| Summary: | Determine best ratio wherein distribute is truly deterministic | ||
|---|---|---|---|
| Product: | [Community] GlusterFS | Reporter: | Chida <chida> |
| Component: | distribute | Assignee: | Harshavardhana <fharshav> |
| Status: | CLOSED NOTABUG | QA Contact: | |
| Severity: | low | Docs Contact: | |
| Priority: | low | ||
| Version: | 2.0.9 | CC: | cww, gluster-bugs, shehjart |
| Target Milestone: | --- | ||
| Target Release: | --- | ||
| Hardware: | All | ||
| OS: | Linux | ||
| Whiteboard: | |||
| Fixed In Version: | Doc Type: | Bug Fix | |
| Doc Text: | Story Points: | --- | |
| Clone Of: | Environment: | ||
| Last Closed: | Type: | --- | |
| Regression: | --- | Mount Type: | --- |
| Documentation: | --- | CRM: | |
| Verified Versions: | Category: | --- | |
| oVirt Team: | --- | RHEL 7.3 requirements from Atomic Host: | |
| Cloudforms Team: | --- | Target Upstream Version: | |
|
Description
Chida
2010-02-19 12:28:23 UTC
This ticket is to find total number of servers v/s total number of files required to reach deterministic file hashing. As example we have seen with 4096 thread runs of mpi_io over a 24server setup leads to file hashing of large number of files to same node perhaps in 400's rather than 150-170 against each server. Whereas 8192 threads leads us to 330-350 thread ratio per server, which is perfect. Much research is required to understand how well with lesser and larger files we can reach deterministic hashing. Please reopen this in the req bugzilla |