glusterfs.git/xlators/mgmt/glusterd/src/glusterd-op-sm.c, branch v3.3.0qa26

transport/socket: configuring tcp window-size

2012-02-29T10:10:44+00:00

Till now, send and recieve buffer window sizes for sockets
were set to a default glusterfs-specific value.
Linux's default window sizes have been found to be better
w.r.t performance, and hence, no more setting it to any
default value.

However, if one wishes, there's the new configuration option:
   network.tcp-window-size 
which takes a size value (int or human readable) and will set
the window size of sockets for both clients and servers.
Nfs clients will also be updated with the same.

Change-Id: I841479bbaea791b01086c42f58401ed297ff16ea
BUG: 795635
Signed-off-by: Rajesh Amaravathi 
Reviewed-on: http://review.gluster.com/2821
Tested-by: Gluster Build System 
Reviewed-by: Amar Tumballi 
Reviewed-by: Jeff Darcy 
Reviewed-by: Vijay Bellur

cluster/afr: Add commands to see self-heald ops

2012-02-21T05:23:37+00:00

Change-Id: Id92d3276e65a6c0fe61ab328b58b3954ae116c74
BUG: 763820
Signed-off-by: Pranith Kumar K 
Reviewed-on: http://review.gluster.com/2775
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

glusterd: auth allow enhancements

2012-02-20T08:30:54+00:00

* PROBLEM:

  When address-based authentication is enabled on a volume,
  the gNfs server, self-heal daemon (shd), and other operations
  such as quota, rebalance, replace-brick and geo-replication
  either stop working or the services are not started if all
  the peers' ipv{4,6} addresses or hostnames are not added in
  the "set auth.allow" operation, breaking the functionality
  of several operations.

  E.g:
    volume vol in a cluster of two peers:
    /mnt/brick1 in 192.168.1.4
    /mnt/brick2 in 192.168.1.5

    option auth.allow 192.168.1.6
    (allow connection requests only from 192.168.1.6)

    This will disrupt the nfs servers on 192.168.1.{4,5}.
    brick server processes reject connection requests from both
    nfs servers (on 4,5), because the peer addresses are not in
    the auth.allow list.

    Same holds true for local mounts (on peer machines),
    self-heal daemon, and other operations which perform
    a glusterfs mount on one of the peers.

* SOLUTION:

  Login-based authentication (username/password pairs,
  henceforth referred to as "keys") for gluster services and
  operations.

  These *per-volume* keys can be used to by-pass the addr-based
  authentication, provided none of the peers' addresses are put
  in the auth.reject list, to enable gluster services like gNfs,
  self-heal daemon and internal operations on volumes when
  auth.allow option is exercised.

* IMPLEMENTATION:

  1. Glusterd generates keys for each volume and stores it in
     memory as well as in respective volfiles.
     A new TRUSTED-FUSE volfile is generated which is
     fuse volfile + keys in protocol/client,
     and is named trusted--fuse.vol.
     This is used by all local mounts. ANY local mount (on any peer)
     is granted the trusted-fuse volfile instead of fuse volfile
     via getspec. non-local mounts are NOT granted the trusted fuse
     volfile.

  2. The keys generated for the volume is written to each server
     volfile telling servers to allow users with these keys.

  3. NFS, self-heal daemon and replace-brick volfiles are updated
     with the volume's authentication keys.

  4. The keys are NOT written to fuse volfiles for obvious reasons.

  5. The ownership of volfiles and logfiles is restricted to root users.

  6. Merging two identical definitions of peer_info_t in auth/addr
     and rpc-lib, throwing away the one in auth/addr.

  7. Code cleanup in numerous places as appropriate.

* IMPORTANT NOTES:

  1. One SHOULD NOT put any of the peer addresses in the auth.reject
     list if one wants any of the glusterd services and features
     such as gNfs, self-heal, rebalance, geo-rep and quota.

  2. If one wants to use username/password based authentication
     to volumes, one shall append to the server, nfs and shd volfiles,
     the keys one wants to use for authentication, *while_retaining
     those_generated_by_glusterd*.
     See doc/authentication.txt file for details.

Change-Id: Ie0331d625ad000d63090e2d622fe1728fbfcc453
BUG: 789942
Signed-off-by: Rajesh Amaravathi 
Reviewed-on: http://review.gluster.com/2733
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

cluster/dht: Rebalance will be a new glusterfs process

2012-02-19T09:31:19+00:00

rebalance will not use any maintainance clients. It is replaced by syncops,
with the volfile. Brickop (communication between glusterd<->glusterfs process)
is used for status and stop commands.

Dept-first traversal of dir is maintained, but data is migrated as and when
encounterd.
fix-layout (dir)
do
        Complete migrate-data of dir
        fix-layout (subdir)
done

Rebalance state is saved in the vol file, for restart-ability.
A disconnect event and pidfile state determine the defrag-status

Signed-off-by: shishirng 
Change-Id: Iec6c80c84bbb2142d840242c28db3d5f5be94d01
BUG: 763844
Reviewed-on: http://review.gluster.com/2540
Tested-by: Gluster Build System 
Reviewed-by: Amar Tumballi

cli, glusterd : Added support for clear-locks command.

2012-02-17T12:50:55+00:00

Change-Id: I8e7cd51d6e3dd968cced1ec4115b6811f2ab5c1b
BUG: 789858
Signed-off-by: Krishnan Parthasarathi 
Reviewed-on: http://review.gluster.com/2552
Tested-by: Gluster Build System 
Reviewed-by: Vijay Bellur

glusterd: Changed op_sm_queue locking mechanism to accomodate nested calls to op_sm

2012-02-03T15:40:46+00:00

Today if an rpc call made inside an op_sm can fail due to a disconnected peer,
resulting in the rpc callback to be called in the same stack with appropriate
status set. All glusterd rpc cbks move the state machine based on the status
returned by the rpc layer, which would result in a nested call to op_sm. With
the current scheme of locking, glusterd would end up in a deadlock situation

The new scheme will fail the nested glusterd_op_sm (). This prevents the
deadlock.  It would work without any change in overall behaviour, as the
current op_sm () call in execution wouldn't return until all events in the
queue are processed.

Change-Id: I6a7ba16d3810b699bcd06dc28a5ff3205a25476f
BUG: 772142
Signed-off-by: Krishnan Parthasarathi 
Reviewed-on: http://review.gluster.com/2625
Tested-by: Gluster Build System 
Reviewed-by: Amar Tumballi 
Reviewed-by: Vijay Bellur

glusterd: provide option to take statedump of the nfs server

2012-01-27T12:23:41+00:00

Currently the cli command for taking statedump is for glusterfs servers
only. Statedump of nfs server cannot be taken. With this patch if one
gives nfs as an option to the statedump command, then the nfs-server's
statedump is taken.

Change-Id: I4ef7a68e608da4aa2f17541d7b42cd78ce2624b6
BUG: 771587
Signed-off-by: Raghavendra Bhat 
Reviewed-on: http://review.gluster.com/2579
Tested-by: Gluster Build System 
Reviewed-by: Amar Tumballi 
Reviewed-by: Vijay Bellur

cli: Extend "volume status" with statedump info

2012-01-27T12:20:04+00:00

This patch enhances and extends the "volume status" command with information
obtained from the statedump of the bricks of volumes.

Adds new status types : clients, inode, fd, mem, callpool
The new syntax of "volume status" is,
 #gluster volume status [all|{ []
                         [misc-details|clients|inode|fd|mem|callpool]}]

Change-Id: I8d019718465bbc3de727653a839de7238f45da5c
BUG: 765495
Signed-off-by: Kaushal M 
Reviewed-on: http://review.gluster.com/2637
Tested-by: Gluster Build System 
Reviewed-by: Krishnan Parthasarathi

glusterd: Fixed crash in stop volume found using efence.

2012-01-20T06:59:10+00:00

Change-Id: I84d38b8af248920a1559d05f0e4f43d3eda0f43e
BUG: 782710
Signed-off-by: Krishnan Parthasarathi 
Reviewed-on: http://review.gluster.com/2651
Reviewed-by: Pranith Kumar Karampuri 
Tested-by: Gluster Build System

cli: volume status enhancement

2012-01-12T09:58:26+00:00

    * Support "gluster volume status (all)" option to display all
      volumes' status.

    * On option "detail" appended to "gluster volume status *",
      amount of storage free, total storage, and backend filesystem
      details like inode size, inode count, free inodes, fs type,
      device name of each brick is displayed.

    * One can also obtain [detailed]status of only one brick.

    * Format of the enhanced volume status command is:
      "gluster volume status [all|] [] [detail]"

    * Some generic functions have been added to common-utils:

           skipword
           get_nth_word
      These functions enable parsing and fetching
      of words in a sentence.

           glusterd_get_brick_root    (in glusterd)
      These are self explanatory.

Change-Id: I6f40c1e19810f8504cd3b1786207364053d82e28
BUG: 765464
Signed-off-by: Rajesh Amaravathi 
Reviewed-on: http://review.gluster.com/777
Tested-by: Gluster Build System 
Reviewed-by: Amar Tumballi