glusterfs.git/xlators/features/upcall/src/upcall.h, branch v3.11dev

md-cache, afr: Reduce the window of stale read

2016-10-20T07:07:55+00:00

Problem:
Consider a replica setup, where one mount writes data to a
file and the other mount reads the file. In afr, read operations
are not transaction based, a brick(read subvolume) is chosen as
a part of lookup or other operations, read is always wound only
to the read subvolume, even if there was write from a different client
that failed on this brick. This stale read continues until there is
a lookup or any write operation from the mount point. Currently, this
is not a major issue, as a lookup is issued before every read and it will
switch the read subvolume to a correct one. But with the plan of
increasing md-cache timeout to 600s, the stale read problem will be
more pronounced, i.e. stale read can continue for 600s(or more if cascaded
with readdirp), as there will be no lookups.

Solution:
Afr doesn't have any built-in solution for stale read(without affecting
the performance). The solution that came up, was to use upcall. When a file
on any brick is marked bad for the first time, upcall sends a notification
to all the clients that had recently accessed the file. The solution has
2 parts:
- Identifying when a file is marked bad, on any of the bricks,
  for the first time
- Client side actions on recieving the notifications

Identifying when a file is marked bad on any of the bricks for the first time:
-----------------------------------------------------------------------------
The idea is to track xattrop in upcall. xattrop currently comes with 2 afr
xattrs - afr dirty bit and afr pending xattrs.
   Dirty xattr is set to 1 before every write, and is unset if write succeeds.
In certain scenarios, dirty xattr can be 0 and still the file could be bad
copy. Hence do not track dirty xattr.
   Pending xattr is set on the good copy, indicating the other bricks that have
bad copy. It is still not as simple as, notifying when any of the pending xattrs
change. It could lead to flood of notifcations, in case the other brick is
completely down or consistantly failing. Hence it is important to notify only
once, the first time a good copy is marked bad.

Client side actions on recieving pending xattr change, notification:
--------------------------------------------------------------------
md-cache will invalidate the cache of that file, so that further lookup is
passed down to afr and hence update the read subvolume. Invalidating only in
md-cache is not enough, consider the folling oder of opertaions:
- pending xattr invalidation - invalidate md-cache
- readdirp on the bad read subvolume - fill md-cache
- lookup (served from md-cache)
- read - wound to the old read subvol.
Hence, along with invalidating md-cache, it is very important to reset the
read subvolume for that file, in afr.

Design Credit: Anuradha Talur, Ravishankar N

1. xattrop doesn't carry info saying post op/pre op.
2. Pre xattrop will have 0 value for all pending xattrs,
   the cbk of pre xattrop carries the on-disk xattr value.
   Non zero indicated healing is required.
3. Post xattrop will have non zero value for any of the
   pending xattrs, if the fop failed on any of the bricks.

Change-Id: I469cbc111714c433984fe1c922be2ef113c25804
BUG: 1211863
Signed-off-by: Poornima G 
Reviewed-on: http://review.gluster.org/15398
Reviewed-by: Pranith Kumar Karampuri 
Tested-by: Pranith Kumar Karampuri 
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System

md-cache: Register the list of xattrs with cache-invalidation

2016-08-31T06:07:01+00:00

Issue:
md-cache caches a specified list of xattrs, and when cache invalidation
is enabled, it makes sense to recieve invalidation only when those xattrs
are modified by other clients. But the current implementation of upcall
is that, it will send invalidation when any of the on-disk xattrs is modified.

Solution:
md-cache sends a list of xattrs that it is interested in, to upcall by
issuing an ipc(). The challenge here is to make sure everytime a brick
goes offline and comes back up, the ipc() needs to be issued to the
bricks. Hence ipc() is sent from md-cache every time there is a
CHILD_UP/CHILD_MODIFIED event.

TODO:
There will be patches following, in cluster xlators, to implement ipc fop.

Change-Id: I6efcf3df474f5ce6eabd3d6694c00c7bd89bc25d
BUG: 1211863
Signed-off-by: Poornima G 
Reviewed-on: http://review.gluster.org/15002
Smoke: Gluster Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Rajesh Joseph 
NetBSD-regression: NetBSD Build System 
Reviewed-by: Prashanth Pai 
Reviewed-by: Raghavendra G

features/upcall: segment fault while join thread reaper_thr in fini()

2016-08-29T12:13:49+00:00

reaper_thr thread may not be started according to option
'cache-invalidation', if it's not started, join it in fini will cause a
segment fault.

Change-Id: I1c145a5feb137767880a08e79f810537283fb6b9
BUG: 1369524
Signed-off-by: Ryan Ding 
[ndevos: check .reaper_init_done and make it a boolean]
Reviewed-on: http://review.gluster.org/15298
Smoke: Gluster Build System 
Reviewed-by: soumya k 
Reviewed-by: Niels de Vos 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System

upcall: Invalidation for xattr should also carry a valid stat

2016-07-05T11:53:03+00:00

xattr modification also impacts the ctime of the file, hence
include the new stat along with the new xattrs, in the
invalidation request

Change-Id: Ieaa4382fa62f397f61a995b926013b9207c6e9da
BUG: 1352671
Signed-off-by: Poornima G 
Reviewed-on: http://review.gluster.org/14828
Smoke: Gluster Build System 
CentOS-regression: Gluster Build System 
NetBSD-regression: NetBSD Build System 
Reviewed-by: Jeff Darcy

upcall: pass dict with xattrs on xattr invalidation

2016-05-19T09:28:07+00:00

In case of xattr invalidation, return a dict containing
the updated xattrs.

[ndevos: move chunks to change 12995 and only address the xattrs-dict here]

Change-Id: I8733f06a519a9a0f24be1bb4b2c38c9c9dce0ce2
BUG: 1211863
Signed-off-by: Poornima G 
Reviewed-on: http://review.gluster.org/12996
Smoke: Gluster Build System 
CentOS-regression: Gluster Build System 
NetBSD-regression: NetBSD Build System 
Reviewed-by: Niels de Vos 
Reviewed-by: soumya k 
Tested-by: soumya k

upcall: Add support to invalidate xattrs

2016-05-11T18:23:00+00:00

When SElinux is used, clients should get a notification that the
extended attributes have been updated. Other components (like md-cache)
will be able to use this too.

A big part of the implementation comes from Poornima through the first
version of http://review.gluster.org/12996.

Also moving the flags from upcall-cache-invalidation.h to the main
libglusterfs upcall-utils.h file, so that other places can easily use
them in future.

Change-Id: I525345bed8f22d029524ff19ccaf726a2c905454
BUG: 1211863
Signed-off-by: Niels de Vos 
Signed-off-by: Poornima G 
Reviewed-on: http://review.gluster.org/12995
Reviewed-by: soumya k 
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System

Upcall: Read gfid from iatt in case of invalid inode

2015-12-01T10:32:50+00:00

When any file/dir is looked upon for the first time, inode
created shall be invalid till it gets linked to the inode table.
In such cases, read the gfid from the iatt structure returned
as part of such fops for UPCALL processing.

Change-Id: Ie5eb2f3be18c34cf7ef172e126c9db5ef7a8512b
BUG: 1283983
Signed-off-by: Soumya Koduri 
Reviewed-on: http://review.gluster.org/12773
Reviewed-by: Kaleb KEITHLEY 
Tested-by: NetBSD Build System 
Tested-by: Gluster Build System 
Reviewed-by: Niels de Vos

build: do not #include "config.h" in each file

2015-05-29T12:43:17+00:00

Instead of including config.h in each file, and have the additional
config.h included from the compiler commandline (-include option).

When a .c file tests for a certain #define, and config.h was not
included, incorrect assumtions were made. With this change, it can not
happen again.

BUG: 1222319
Change-Id: I4f9097b8740b81ecfe8b218d52ca50361f74cb64
Signed-off-by: Niels de Vos 
Reviewed-on: http://review.gluster.org/10808
Tested-by: Gluster Build System 
Tested-by: NetBSD Build System
Reviewed-by: Kaleb KEITHLEY 
Reviewed-by: Pranith Kumar Karampuri

Upcall: Send stat as part of cache_invalidation notifications

2015-05-05T13:57:43+00:00

Have added support to send attributes of both entries and
its parent (include oldparent in case of RENAME fop) in the
same notification request to avoid multiple rpc requests.

Also, made changes in gfapi to send parent object and its
attributes changed in a single upcall event.

Change-Id: I92833da3bcec38d65216921c2ce4d10367c32ef1
BUG: 1200262
Signed-off-by: Soumya Koduri 
Reviewed-on: http://review.gluster.org/10460
Tested-by: Gluster Build System 
Reviewed-by: Kaleb KEITHLEY

Upcall: Cleanup expired client entries

2015-05-04T23:27:41+00:00

To cleanup expired client entries (with access_time > 2*CACHE_INVALIDATION_TIMEOUT),
have
        * defined a global list to contain all the upcall_inode_ctx allocated
        * Every time a upcall_inode_ctx is allocated, it is added to the global list
        * during inode_forget, that upcall_inode_ctx is marked for destroy
        * created a reaper thread which scans through that list
                * cleans up expired client entries
                * frees the inode_ctx with destroy_mode set.

Note: This reaper thread is initialized only when features.cache_invalidation option
is enabled.

Change-Id: Iea2a63eb31b8e08d5709e7e090cf26fd13d01265
BUG: 1200267
Signed-off-by: Soumya Koduri 
Reviewed-on: http://review.gluster.org/10342
Tested-by: Gluster Build System 
Reviewed-by: Kaleb KEITHLEY