RDS: convert bind hash table to re-sizable hashtable

To further improve the RDS connection scalabilty on massive systems
where number of sockets grows into tens of thousands of sockets, there
is a

RDS: convert bind hash table to re-sizable hashtable

To further improve the RDS connection scalabilty on massive systems
where number of sockets grows into tens of thousands of sockets, there
is a need of larger bind hashtable. Pre-allocated 8K or 16K table is
not very flexible in terms of memory utilisation. The rhashtable
infrastructure gives us the flexibility to grow the hashtbable based
on use and also comes up with inbuilt efficient bucket(chain) handling.

Reviewed-by: David Miller <davem@davemloft.net>
Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

show more ...

Merge remote-tracking branch 'mac80211-next/master' into next

Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

This merge resolves conflicts with 75aec9df3a78 ("bridge: Remove
br_nf_push_frag_xmit_sk") as part of Eric Biede

Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

This merge resolves conflicts with 75aec9df3a78 ("bridge: Remove
br_nf_push_frag_xmit_sk") as part of Eric Biederman's effort to improve
netns support in the network stack that reached upstream via David's
net-next tree.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

Conflicts:
net/bridge/br_netfilter_hooks.c

show more ...

Merge branch 'x86/urgent' into core/efi, to pick up a pending EFI fix

Signed-off-by: Ingo Molnar <mingo@kernel.org>

RDS: Invoke ->laddr_check() in rds_bind() for explicitly bound transports.

The IP address passed to rds_bind() should be vetted by the
transport's ->laddr_check() for a previously bound transport.
T

RDS: Invoke ->laddr_check() in rds_bind() for explicitly bound transports.

The IP address passed to rds_bind() should be vetted by the
transport's ->laddr_check() for a previously bound transport.
This needs to be done to avoid cases where, for example,
the application has asked for an IB transport,
but the IP address passed to bind is only usable on
ethernet interfaces.

Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

show more ...

Merge remote-tracking branch 'net-next/master' into mac80211-next

Merge net-next to get some driver changes that patches depend
on (in order to avoid conflicts).

Signed-off-by: Johannes Berg <johan

Merge remote-tracking branch 'net-next/master' into mac80211-next

Merge net-next to get some driver changes that patches depend
on (in order to avoid conflicts).

Signed-off-by: Johannes Berg <johannes.berg@intel.com>

show more ...

Merge remote-tracking branch 'asoc/fix/rt5645' into asoc-fix-rt5645

Merge branch 'net/rds/4.3-v3' of git://git.kernel.org/pub/scm/linux/kernel/git/ssantosh/linux

Santosh Shilimkar says:

====================
RDS: connection scalability and performance improvements

Merge branch 'net/rds/4.3-v3' of git://git.kernel.org/pub/scm/linux/kernel/git/ssantosh/linux

Santosh Shilimkar says:

====================
RDS: connection scalability and performance improvements

[v4]
Re-sending the same patches from v3 again since my repost of
patch 05/14 from v3 was whitespace damaged.

[v3]
Updated patch "[PATCH v2 05/14] RDS: defer the over_batch work to
send worker" as per David Miller's comment [4] to avoid the magic
value usage. Patch now makes use of already available but unused
send_batch_count module parameter. Rest of the patches are same as
earlier version v2 [3]

[v2]:
Dropped "[PATCH 05/15] RDS: increase size of hash-table to 8K" from
earlier version [1]. I plan to address the hash table scalability using
re-sizable hash tables as suggested by David Laight and David Miller [2]

This series addresses RDS connection bottlenecks on massive workloads and
improve the RDMA performance almost by 3X. RDS TCP also gets a small gain
of about 12%.

RDS is being used in massive systems with high scalability where several
hundred thousand end points and tens of thousands of local processes
are operating in tens of thousand sockets. Being RC(reliable connection),
socket bind and release happens very often and any inefficiencies in
bind hash look ups hurts the overall system performance. RDS bin hash-table
uses global spin-lock which is the biggest bottleneck. To make matter worst,
it uses rcu inside global lock for hash buckets.
This is being addressed by simply using per bucket rw lock which makes the
locking simple and very efficient. The hash table size is still an issue and
I plan to address it by using re-sizable hash tables as suggested on the list.

For RDS RDMA improvement, the completion handling is revamped so that we
can do batch completions. Both send and receive completion handlers are
split logically to achieve the same. RDS 8K messages being one of the
key usecase, mr pool is adapted to have the 8K mrs along with default 1M
mrs. And while doing this, few fixes and couple of bottlenecks seen with
rds_sendmsg() are addressed.

Series applies against 4.3-rc1 as well net-next. Its tested on Oracle
hardware with IB fabric for both bcopy as well as RDMA mode. RDS TCP is
tested with iXGB NIC. Like last time, iWARP transport is untested with
these changes. The patchset is also available at below git repo:

git://git.kernel.org/pub/scm/linux/kernel/git/ssantosh/linux.git net/rds/4.3-v3

As a side note, the IB HCA driver I used for testing misses at least 3
important patches in upstream to see the full blown IB performance and
am hoping to get that in mainline with help of them.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

show more ...

Merge branch 'for-4.3-rc/ti-clk-fixes' of https://github.com/t-kristo/linux-pm into clk-fixes

Pull fixes from Tero Kristo:

"A few TI clock driver fixes to pull against 4.3-rc"

* 'for-4.3-rc/ti-clk

Merge branch 'for-4.3-rc/ti-clk-fixes' of https://github.com/t-kristo/linux-pm into clk-fixes

Pull fixes from Tero Kristo:

"A few TI clock driver fixes to pull against 4.3-rc"

* 'for-4.3-rc/ti-clk-fixes' of https://github.com/t-kristo/linux-pm: (3 commits)
clk: ti: dflt: fix enable_reg validity check
clk: ti: fix dual-registration of uart4_ick
clk: ti: clk-7xx: Remove hardwired ABE clock configuration

show more ...

RDS: Use per-bucket rw lock for bind hash-table

One global lock protecting hash-tables with 1024 buckets isn't
efficient and it shows up in a massive systems with truck
loads of RDS sockets serving

RDS: Use per-bucket rw lock for bind hash-table

One global lock protecting hash-tables with 1024 buckets isn't
efficient and it shows up in a massive systems with truck
loads of RDS sockets serving multiple databases. The
perf data clearly highlights the contention on the rw
lock in these massive workloads.

When the contention gets worse, the code gets into a state where
it decides to back off on the lock. So while it has disabled interrupts,
it sits and backs off on this lock get. This causes the system to
become sluggish and eventually all sorts of bad things happen.

The simple fix is to move the lock into the hash bucket and
use per-bucket lock to improve the scalability.

Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>

show more ...

RDS: fix rds_sock reference bug while doing bind

One need to take rds socket reference while using it and release it
once done with it. rds_add_bind() code path does not do that so
lets fix it.

Sig

RDS: fix rds_sock reference bug while doing bind

One need to take rds socket reference while using it and release it
once done with it. rds_add_bind() code path does not do that so
lets fix it.

Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>

show more ...

RDS: make socket bind/release locking scheme simple and more efficient

RDS bind and release locking scheme is very inefficient. It
uses RCU for maintaining the bind hash-table which is great but
it

RDS: make socket bind/release locking scheme simple and more efficient

RDS bind and release locking scheme is very inefficient. It
uses RCU for maintaining the bind hash-table which is great but
it also needs to hold spinlock for [add/remove]_bound(). So
overall usecase, the hash-table concurrent speedup doesn't pay off.
In fact blocking nature of synchronize_rcu() makes the RDS
socket shutdown too slow which hurts RDS performance since
connection shutdown and re-connect happens quite often to
maintain the RC part of the protocol.

So we make the locking scheme simpler and more efficient by
replacing spin_locks with reader/writer locks and getting rid
off rcu for bind hash-table.

In subsequent patch, we also covert the global lock with per-bucket
lock to reduce the global lock contention.

Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>

show more ...

Merge remote-tracking branch 'airlied/drm-next' into drm-intel-next

Backmerge to catch up with 4.3. slightly more involved conflict in the
irq code, but nothing beyond adjacent changes.

Signed-off-

Merge remote-tracking branch 'airlied/drm-next' into drm-intel-next

Backmerge to catch up with 4.3. slightly more involved conflict in the
irq code, but nothing beyond adjacent changes.

Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>

show more ...

Merge tag 'v4.3-rc3' into next

Merge with Linux 4.3-rc3 to bring in MFD DA9062 changes to merge DA9062
OnKey driver.

Merge tag 'v4.3-rc2' into k.o/for-4.3-v1

Linux 4.3-rc2

Merge tag 'v4.3-rc2' into topic/drm-misc

Backmerge Linux 4.3-rc2 because of conflicts in the dp helper code
between bugfixes and new code. Just adjacent lines really.

On top of that there's a silen

Merge tag 'v4.3-rc2' into topic/drm-misc

Backmerge Linux 4.3-rc2 because of conflicts in the dp helper code
between bugfixes and new code. Just adjacent lines really.

On top of that there's a silent conflict in the new fsl-dcu driver
merged into 4.3 and

commit 844f9111f6f54f88eb2f0fac121b82ce77193866
Author: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Date: Wed Sep 2 10:42:40 2015 +0200

drm/atomic: Make prepare_fb/cleanup_fb only take state, v3.

which Thierry Reding spotted and provided a fixup for.

Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>

show more ...

Merge branch 'for-linus' into for-next

Merge tag 'v4.3-rc1' into spi-fix-doc

Linux 4.3-rc1

Merge branch 'fixes-rc1' into omap-for-v4.3/fixes

Merge tag 'v4.3-rc1' into MTD -next development

Merge tag 'v4.3-rc1' into patchwork

Linux 4.3-rc1

* tag 'v4.3-rc1': (11838 commits)
Linux 4.3-rc1
blk: rq_data_dir() should not return a boolean
writeback: plug writeback in wb_writeback() an

Merge tag 'v4.3-rc1' into patchwork

Linux 4.3-rc1

* tag 'v4.3-rc1': (11838 commits)
Linux 4.3-rc1
blk: rq_data_dir() should not return a boolean
writeback: plug writeback in wb_writeback() and writeback_inodes_wb()
thermal: fix intel PCH thermal driver mismerge
ARCv2: [axs103_smp] Reduce clk for SMP FPGA configs
revert "ocfs2/dlm: use list_for_each_entry instead of list_for_each"
mm/early_ioremap: add explicit #include of asm/early_ioremap.h
fs/seq_file: convert int seq_vprint/seq_printf/etc... returns to void
selftests: enhance membarrier syscall test
selftests: add membarrier syscall test
sys_membarrier(): system-wide memory barrier (generic, x86)
MODSIGN: fix a compilation warning in extract-cert
Revert "writeback: plug writeback at a high level"
scsi_dh: fix randconfig build error
target: use stringify.h instead of own definition
target/user: Fix UFLAG_UNKNOWN_OP handling
target: Remove no-op conditional
target/user: Remove unused variable
target: Fix max_cmd_sn increment w/o cmdsn mutex regressions
target: Attach EXTENDED_COPY local I/O descriptors to xcopy_pt_sess
...

show more ...

Merge tag 'v4.3-rc1' into perf/core, to refresh the tree

Signed-off-by: Ingo Molnar <mingo@kernel.org>

Merge tag 'v4.3-rc1' into locking/core, to refresh the tree

Signed-off-by: Ingo Molnar <mingo@kernel.org>

Merge tag 'v4.3-rc1' into sched/core, to refresh the branch

Signed-off-by: Ingo Molnar <mingo@kernel.org>

Merge branch 'next' into for-linus

Prepare first round of input updates for 4.3 merge window.