Note: This bug is displayed in read-only format because the product is no longer active in Red Hat Bugzilla.
This project is now read‑only. Starting Monday, February 2, please use https://ibm-ceph.atlassian.net/ for all bug tracking management.

Bug 2371495

Summary: [IBM_Support] File splitting and file moves on cephfs subvolume are slow
Product: [Red Hat Storage] Red Hat Ceph Storage Reporter: Steve Baldwin <sbaldwin>
Component: CephFSAssignee: Patrick Donnelly <pdonnell>
Status: CLOSED CURRENTRELEASE QA Contact: Manimaran M <manim>
Severity: high Docs Contact:
Priority: high    
Version: 7.1CC: bkunal, ceph-eng-bugs, cephqe-warriors, gfarnum, hyelloji, isawant, ngangadh, pchikhal, pdhange, pdonnell, rsachere, tdesala, tserlin, vereddy, vmaurya, vshankar, vumrao
Target Milestone: ---Flags: pdhange: needinfo-
isawant: needinfo-
hyelloji: needinfo+
Target Release: 9.0   
Hardware: x86_64   
OS: Linux   
Whiteboard:
Fixed In Version: ceph-19.2.1-227 Doc Type: Bug Fix
Doc Text:
Cause: MDS would incorrectly delay flushing its log to satisfy durability requirements when certain internal lock flows were executed before a rename operation replies to a client. Consequence: Some operations would have delayed resolution for up to the MDS tick interval (5 seconds). Fix: MDS now flushes its log correctly. Result: Conflicting operations are no longer artificially delayed.
 Story Points: ---
Clone Of: Environment:
Last Closed: 2025-09-16 00:12:28 UTC Type: Bug
Regression: --- Mount Type: ---
Documentation: --- CRM:
Verified Versions: Category: ---
oVirt Team: --- RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: --- Target Upstream Version:
Embargoed:
Bug Depends On:    
Bug Blocks: 2375845, 2376164, 2383118    

Description Steve Baldwin 2025-06-10 16:11:10 UTC 
Description of problem:
Customer is experiencing a significant degraded performance when executing a file split/move operation (1 million line file is split into 50,000 files) and files are moved to different directories

Version-Release number of selected component (if applicable):
ceph 18.2.1-298 (7.1z3)
odf  4.14.17

How reproducible:
Always at the customer site.  This is occurring in 3 of the 4 clusters.

Steps to Reproduce:
1. Receive 4 1 million line files from mainframe
2. Execute a split/move operation to break up 1 of the million line file into 50,000 files and move files to different directories.


Actual results:
File splits and moves are significantly slower than they were prior to the upgrade.

Expected results:
File splits and moves should produce similar performance as on the older version. 

Additional info:
The cluster which does not experience the issue is running older version of ceph/odf/ocp version (4.12)
Comment 45 Red Hat Bugzilla 2026-02-06 04:26:18 UTC 
The needinfo request[s] on this closed bug have been removed as they have been unresolved for 120 days or the product is inactive and locked