Object update was originally planned to be used for cross-server
updates, so nothign to do with the client. The idea was
later significantly reworked anyway so even wire structs should
not be retained.
This gets rid of update_cmd_t, UPDATE and UPDATE_REPLY rpc and
corresponding subcommands, swabbig logic and such.
Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Replace it with direct reference of enum loc_flags
Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Typedefs fld_hash_func_t and fld_scan_func_t are used exectly once in
the following structure so don't really help anything at all.
Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This member comes from the dawn of time and is no longer needed
Signed-off-by: Oleg Drokin <green@linuxhacker.ru>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
In lnet_router_checker(), there are two LASSERTS. Neither protects
us from anything and one of them triggered for a customer crashing
the system unecessarily. This patch removes them.
Signed-off-by: Doug Oucharek <doug.s.oucharek@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-7362
Reviewed-on: http://review.whamcloud.com/17003
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Chris Horn <hornc@cray.com>
Reviewed-by: Matt Ezell <ezellma@ornl.gov>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
lctl show_route and lctl route_list will output router aliveness
information via lnet_get_route(). lnet_get_route() should use the
lnet_is_route_alive() function, introduced in e8a1124
http://review.whamcloud.com/7857, to determine route aliveness.
Signed-off-by: Chris Horn <hornc@cray.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-5733
Reviewed-on: http://review.whamcloud.com/14055
Reviewed-by: James Simmons <uja.ornl@yahoo.com>
Reviewed-by: Amir Shehata <amir.shehata@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This patch ensures that the correct number of router buffers are
allocated. It keeps a count that keeps track of the number of
buffers allocated. Another count keeps the number of buffers
requested. The number of buffers allocated is set when creating
new buffers and reduced when buffers are freed.
The number of requested buffer is set when the buffers are
allocated and is checked when credits are returned to determine
whether the buffer should be freed or kept.
In lnet_rtrpool_adjust_bufs() grab lnet_net_lock() before using
rbp_nbuffers to ensure that it doesn't change by
lnet_return_rx_credits_locked() during the process of allocating
new buffers. All other access to rbp_nbuffers is already being
protected by lnet_net_lock().
This avoids the case where we allocate less than the desired
number of buffers.
Signed-off-by: Amir Shehata <amir.shehata@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-6122
Reviewed-on: http://review.whamcloud.com/13519
Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com>
Reviewed-by: Doug Oucharek <doug.s.oucharek@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
On some platforms having sock.h in lib-types.h would collide with
other included header files being used in the LNet layer. Looking
at what was needed from sock.h only acceptor.c is dependent on it.
To avoid these issues we just use sock.h only in acceptor.c.
Signed-off-by: James Simmons <jsimmons@infradead.org>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-6763
Reviewed-on: http://review.whamcloud.com/15386
Reviewed-by: Chris Horn <hornc@cray.com>
Reviewed-by: Amir Shehata <amir.shehata@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This patch will avoid potential race, around socket sleepers
wait list, during acceptor thread termination and using
sk_callback_lock RW-Lock protection.
Signed-off-by: Bruno Faccini <bruno.faccini@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-6476
Reviewed-on: http://review.whamcloud.com/14503
Reviewed-by: Amir Shehata <amir.shehata@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
A lot of symbols don't need to be exported at all because they are
only used in the module they belong to.
Signed-off-by: Frank Zago <fzago@cray.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-5829
Reviewed-on: http://review.whamcloud.com/13320
Reviewed-by: James Simmons <uja.ornl@gmail.com>
Reviewed-by: Isaac Huang <he.huang@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
When shutting down an NI in a busy system, some messages received
on this NI, might be on the lazy portal. They would have grabbed
a ref count on the NI. Therefore NI will not be removed until
messages are processed.
In order to avoid this scenario, when an NI is shutdown go through
all messages queued on the lazy portal and drop messages for the
NI being shutdown
Signed-off-by: Amir Shehata <amir.shehata@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-6040
Reviewed-on: http://review.whamcloud.com/13836
Reviewed-by: Isaac Huang <he.huang@intel.com>
Reviewed-by: Liang Zhen <liang.zhen@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
There is a use case where lnet can be unloaded while there are
no NIs configured. Removing lnet in this case will cause
LNetFini() to be called without a prior call to LNetNIFini().
This will cause the LASSERT(the_lnet.ln_refcount == 0) to be
triggered.
To deal with this use case when LNet is configured a reference
count on the module is taken using try_module_get(). This way
LNet must be unconfigured before it could be removed; therefore
avoiding the above case. When LNet is unconfigured module_put()
is called to return the reference count.
Signed-off-by: Amir Shehata <amir.shehata@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-6010
Reviewed-on: http://review.whamcloud.com/13110
Reviewed-by: James Simmons <uja.ornl@gmail.com>
Reviewed-by: Doug Oucharek <doug.s.oucharek@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
In lnet/lnet/ and lnet/selftest/ assume a kernel build (assume that
__KERNEL__ is defined). Remove some common code only needed for user
space LNet.
Only part of the work of this patch got merged. This is the final
bits.
Signed-off-by: John L. Hammond <john.hammond@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-2675
Reviewed-on: http://review.whamcloud.com/13121
Reviewed-by: James Simmons <uja.ornl@gmail.com>
Reviewed-by: Amir Shehata <amir.shehata@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This patch starts router checker thread all the time.
The router checker only checks routes by ping if
live_router_check_interval or dead_router_check_interval are set
to something other than 0, and there are routes configured.
If these conditions are not met the router checker sleeps until woken
up when a route is added. It is also woken up whenever the RC is
being stopped to ensure the thread doesn't hang.
In the future when DLC starts configuring the live and dead
router_check_interval parameters, then by manipulating them
the router checker can be turned on and off by the user.
Signed-off-by: Amir Shehata <amir.shehata@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-6003
Reviewed-on: http://review.whamcloud.com/13035
Reviewed-by: Liang Zhen <liang.zhen@intel.com>
Reviewed-by: Doug Oucharek <doug.s.oucharek@intel.com>
Reviewed-by: James Simmons <uja.ornl@gmail.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
After adding a route, lnet_check_routes() is called to ensure that
the route added doesn't invalidate the routing configuration. If
lnet_check_routes() fails then the route just added, which caused the
current configuration to be invalidated is deleted, and an error
is returned to the user.
Signed-off-by: Amir Shehata <amir.shehata@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-6218
Reviewed-on: http://review.whamcloud.com/13445
Reviewed-by: Liang Zhen <liang.zhen@intel.com>
Reviewed-by: Doug Oucharek <doug.s.oucharek@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Return -EEXIST and not -EINVAL when trying to add a
network interface which is not unique.
Some minor cleanup in api-ni.c
Signed-off-by: Amir Shehata <amir.shehata@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-5875
Reviewed-on: http://review.whamcloud.com/13056
Reviewed-by: Isaac Huang <he.huang@intel.com>
Reviewed-by: James Simmons <uja.ornl@gmail.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Currently if there exists a route that goes over a
remote net and then this net is added dynamically as
a local net, then traffic stops because the code in
lnet_send() determines that the destination nid
can be reached from another local_ni, but the src_nid
is still stuck on the earlier NI, because the src_nid
is stored in the ptlrpc layer and is not updated
when a local NI is configured.
Signed-off-by: Amir Shehata <amir.shehata@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-5874
Reviewed-on: http://review.whamcloud.com/12912
Reviewed-by: Isaac Huang <he.huang@intel.com>
Reviewed-by: James Simmons <uja.ornl@gmail.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
With DLC it's possible to start up a system with no NIs that require
the acceptor thread, and thus it won't start. Later on the user
can add an NI that requires the acceptor thread to start, it is
then necessary to start it up.
If the user removes a NI and as a result there are no more
NIs that require the acceptor thread then it should be stopped.
This patch adds logic in the dynamically adding and removing NIs
code to ensure the above logic is implemented.
Signed-off-by: Amir Shehata <amir.shehata@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-6002
Reviewed-on: http://review.whamcloud.com/13010
Reviewed-by: Isaac Huang <he.huang@intel.com>
Reviewed-by: Doug Oucharek <doug.s.oucharek@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
It is preferable to use NULL instead of 0 for pointers. This fixes sparse
warnings such as:
lustre/fld/fld_request.c:126:17: warning: Using plain integer as NULL pointer
The second parameter of class_match_param() was changed to a const, to
be able to remove a cast in one user, to prevent splitting a long
line. No other code change.
Signed-off-by: Frank Zago <fzago@cray.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-5396
Reviewed-on: http://review.whamcloud.com/12567
Reviewed-by: Dmitry Eremin <dmitry.eremin@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Bob Glossman <bob.glossman@intel.com>
Reviewed-by: James Simmons <uja.ornl@gmail.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Some functions and variables are only used in their C file, so reduce
their scope. This reduces the code size, and fixes sparse warnings
such as:
warning: symbol 'proc_lnet_routes' was not declared.
Should it be static?
warning: symbol 'proc_lnet_routers' was not declared.
Should it be static?
Some prototypes were removed from C files and added to the proper
header.
Signed-off-by: Frank Zago <fzago@cray.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-5396
Reviewed-on: http://review.whamcloud.com/12206
Reviewed-by: James Simmons <uja.ornl@gmail.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
When adding route it ignored specific scenarios, namely:
1. route already exists
2. route is on a local net
3. route is unreacheable
This patch returns the appropriate return codes from the lower level
function lnet_add_route(), and then ignores the above case from the
calling function, lnet_parse_route(). This is needed so we don't
halt processing routes in the module parameters.
However, we can now add routes dynamically, and it should be returned
to the user whether adding the requested route succeeded or failed.
In userspace it is determined whether to continue adding routes or to
halt processing. Currently "lnetctl import < config" continues
adding the rest of the configuration and reports at the end which
operations passed and which ones failed.
Signed-off-by: Amir Shehata <amir.shehata@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-6045
Reviewed-on: http://review.whamcloud.com/13116
Reviewed-by: James Simmons <uja.ornl@gmail.com>
Reviewed-by: Doug Oucharek <doug.s.oucharek@intel.com>
Reviewed-by: Isaac Huang <he.huang@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This patch addresses a set of related issues: LU-5568, LU-5734,
LU-5839, LU-5849, LU-5850.
Create the local lnet_startup_lndni() API. This function starts
up one LND. lnet_startup_lndnis() calls this function in a loop
on every ni in the list passed in. lnet_startup_lndni() is
responsible for cleaning up after itself in case of failure.
It calls lnet_free_ni() if the ni fails to start. It calls
lnet_shutdown_lndni() if it successfully called the
lnd startup function, but fails later on.
lnet_startup_lndnis() also cleans up after itself.
If lnet_startup_lndni() fails then lnet_shutdown_lndnis() is
called to clean up all nis that might have been
started, and then free the rest of the nis on the list
which have not been started yet.
To facilitate the above changes lnet_dyn_del_ni() now
manages the ping info. It calls lnet_shutdown_lndni(),
to shutdown the NI. lnet_shutdown_lndni() is no longer
an exposed API and doesn't manage the ping info, making
it callable from lnet_startup_lndni() as well.
There are two scenarios for calling lnet_startup_lndni()
1. from lnet_startup_lndnis()
If lnet_startup_lndni() fails it requires to shutdown the ni
without doing anything with the ping information as it hasn't
been created yet.
2. from lnet_dyn_add_ni()
As above it will shutdown the ni, and then lnet_dyn_add_ni() will
take care of managing the ping info
The second part of this change is to ensure that the LOLND is not
added by lnet_parse_networks(), but the caller which needs to do
it (IE: LNetNIInit)
This change ensures that lnet_dyn_add_ni() need only check if there is
only one net that's being added, if not then it frees everything,
otherwise it proceeds to startup the requested net.
Signed-off-by: Amir Shehata <amir.shehata@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-5734
Reviewed-on: http://review.whamcloud.com/12658
Reviewed-by: Liang Zhen <liang.zhen@intel.com>
Reviewed-by: Isaac Huang <he.huang@intel.com>
Reviewed-by: James Simmons <uja.ornl@gmail.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Remove LUSTRE_LNET_PID (12354) and LUSTRE_SRV_LNET_PID (12345) from
the libcfs headers and replace their uses with a new macro
LNET_PID_LUSTRE (also 12345) in lnet/types.h.
Signed-off-by: John L. Hammond <john.hammond@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-2675
Reviewed-on: http://review.whamcloud.com/11985
Reviewed-by: James Simmons <uja.ornl@gmail.com>
Reviewed-by: Bob Glossman <bob.glossman@intel.com>
Reviewed-by: Dmitry Eremin <dmitry.eremin@intel.com>
Reviewed-by: Andreas Dilger <andreas.dilger@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The function lnet_unprepare can be made static.
Signed-off-by: Frank Zago <fzago@cray.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-5396
Reviewed-on: http://review.whamcloud.com/11306
Reviewed-by: James Simmons <uja.ornl@gmail.com>
Reviewed-by: Patrick Farrell <paf@cray.com>
Reviewed-by: Amir Shehata <amir.shehata@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This is the sixth patch of a set of patches that enables DLC.
This patch enables the user space to call into the kernel space
DLC code. Added handlers in the LNetCtl function to call
the new functions added for Dynamic Lnet Configuration
Signed-off-by: Amir Shehata <amir.shehata@intel.com>
ntel-bug-id: https://jira.hpdd.intel.com/browse/LU-2456
Reviewed-on: http://review.whamcloud.com/8023
Reviewed-by: James Simmons <uja.ornl@gmail.com>
Reviewed-by: Doug Oucharek <doug.s.oucharek@intel.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
If there is an invalid networks or ip2nets lnet_parse_networks()
gets called with a NULL 'network' string parameter
lnet_parse_networks() needs to sanitize its input string now that
it's being called from multiple places. Instead, check for
a NULL string everytime the function is called, which reduces the
probability of errors with other code modifications.
Signed-off-by: Amir Shehata <amir.shehata@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-5540
Reviewed-on: http://review.whamcloud.com/11626
Reviewed-by: Isaac Huang <he.huang@intel.com>
Reviewed-by: Doug Oucharek <doug.s.oucharek@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This is the fifth patch of a set of patches that enables DLC.
This patch adds the new structures which will be used
in the IOCTL communication. It also added a set of
show operations to show buffers, networks, statistics
and peer information.
Signed-off-by: Amir Shehata <amir.shehata@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-2456
Reviewed-on: http://review.whamcloud.com/8022
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Doug Oucharek <doug.s.oucharek@intel.com>
Reviewed-by: James Simmons <uja.ornl@gmail.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This is the fourth patch of a set of patches that enables DLC.
This patch changes the IOCTL infrastructure in preparation of
adding extra IOCTL communication between user and kernel space.
The changes include:
- adding a common header to be passed to ioctl infra functions
instead of passing an exact structure. This header is meant
to be included in all structures to be passed through that
interface. The IOCTL handler casts this header to a particular
type that it expects
- All sanity testing on the past in structure is performed in the
generic ioctl infrastructure code.
- All ioctl handlers changed to take the header instead of a
particular structure type
Signed-off-by: Amir Shehata <amir.shehata@intel.com>
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-2456
Reviewed-on: http://review.whamcloud.com/8021
Reviewed-by: Doug Oucharek <doug.s.oucharek@intel.com>
Reviewed-by: James Simmons <uja.ornl@gmail.com>
Reviewed-by: John L. Hammond <john.hammond@intel.com>
Reviewed-by: Oleg Drokin <oleg.drokin@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This resolves the merge issues and confusions people were having with
the goldfish drivers due to changes for them showing up in two different
trees.
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
