osd: fix inaccurate counter and skip over queueing an empty transaction #7754
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
xiexingguo
changed the title
xiexingguo
force-pushed
the
xxg-wip-14845
branch
from
e4a1a14
to
136e972
Compare
xiexingguo
changed the title
|
@liewegas Mind having a look at this one? Thanks:) |
xiexingguo
force-pushed
the
xxg-wip-14845
branch
2 times, most recently
from
e95f8eb
to
9bc9d5f
Compare
The problem here is that we may skip some meta objects which shall not be counted since they are not really queued. Besides, the counter itself is not very accurate, e.g., if we set osd_target_transaction_size to 30, we may actually queue 31 transactions to trigger a commit. Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
xiexingguo
force-pushed
the
xxg-wip-14845
branch
from
9bc9d5f
to
29088c3
Compare
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
xiexingguo
force-pushed
the
xxg-wip-14845
branch
from
29088c3
to
283cbfa
Compare
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
Make sure the file_object string will be bigger enough (e.g., should be 16(for ino) + 1(for dot) + 16(for bno) + 1(for nul terminator) == 34 at maximum). And update sprintf to snprintf correspondingly, which is safer. Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
which is never used by anyone. Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
In one of our test environments an osd is unable to back to work due to the journal is totally unrecoverable. The os_flags field is introduced to handle such a case but never be made an option and visible to normal user. This commit tries to make os_flags field a configurable option and no flags is enabled by default and thus shall cause no compatibility relevant issues. Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
… cmds Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
This is not necessary and does no good for performance. Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
xiexingguo
force-pushed
the
xxg-wip-14845
branch
from
2fc5c4d
to
15c7ce3
Compare
|
@liewegas Append more fixes and ping. |
|
Can you move the map sharing into a separate PR? I'm not sure those are a good idea, since it will make the receiving OSD pull those maps from the monitor. The rest looks good! |
OSD_SUPERBLOCK_GOBJECT is a better name, I think. Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
xiexingguo
force-pushed
the
xxg-wip-14845
branch
from
15c7ce3
to
82419db
Compare
liewegas
added a commit
that referenced
this pull request
Mar 18, 2016
osd: fix inaccurate counter and skip over queueing an empty transaction Reviewed-by: Sage Weil <sage@redhat.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR consists of two changes:
the first change tries to fix counter for batch transactions triggered to remove non-meta objects, this is problematic because that we may skip some meta objects which shall not be counted since they are not really queued. Besides, the counter itself is not very accurate, e.g., if we set osd_target_transaction_size to 30, we may actually queue 31 transactions to trigger a commit.
the second change tries to skip over an empty transaction(especially we have to wait for its finish), which is for the sake of performance.