| Commit message (Collapse) | Author | Age | Files | Lines |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Summary:
Halo Geo-replication is a feature which allows Gluster or NFS clients to write
locally to their region (as defined by a latency "halo" or threshold if you
like), and have their writes asynchronously propagate from their origin to the
rest of the cluster. Clients can also write synchronously to the cluster
simply by specifying a halo-latency which is very large (e.g. 10seconds) which
will include all bricks.
In other words, it allows clients to decide at mount time if they desire
synchronous or asynchronous IO into a cluster and the cluster can support both
of these modes to any number of clients simultaneously.
There are a few new volume options due to this feature:
halo-shd-latency: The threshold below which self-heal daemons will
consider children (bricks) connected.
halo-nfsd-latency: The threshold below which NFS daemons will consider
children (bricks) connected.
halo-latency: The threshold below which all other clients will
consider children (bricks) connected.
halo-min-replicas: The minimum number of replicas which are to
be enforced regardless of latency specified in the above 3 options.
If the number of children falls below this threshold the next
best (chosen by latency) shall be swapped in.
New FUSE mount options:
halo-latency & halo-min-replicas: As descripted above.
This feature combined with multi-threaded SHD support (D1271745) results in
some pretty cool geo-replication possibilities.
Operational Notes:
- Global consistency is gaurenteed for synchronous clients, this is provided by
the existing entry-locking mechanism.
- Asynchronous clients on the other hand and merely consistent to their region.
Writes & deletes will be protected via entry-locks as usual preventing
concurrent writes into files which are undergoing replication. Read operations
on the other hand should never block.
- Writes are allowed from _any_ region and propagated from the origin to all
other regions. The take away from this is care should be taken to ensure
multiple writers do not write the same files resulting in a gfid split-brain
which will require resolution via split-brain policies (majority, mtime &
size). Recommended method for preventing this is using the nfs-auth feature to
define which region for each share has RW permissions, tiers not in the origin
region should have RO perms.
TODO:
- Synchronous clients (including the SHD) should choose clients from their own
region as preferred sources for reads. Most of the plumbing is in place for
this via the child_latency array.
- Better GFID split brain handling & better dent type split brain handling
(i.e. create a trash can and move the offending files into it).
- Tagging in addition to latency as a means of defining which children you wish
to synchronously write to
Test Plan:
- The usual suspects, clang, gcc w/ address sanitizer & valgrind
- Prove tests
Reviewers: jackl, dph, cjh, meyering
Reviewed By: meyering
Subscribers: ethanr
Differential Revision: https://phabricator.fb.com/D1272053
Tasks: 4117827
Change-Id: I694a9ab429722da538da171ec528406e77b5e6d1
BUG: 1428061
Signed-off-by: Kevin Vigor <kvigor@fb.com>
Reviewed-on: http://review.gluster.org/16099
Reviewed-on: https://review.gluster.org/16177
Tested-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
Smoke: Gluster Build System <jenkins@build.gluster.org>
NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org>
CentOS-regression: Gluster Build System <jenkins@build.gluster.org>
Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
When SSL is enabled or if "transport.socket.own-thread" option is set
then socket_poller is run as different thread. Currently during
disconnect or PARENT_DOWN scenario we don't wait for this thread
to terminate. PARENT_DOWN will disconnect the socket layer and
cleanup resources used by socket_poller.
Therefore before disconnect we should wait for poller thread to exit.
Change-Id: I71f984b47d260ffd979102f180a99a0bed29f0d6
BUG: 1404181
Signed-off-by: Rajesh Joseph <rjoseph@redhat.com>
Reviewed-on: http://review.gluster.org/16141
Smoke: Gluster Build System <jenkins@build.gluster.org>
NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org>
CentOS-regression: Gluster Build System <jenkins@build.gluster.org>
Reviewed-by: Kaushal M <kaushal@redhat.com>
Reviewed-by: Raghavendra Talur <rtalur@redhat.com>
Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Cleaning dead initializations.
Change-Id: I53ae506593cd10441d61df3b2c9249544a7871f7
BUG: 1254067
Signed-off-by: Prasanna Kumar Kalever <prasanna.kalever@redhat.com>
Reviewed-on: http://review.gluster.org/11932
Tested-by: Prasanna Kumar Kalever <pkalever@redhat.com>
NetBSD-regression: NetBSD Build System <jenkins@build.gluster.org>
CentOS-regression: Gluster Build System <jenkins@build.gluster.com>
Smoke: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Raghavendra Talur <rtalur@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
While doing glfs_fini(), all the xlators are first notified of
PARENT_DOWN. protocol-client xlator on receving that notification
does rpc_clnt_disable which disassociates rpc->conn with its
transport object and does socket shutdown. So any further references
to conn->trans should not happen during rpc connection cleanup which
is done mainly as part of epoll event handling of EPOLLERR/EPOLLHUP.
BUG: 1250797
Change-Id: I7d0346451d40372ad59a6a2326176fbb1e694712
Signed-off-by: Soumya Koduri <skoduri@redhat.com>
Reviewed-on: http://review.gluster.org/11845
Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Kaleb KEITHLEY <kkeithle@redhat.com>
|
|
|
|
|
|
|
|
|
|
| |
See http://review.gluster.org/9613 for more details.
Change-Id: I05ac0267b8c6f4e9b354acbbdf5469835455fb10
Signed-off-by: Krishnan Parthasarathi <kparthas@redhat.com>
Reviewed-on: http://review.gluster.org/10821
Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
Tested-by: Raghavendra G <rgowdapp@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
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 <ndevos@redhat.com>
Reviewed-on: http://review.gluster.org/10808
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Tested-by: NetBSD Build System
Reviewed-by: Kaleb KEITHLEY <kkeithle@redhat.com>
Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Coverity CIDs:
1210973
1124887
1124888
1124682
1124849
1124503
Change-Id: I012f6cf9d14753f572ab94aae6d442d1ef8df79a
BUG: 789278
Signed-off-by: Nandaja Varma <nandaja.varma@gmail.com>
Reviewed-on: http://review.gluster.org/9600
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Vijay Bellur <vbellur@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
In ping-timer implementation, the timer event takes a ref on the rpc
object. This ref needs to be removed after every timeout event.
ping-timer mechanism could be holding the last ref. For e.g, when a peer
is detached and its rpc object was unref'd. In this case, ping-timer
mechanism would try to acquire conn->mutex to perform the 'last' unref
while being inside the critical section already. This will result in a
deadlock.
Change-Id: I74f80dd08c9348bd320a1c6d12fc8cd544fa4aea
BUG: 1206134
Signed-off-by: Krishnan Parthasarathi <kparthas@redhat.com>
Reviewed-on: http://review.gluster.org/9613
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Vijay Bellur <vbellur@redhat.com>
|
|
|
|
|
|
|
|
| |
Change-Id: I4ddc371d01ec763706a168a215410015ee2a3787
Signed-off-by: Krishnan Parthasarathi <kparthas@redhat.com>
Reviewed-on: http://review.gluster.org/9578
Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
Tested-by: Raghavendra G <rgowdapp@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This can be seen as below,
># cat $META/graphs/active/vol-client-0/private |grep ping_msgs_sent
ping_msgs_sent = 2
># cat $META/graphs/active/vol-client-0/private |grep "^msgs_sent"
msgs_sent = 13
where $META is /<fuse-mountpt>/.meta
Change-Id: I2107ec2b045bac701377760635e18758adb943a3
Signed-off-by: Krishnan Parthasarathi <kparthas@redhat.com>
Reviewed-on: http://review.gluster.org/8285
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Atin Mukherjee <amukherj@redhat.com>
Reviewed-by: Anand Avati <avati@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This is to avoid indefinite recursion of the following kind, that could
lead to a stack overflow:
rpc_clnt_start_ping() -> rpc_clnt_ping() -> rpc_clnt_submit() ->
rpc_clnt_start_ping() -> rpc_clnt_ping() -> rpc_clnt_submit() ...
and so on,
since it is possible that before rpc_clnt_start_ping() is called a
second time by the thread executing this codepath, the response to
previous ping request could ALWAYS come by and cause epoll thread to
reset conn->ping_started to 0.
This patch also fixes the issue of excessive ping traffic, which was
due to the client sending one ping rpc for every fop in the worst case.
Also removed dead code in glusterd.
Change-Id: I7c5e6ae3b1c9d23407c0a12a319bdcb43ba7a359
BUG: 1116243
Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com>
Reviewed-on: http://review.gluster.org/8257
Reviewed-by: Pranith Kumar Karampuri <pkarampu@redhat.com>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Vijay Bellur <vbellur@redhat.com>
|
|
|
|
|
|
|
|
|
| |
Change-Id: Iae85cdfc223875688ea17155fffcf2a3a435d245
BUG: 764890
Signed-off-by: Krutika Dhananjay <kdhananj@redhat.com>
Reviewed-on: http://review.gluster.org/8044
Reviewed-by: Vijay Bellur <vbellur@redhat.com>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
When there are too many IO happening, brick process epoll thread
will be busy and fails to respond to the glusterd pick packet within
30sec.
Also epoll thread can be blocked by a big-lock.
Solution is to disable ping-timer by default and only enable where ever
required
Later when the epoll thread model changed and made lighter,
we need to revert back this change. http://review.gluster.com/3842 is
one such approach.
Change-Id: I7f80ad3eb00f7d9c4d4527305932f7cf4920e73f
BUG: 1097224
Signed-off-by: Vijaikumar M <vmallika@redhat.com>
Reviewed-on: http://review.gluster.org/7753
Reviewed-by: Krishnan Parthasarathi <kparthas@redhat.com>
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Vijay Bellur <vbellur@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
- Removed an unnecessary ref on rpc_clnt object.
- Removed saved_frames_delete function, which was unused.
Change-Id: Ie8a9c4bb20c1fd59744b64b56eb043eca095e5e3
BUG: 1094655
Signed-off-by: Krishnan Parthasarathi <kparthas@redhat.com>
Reviewed-on: http://review.gluster.org/7678
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Raghavendra G <rgowdapp@redhat.com>
Tested-by: Raghavendra G <rgowdapp@redhat.com>
|
|
This patch refactors the existing client ping timer implementation, and makes
use of the common code for implementing both client ping timer and the
glusterd ping timer.
A new gluster rpc program for ping is introduced. The ping timer is only
started for peers that have this new program. The deafult glusterd ping
timeout is 30 seconds. It is configurable by setting the option
'ping-timeout' in glusterd.vol .
Also, this patch introduces changes in the glusterd-handshake path. The client
programs for a peer are now set in the callback of dump_versions, for both
the older handshake and the newer op-version handshake. This is the only place
in the handshake process where we know what programs a peer supports.
Change-Id: I035815ac13449ca47080ecc3253c0a9afbe9016a
BUG: 1038261
Signed-off-by: Vijaikumar M <vmallika@redhat.com>
Signed-off-by: Krishnan Parthasarathi <kparthas@redhat.com>
Reviewed-on: http://review.gluster.org/5202
Tested-by: Gluster Build System <jenkins@build.gluster.com>
Reviewed-by: Anand Avati <avati@redhat.com>
|