From: "Yan, Zheng" <zheng.z.yan@intel.com>
To: Sage Weil <sage@inktank.com>
Cc: ceph-devel@vger.kernel.org
Subject: Re: [PATCH 07/25] mds: don't early reply rename
Date: Tue, 29 Jan 2013 09:44:09 +0800 [thread overview]
Message-ID: <51072969.1040705@intel.com> (raw)
In-Reply-To: <alpine.DEB.2.00.1301281342130.2055@cobra.newdream.net>
On 01/29/2013 05:44 AM, Sage Weil wrote:
> On Wed, 23 Jan 2013, Yan, Zheng wrote:
>> From: "Yan, Zheng" <zheng.z.yan@intel.com>
>>
>> _rename_finish() does not send dentry link/unlink message to replicas.
>> We should prevent dentries that are modified by the rename operation
>> from getting new replicas when the rename operation is committing. So
>> don't mark xlocks "done" and early reply for rename
>
> Can we change this to only skip early reply if there are replicas? Or
> change things so we do send thos messages (or something isilar) early? As
> is this will kill workloads like rsync that rename every file.
>
How about not mark xlocks on dentries done.
Regards
Yan, Zheng
> Thanks!
> s
>
>>
>> Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
>> ---
>> src/mds/Server.cc | 8 ++++++++
>> 1 file changed, 8 insertions(+)
>>
>> diff --git a/src/mds/Server.cc b/src/mds/Server.cc
>> index eced76f..4492341 100644
>> --- a/src/mds/Server.cc
>> +++ b/src/mds/Server.cc
>> @@ -796,6 +796,14 @@ void Server::early_reply(MDRequest *mdr, CInode *tracei, CDentry *tracedn)
>> return;
>> }
>>
>> + // _rename_finish() does not send dentry link/unlink message to replicas.
>> + // so do not mark xlocks "done", the xlocks prevent srcdn and destdn from
>> + // getting new replica.
>> + if (mdr->client_request->get_op() == CEPH_MDS_OP_RENAME) {
>> + dout(10) << "early_reply - rename, not allowed" << dendl;
>> + return;
>> + }
>> +
>> MClientRequest *req = mdr->client_request;
>> entity_inst_t client_inst = req->get_source_inst();
>> if (client_inst.name.is_mds())
>> --
>> 1.7.11.7
>>
>> --
>> To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
>> the body of a message to majordomo@vger.kernel.org
>> More majordomo info at http://vger.kernel.org/majordomo-info.html
>>
>>
next prev parent reply other threads:[~2013-01-29 1:44 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-01-23 3:08 [PATCH 00/24] fixes for MDS cluster recovery Yan, Zheng
2013-01-23 3:08 ` [PATCH 01/25] mds: fix end check in Server::handle_client_readdir() Yan, Zheng
2013-01-23 17:17 ` Sage Weil
2013-01-24 2:16 ` Yan, Zheng
2013-01-23 3:08 ` [PATCH 02/25] mds: check deleted directory in Server::rdlock_path_xlock_dentry Yan, Zheng
2013-01-23 3:08 ` [PATCH 03/25] mds: lock remote inode's primary dentry during rename Yan, Zheng
2013-01-23 3:08 ` [PATCH 04/25] mds: allow journaling multiple root inodes in EMetaBlob Yan, Zheng
2013-01-23 3:08 ` [PATCH 05/25] mds: introduce XSYN to SYNC lock state transition Yan, Zheng
2013-01-23 3:08 ` [PATCH 06/25] mds: properly set error_dentry for discover reply Yan, Zheng
2013-01-23 3:08 ` [PATCH 07/25] mds: don't early reply rename Yan, Zheng
2013-01-28 21:44 ` Sage Weil
2013-01-29 1:44 ` Yan, Zheng [this message]
2013-01-29 2:23 ` Sage Weil
2013-01-29 2:56 ` Yan, Zheng
2013-01-23 3:08 ` [PATCH 08/25] mds: fix "had dentry linked to wrong inode" warning Yan, Zheng
2013-01-23 3:08 ` [PATCH 09/25] mds: splits rename force journal check into separate function Yan, Zheng
2013-01-23 3:08 ` [PATCH 10/25] mds: force journal straydn for rename if necessary Yan, Zheng
2013-01-23 3:08 ` [PATCH 11/25] mds: don't journal non-auth rename source directory Yan, Zheng
2013-01-23 3:08 ` [PATCH 12/25] mds: preserve non-auth/unlinked objects until slave commit Yan, Zheng
2013-01-23 3:08 ` [PATCH 13/25] mds: fix slave rename rollback Yan, Zheng
2013-01-23 3:08 ` [PATCH 14/25] mds: split reslove into two sub-stages Yan, Zheng
2013-01-23 3:08 ` [PATCH 15/25] mds: send resolve messages after all MDS reach resolve stage Yan, Zheng
2013-01-23 3:08 ` [PATCH 16/25] mds: Always use {push,pop}_projected_linkage to change linkage Yan, Zheng
2013-01-23 3:08 ` [PATCH 17/25] mds: don't replace existing slave request Yan, Zheng
2013-01-23 3:08 ` [PATCH 18/25] mds: fix for MDCache::adjust_bounded_subtree_auth Yan, Zheng
2013-01-23 3:08 ` [PATCH 19/25] mds: fix for MDCache::disambiguate_imports Yan, Zheng
2013-01-23 3:08 ` [PATCH 20/25] mds: journal inode's projected parent when doing link rollback Yan, Zheng
2013-01-23 3:08 ` [PATCH 21/25] mds: don't journal opened non-auth inode Yan, Zheng
2013-01-23 3:08 ` [PATCH 22/25] mds: properly clear CDir::STATE_COMPLETE when replaying EImportStart Yan, Zheng
2013-01-23 3:08 ` [PATCH 23/25] mds: move variables special to rename into MDRequest::more Yan, Zheng
2013-01-23 3:09 ` [PATCH 24/25] mds: rejoin remote wrlocks and frozen auth pin Yan, Zheng
2013-01-23 3:09 ` [PATCH 25/25] mds: fetch missing inodes from disk Yan, Zheng
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=51072969.1040705@intel.com \
--to=zheng.z.yan@intel.com \
--cc=ceph-devel@vger.kernel.org \
--cc=sage@inktank.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox