Skip to content

[DNM] simple multithread mds#10560

Closed
ukernel wants to merge 38 commits intoceph:masterfrom
ukernel:wip-mds-multithread
Closed

[DNM] simple multithread mds#10560
ukernel wants to merge 38 commits intoceph:masterfrom
ukernel:wip-mds-multithread

Conversation

@ukernel
Copy link
Contributor

@ukernel ukernel commented Aug 3, 2016

Simple in-memory MDS for verifying lock design. So far only getattr,setattr,mkdir,mknod,symlink, link,unlink,readdir and rename work.

Basically, The mutex in CInode protects inode itself and its primary parent linkage. The mutex in directory inode also protects inode's CDirs and CDentries in CDirs.

A strange thing of this lock design is that: updateing an inode needs two locks: inode's mutex and its parent dir inode's mutex. The reason is that inode is stored in dirfrag, updating an inode actually updates dirfrag.

@ukernel ukernel added the cephfs Ceph File System label Aug 3, 2016
@ukernel ukernel force-pushed the wip-mds-multithread branch 4 times, most recently from 01b16dc to 64420a1 Compare August 11, 2016 09:34
@ukernel ukernel force-pushed the wip-mds-multithread branch 2 times, most recently from a7b913b to e76193a Compare August 15, 2016 12:38
@ukernel
Copy link
Contributor Author

ukernel commented Aug 15, 2016

now, the multi-threads MDS can survive fsstress

@ukernel ukernel force-pushed the wip-mds-multithread branch from e76193a to 986fbed Compare August 23, 2016 09:42
@ukernel
Copy link
Contributor Author

ukernel commented Aug 23, 2016

bring back basic journal code (no trim log code). we can run some basic performance test on it

@ukernel ukernel force-pushed the wip-mds-multithread branch 7 times, most recently from 36b259e to a8b6d46 Compare September 1, 2016 00:05
@ukernel ukernel force-pushed the wip-mds-multithread branch 7 times, most recently from d4d61e3 to e49e948 Compare September 6, 2016 14:30
@ukernel ukernel force-pushed the wip-mds-multithread branch 4 times, most recently from fcce6a2 to 2f54984 Compare September 13, 2016 13:58
@ukernel ukernel force-pushed the wip-mds-multithread branch 2 times, most recently from f2a7d8a to ba19765 Compare September 20, 2016 08:42
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Signed-off-by: Yan, Zheng <zyan@redhat.com>
For inter-operation between mds and mds2

Signed-off-by: Yan, Zheng <zyan@redhat.com>
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Signed-off-by: Yan, Zheng <zyan@redhat.com>
@ukernel ukernel force-pushed the wip-mds-multithread branch from 6909263 to d32a66a Compare October 27, 2016 07:49
@ghost
Copy link

ghost commented Nov 17, 2016

jenkins test this please (no logs)

@ghost
Copy link

ghost commented Nov 21, 2016

jenkins test this please (eio now ignored in master)

@ukernel ukernel changed the title [DNM] simple in memory multithread mds [DNM] simple multithread mds Jan 12, 2017
Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
endif()

add_subdirectory(script)

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@ukernel It would be good to make Commit title as

DNM: simple multithreaded mds

@stale
Copy link

stale bot commented Oct 17, 2018

This pull request has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs.
If you are a maintainer or core committer, please follow-up on this issue to identify what steps should be taken by the author to move this proposed change forward.
If you are the author of this pull request, thank you for your proposed contribution. If you believe this change is still appropriate, please ensure that any feedback has been addressed and ask for a code review.

@stale stale bot added the stale label Oct 17, 2018
@batrick batrick removed the stale label Mar 7, 2019
@stale
Copy link

stale bot commented May 6, 2019

This pull request has been automatically marked as stale because it has not had any activity for 60 days. It will be closed if no further activity occurs for another 30 days.
If you are a maintainer or core committer, please follow-up on this pull request to identify what steps should be taken by the author to move this proposed change forward.
If you are the author of this pull request, thank you for your proposed contribution. If you believe this change is still appropriate, please ensure that any feedback has been addressed and ask for a code review.

@stale stale bot added the stale label May 6, 2019
@stale
Copy link

stale bot commented Aug 4, 2019

This pull request has been automatically closed because there has been no activity for 90 days. Please feel free to reopen this pull request (or open a new one) if the proposed change is still appropriate. Thank you for your contribution!

@stale stale bot closed this Aug 4, 2019
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants