or by building another module that automatically selects it.
Modify BNX2X config option to 'select ZLIB_INFLATE' like BNX2
and others. This seems to fix it.
Signed-off-by: Lee Schermerhorn [EMAIL PROTECTED]
You are right.
My mistake, Thanks.
Acked-by: Eliezer Tamir [EMAIL PROTECTED
On 01/03/2013 23:24, David Miller wrote:
From: Eliezer Tamir eliezer.ta...@linux.jf.intel.com
Date: Wed, 27 Feb 2013 09:55:49 -0800
This patchset adds the ability for the socket layer code to poll directly
on an Ethernet device's RX queue. This eliminates the cost of the interrupt
and context
On 04/03/2013 09:37, Cong Wang wrote:
On 02/28/2013 01:55 AM, Eliezer Tamir wrote:
Open issues:
1. Find a way to avoid the need to change the sk and skb structs.
One big disadvantage of how we do this right now is that when a device is
removed, it's hard to prevent it from getting polled
On 03/03/2013 20:35, Eric Dumazet wrote:
On Wed, 2013-02-27 at 09:55 -0800, Eliezer Tamir wrote:
index 821c7f4..d1d1016 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -408,6 +408,10 @@ struct sk_buff {
struct sock *sk;
struct net_device
A dumb question: is bypassing tcpdump/netfilters/qdisc etc. what we
always want? Isn't this a security issue?
We are not bypassing any of the regular stack checks/hooks, we call the
normal netif_rx_skb().
correction, netif_receive_skb()
--
To unsubscribe from this list: send the line
On 04/03/2013 16:52, Eric Dumazet wrote:
On Mon, 2013-03-04 at 10:43 +0200, Eliezer Tamir wrote:
One could for example increment the generation id every time the RTNL is
taken. or is this too much?
RTNL is taken for a lot of operations, it would be better to have a
finer grained increment
On 05/03/2013 18:43, Ben Hutchings wrote:
On Wed, 2013-02-27 at 09:55 -0800, Eliezer Tamir wrote:
Should the units really be cycles or, say, microseconds? I assume that
a sysctl setter can do a conversion to cycles so that there's no need to
multiply every time the value is used. (If the CPU
This patchset adds the ability for the socket layer code to poll directly
on an Ethernet device's RX queue. This eliminates the cost of the interrupt
and context switch and with proper tuning allows us to get very close
to the HW latency.
This is a follow up to Jesse Brandeburg's Kernel Plumbers
an example of how one could add support for ndo_ll_poll to TCP.
Signed-off-by: Alexander Duyck alexander.h.du...@intel.com
Signed-off-by: Jesse Brandeburg jesse.brandeb...@intel.com
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
net/ipv4/Kconfig | 11 +++
net/ipv4
-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
drivers/net/ethernet/intel/ixgbe/ixgbe.h | 96 +
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 65 +++--
2 files changed, 152 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/intel
Add additional statistics to the ixgbe driver for ndo_ll_poll
Defined under LL_EXTENDED_STATS
Signed-off-by: Alexander Duyck alexander.h.du...@intel.com
Signed-off-by: Jesse Brandeburg jesse.brandeb...@intel.com
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
drivers/net/ethernet
A module to measure time between two symbols.
For each delta compile with EXTRA_CFLAGS=-DSTAGE=$stage
where stage is from 0 to 20
Signed-off-by: Alexander Duyck alexander.h.du...@intel.com
Signed-off-by: Jesse Brandeburg jesse.brandeb...@intel.com
Signed-off-by: Eliezer Tamir eliezer.ta
-by: Alexander Duyck alexander.h.du...@intel.com
Signed-off-by: Jesse Brandeburg jesse.brandeb...@intel.com
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
include/linux/netdevice.h |3 ++
include/linux/skbuff.h |4 ++
include/net/ll_poll.h | 71
On 27/02/2013 20:47, Tom Herbert wrote:
On Wed, Feb 27, 2013 at 10:13 AM, Stephen Hemminger
step...@networkplumber.org wrote:
Have you looked at netmap? Seems like a cleaner user API for this.
That might be a bit orthogonal to this. I believe the intent it to
allow spin polling from socket
On 27/02/2013 20:41, Eric Dumazet wrote:
On Wed, 2013-02-27 at 09:56 -0800, Eliezer Tamir wrote:
@@ -1458,7 +1459,9 @@ static void ixgbe_rx_skb(struct ixgbe_q_vector *q_vector,
{
struct ixgbe_adapter *adapter = q_vector-adapter;
- if (!(adapter-flags IXGBE_FLAG_IN_NETPOLL
On 27/02/2013 21:58, Rick Jones wrote:
On 02/27/2013 09:55 AM, Eliezer Tamir wrote:
Performance numbers:
Kernel Config C3/6 rx-usecs TCP UDP
3.8rc6 typicaloff adaptive 37k 40k
3.8rc6 typicaloff 0*50k 56k
3.8rc6 optimized off 0*61k 67k
3.8rc6
On 27/02/2013 23:42, Ben Greear wrote:
On 02/27/2013 12:40 PM, Eliezer Tamir wrote:
On 27/02/2013 21:58, Rick Jones wrote:
On 02/27/2013 09:55 AM, Eliezer Tamir wrote:
*rx-usecs=0 is usually not useful in a production environment.
I would think that latency-sensitive folks would be using rx
placeholder.
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
include/net/busy_poll.h |5 -
1 files changed, 0 insertions(+), 5 deletions(-)
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index f18b919..8e2dfc1 100644
--- a/include/net/busy_poll.h
+++ b/include/net
Move the low latency mib counter to the ip section.
Rename it from low latency to busy poll.
Reported-by: Shawn Bohrer sboh...@rgmadvisors.com
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
include/net/busy_poll.h |4 ++--
include/uapi/linux/snmp.h |2 +-
net/ipv4
On 06/08/2013 13:14, Eric Dumazet wrote:
On Tue, 2013-08-06 at 12:52 +0300, Eliezer Tamir wrote:
Move the low latency mib counter to the ip section.
Rename it from low latency to busy poll.
Reported-by: Shawn Bohrer sboh...@rgmadvisors.com
Signed-off-by: Eliezer Tamir eliezer.ta
Rename mib counter from low latency to busy poll
v1 also moved the counter to the ip MIB (suggested by Shawn Bohrer)
Eric Dumazet suggested that the current location is better.
So v2 just renames the counter to fit the new naming convention.
Signed-off-by: Eliezer Tamir eliezer.ta
On 22/08/2013 23:14, David Miller wrote:
From: Eliezer Tamir eliezer.ta...@linux.intel.com
Date: Wed, 21 Aug 2013 13:39:54 +0300
+SK_LL_STATE_MISS_2, /* data came through napi poll twice in a row */
Please rename this to SK_LL_STATE_MISS_MULTI or something like that.
Thanks.
OK
On 22/08/2013 23:11, Eric Wong wrote:
Eliezer Tamir eliezer.ta...@linux.intel.com wrote:
Performance:
using sockperf, Intel X520 NICs,
Supermicro 6026TT-BTF systems with E5-2690 Xeon CPUs
100 UDP sockets avg. latency 5.756 (std-dev 0.510)
1k UDP sockets avg. latency 5.780 (std-dev 0.536
Add a cpu_relaxt to sk_busy_loop.
Julie Cummings reported performance issues when hyperthreading is on.
Arjan van de Ven observed that we should have a cpu_relax() in the
busy poll loop.
Reported-by: Julie Cummings julie.a.cummi...@intel.com
Signed-off-by: Eliezer Tamir eliezer.ta
On 26/08/2013 00:30, Amir Vadai wrote:
I'm on vacation, will test and have some inputs later this week when I be
back.
Hello Amir,
Ping me when you get back and I will send you my latest so you can
play with it.
--
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the
algorithm.
Willem de Brujin: advice on style, where to put things, RCU.
Special thanks for finding bugs in earlier versions: Julie Cummings.
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
fs/eventpoll.c | 131 +
include/linux/poll.h|2
On 21/08/2013 16:53, Eric Dumazet wrote:
On Wed, 2013-08-21 at 13:39 +0300, Eliezer Tamir wrote:
Instead of remembering the napi_id for all the sockets in an epoll,
we only track the first socket we see with any unique napi_id.
The rational for this is that while there may be many thousands
On 10/07/2013 02:06, David Miller wrote:
From: Jonathan Corbet cor...@lwn.net
Date: Tue, 9 Jul 2013 16:25:14 -0600
On Mon, 08 Jul 2013 16:20:34 +0300
Eliezer Tamir eliezer.ta...@linux.intel.com wrote:
Rename POLL_LL to POLL_BUSY_LOOP.
So pardon me if I speak out of turn, but it occurs
On 10/07/2013 07:41, David Miller wrote:
From: Eliezer Tamir eliezer.ta...@linux.intel.com
Date: Wed, 10 Jul 2013 06:29:16 +0300
If the following names changes are acceptable I will try to send out
a patch today.
2. ndo_ll_poll - ndo_busy_poll
- not technically accurate since the ndo
Rename LL_SO to BUSY_POLL_SO
Rename sysctl_net_ll_{read,poll} to sysctl_busy_{read,poll}
Fix up users of these variables.
Fix documentation for sysctl.
a patch for the socket.7 man page will follow separately,
because of limitations of my mail setup.
Signed-off-by: Eliezer Tamir eliezer.ta
Rename the file and correct all the places where it is included.
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c |2
drivers/net/ethernet/intel/ixgbe/ixgbe.h|2
drivers/net/ethernet/mellanox/mlx4/en_netdev.c
Rename ndo_ll_poll to ndo_busy_poll.
Rename sk_mark_ll to sk_mark_napi_id.
Rename skb_mark_ll to skb_mark_napi_id.
Correct all useres of these functions.
Update comments and defines in include/net/busy_poll.h
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
drivers/net/ethernet
Rename LL_SO to BUSY_POLL_SO
Rename sysctl_net_ll_{read,poll} to sysctl_busy_{read,poll}
Fix up users of these variables.
Fix documentation for sysctl.
a patch for the socket.7 man page will follow separately,
because of limitations of my mail setup.
Signed-off-by: Eliezer Tamir eliezer.ta
Rename the file and correct all the places where it is included.
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c |2
drivers/net/ethernet/intel/ixgbe/ixgbe.h|2
drivers/net/ethernet/mellanox/mlx4/en_netdev.c
-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c |2 +-
drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c |2 +-
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c|4 ++--
drivers/net/ethernet/mellanox/mlx4/en_netdev.c |2 +-
drivers
Add description for the SO_BUSY_POLL socket option to the socket(7) manpage.
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
man7/socket.7 | 25 +
1 files changed, 25 insertions(+), 0 deletions(-)
diff --git a/man7/socket.7 b/man7/socket.7
index f2213eb
On 10/07/2013 16:17, Arend van Spriel wrote:
On 07/10/2013 02:13 PM, Eliezer Tamir wrote:
Rename the file and correct all the places where it is included.
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
include/net/busy_poll.h | 183
David,
Here are three patches that complete the rename of lls to busy-poll
1. rename include/net/ll_poll.h to include/net/busy_poll.h
2. Rename ndo_ll_poll to ndo_busy_poll.
Rename sk_mark_ll to sk_mark_napi_id.
Rename skb_mark_ll to skb_mark_napi_id.
Correct all useres of these
Rename ndo_ll_poll to ndo_busy_poll.
Rename sk_mark_ll to sk_mark_napi_id.
Rename skb_mark_ll to skb_mark_napi_id.
Correct all useres of these functions.
Update comments and defines in include/net/busy_poll.h
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
drivers/net/ethernet
Rename the file and correct all the places where it is included.
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c |2
drivers/net/ethernet/intel/ixgbe/ixgbe.h|2
drivers/net/ethernet/mellanox/mlx4/en_netdev.c
Add description for the SO_BUSY_POLL socket option to the socket(7) manpage.
v2
fixed typos reported by Rasmus Villemoes
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
man7/socket.7 | 25 +
1 files changed, 25 insertions(+), 0 deletions(-)
diff --git
Rename LL_SO to BUSY_POLL_SO
Rename sysctl_net_ll_{read,poll} to sysctl_busy_{read,poll}
Fix up users of these variables.
Fix documentation for sysctl.
a patch for the socket.7 man page will follow separately,
because of limitations of my mail setup.
Signed-off-by: Eliezer Tamir eliezer.ta
On 10/07/2013 21:03, Michael Kerrisk wrote:
On 07/10/13 16:18, Eliezer Tamir wrote:
Add description for the SO_BUSY_POLL socket option to the socket(7) manpage.
What's the status of this feature. A quick grep seems to show
that the feature is not yet in mainline. What is the plan?
The basic
On 18/06/2013 13:25, Eric Dumazet wrote:
On Tue, 2013-06-18 at 11:58 +0300, Eliezer Tamir wrote:
@@ -393,6 +394,15 @@ static inline void wait_key_set(poll_table *wait, unsigned
long in,
wait-_key |= POLLOUT_SET;
}
+static inline void wait_key_set_lls(poll_table *wait, bool
On 18/06/2013 13:25, Eric Dumazet wrote:
On Tue, 2013-06-18 at 11:58 +0300, Eliezer Tamir wrote:
@@ -731,7 +755,11 @@ static inline unsigned int do_pollfd(struct pollfd
*pollfd, poll_table *pwait)
mask = DEFAULT_POLLMASK;
if (f.file-f_op
On 18/06/2013 17:35, Eric Dumazet wrote:
On Tue, 2013-06-18 at 16:25 +0300, Eliezer Tamir wrote:
One other thing,
sock_poll() will only ll_poll if the flag was set _and_ the socket has a
none-zero value in sk-sk_ll_usec so you still only poll on sockets
that were enabled for LLS, not on every
On 18/06/2013 17:45, Eliezer Tamir wrote:
On 18/06/2013 17:35, Eric Dumazet wrote:
On Tue, 2013-06-18 at 16:25 +0300, Eliezer Tamir wrote:
One other thing,
sock_poll() will only ll_poll if the flag was set _and_ the socket has a
none-zero value in sk-sk_ll_usec so you still only poll
David,
Here is a rework of the select/poll patch.
One question: do we need in sock_poll() to test that sock-sk is not null?
(Thanks to Willem de Bruijn for pointing this out.)
When select or poll are used on a lot of sockets the sysctl value
needs to be set higher than 50. For 300 sockets a
.
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
Documentation/sysctl/net.txt| 18 --
fs/select.c | 34 +-
include/net/ll_poll.h | 34 ++
include/uapi/asm-generic
-benchmark.
[this patch needs the poll patch to be applied first]
with sockperf doing epoll on 1000 sockets I see an avg latency of 6us
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
fs/eventpoll.c | 39 +--
1 files changed, 33 insertions
On 21/11/2013 15:39, Peter Zijlstra wrote:
On Thu, Nov 21, 2013 at 03:26:17PM +0200, Eliezer Tamir wrote:
We don't override any limit the user has put on the system call.
You are in fact, note how the normal select @endtime argument is only
set up _after_ you're done polling. So
On 22/11/2013 13:30, Peter Zijlstra wrote:
On Fri, Nov 22, 2013 at 08:56:00AM +0200, Eliezer Tamir wrote:
On 21/11/2013 15:39, Peter Zijlstra wrote:
On Thu, Nov 21, 2013 at 03:26:17PM +0200, Eliezer Tamir wrote:
Please use local_clock(), yes its slightly more expensive, but I doubt
you can
On 26/11/2013 17:57, Peter Zijlstra wrote:
Replace sched_clock() usage with local_clock() which has a bounded
drift between CPUs (2 jiffies).
Peter,
I have tested this patch and I see a performance regression of about
1.5%.
Maybe it would be better, rather then testing in the fast path,
On 28/11/2013 19:40, Peter Zijlstra wrote:
On Thu, Nov 28, 2013 at 06:49:00PM +0200, Eliezer Tamir wrote:
I have tested this patch and I see a performance regression of about
1.5%.
Cute, can you qualify your metric? Since this is a poll loop the only
metric that would be interesting
On 20/11/2013 18:04, Peter Zijlstra wrote:
The only valid use of preempt_enable_no_resched() is if the very next
line is schedule() or if we know preemption cannot actually be enabled
by that statement due to known more preempt_count 'refs'.
The reason I used the no resched version is that
On 08/06/2013 00:48, David Miller wrote:
From: Eliezer Tamir eliezer.ta...@linux.intel.com
Date: Wed, 05 Jun 2013 13:34:00 +0300
And here is v9.
Except for typo fixes in comments/description, only 2/7 and 5/7 were changed.
Thanks to everyone for their input.
Since there is some discussion
Adds a napi_id and a hashing mechanism to lookup a napi by id.
This will be used by subsequent patches to implement low latency
Ethernet device polling.
Based on a code sample by Eric Dumazet.
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
include/linux/netdevice.h | 29
David,
I removed the select/poll patch (was 5/7 in v9) from the set.
The rest are the same patches that were in v9.
Please consider applying.
Thanks to everyone for their input.
-Eliezer
Change log:
v10
- removed select/poll support. (we will work on this some more and try again)
v9
- correct
will be added by subsequent patches.
Signed-off-by: Alexander Duyck alexander.h.du...@intel.com
Signed-off-by: Jesse Brandeburg jesse.brandeb...@intel.com
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
Documentation/sysctl/net.txt |7 ++
include/linux/netdevice.h|3
tries to read we busy poll.
Signed-off-by: Alexander Duyck alexander.h.du...@intel.com
Signed-off-by: Jesse Brandeburg jesse.brandeb...@intel.com
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
net/core/datagram.c |4
net/ipv4/udp.c |6 +-
net/ipv6/udp.c
alexander.h.du...@intel.com
Signed-off-by: Jesse Brandeburg jesse.brandeb...@intel.com
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
drivers/net/ethernet/intel/ixgbe/ixgbe.h | 120 +
drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c |2
drivers/net/ethernet
-by: Alexander Duyck alexander.h.du...@intel.com
Signed-off-by: Jesse Brandeburg jesse.brandeb...@intel.com
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
net/ipv4/tcp.c |5 +
net/ipv4/tcp_ipv4.c |2 ++
net/ipv6/tcp_ipv6.c |2 ++
3 files changed, 9 insertions(+), 0
Add additional statistics to the ixgbe driver for ndo_ll_poll
Defined under LL_EXTENDED_STATS
Signed-off-by: Alexander Duyck alexander.h.du...@intel.com
Signed-off-by: Jesse Brandeburg jesse.brandeb...@intel.com
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
drivers/net/ethernet
On 10/06/2013 23:41, David Miller wrote:
From: Eliezer Tamir eliezer.ta...@linux.intel.com
Date: Mon, 10 Jun 2013 11:39:30 +0300
I removed the select/poll patch (was 5/7 in v9) from the set.
The rest are the same patches that were in v9.
Reply to this email with some text to put in the merge
On 11/06/2013 07:24, David Miller wrote:
From: Eliezer Tamir eliezer.ta...@linux.intel.com
Date: Tue, 11 Jun 2013 05:25:42 +0300
Here is the text from the RFC and v2 cover letters, updated and
merged. If this is too long, please tell me what you think should
be removed.
It's perfect
On 11/06/2013 10:32, Eric Dumazet wrote:
On Tue, 2013-06-11 at 09:49 +0300, Eliezer Tamir wrote:
I would like to hear opinions on what needs to be added to make this
feature complete.
The list I have so far is:
1. add a socket option
Yes, please. I do not believe all sockets on the machine
On 11/06/2013 11:14, David Miller wrote:
From: Eliezer Tamir eliezer.ta...@linux.intel.com
Date: Tue, 11 Jun 2013 09:49:31 +0300
I would like to hear opinions on what needs to be added to make this
feature complete.
I actually would like to see the Kconfig option go away, that's
my only
David,
Here are two more patches.
Patch 1 removes the config menu for NET_LL_RX_POLL and defaults to y.
Patch 2 adds an SO_LL socket option to allow per-socket control of busy polling.
The patches do not depend on each other.
If one of them needs more work, please consider applying the other.
Remove NET_LL_RX_POLL from the config menu.
Change default to y.
Busy polling still needs to be enabled at runtime via sysctl.
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
net/Kconfig | 11 ++-
1 files changed, 2 insertions(+), 9 deletions(-)
diff --git a/net
adds a socket option for low latency polling.
This allows overriding the global sysctl value with a per-socket one.
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
arch/alpha/include/uapi/asm/socket.h |2 ++
arch/avr32/include/uapi/asm/socket.h |2 ++
arch/cris
Add lls socket option support to sockperf.
Right now we always get the option before set to show the option is
working properly. We should probably remove that in an official release.
use --lls (value in usecs) to override global setting.
---
src/Defs.h |3 +++
src/SockPerf.cpp |
On 11/06/2013 17:45, Eric Dumazet wrote:
On Tue, 2013-06-11 at 17:24 +0300, Eliezer Tamir wrote:
adds a socket option for low latency polling.
This allows overriding the global sysctl value with a per-socket one.
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
-static inline
On 11/06/2013 23:24, Ben Hutchings wrote:
On Tue, 2013-06-11 at 17:24 +0300, Eliezer Tamir wrote:
adds a socket option for low latency polling.
This allows overriding the global sysctl value with a per-socket one.
[...]
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -913,6 +913,23
On 12/06/2013 11:36, Amir Vadai wrote:
On 11/06/2013 17:26, Eliezer Tamir wrote:
Add lls socket option support to sockperf.
Right now we always get the option before set to show the option is
working properly. We should probably remove that in an official release.
use --lls (value in usecs
adds a socket option for low latency polling.
This allows overriding the global sysctl value with a per-socket one.
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
arch/alpha/include/uapi/asm/socket.h |2 ++
arch/avr32/include/uapi/asm/socket.h |2 ++
arch/cris
There is no reason for sysctl_net_ll_poll to be an unsigned long.
Change it into an unsigned int.
Fix the proc handler.
Add a cast in ll_end_time()
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
include/net/ll_poll.h |5 +++--
net/core/sysctl_net_core.c |4 ++--
net
David,
Here are two clean up patches, plus one that adds a socket option for LLS.
Patch 1 removes the config menu for NET_LL_RX_POLL and defaults to y.
Patch 2 converts sysctl_net_ll_poll into an unsigned int
Patch 3 adds an SO_LL socket option to allow per-socket control of busy polling.
I
Remove NET_LL_RX_POLL from the config menu.
Change default to y.
Busy polling still needs to be enabled at run time.
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
net/Kconfig | 11 ++-
1 files changed, 2 insertions(+), 9 deletions(-)
diff --git a/net/Kconfig b/net
Add lls socket option support.
use --lls (value in usecs) to override global setting.
Right now we always get and print the value of the option before we set,
to show that the option works properly.
This should be removed in an official release.
---
src/Defs.h |3 +++
src/SockPerf.cpp
On 12/06/2013 15:04, Avner Ben Hanoch wrote:
Maybe better, I suggest opening an issue in sockperf issue system -
https://code.google.com/p/sockperf/issues/list
Then anyone can add notes or read/receive them.
Thanks,
I will do that once the review of the Linux patch is complete.
-Eliezer
--
On 12/06/2013 15:44, Eric Dumazet wrote:
On Wed, 2013-06-12 at 14:20 +0300, Eliezer Tamir wrote:
adds a socket option for low latency polling.
This allows overriding the global sysctl value with a per-socket one.
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
It seems
On 12/06/2013 15:54, Eliezer Tamir wrote:
On 12/06/2013 15:44, Eric Dumazet wrote:
On Wed, 2013-06-12 at 14:20 +0300, Eliezer Tamir wrote:
adds a socket option for low latency polling.
This allows overriding the global sysctl value with a per-socket one.
Signed-off-by: Eliezer Tamir
On 13/06/2013 05:01, Stephen Hemminger wrote:
On Wed, 12 Jun 2013 15:12:05 -0700 (PDT)
David Miller da...@davemloft.net wrote:
From: Eliezer Tamir eliezer.ta...@linux.intel.com
Date: Tue, 11 Jun 2013 17:24:28 +0300
depends on X86_TSC
Wait a second, I didn't notice this before
On 13/06/2013 11:00, Daniel Borkmann wrote:
On 06/13/2013 04:13 AM, Eliezer Tamir wrote:
On 13/06/2013 05:01, Stephen Hemminger wrote:
On Wed, 12 Jun 2013 15:12:05 -0700 (PDT)
David Miller da...@davemloft.net wrote:
From: Eliezer Tamir eliezer.ta...@linux.intel.com
Date: Tue, 11 Jun 2013 17
Use sched_clock() instead of get_cycles().
We can use sched_clock() because we don't care much about accuracy.
Remove the dependency on X86_TSC
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
include/net/ll_poll.h | 23 +++
net/Kconfig |1 -
2
David,
Here are three clean up patches, plus one that adds a socket option for LLS.
Patch 1 converts low latency sockets to sched_clock.
Patch 2 removes the config menu for NET_LL_RX_POLL and defaults to y.
Patch 3 converts sysctl_net_ll_poll into an unsigned int
Patch 4 adds an SO_LL socket
Remove NET_LL_RX_POLL from the config menu.
Change default to y.
Busy polling still needs to be enabled at run time.
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
net/Kconfig | 11 ++-
1 files changed, 2 insertions(+), 9 deletions(-)
diff --git a/net/Kconfig b/net
There is no reason for sysctl_net_ll_poll to be an unsigned long.
Change it into an unsigned int.
Fix the proc handler.
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
include/net/ll_poll.h |2 +-
net/core/sysctl_net_core.c |4 ++--
net/socket.c |2
adds a socket option for low latency polling.
This allows overriding the global sysctl value with a per-socket one.
Unexport sysctl_net_ll_poll since for now it's not needed in modules.
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
arch/alpha/include/uapi/asm/socket.h |2
Add lls socket option support to sockperf.
Right now we always get the option before set to show the option is
working properly. We should probably remove that in an official release.
use --lls (value in usecs) to override global setting.
---
src/Defs.h |3 +++
src/SockPerf.cpp |
On 13/06/2013 17:49, Eliezer Tamir wrote:
Add lls socket option support to sockperf.
Right now we always get the option before set to show the option is
working properly. We should probably remove that in an official release.
use --lls (value in usecs) to override global setting.
Sorry
Add lls socket option support.
use --lls (value in usecs) to override global setting.
Right now we always get and print the value of the option before we set,
to show that the option works properly.
This should be removed in an official release.
---
src/Defs.h |3 +++
src/SockPerf.cpp
On 13/06/2013 18:31, Eric Dumazet wrote:
On Thu, 2013-06-13 at 17:46 +0300, Eliezer Tamir wrote:
+extern unsigned int sysctl_net_ll_poll __read_mostly;
Oh well, you re-introduce the overflow
hint : you defined
#define USECS_TO_NS(us) (us 10)
ouch!
(thanks)
--
To unsubscribe from
David,
Here are three clean up patches, plus one that adds a socket option for LLS.
Patch 1 converts sysctl_net_ll_poll into an unsigned int
Patch 2 converts low latency sockets to sched_clock.
Patch 3 removes the config menu for NET_LL_RX_POLL and defaults to y.
Patch 4 adds an SO_LL socket
Remove NET_LL_RX_POLL from the config menu.
Change default to y.
Busy polling still needs to be enabled at run time.
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
net/Kconfig | 11 ++-
1 files changed, 2 insertions(+), 9 deletions(-)
diff --git a/net/Kconfig b/net
There is no reason for sysctl_net_ll_poll to be an unsigned long.
Change it into an unsigned int.
Fix the proc handler.
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
include/net/ll_poll.h |5 +++--
net/core/sysctl_net_core.c |4 ++--
net/socket.c
Use sched_clock() instead of get_cycles().
We can use sched_clock() because we don't care much about accuracy.
Remove the dependency on X86_TSC
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
include/net/ll_poll.h | 32 +---
net/Kconfig
adds a socket option for low latency polling.
This allows overriding the global sysctl value with a per-socket one.
Unexport sysctl_net_ll_poll since for now it's not needed in modules.
Signed-off-by: Eliezer Tamir eliezer.ta...@linux.intel.com
---
arch/alpha/include/uapi/asm/socket.h |2
Add lls socket option support.
use --lls (value in usecs) to override global setting.
Right now we always get and print the value of the option before we set,
to show that the option works properly.
This should be removed in an official release.
---
src/Defs.h |3 +++
src/SockPerf.cpp
On 14/06/2013 06:12, Eric Dumazet wrote:
On Fri, 2013-06-14 at 04:57 +0300, Eliezer Tamir wrote:
Use sched_clock() instead of get_cycles().
We can use sched_clock() because we don't care much about accuracy.
Remove the dependency on X86_TSC
Signed-off-by: Eliezer Tamir eliezer.ta
1 - 100 of 482 matches
Mail list logo
