[Bugs] [Bug 1224157] New: Bitrot file crawling is too slow

bugzilla at redhat.com bugzilla at redhat.com
Fri May 22 09:32:37 UTC 2015 

https://bugzilla.redhat.com/show_bug.cgi?id=1224157

            Bug ID: 1224157
           Summary: Bitrot file crawling is too slow
           Product: Red Hat Gluster Storage
           Version: 3.1
         Component: glusterfs
     Sub Component: bitrot
          Severity: medium
          Assignee: rhs-bugs at redhat.com
          Reporter: rmekala at redhat.com
        QA Contact: rmekala at redhat.com
                CC: bugs at gluster.org, hchiramm at redhat.com,
                    nsathyan at redhat.com, vshankar at redhat.com



+++ This bug was initially created as a clone of Bug #1215120 +++

Description of problem:
===========================
Bitrot file crawling is too slow 


Version-Release number of selected component (if applicable):
==================================================================
glusterfs-server-3.7dev-0.1009.git8b987be.el6.x86_64

How reproducible:
======================
Always


Steps to Reproduce:
1.Create volume with one brick and create 100k files on the volume
2.After some time add one more brick and do rebalance
3.After rebalance bitrot is crawling the bricks but it is crawling one file per
min


Expected results:
======================
We need to optimise the crawling based on the system resouces avilability 

Additional info:

[root at rhs-client38 rajesh_snapshot]# strace -s 250 -tt -e open,close,getdents
-f -p 30343
Process 30343 attached with 24 threads - interrupt to quit
[pid 30583] 12:20:26.218247
open("/pavanbrick1/rajesh_snapshot/.glusterfs/f5/21/f521be5f-733a-4b62-a8de-cd4aab9d0e4c",
O_RDWR) = 34
[pid 30357] 12:20:26.221952 close(34)   = 0
[pid 30356] 12:20:28.818774
open("/pavanbrick1/rajesh_snapshot/.glusterfs/health_check", O_RDWR|O_CREAT,
0644) = 34
[pid 30356] 12:20:28.819006 close(34)   = 0

[pid 30356] 12:20:58.819232
open("/pavanbrick1/rajesh_snapshot/.glusterfs/health_check", O_RDWR|O_CREAT,
0644) = 34
[pid 30356] 12:20:58.819482 close(34)   = 0



[pid 30601] 12:21:26.225473
open("/pavanbrick1/rajesh_snapshot/.glusterfs/25/09/25094c22-b201-4bdf-97b2-fcef7da3c72e",
O_RDWR) = 34
[pid 30357] 12:21:26.228372 close(34)   = 0
[pid 30356] 12:21:28.819714
open("/pavanbrick1/rajesh_snapshot/.glusterfs/health_check", O_RDWR|O_CREAT,
0644) = 34
[pid 30356] 12:21:28.819946 close(34)   = 0
[pid 30356] 12:21:58.820147
open("/pavanbrick1/rajesh_snapshot/.glusterfs/health_check", O_RDWR|O_CREAT,
0644) = 34
[pid 30356] 12:21:58.820398 close(34)   = 0
[pid 30351] 12:22:26.232470
open("/pavanbrick1/rajesh_snapshot/.glusterfs/64/5f/645f7641-d8b7-416f-b659-93a70ed9dbf7",
O_RDWR) = 34
[pid 30357] 12:22:26.235462
open("/pavanbrick1/rajesh_snapshot/.glusterfs/landfill",
O_RDONLY|O_NONBLOCK|O_DIRECTORY|O_CLOEXEC) = 35
[pid 30357] 12:22:26.235571 getdents(35, /* 2 entries */, 32768) = 48
[pid 30357] 12:22:26.235671 getdents(35, /* 0 entries */, 32768) = 0
[pid 30357] 12:22:26.235748 close(35)   = 0
[pid 30357] 12:22:26.235906 close(34)   = 0
[pid 30356] 12:22:28.820625
open("/pavanbrick1/rajesh_snapshot/.glusterfs/health_check", O_RDWR|O_CREAT,
0644) = 34
[pid 30356] 12:22:28.820841 close(34)   = 0
[pid 30356] 12:22:58.821067
open("/pavanbrick1/rajesh_snapshot/.glusterfs/health_check", O_RDWR|O_CREAT,
0644) = 34
[pid 30356] 12:22:58.821284 close(34)   = 0
[pid 30601] 12:23:26.238836
open("/pavanbrick1/rajesh_snapshot/.glusterfs/12/d0/12d05f24-a61e-4e00-a77a-1900c701686a",
O_RDWR) = 34
[pid 30357] 12:23:26.241880 close(34)   = 0
[pid 30356] 12:23:28.821488
open("/pavanbrick1/rajesh_snapshot/.glusterfs/health_check", O_RDWR|O_CREAT,
0644) = 34
[pid 30356] 12:23:28.821743 close(34)   = 0
[pid 30356] 12:23:58.821967
open("/pavanbrick1/rajesh_snapshot/.glusterfs/health_check", O_RDWR|O_CREAT,
0644) = 34
[pid 30356] 12:23:58.822190 close(34)   = 0
[pid 30583] 12:24:26.245770
open("/pavanbrick1/rajesh_snapshot/.glusterfs/ea/d3/ead3c047-1317-43ce-a021-3548e3a4f84e",
O_RDWR) = 34
[pid 30357] 12:24:26.248618 close(34)   = 0
[pid 30356] 12:24:28.822393
open("/pavanbrick1/rajesh_snapshot/.glusterfs/health_check", O_RDWR|O_CREAT,
0644) = 34
[pid 30356] 12:24:28.822687 close(34)   = 0
[pid 30356] 12:24:58.822882
open("/pavanbrick1/rajesh_snapshot/.glusterfs/health_check", O_RDWR|O_CREAT,
0644) = 34
[pid 30356] 12:24:58.823130 close(34)   = 0
[pid 30601] 12:25:26.252417
open("/pavanbrick1/rajesh_snapshot/.glusterfs/fd/c1/fdc16026-7c95-4777-b49d-d9551c4c48e8",
O_RDWR) = 34
[pid 30357] 12:25:26.256171 close(34)   = 0
[pid 30356] 12:25:28.823367
open("/pavanbrick1/rajesh_snapshot/.glusterfs/health_check", O_RDWR|O_CREAT,
0644) = 34
[pid 30356] 12:25:28.823615 close(34)   = 0
[pid 30356] 12:25:58.823843
open("/pavanbrick1/rajesh_snapshot/.glusterfs/health_check", O_RDWR|O_CREAT,
0644) = 34
[pid 30356] 12:25:58.824062 close(34)   = 0
[pid 30583] 12:26:26.259865
open("/pavanbrick1/rajesh_snapshot/.glusterfs/97/b6/97b6e87f-47aa-4f40-9230-c1283f0391d4",
O_RDWR) = 34
[pid 30357] 12:26:26.262834 close(34)   = 0
[pid 30356] 12:26:28.824251
open("/pavanbrick1/rajesh_snapshot/.glusterfs/health_check", O_RDWR|O_CREAT,
0644) = 34
[pid 30356] 12:26:28.824450 close(34)   = 0

--- Additional comment from Venky Shankar on 2015-04-28 08:36:51 EDT ---

patch http://review.gluster.org/#/c/10375/ fixes this issue.

-- 
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=ZOXFSSnRmK&a=cc_unsubscribe

More information about the Bugs mailing list