New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
os/bluestore: misc fixes #10771
os/bluestore: misc fixes #10771
Conversation
I think this is a poorly named function.. the comment says // This asks the OS to initiate flushing the cached data to disk, so RangeStartFlush would have been better. In any case, it's not a data integrity call, so I think it's okay as it. What I want to avoid is flushing the same block twice... |
file_map should be accessed under the protection of the global lock. 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 assert is used to guarantee that we don't access violation but currently has no effect. Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
b9c12ef
to
d2cfbb9
Compare
@liewegas Dropped that change and appended more changes.
|
derr << __func__ << " allocated: " << allocated << \ | ||
" offset: " << offset << " length: " << length << dendl; | ||
derr << __func__ << " allocated: 0x" << std::hex << allocated | ||
<< " offset: 0x" << offset << " length: 0x" << length << std::dec |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
please include the std::dec at the end
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@liewegas Sir, I did... The std::dec
lies at the end of this line.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Oops, yes, sorry about that!
otherwise lgtm, thanks! |
We shall round nbytes up to be page-size(4096) aligned instead of
truncating it down, as syncing more is usually okay
while syncing less indicates potential data loss.
Signed-off-by: xie xingguo xie.xingguo@zte.com.cn