glusterfs.git/rpc/rpc-transport/socket/src, branch v3.10.0rc1

socket: GF_REF_PUT should be called outside lock

2017-02-07T11:49:43+00:00

GF_REF_PUT was called inside lock which can call
socket_poller_mayday which inturn tries to take the
same lock. This can lead to deadlock scenario.

>Reviewed-on: https://review.gluster.org/16343
>Reviewed-by: Raghavendra G 
>CentOS-regression: Gluster Build System 
>Smoke: Gluster Build System 
>NetBSD-regression: NetBSD Build System 

BUG: 1419503
Change-Id: Ib3b161bcfeac810bd3593dc04c10ef984f996b17
Signed-off-by: Rajesh Joseph 
Reviewed-on: https://review.gluster.org/16548
Tested-by: Atin Mukherjee 
Reviewed-by: Raghavendra G 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Smoke: Gluster Build System

socket: retry connect immediately if it fails

2017-02-03T00:43:24+00:00

Previously we relied on a complex dance of setting flags, shutting
down the socket, tearing stuff down, getting an event, tearing more
stuff down, and waiting for a higher-level retry.  What we really
need, in the case where we're just trying to connect prematurely e.g.
to a brick that hasn't fully come up yet, is a simple retry of the
connect(2) call.

This was discovered by observing failures in ec-new-entry.t with
multiplexing enabled, but probably fixes other random failures as
well.

Backport of:
> Change-Id: Ibedb8942060bccc96b02272a333c3002c9b77d4c
> BUG: 1385758
> Reviewed-on: https://review.gluster.org/16510

BUG: 1418091
Change-Id: I4bac26929a12cabcee4f9e557c8b4d520948378b
Signed-off-by: Jeff Darcy 
Reviewed-on: https://review.gluster.org/16533
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Shyamsundar Ranganathan

rpc/socket.c : Bonnie++ hangs during rewrites in ganesha + SSL

2017-02-02T17:33:45+00:00

Problem: Bonnie++ rewrite operation hangs in ganesha + SSL environment

Solution: Bonnie++ hangs during execution of rewrite operation in
          ganesha + SSL environment.It was hanged due to blocking on poll
          call in ssl_do because no POLLOUT event was getting on socket.
          Socket is not getting POLLOUT event because all other threads
          are waiting to get lock and lock is not released ssl_do
          because it is not getting any event on poll.To correct it
          update the condition in ssl_do as same in getting error
          SSL_ERROR_WANT_READ.

Test:     To test the patch followed below procedure
          1) Setup 2X2 Ganesha + SSL environment.
          2) Run bonnie from 3 nfs client parallely
          3) After run "Rewwrite operation" by bonnie it is hanged.
          4) After apply the patch it is not hanged.

> BUG: 1418213
> Change-Id: I5985cbbc4cfdac5d287268d791e31c274abc3c8d
> Signed-off-by: Mohit Agrawal 
> Reviewed-on: https://review.gluster.org/16501
> Smoke: Gluster Build System 
> NetBSD-regression: NetBSD Build System 
> Reviewed-by: Jeff Darcy 
> CentOS-regression: Gluster Build System 
> Reviewed-by: Vijay Bellur 
> (cherry picked from commit d7077bca4b372a056d23416294e729637e9af94e)

Change-Id: Id029c71382025477bb5ff31f28ec537e4fe58b03
BUG: 1418541
Reviewed-on: https://review.gluster.org/16513
Tested-by: MOHIT AGRAWAL 
NetBSD-regression: NetBSD Build System 
Smoke: Gluster Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Shyamsundar Ranganathan

libglusterfs+transport+io-threads: fix 256KB stack abuse

2017-02-02T17:32:49+00:00

Some functions were allocating 64K booleans, which are (crazily)
mapped to 4-byte ints, for a total of 256KB per call.  Changed to use
bitfields instead, so usage is now only 8KB per call.  This was the
impediment to changing the io-threads stack size, so that has been
adjusted too.

Backport of:
> Change-Id: I8781c4f2c8f2b830f4535e366995fac8dd0a8653
> BUG: 1418095
> Reviewed-on: https://review.gluster.org/15745

Change-Id: Ia5dada61703e6bea95f2511da71feb573fc9a429
BUG: 1418536
Signed-off-by: Jeff Darcy 
Reviewed-on: https://review.gluster.org/16511
Reviewed-by: N Balachandran 
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
Reviewed-by: Vijay Bellur 
CentOS-regression: Gluster Build System

core: run many bricks within one glusterfsd process

2017-02-02T00:54:58+00:00

This patch adds support for multiple brick translator stacks running in
a single brick server process.  This reduces our per-brick memory usage
by approximately 3x, and our appetite for TCP ports even more.  It also
creates potential to avoid process/thread thrashing, and to improve QoS
by scheduling more carefully across the bricks, but realizing that
potential will require further work.

Multiplexing is controlled by the "cluster.brick-multiplex" global
option.  By default it's off, and bricks are started in separate
processes as before.  If multiplexing is enabled, then *compatible*
bricks (mostly those with the same transport options) will be started in
the same process.

Backport of:
> Change-Id: I45059454e51d6f4cbb29a4953359c09a408695cb
> BUG: 1385758
> Reviewed-on: https://review.gluster.org/14763

Change-Id: I4bce9080f6c93d50171823298fdf920258317ee8
BUG: 1418091
Signed-off-by: Jeff Darcy 
Reviewed-on: https://review.gluster.org/16496
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Shyamsundar Ranganathan

socket: socket disconnect should wait for poller thread exit

2016-12-22T04:49:19+00:00

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 
Reviewed-on: http://review.gluster.org/16141
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Kaushal M 
Reviewed-by: Raghavendra Talur 
Reviewed-by: Raghavendra G

socket: Keepalives should happen on IPv6 as well as IPv4

2016-12-16T20:30:05+00:00

Summary:
- Check for AF_INET *and* AF_INET6.
- This is a cherry-pick of D3057373 to 3.8

Signed-off-by: Shreyas Siravara 
Change-Id: I53eb79284eddfee6e13821c6570809f575b96769
BUG: 1405478
Reviewed-on: http://review.gluster.org/16167
Reviewed-by: Jeff Darcy 
Tested-by: Jeff Darcy 
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Vijay Bellur

rpc/socket.c : Modify socket_poller code in case of ENODATA error code.

2016-10-24T05:30:52+00:00

Problem:  Continuous warning message(ENODATA) are coming in socket_rwv
          while SSL is enabled.

Solution: To avoid the warning message update one condition in
          socket_poller loop code before break from loop in case
          of error returned by poll functions.

BUG: 1386450
Change-Id: I19b3a92d4c3ba380738379f5679c1c354f0ab9b1
Signed-off-by: Mohit Agrawal 
Reviewed-on: http://review.gluster.org/15677
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Raghavendra G

rpc/socket: Close pipe on disconnection

2016-10-24T04:10:50+00:00

Encrypted connections create a pipe, which isn't closed when the
connection disconnects. This leaks fds, and gluster eventually ends up
in a situation with fd starvation which leads to operation failures.

Change-Id: I144e1f767cec8c6fc1aa46b00cd234129d2a4adc
BUG: 1336371
Signed-off-by: Kaushal M 
Reviewed-on: http://review.gluster.org/14356
Tested-by: MOHIT AGRAWAL 
Smoke: Gluster Build System 
CentOS-regression: Gluster Build System 
NetBSD-regression: NetBSD Build System 
Reviewed-by: Raghavendra G

rpc/socket.c : Modify gf_log message in socket_poller code in case of error

2016-10-13T06:59:37+00:00

Problem:  In case of SSL after stopping the volume if client(mount point) is
          still trying to write the data on socket then it will throw an EIO
          error on that socket and given this log message is captured at every
          attempt this would flood the log file.

Solution: To reduce the frequency of stored log message use GF_LOG_OCCASIONALLY
          instead of gf_log.

BUG: 1381115
Change-Id: I66151d153c2cbfb017b3ebc4c52162278c0f537c
Signed-off-by: Mohit Agrawal 
Reviewed-on: http://review.gluster.org/15605
Smoke: Gluster Build System 
NetBSD-regression: NetBSD Build System 
CentOS-regression: Gluster Build System 
Reviewed-by: Atin Mukherjee