glusterfs.git/transport, branch v8dev

structuring of protocol - 2

2010-05-04T06:40:05+00:00

* 'transports/' and 'auth/' moved to xlators/protocol/
* transport.{c,h}, authenticate.{c,h}, protocol.h moved to
    xlators/protocol/lib/src/

Signed-off-by: Amar Tumballi 
Signed-off-by: Anand V. Avati 

BUG: 875 (Implement a new protocol to provide proper backward/forward compatibility)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=875

Memory accounting changes

2010-04-23T13:32:52+00:00

Memory accounting Changes. Thanks to Vinayak Hegde and Csaba Henk for their
contributions.

Signed-off-by: Vijay Bellur 
Signed-off-by: Anand V. Avati 

BUG: 329 (Replacing memory allocation functions with mem-type functions)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=329

Hardcoded infiniband port is now handled dynamically by searching for active ports.

2010-03-31T16:29:36+00:00

* If user specifies a port then that port will be used regardless of which port is active.
* If user doesn't specify any port then any one of the active ports is used.

Signed-off-by: Harshavardhana 
Signed-off-by: Anand V. Avati 

BUG: 793 (Infiniband port handling should be dynamic by picking up from active ports)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=793

socket: Add NULL check for failed ioq entry allocation

2010-03-02T16:22:01+00:00

This is seen in OOM situations.

Signed-off-by: Shehjar Tikoo 
Signed-off-by: Anand V. Avati 

BUG: 679 (Crash in socket_ioq_new)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=679

transport/socket: guess an appropriate address family when it is not specified in configuration.

2010-01-28T14:11:33+00:00

Signed-off-by: Raghavendra G 
Signed-off-by: Anand V. Avati 

BUG: 561 (with address family set to 'inet-sdp', transport/socket doesn't work correctly)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=561

transport/socket: use appropriate address family macro when address family is inet-sdp.

2010-01-22T13:34:35+00:00

- sa_family should be set to AF_INET_SDP only during call to socket system
    call. For all other calls, sa_family should be AF_INET.

Signed-off-by: Raghavendra G 
Signed-off-by: Anand V. Avati 

BUG: 561 (with address family set to 'inet-sdp', transport/socket doesn't work correctly)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=561

transport/socket: Enable NODELAY even if no option is set.

2010-01-12T10:12:49+00:00

Signed-off-by: Vijay Bellur 
Signed-off-by: Anand V. Avati 

BUG: 524 (TCP_NODELAY not set when expected on client)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=524

transport/ib-verbs: assign to qpreg before accessing it in __ib_verbs_lookup_peer.

2009-11-19T10:57:45+00:00

Signed-off-by: Raghavendra G 
Signed-off-by: Anand V. Avati 

BUG: 381 (glusterfs crash in ib-verbs)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=381

transport/ib-verbs: fix race-condition resulting in freeing of transport while it was still being used.

2009-11-16T08:41:36+00:00

- while handling a failed work completion status, the transport is
    disconnected. But further down in the code, the transport is still
    used. There can be a possibility that transport might've been freed
    by the time control reaches this point. More detailed description of
    events leading to this situation can be found at
    http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=381

Signed-off-by: Raghavendra G 
Signed-off-by: Anand V. Avati 

BUG: 381 (glusterfs crash in ib-verbs)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=381

transport/ib-verbs: synchronize ib_verbs_recv_completion_proc with ib_verbs_receive so that the former doesn't overwrite the pointer from which latter reads.

2009-11-16T08:41:32+00:00

- There can be a condition wherein,
    1. the thread executing ib_verbs_recv_completion_proc (thr 1) stores the
       buffer pointer and notifies the upper translators about a POLLIN event.
    2. the thread waiting for events on socket (thr 2) calls transport_receive,
       but in ib_verbs_receive it has not still read the data.
    3. thr 1 receives work completion event for another work request and
       overwrites the buffer pointer.
    4. thr 2 reads from the new pointer there by missing the data stored in
       buffer pointed by pointer which got overwritten.

Signed-off-by: Raghavendra G 
Signed-off-by: Anand V. Avati 

BUG: 382 (Data can be lost before it is read in ib_verbs_receive.)
URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=382