Version-Release number of selected component (if applicable):
gfs2-utils-3.1.10-3.el7

How reproducible:
Easily, with enough time

Steps to Reproduce:
1. Create a 300TB GFS2 file system
2. Fill it to 80% full with millions of files
3. run fsck.gfs2 on it

Actual results:

[root@dash-02 sts-rhel7.4]# gfs2/bin/fsck-perf -l $PWD -k -S 299.99T
GFS2 fsck master (built Mar 29 2017 09:51:30)
Copyright (C) Red Hat, Inc.  2004-2010  All rights reserved.
  VG   #PV #LV #SN Attr   VSize    VFree
  fsck   6   0   0 wz--n- <300.00t <300.00t
  Using default stripesize 64.00 KiB.
  Rounding up size to full physical extent 299.99 TiB
  Rounding size 299.99 TiB (78640579 extents) up to stripe boundary size 299.99 TiB(78640584 extents).
  Wiping gfs2 signature on /dev/fsck/perf.
  Logical volume "perf" created.
=== mkfs.gfs2 299.99T ===
Warning: device is not properly aligned. This may harm performance.
/dev/fsck/perf is a symbolic link to /dev/dm-15
This will destroy any data on /dev/dm-15
Adding journals: Done
Building resource groups: Done
Creating quota file: Done
Writing superblock and syncing: Done
Device:                    /dev/fsck/perf
Block size:                4096
Device size:               307189.78 GB (80527958016 blocks)
Filesystem size:           307189.72 GB (80527937588 blocks)
Journals:                  1
Resource groups:           1227860
Locking protocol:          "lock_nolock"
Lock table:                ""
UUID:                      19fa73a2-893c-401c-8c5b-08a11dbd54ad
3.01user 29.20system 1:20.77elapsed 39%CPU (0avgtext+0avgdata 499932maxresident)k
3984inputs+49610040outputs (0major+290025minor)pagefaults 0swaps
=== fsck.gfs2 0% full ===
Tue Apr 11 12:06:13 CDT 2017
Initializing fsck
Validating resource group index.
Level 1 resource group check: Checking if all rgrp and rindex values are good.
(level 1 passed)
Starting pass1
Reconciling bitmaps.
reconcile_bitmaps completed in 7m18.074s
pass1 completed in 7m24.522s
Starting pass1b
pass1b completed in 0.000s
Starting pass2
pass2 completed in 0.000s
Starting pass3
pass3 completed in 0.000s
Starting pass4
pass4 completed in 2m57.362s
Starting check_statfs
check_statfs completed in 0.071s
gfs2_fsck complete
663.58user 39.96system 13:15.41elapsed 88%CPU (0avgtext+0avgdata 39742632maxresident)k
49612664inputs+272outputs (0major+19923519minor)pagefaults 0swaps
=== mockup ===
Tue Apr 11 12:19:35 CDT 2017
Increasing mu to 18.01
Working directory: /mnt/perf
Number of files: 1000000000
Mu: 18.0093092464
Sigma: 1.8
235951704 files created
80% full
16550.49user 560922.02system 62:39:14elapsed 256%CPU (0avgtext+0avgdata 19356maxresident)k
23410584inputs+265964210032outputs (674major+268541011minor)pagefaults 0swaps
Filesystem                    Size  Used Avail Use% Mounted on
/dev/mapper/fsck-perf-nodata  300T  241T   60T  81% /mnt/perf
Filesystem                        Inodes     IUsed       IFree IUse% Mounted on
/dev/mapper/fsck-perf-nodata 16322557438 236036021 16086521417    2% /mnt/perf
kworkers:
1298
=== fsck.gfs2 80% full ===
Fri Apr 14 02:58:56 CDT 2017
Initializing fsck
Validating resource group index.
Level 1 resource group check: Checking if all rgrp and rindex values are good.
(level 1 passed)
Starting pass1
Large file at ...
Reconciling bitmaps.
reconcile_bitmaps completed in 7m28.573s
pass1 completed in 6d21h40m6.121s
Starting pass1b
pass1b completed in 0.000s
Starting pass2
pass2 completed in 1h5m27.953s
Starting pass3
pass3 completed in 0.045s
Starting pass4
pass4 completed in 3m1.923s
Starting check_statfs
check_statfs completed in 0.137s
gfs2_fsck complete
32496.80user 5599.91system 166:52:46elapsed 6%CPU (0avgtext+0avgdata 47736764maxresident)k
5764330680inputs+336outputs (31065major+201090615minor)pagefaults 0swaps



Expected results:


Additional info:

Comment 8 Andrew Price 2020-10-06 10:54:33 UTC
I'm going to close this one as the work is still at the experimental stage and the changes required would likely be too intrusive for 7.9.z. Bug 1721973 is the RHEL8 version.


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