Aren/haiku
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

- AttributeIterator::Update() now take into account differences between its

Browse Source 
view of the small data section and the outside view.

Long version:

AttributeIterator is a higher level class designed to make it easy to iterate
through attributes in the small data section. The first attribute in the small
data section is the special "name" attribute that is used to reconstruct the
node path when you only have a node handy. As this attribute is not user
visible nor user modifiable (except by changing a node name of course), it is
considered a special attribute so the AttributeIterator class ignores it and
starts iterating from the second attribute on.

As opposed to this, internally the Inode class accesses the small data section
directly without using the AttributeIterator class so whenever it indexes items
in the small data section, it takes into account the special "name" attribute.

This creates a off-by-one relationship between those 2 representations and this
was a problem because whenever the small data section changed, all iterators
had to be updated (through a call to AttributeIterator::Update() having an
index parameter that represented the outside view and not the AttributeIterator
view, so iterators would not be adjusted correctly and the end result is that
every other attribute was not removed from the index. This would cause all
types of havoc with indexes, the simplest one being that entries in indexes
would point to non-existing nodes.

Ingo, pleased now? ;)



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@27196 a95241bf-73f2-0310-859d-f6bbb57e9c96
This commit is contained in:
Bruno G. Albuquerque 2008-08-25 12:25:15 +00:00
parent b6ebf6d8ae
commit e1d9b81384
1 changed files with 6 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
src/add-ons/kernel/file_systems/bfs/Inode.cpp
View File

@ -633,11 +633,7 @@ Inode::_RemoveSmallData(Transaction& transaction, NodeGetter& nodeGetter,
nodeGetter.MakeWritable(transaction);
// TODO(bga): It seems that the first item in the small data section is not
// a nomela attribute (for example, it does not have a name). We take this
// into account and decrement index before passing it along. Although this
// fix one bug, it may be as well just masking out a different bug.
status_t status = _RemoveSmallData(node, item, index - 1);
status_t status = _RemoveSmallData(node, item, index);
if (status == B_OK)
status = WriteBack(transaction);
@ -2680,8 +2676,11 @@ AttributeIterator::GetNext(char* name, size_t* _length, uint32* _type,
void
AttributeIterator::Update(uint16 index, int8 change)
{
// fCurrentSmallData points already to the next item
if (index < fCurrentSmallData)
// fCurrentSmallData points already to the next item. OTOH, index is always
// the position when considering the special name attribute while the
// attribute iterators do ignore that (they always start at the second
// position in the small data section, not the first).
if (index <= fCurrentSmallData)
fCurrentSmallData += change;
}