summaryrefslogtreecommitdiffstats
path: root/rpc/rpc-transport
Commit message (Collapse)AuthorAgeFilesLines
* rpc-transport/socket: Set NODELAY for connect socketVijay Bellur2012-04-191-0/+10
| | | | | | | | | | | | | This is essentially a re-introduction of setting TCP_NODELAY on the connect socket which was erroneously removed as part of commit 2da18b6 Change-Id: Icc3a8faafce0e63a9dde592a48f22b90a72860d1 BUG: 795635 Signed-off-by: Vijay Bellur <vijay@gluster.com> Reviewed-on: http://review.gluster.com/3197 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Pranith Kumar Karampuri <pranithk@gluster.com>
* transport/socket: configuring tcp window-sizeRajesh Amaravathi2012-02-292-54/+64
| | | | | | | | | | | | | | | | | | | | | | | 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 <sane_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 <rajesh@redhat.com> Reviewed-on: http://review.gluster.com/2821 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Amar Tumballi <amarts@redhat.com> Reviewed-by: Jeff Darcy <jdarcy@redhat.com> Reviewed-by: Vijay Bellur <vijay@gluster.com>
* iobuf: use 'iobuf_get2()' to get variable sized buffersAmar Tumballi2012-02-202-17/+21
| | | | | | | | | | | added 'TODO' in places where it is missing. Change-Id: Ia802c94e3bb76930f7c88c990f078525be5459f5 Signed-off-by: Amar Tumballi <amar@gluster.com> BUG: 765264 Reviewed-on: http://review.gluster.com/388 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vijay@gluster.com>
* core: change lk-owner as a 1k bufferAmar Tumballi2012-01-241-1/+1
| | | | | | | | | | | | | so, NLM can send the lk-owner field directly to the locks translators, while doing the same effort, also enabled sending maximum of 500 aux gid over protocol. Change-Id: I87c2514392748416f7ffe21d5154faad2e413969 Signed-off-by: Amar Tumballi <amar@gluster.com> BUG: 767229 Reviewed-on: http://review.gluster.com/779 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Anand Avati <avati@gluster.com>
* transport/rdma: Add attr_timeout, attr_retry_cnt, attr_rnr_retryHarshavardhana2011-12-202-7/+43
| | | | | | | | | | | | as configurable options Change-Id: Ifc4710f149be35979746ddfbfb4181638601bc64 BUG: 766040 Signed-off-by: Harshavardhana <fharshav@redhat.com> Reviewed-on: http://review.gluster.com/766 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Jeff Darcy <jdarcy@redhat.com> Reviewed-by: Vijay Bellur <vijay@gluster.com>
* rpc-transport/socket: Donot fail reconnect if error is ENOENTshishir gowda2011-12-191-1/+1
| | | | | | | | | | | | | A AF_UNIX family socket should retry connect if error is ENOENT. Signed-off-by: shishir gowda <shishirng@gluster.com> Change-Id: I23b1da12faadc8043d370862bfe29c0c5c223364 BUG: 767932 Reviewed-on: http://review.gluster.com/795 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Jeff Darcy <jdarcy@redhat.com> Reviewed-by: Amar Tumballi <amar@gluster.com> Reviewed-by: Vijay Bellur <vijay@gluster.com>
* rpc-transport/rdma: add gf_ prefix to all procedure, variable namesRaghavendra G2011-11-242-1045/+1098
| | | | | | | | | Change-Id: I251be23d2c60b88589f71e7a8c3b1f2b7e3eb3e6 BUG: 3319 Reviewed-on: http://review.gluster.com/148 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Amar Tumballi <amar@gluster.com> Reviewed-by: Anand Avati <avati@gluster.com>
* glusterfs: An effort to fix all the spell mistakes and typoHarshavardhana2011-11-164-6/+6
| | | | | | | | | | | | | | | in the entire glusterfs codebase. This patch fixes many of spell mistakes and typo in the entire glusterfs codebase and all supported modules. Change-Id: I83238a41aa08118df3cf4d1d605505dd3cda35a1 BUG: 3809 Signed-off-by: Harshavardhana <fharshav@redhat.com> Reviewed-on: http://review.gluster.com/731 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Amar Tumballi <amar@gluster.com> Reviewed-by: Vijay Bellur <vijay@gluster.com>
* rpc-transport/rdma: send correct vector count when both rpc-header and ↵Raghavendra G2011-11-151-2/+10
| | | | | | | | | | | program-header are received through rdma-reads. Change-Id: I1b0b91eb7216f32a5748325d6dda37f3998302c7 BUG: 3754 Reviewed-on: http://review.gluster.com/697 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Amar Tumballi <amar@gluster.com> Reviewed-by: Vijay Bellur <vijay@gluster.com>
* rpc: fix wrong wiping of state machine's stateAnand Avati2011-09-251-1/+1
| | | | | | | | | | | | | | | The macro __socket_proto_read() is used to read one sub-header in a fragment after another. It also has to 'get out' of the state machine's switch/case construct in two situations - a) finished reading the full header b) after a partial read, (and return in the same state at next pollin) The 'reset' of the state should happen only after a full read of the header and not if there was a partial read of the header. Change-Id: I3650a83e1fae0f317cfd1b549835c72e39dc5253
* socket: provide proper arguments to getaddrinfoAmar Tumballi2011-09-131-1/+1
| | | | | | | | | | | | | | | | | ----- from 'man getaddrinfo' : If hints.ai_flags includes the AI_ADDRCONFIG flag, then IPv4 addresses are returned in the list pointed to by res only if the local system has at least one IPv4 address configured, and IPv6 addresses are only returned if the local system has at least one IPv6 address configured. ----- Change-Id: Ie30344daf1bb9d41ac58741b38e83af35cd8b5e9 BUG: 2456 Reviewed-on: http://review.gluster.com/405 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vijay@gluster.com>
* Eliminate many "var set but not used" warnings with newer gcc.Jeff Darcy2011-09-071-24/+2
| | | | | | | | | | | | | | | | This fixes ~200 such warnings, but leaves three categories untouched. (1) Rpcgen code. (2) Macros which set variables in the outer (calling function) scope. (3) Variables which are set via function calls which may have side effects. Change-Id: I6554555f78ed26134251504b038da7e94adacbcd BUG: 2550 Reviewed-on: http://review.gluster.com/371 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Anand Avati <avati@gluster.com>
* modify to the way we used XDR definitions files (.x files)Amar Tumballi2011-09-071-1/+0
| | | | | | | | | | | | | | | | | | | | | | | | Earlier: step 1: copy the existing <xdr>.x files to /tmp step 2: generate '.[ch]' files using 'rpcgen <xdr>.x' step 3: check diff with the to the existing files, add only your part of changes back to the original file. (ignore other changes). step 4: there is another file to write wrapper functions to convert structures to/from XDR buffers, update it with your new structure. step 5: use these wrapper functions in the newly written procedures. step 6: commit :-| Now: step 1: update (mostly adding only) the <xdr>.x file step 2: run '<path-to-src>/extras/generate-xdr-files.sh <xdr>.x' command step 3: implement rpc procedure to handle the request/response. step 4: commit :-) Change-Id: I219f9159fc980438c86e847c6b030be96e595ea2 BUG: 3488 Reviewed-on: http://review.gluster.com/341 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Anand Avati <avati@gluster.com>
* mem-pool: Make mem-pool ptr avialable in ptrshishir gowda2011-08-251-4/+4
| | | | | | | | | | | | | | | | | The header of the ptr returned from mem-pool will now store the mem-pool ptr it belongs to. mem_put will now take only the pointer to be freed. Also, changing MALLOC call to GF_CALLOC in mem_get when we run out of entries in mem-pool. This also will have the header information saved. Change-Id: I3de182663a7f5b49c9e9425e9531775b70bdff67 BUG: 3390 Reviewed-on: http://review.gluster.com/205 Reviewed-by: Amar Tumballi <amar@gluster.com> Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Vijay Bellur <vijay@gluster.com>
* Change Copyright current yearPranith Kumar K2011-08-108-8/+8
| | | | | | | | Change-Id: I2d10f2be44f518f496427f257988f1858e888084 BUG: 3348 Reviewed-on: http://review.gluster.com/200 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Anand Avati <avati@gluster.com>
* LICENSE: s/GNU Affero General Public/GNU General Public/Pranith Kumar K2011-08-068-24/+24
| | | | | | | | Change-Id: I3914467611e573cccee0d22df93920cf1b2eb79f BUG: 3348 Reviewed-on: http://review.gluster.com/182 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Anand Avati <avati@gluster.com>
* Variable IOBUF: Use variable iobuf for cli/glusterd/glusterfsd(mgmt)shishir gowda2011-07-311-9/+11
| | | | | | | | | | | | By using variable iobufs, xfer data size is no more limited to 128K (default). This helps in scaling. Change-Id: Iab453db9223d887306d150cd6fe0b1eae9c422cc BUG: 2472 Reviewed-on: http://review.gluster.com/13 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Amar Tumballi <amar@gluster.com> Reviewed-by: Anand Avati <avati@gluster.com>
* RPC unify code changekrishna2011-07-292-31/+61
| | | | | | | | | Change-Id: Ibe18a2a63fd023ac57652c4dfc8ac8a69d983b83 BUG: 3112 Signed-off-by: krishna <krishna@gluster.com> Reviewed-on: http://review.gluster.com/116 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Amar Tumballi <amar@gluster.com>
* Glusterd: Remove dependency on AI_ADDRCONFIG for AF_UNSPECGaurav2011-07-272-5/+16
| | | | | | | | | Change-Id: I0a22b2cc5a0ea1a57633fddabad54aca7b3d4e86 BUG: 2456 Reviewed-on: http://review.gluster.com/102 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Csaba Henk <csaba@gluster.com> Reviewed-by: Vijay Bellur <vijay@gluster.com>
* rpc-transport/socket: avoid logging socket read failsRajesh2011-07-252-8/+28
| | | | | | | | | | | | | | An option, transport.socket.read-fail-log was added in glusterd. This can also be added to any translator which uses socket.c. A gf_boolean_t flag(read_fail_log) is added in socket_private_t. Using this, logging of socket read failures can be controlled. The options is set to 'off' in glusterd.vol by default. Change-Id: I85cf4afc1f534f5f51018449d5d84baef18fce23 BUG: 3156 Reviewed-on: http://review.gluster.com/22 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Anand Avati <avati@gluster.com>
* glusterd: Add bind-insecure xlator-option for glusterdshishir gowda2011-07-241-1/+1
| | | | | | | | | | | | This is required if the number of connections from the glusterd increases. Change-Id: Iff78773f593a8bfae13ec9eec52c5a67ea936ef2 BUG: 3142 Signed-off-by: shishir gowda <shishirng@gluster.com> Reviewed-on: http://review.gluster.com/11 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Pavan T C <tcp@gluster.com>
* rpc-transport/rdma: call ibv_fork_init to make rdma work with fork.Raghavendra G2011-07-011-0/+1
| | | | | | | | Signed-off-by: Raghavendra G <raghavendra@gluster.com> Signed-off-by: Anand Avati <avati@gluster.com> BUG: 3091 (rebalance fails with "transport endpoint not connected" in 3.2.1 rdma set-up) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=3091
* logging: fill proper domain names at places where it is missingAmar Tumballi2011-06-161-6/+6
| | | | | | | | | | also changed some error messages where it was not explicit Signed-off-by: Amar Tumballi <amar@gluster.com> Signed-off-by: Anand Avati <avati@gluster.com> BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346
* rdma: fix the excessive logsAmar Tumballi2011-06-161-2/+3
| | | | | | | | Signed-off-by: Amar Tumballi <amar@gluster.com> Signed-off-by: Anand Avati <avati@gluster.com> BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346
* build warning fixesAmar Tumballi2011-06-164-57/+48
| | | | | | | | | | mainly fixes all the sockaddr related 'strict aliasing' warnings Signed-off-by: Amar Tumballi <amar@gluster.com> Signed-off-by: Anand Avati <avati@gluster.com> BUG: 2550 (build warnings) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2550
* rpc-transport/rdma: don't return '0' in case of un-initiated rdma_connect()Amar Tumballi2011-06-081-4/+1
| | | | | | | | | | | | | needed to handle the re-configuration of the port in client protocol. If there is a successful 'connect()' after the query port, the remote-port value gets reset to '0'. In this case, if the connect() return 0 for already connected socket, the query_portmap will keep happening in a loop. Signed-off-by: Amar Tumballi <amar@gluster.com> Signed-off-by: Anand Avati <avati@gluster.com> BUG: 2294 (Currently there is no way through cli to make a volume listen on both the transports (socket/rdma)) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2294
* client_bind: When allow-insecure xlator option is set, donot bind.shishir gowda2011-05-311-3/+1
| | | | | | | | | | There is no need to bind a client, as connect will assign a port. Signed-off-by: shishir gowda <shishirng@gluster.com> Signed-off-by: Anand Avati <avati@gluster.com> BUG: 2868 (Add xlator-option to support insecure-bind for clients) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2868
* rpc: TCP_KEEPALIVE undeclared in NetBSDAnand Avati2011-05-301-1/+1
| | | | | | | | | | | Works around "error: 'TCP_KEEPALIVE' undeclared" on NetBSD Thanks to: Emmanuel Dreyfus <manu@netbsd.org> Signed-off-by: Anand Avati <avati@gluster.com> BUG: 2923 (NetBSD port) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2923
* rpc-clnt: consider the (re-)configured port for only one connect() callAmar Tumballi2011-05-301-1/+2
| | | | | | | | | | | this way, if remote_port is set due to queryport, that can fall back to default port (or 'option remote-port' value) when it disconnects. Signed-off-by: Amar Tumballi <amar@gluster.com> Signed-off-by: Anand Avati <avati@gluster.com> BUG: 2709 (issues with port (re-)configuration in client protocol) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2709
* rpc: Introduce option for listen()'s backlogVijay Bellur2011-05-302-1/+15
| | | | | | | | Signed-off-by: Vijay Bellur <vijay@gluster.com> Signed-off-by: Anand Avati <avati@gluster.com> BUG: 2941 (glusterd breaks when starting ~100 volumes) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2941
* Introduce client-allow-insecure xlator-option.shishir gowda2011-05-121-1/+5
| | | | | | | | | | | | | | | | | | Allows glusterfs clients to bind to any port and does not restrict it to 1024. This is a xlator-option only, and is not supported in volume set cmd. The reason is, few clients may choose this, and few may not. Hence only supported as a xlator-option during mount time. For this to work with glusterfs, server.allow-insecure should be set to on Signed-off-by: shishir gowda <shishirng@gluster.com> Signed-off-by: Anand Avati <avati@gluster.com> BUG: 2868 (Add xlator-option to support insecure-bind for clients) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2868
* remove excessive logs due to log enhancementAmar Tumballi2011-04-131-7/+13
| | | | | | | | Signed-off-by: Amar Tumballi <amar@gluster.com> Signed-off-by: Anand Avati <avati@gluster.com> BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346
* rpc: Don't warn on failure to bind to privileged portPranith K2011-03-261-1/+1
| | | | | | | | Signed-off-by: Pranith Kumar K <pranithk@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 2582 (allow option to accept messages from insecure ports) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2582
* CLI : Validate options farmework.Gaurav2011-03-231-26/+7
| | | | | | | | Signed-off-by: Gaurav <gaurav@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 2064 (NFS options are removed upon glusterd restart) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2064
* spelling errors fixed across the code baseAmar Tumballi2011-03-222-4/+4
| | | | | | | | | | | | | recieve -> receive maintainence -> maintenance verison -> version commited -> committed Signed-off-by: Amar Tumballi <amar@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 2262 (Spelling errors in source) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2262
* rpc-transport: log enhancementAmar Tumballi2011-03-174-202/+187
| | | | | | | | Signed-off-by: Amar Tumballi <amar@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346
* rpc-transport: whitespace cleanupAmar Tumballi2011-03-176-493/+493
| | | | | | | | Signed-off-by: Amar Tumballi <amar@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 2346 (Log message enhancements in GlusterFS - phase 1) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2346
* rpc-transport/rdma: handle cases where peer is NULL in send_completion.Raghavendra G2011-03-121-1/+1
| | | | | | | | | | | | | | - There can be valid cases where peer is NULL - For eg., race b/w pollin received on handshake socket and as a result transport getting disconnected and handling of a send/recv completion on the same qp for some previous read/write - in send/recv_completion_process. Hence we should be checking for a valid peer pointer before accessing it. Signed-off-by: Raghavendra G <raghavendra@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 2514 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2514
* rpc: Changes for handling unix domain sockets avoid racePranith K2011-03-101-0/+16
| | | | | | | | Signed-off-by: Pranith Kumar K <pranithk@gluster.com> Signed-off-by: Vijay Bellur <vijay@dev.gluster.com> BUG: 1965 (need a cmd to get io-stat details) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1965
* rdma : prevent confusing logs when both 'poll_in' and 'poll_err' are received.Amar Tumballi2010-12-271-1/+1
| | | | | | | | Signed-off-by: Amar Tumballi <amar@gluster.com> Signed-off-by: Anand V. Avati <avati@dev.gluster.com> 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
* setsockopt should be called with solaris specific arguments for solaris servershishir gowda2010-12-141-0/+5
| | | | | | | | | | | | | | | ----- Original Message ----- From: "Raghavendra Bhat" <raghavendrabhat@gluster.com> To: glusterfs@dev.gluster.com Sent: Tuesday, December 14, 2010 11:56:43 AM Subject: [PATCH BUG:2205 v4] setsockopt should be called with solaris specific arguments for solaris server Looks fine to me. Signed-off-by: Raghavendra Bhat <raghavendrabhat@gluster.com> Signed-off-by: Anand V. Avati <avati@dev.gluster.com> BUG: 2205 ([glusterfs-3.1.2qa1]: error while setting the keepalive time interval) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2205
* rpc-transport/rdma: QP configuration changes.Raghavendra G2010-12-121-29/+46
| | | | | | | | | | | | - set send and recv count to 4K. - set max_send_sge of QP to 2 since for msgs of type RDMA_NOMSG, there can be two vectors - rpc header and message from program. Signed-off-by: Raghavendra G <raghavendra@gluster.com> Signed-off-by: Anand V. Avati <avati@dev.gluster.com> BUG: 2197 (applications running on large number of clients simultaneously result in ibv_post_send errors on server.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2197
* rpc-transport/rdma: add informative debug messages when posting of send ↵Raghavendra G2010-12-121-13/+33
| | | | | | | | | | requests fail. Signed-off-by: Raghavendra G <raghavendra@gluster.com> Signed-off-by: Anand V. Avati <avati@dev.gluster.com> BUG: 2197 (applications running on large number of clients simultaneously result in ibv_post_send errors on server.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2197
* rpc-transport: don't merge payload iobuf and iobuf which holds program ↵Raghavendra G2010-11-253-34/+29
| | | | | | | | | | | | | header into single iobref. - io-cache holds a reference on iobref passed from transport layer. Hence, two iobufs are accounted instead of one in calculated used cache size. Signed-off-by: Raghavendra G <raghavendra@gluster.com> Signed-off-by: Anand V. Avati <avati@dev.gluster.com> BUG: 2135 () URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2135
* rpc-transport/rdma: set the default quota of recv buffers to 128.Raghavendra G2010-11-091-2/+2
| | | | | | | | | | - since quota is returned once the reply is recieved, 32 is too less value. Signed-off-by: Raghavendra G <raghavendra@gluster.com> Signed-off-by: Anand V. Avati <avati@dev.gluster.com> BUG: 2060 (Infiniteband errors on large file find) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2060
* rpc-transport/rdma: create request_context only if message contains read ↵Raghavendra G2010-11-071-18/+28
| | | | | | | | | | chunks or write chunks. Signed-off-by: Raghavendra G <raghavendra@gluster.com> Signed-off-by: Anand V. Avati <avati@dev.gluster.com> BUG: 1992 (glusterd crashed while submitting a callback.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1992
* rpc-transport/rdma: Fix 2KB as threshold size for msgs that can be ↵Raghavendra G2010-11-072-13/+23
| | | | | | | | | | | | | transferred inline. - Any fop/mop that can result a reply whose size is greater than this threshold allocates and submits a buffer along with the request to receive reply. Signed-off-by: Raghavendra G <raghavendra@gluster.com> Signed-off-by: Anand V. Avati <avati@dev.gluster.com> BUG: 513 (Introduce 0 copy rdma) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=513
* rpc-transport/rdma: increment post->ctx.count in a loop doint rdma_read.Raghavendra G2010-11-071-5/+5
| | | | | | | | | | | - incrementing by the number of read chunks even before doing rdma read will cause issues since post->ctx.count is used while posting rdma read. Signed-off-by: Raghavendra G <raghavendra@gluster.com> Signed-off-by: Anand V. Avati <avati@dev.gluster.com> BUG: 1877 (data corruption while running arequal.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1877
* socket: avoid check on lowlat for enabling nodelayVijay Bellur2010-11-021-6/+1
| | | | | | | | Signed-off-by: Vijay Bellur <vijay@gluster.com> Signed-off-by: Anand V. Avati <avati@dev.gluster.com> BUG: 2040 (Using 'du' and 'ls' command, it got slow performance) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=2040
* rpc-transport: fix race-condition between rdma-read completion and updating ↵Raghavendra G2010-10-291-1/+1
| | | | | | | | | | | | | | the count of number of vectors to be passed to rpc. - If rdma read completes before incrementing the vector count, the count value sent to rpc will be improper. For fops like write, this may result in missing out a vector to be written, thereby causing data corruption. Signed-off-by: Raghavendra G <raghavendra@gluster.com> Signed-off-by: Anand V. Avati <avati@dev.gluster.com> BUG: 1877 (data corruption while running arequal.) URL: http://bugs.gluster.com/cgi-bin/bugzilla3/show_bug.cgi?id=1877
generated by cgit (git 2.34.1) at 2024-11-06 05:29:56 +0000