| Commit message (Collapse) | Author | Age | Files | Lines |
... | |
|
|
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
BUG: 221 (stat prefetch implementation)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=221
|
|
|
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
BUG: 221 (stat prefetch implementation)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=221
|
|
|
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
BUG: 221 (stat prefetch implementation)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=221
|
|
|
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
BUG: 221 (stat prefetch implementation)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=221
|
|
|
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
BUG: 221 (stat prefetch implementation)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=221
|
|
|
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
BUG: 221 (stat prefetch implementation)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=221
|
|
|
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
BUG: 221 (stat prefetch implementation)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=221
|
|
|
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
BUG: 221 (stat prefetch implementation)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=221
|
|
|
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
BUG: 221 (stat prefetch implementation)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=221
|
|
|
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
BUG: 221 (stat prefetch implementation)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=221
|
|
|
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
BUG: 221 (stat prefetch implementation)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=221
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
- we need following extra members along with cache
1. basename of path on which fd is opened. This is necessary to search
for cached entry in fd based fops.
2. inode corresponding to dirname of path on which fd is opened. This
is necessary to get cache where entry corresponding to file on which
fd is opened.
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
BUG: 221 (stat prefetch implementation)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=221
|
|
|
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
BUG: 221 (stat prefetch implementation)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=221
|
|
|
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
BUG: 221 (stat prefetch implementation)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=221
|
|
|
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
BUG: 221 (stat prefetch implementation)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=221
|
|
|
|
|
|
|
|
|
|
|
| |
- stat-prefetch aims to optimize operations like 'ls -l' where a readdir
is immediately followed by stat calls on each of the directory entry read.
More details on design can be found in doc/stat-prefetch-design.txt
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
BUG: 221 (stat prefetch implementation)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=221
|
|
|
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
BUG: 130 (build warnings)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=130
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|
|
|
|
|
|
| |
- writev on any fd opened on a file invalidates the cache stored during lookup
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
- pseudo-code of the algorithm is given below
if (content is cached) {
validate-contents ();
if (content cached is valid) {
stack unwind with cached content;
} else {
goto read-from-storage;
}
} else {
goto read-from-storage;
}
return;
read-from-storage:
if (open is already done on fd) {
stack-wind read;
} else {
add the current readv to list of operations waiting on completion of
open;
if (open on the fd is in transit) {
do nothing;
} else {
stack-wind open;
}
}
return;
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|
|
|
|
|
|
|
|
| |
- The file is opened actually only if it is not cached already in lookup.
This adds responsibility for fops operating on fds to make sure that a
valid fd actually opened on a file is used to complete the fop.
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
lookup can fetch the entire file in xattr dictionary using the key
"glusterfs.content". We set the maximum size of the file that can
be fetched so in the xattr_req dictionary using the same key. If file-size
is less than or equal to the value set in dictionary, the content is stored
in the dictionary using same key in lookup_cbk.
For small files, we can do an optimization wherein we do not really send the
calls open, read and close to the storage translators. Instead there can be
an xlator which fakes open, read and close calls. For reads, it sends the data
it has cached during lookup and hence saving the time for open, read and close
calls to reach storage translators (this time can be significant if calls have
to go through network to reach storage translator).
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|
|
|
|
|
|
|
|
| |
open() & create() calls should reset frame->local to NULL.
bz# 104
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|
|
|
|
|
|
|
|
|
| |
Write calls should not be pushed to background only when the
mandatory locking is enabled, in all other cases (eg: O_SYNC,
O_DIRECT etc), we should not be 'caching' any data, but the
calls can be pushed to the background.
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|
|
|
|
|
|
|
|
| |
- wb_sync did not set local = NULL after stack_wind. It also used to free
local if its not NULL as part of cleanup process. Hence there was a double
free in STACK_DESTROY done in wb_sync_cbk.
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|
| |
|
| |
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
We're performing a calculation for skewing idle time
that resulted in a timespec.tv_nsec value becoming larger than
1000 million or less than 0, forcing sem_timedwait to return
with an EINVAL instead of waiting for a request notification
from sem_post in iot_notify_worker(). This resulted in a missed
notification that resulted in a hang followed by a timeout
on the protocol/client side.
This commit avoids the over- and under-flow in tv_nsec by
skewing the tv_sec value instead.
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|
|
|
|
|
|
|
|
|
|
|
| |
their context.
- since a successful open/create will _always_ set a pointer to ra_file_t in
context of fd, this fix makes sense.
- an example of operations on bad fd can be afr sending read on the child
which was down during open.
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|
|
|
|
|
|
| |
memory allocation for ra_file in open/create
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|
|
|
|
| |
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
1. A page will be put on the inode waitq if the 'freshness' has to be verified with an fstat()
2. while the fstat is in transit, other calls (like lookup) can update ioc_inode->tv, resetting the freshness (page still on inode waitq)
3. Another read request on the same page, after the updated freshness, will wake up the page frames neglecting the fact that the page is also waiting on the inode (waiting for the fstat completion)
4. once the page's frames are woken, the page becomes elegible for purging and can get destroyed for various reasons, leaving a destroyed page pointer in the inode's waitq
5. fstat returns and hits the destroyed page pointer causing a crash
The fix is to all together disable cache hits when any page of the same inode is under validation. The otherwise cache hit will now be subjected to the ongoing validation by getting queued to the inode waitq.
Signed-off-by: Anand V. Avati <avati@dev.gluster.com>
|