* [NET_SCHED 01/04]: Constify struct tcf_ext_map
From: Patrick McHardy @ 2008-01-31 17:58 UTC (permalink / raw)
To: davem; +Cc: netdev, shemminger, Patrick McHardy
In-Reply-To: <20080131175758.25151.20370.sendpatchset@localhost.localdomain>
[NET_SCHED]: Constify struct tcf_ext_map
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
commit 12e33ddf57910b685501df10bd92223ea9b98fd6
tree 1ce47c7b6b6b968940f3dc28f9d7839e78c85089
parent 8af03e782cae1e0a0f530ddd22301cdd12cf9dc0
author Patrick McHardy <kaber@trash.net> Wed, 30 Jan 2008 21:59:26 +0100
committer Patrick McHardy <kaber@trash.net> Thu, 31 Jan 2008 18:52:55 +0100
include/net/pkt_cls.h | 6 +++---
net/sched/cls_api.c | 6 +++---
net/sched/cls_basic.c | 2 +-
net/sched/cls_fw.c | 2 +-
net/sched/cls_route.c | 2 +-
net/sched/cls_tcindex.c | 2 +-
net/sched/cls_u32.c | 2 +-
7 files changed, 11 insertions(+), 11 deletions(-)
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 8716eb7..d349c66 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -131,14 +131,14 @@ tcf_exts_exec(struct sk_buff *skb, struct tcf_exts *exts,
extern int tcf_exts_validate(struct tcf_proto *tp, struct nlattr **tb,
struct nlattr *rate_tlv, struct tcf_exts *exts,
- struct tcf_ext_map *map);
+ const struct tcf_ext_map *map);
extern void tcf_exts_destroy(struct tcf_proto *tp, struct tcf_exts *exts);
extern void tcf_exts_change(struct tcf_proto *tp, struct tcf_exts *dst,
struct tcf_exts *src);
extern int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts,
- struct tcf_ext_map *map);
+ const struct tcf_ext_map *map);
extern int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts,
- struct tcf_ext_map *map);
+ const struct tcf_ext_map *map);
/**
* struct tcf_pkt_info - packet information
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 3377ca0..0fbedca 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -482,7 +482,7 @@ EXPORT_SYMBOL(tcf_exts_destroy);
int tcf_exts_validate(struct tcf_proto *tp, struct nlattr **tb,
struct nlattr *rate_tlv, struct tcf_exts *exts,
- struct tcf_ext_map *map)
+ const struct tcf_ext_map *map)
{
memset(exts, 0, sizeof(*exts));
@@ -535,7 +535,7 @@ void tcf_exts_change(struct tcf_proto *tp, struct tcf_exts *dst,
EXPORT_SYMBOL(tcf_exts_change);
int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts,
- struct tcf_ext_map *map)
+ const struct tcf_ext_map *map)
{
#ifdef CONFIG_NET_CLS_ACT
if (map->action && exts->action) {
@@ -571,7 +571,7 @@ EXPORT_SYMBOL(tcf_exts_dump);
int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts,
- struct tcf_ext_map *map)
+ const struct tcf_ext_map *map)
{
#ifdef CONFIG_NET_CLS_ACT
if (exts->action)
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index bfb4342..956915c 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -35,7 +35,7 @@ struct basic_filter
struct list_head link;
};
-static struct tcf_ext_map basic_ext_map = {
+static const struct tcf_ext_map basic_ext_map = {
.action = TCA_BASIC_ACT,
.police = TCA_BASIC_POLICE
};
diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index 436a6e7..b0f90e5 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -47,7 +47,7 @@ struct fw_filter
struct tcf_exts exts;
};
-static struct tcf_ext_map fw_ext_map = {
+static const struct tcf_ext_map fw_ext_map = {
.action = TCA_FW_ACT,
.police = TCA_FW_POLICE
};
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index f7e7d39..784dcb8 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -62,7 +62,7 @@ struct route4_filter
#define ROUTE4_FAILURE ((struct route4_filter*)(-1L))
-static struct tcf_ext_map route_ext_map = {
+static const struct tcf_ext_map route_ext_map = {
.police = TCA_ROUTE4_POLICE,
.action = TCA_ROUTE4_ACT
};
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index ee60b2d..7a7bff5 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -55,7 +55,7 @@ struct tcindex_data {
int fall_through; /* 0: only classify if explicit match */
};
-static struct tcf_ext_map tcindex_ext_map = {
+static const struct tcf_ext_map tcindex_ext_map = {
.police = TCA_TCINDEX_POLICE,
.action = TCA_TCINDEX_ACT
};
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index e8a7756..b18fa95 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -82,7 +82,7 @@ struct tc_u_common
u32 hgenerator;
};
-static struct tcf_ext_map u32_ext_map = {
+static const struct tcf_ext_map u32_ext_map = {
.action = TCA_U32_ACT,
.police = TCA_U32_POLICE
};
^ permalink raw reply related
* [NET_SCHED 00/04]: External SFQ classifiers/flow classifier
From: Patrick McHardy @ 2008-01-31 17:58 UTC (permalink / raw)
To: davem; +Cc: netdev, shemminger, Patrick McHardy
These patches add support for external classifiers to SFQ and add a
new "flow" classifier, which can do hashing based on user-specified
keys or deterministic mapping of keys to classes. Additionally there
is a patch to make the SFQ queues visisble as classes to verify that
the hash is indeed doing something useful and a patch to consifiy
struct tcf_ext_map, which I had queued in the same tree.
Please apply, thanks.
include/linux/pkt_cls.h | 50 ++++
include/linux/pkt_sched.h | 5 +
include/net/pkt_cls.h | 6 +-
net/sched/Kconfig | 11 +
net/sched/Makefile | 1 +
net/sched/cls_api.c | 6 +-
net/sched/cls_basic.c | 2 +-
net/sched/cls_flow.c | 660 +++++++++++++++++++++++++++++++++++++++++++++
net/sched/cls_fw.c | 2 +-
net/sched/cls_route.c | 2 +-
net/sched/cls_tcindex.c | 2 +-
net/sched/cls_u32.c | 2 +-
net/sched/sch_sfq.c | 134 +++++++++-
13 files changed, 868 insertions(+), 15 deletions(-)
create mode 100644 net/sched/cls_flow.c
Patrick McHardy (4):
[NET_SCHED]: Constify struct tcf_ext_map
[NET_SCHED]: sch_sfq: add support for external classifiers
[NET_SCHED]: sch_sfq: make internal queues visible as classes
[NET_SCHED]: Add flow classifier
^ permalink raw reply
* Re: e1000 full-duplex TCP performance well below wire speed
From: Rick Jones @ 2008-01-31 17:55 UTC (permalink / raw)
To: Carsten Aulbert
Cc: Brandeburg, Jesse, Bruce Allen, netdev, Henning Fehrmann,
Bruce Allen
In-Reply-To: <47A1B294.8080609@aei.mpg.de>
> netperf was used without any special tuning parameters. Usually we start
> two processes on two hosts which start (almost) simultaneously, last for
> 20-60 seconds and simply use UDP_STREAM (works well) and TCP_STREAM, i.e.
>
> on 192.168.0.202: netperf -H 192.168.2.203 -t TCP_STREAL -l 20
> on 192.168.0.203: netperf -H 192.168.2.202 -t TCP_STREAL -l 20
>
> 192.168.0.20[23] here is on eth0 which cannot do jumbo frames, thus we
> use the .2. part for eth1 for a range of mtus.
>
> The server is started on both nodes with the start-stop-daemon and no
> special parameters I'm aware of.
So long as you are relying on external (netperf relative) means to
report the throughput, those command lines would be fine. I wouldn't be
comfortably relying on the sum of the netperf-reported throughtputs with
those comand lines though. Netperf2 has no test synchronization, so two
separate commands, particularly those initiated on different systems,
are subject to skew errors. 99 times out of ten they might be epsilon,
but I get a _little_ paranoid there.
There are three alternatives:
1) use netperf4. not as convenient for "quick" testing at present, but
it has explicit test synchronization, so you "know" that the numbers
presented are from when all connections were actively transferring data
2) use the aforementioned "burst" TCP_RR test. This is then a single
netperf with data flowing both ways on a single connection so no issue
of skew, but perhaps an issue of being one connection and so one process
on each end.
3) start both tests from the same system and follow the suggestions
contained in :
<http://www.netperf.org/svn/netperf2/tags/netperf-2.4.4/doc/netperf.html>
particluarly:
<http://www.netperf.org/svn/netperf2/tags/netperf-2.4.4/doc/netperf.html#Using-Netperf-to-Measure-Aggregate-Performance>
and use a combination of TCP_STREAM and TCP_MAERTS (STREAM backwards) tests.
happy benchmarking,
rick jones
^ permalink raw reply
* Re: [PATCH 0/6] preparations to enable netdevice notifiers inside a namespace (resend)
From: Daniel Lezcano @ 2008-01-31 17:46 UTC (permalink / raw)
To: Benjamin Thery; +Cc: Denis V. Lunev, Linux Containers, netdev
In-Reply-To: <939d53060801310847y31c4542do271edd48e44745c7@mail.gmail.com>
Benjamin Thery wrote:
> On Jan 31, 2008 3:58 PM, Daniel Lezcano <daniel.lezcano@free.fr> wrote:
>
>> Denis V. Lunev wrote:
>>> Here are some preparations and cleanups to enable network device/inet
>>> address notifiers inside a namespace.
>>>
>>> This set of patches has been originally sent last Friday. One cleanup
>>> patch from the original series is dropped as wrong, thanks to Daniel
>>> Lezcano.
>> Can you explain please.
>
>
> I think Denis refers to the patch called "3/7 Prohibit assignment of
> 0.0.0.0as interface address." ,
> he dropped because it was inappropriate, no?
Yes, you are right, Denis explained me in a private email. I think I
really need to sleep a little more :)
^ permalink raw reply
* RE: e1000 full-duplex TCP performance well below wire speed
From: Brandeburg, Jesse @ 2008-01-31 17:33 UTC (permalink / raw)
To: Carsten Aulbert; +Cc: Bruce Allen, netdev, Henning Fehrmann, Bruce Allen
In-Reply-To: <47A204E5.7060406@aei.mpg.de>
Carsten Aulbert wrote:
> PS: Am I right that the TCP_RR tests should only be run on a single
> node at a time, not on both ends simultaneously?
yes, they are a request/response test, and so perform the bidirectional
test with a single node starting the test.
^ permalink raw reply
* Re: e1000 full-duplex TCP performance well below wire speed
From: Bill Fink @ 2008-01-31 17:36 UTC (permalink / raw)
To: Bruce Allen
Cc: SANGTAE HA, Linux Kernel Mailing List, netdev, Stephen Hemminger
In-Reply-To: <Pine.LNX.4.63.0801310951060.10967@trinity.phys.uwm.edu>
Hi Bruce,
On Thu, 31 Jan 2008, Bruce Allen wrote:
> > I see similar results on my test systems
>
> Thanks for this report and for confirming our observations. Could you
> please confirm that a single-port bidrectional UDP link runs at wire
> speed? This helps to localize the problem to the TCP stack or interaction
> of the TCP stack with the e1000 driver and hardware.
Yes, a single-port bidirectional UDP test gets full GigE line rate
in both directions with no packet loss.
[bill@chance4 ~]$ nuttcp -f-beta -Itx -u -Ru -w2m 192.168.6.79 & nuttcp -f-beta -Irx -r -u -Ru -w2m 192.168.6.79
tx: 1187.0078 MB / 10.04 sec = 992.0550 Mbps 19 %TX 7 %RX 0 / 151937 drop/pkt 0.00 %loss
rx: 1187.1016 MB / 10.03 sec = 992.3408 Mbps 19 %TX 7 %RX 0 / 151949 drop/pkt 0.00 %loss
-Bill
^ permalink raw reply
* Re: e1000 full-duplex TCP performance well below wire speed
From: Carsten Aulbert @ 2008-01-31 17:27 UTC (permalink / raw)
To: Brandeburg, Jesse; +Cc: Bruce Allen, netdev, Henning Fehrmann, Bruce Allen
In-Reply-To: <36D9DB17C6DE9E40B059440DB8D95F52044F8EC9@orsmsx418.amr.corp.intel.com>
Hi all,
Brandeburg, Jesse wrote:
>>> I would suggest you try TCP_RR with a command line something like
>>> this: netperf -t TCP_RR -H <hostname> -C -c -- -b 4 -r 64K
>> I did that and the results can be found here:
>> https://n0.aei.uni-hannover.de/wiki/index.php/NetworkTest
>
> seems something went wrong and all you ran was the 1 byte tests, where
> it should have been 64K both directions (request/response).
>
Yes, shell-quoting got me there. I'll re-run the tests, so please don't
look at the TCP_RR results too closely. I think I'll be able to run
maybe one or two more tests today, rest will follow tomorrow.
Thanks for bearing with me
Carsten
PS: Am I right that the TCP_RR tests should only be run on a single node
at a time, not on both ends simultaneously?
^ permalink raw reply
* Re: [PATCH] Disable TSO for non standard qdiscs
From: Stephen Hemminger @ 2008-01-31 17:23 UTC (permalink / raw)
To: Andi Kleen; +Cc: netdev
In-Reply-To: <20080131124632.GA25299@basil.nowhere.org>
On Thu, 31 Jan 2008 13:46:32 +0100
Andi Kleen <andi@firstfloor.org> wrote:
>
> TSO interacts badly with many queueing disciplines because they rely on
> reordering packets from different streams and the large TSO packets can
> make this difficult. This patch disables TSO for sockets that send over
> devices with non standard queueing disciplines. That's anything but noop
> or pfifo_fast and pfifo right now.
>
> Longer term other queueing disciplines could be checked if they
> are also ok with TSO. If yes they can set the TCQ_F_GSO_OK flag too.
>
> It is still enabled for the standard pfifo_fast because that will never
> reorder packets with the same type-of-service. This means 99+% of all users
> will still be able to use TSO just fine.
>
> The status is only set up at socket creation so a shifted route
> will not reenable TSO on a existing socket. I don't think that's a
> problem though.
>
> Signed-off-by: Andi Kleen <ak@suse.de>
>
Fix the broken qdisc instead.
--
Stephen Hemminger <stephen.hemminger@vyatta.com>
^ permalink raw reply
* RE: e1000 full-duplex TCP performance well below wire speed
From: Brandeburg, Jesse @ 2008-01-31 17:20 UTC (permalink / raw)
To: Carsten Aulbert; +Cc: Bruce Allen, netdev, Henning Fehrmann, Bruce Allen
In-Reply-To: <47A1E553.8010006@aei.mpg.de>
Carsten Aulbert wrote:
> We are using MSI, /proc/interrupts look like:
> n0003:~# cat /proc/interrupts
> 378: 17234866 0 0 0 PCI-MSI-edge
> eth1
> 379: 129826 0 0 0 PCI-MSI-edge
> eth0
> (sorry for the line break).
>
> What we don't understand is why only core0 gets the interrupts, since
> the affinity is set to f:
> # cat /proc/irq/378/smp_affinity
> f
without CONFIG_IRQBALANCE set, and no irqbalance daemon running, this is
expected. Seems it is also dependent upon your system hardware.
> Right now, irqbalance is not running, though I can give it shot if
> people think this will make a difference.
probably won't make much of a difference if you only have a single
interrupt source generating interrupts. If you are using both adapters
simultaneously, please use smp_affinity or turn on irqbalance.
>> I would suggest you try TCP_RR with a command line something like
>> this: netperf -t TCP_RR -H <hostname> -C -c -- -b 4 -r 64K
>
> I did that and the results can be found here:
> https://n0.aei.uni-hannover.de/wiki/index.php/NetworkTest
seems something went wrong and all you ran was the 1 byte tests, where
it should have been 64K both directions (request/response).
> The results with netperf running like
> netperf -t TCP_STREAM -H <host> -l 20
> can be found here:
> https://n0.aei.uni-hannover.de/wiki/index.php/NetworkTestNetperf1
> I reran the tests with
> netperf -t <test> -H <host> -l 20 -c -C
> or in the case of TCP_RR with the suggested burst settings -b 4 -r 64k
I get:
TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to foo
(134.134.3.121) port 0 AF_INET : first burst 4
Local /Remote
Socket Size Request Resp. Elapsed Trans. CPU CPU S.dem
S.dem
Send Recv Size Size Time Rate local remote local
remote
bytes bytes bytes bytes secs. per sec % S % S us/Tr
us/Tr
16384 87380 65536 65536 10.00 1565.34 14.17 27.18 362.220
347.243
16384 87380
>> Yes, InterruptThrottleRate=8000 means there will be no more than 8000
>> ints/second from that adapter, and if interrupts are generated faster
>> than that they are "aggregated."
>>
>> Interestingly since you are interested in ultra low latency, and may
>> be willing to give up some cpu for it during bulk transfers you
>> should try InterruptThrottleRate=1 (can generate up to 70000 ints/s)
>>
>
> On the web page you'll see that there are about 4000 interrupts/s for
> most tests and up to 20,000/s for the TCP_RR test. Shall I change the
> throttle rate?
that's the auto-tuning, I suggest just InterruptThrottleRate=4000 or
8000 if all you're concerned about is bulk traffic performance.
>>>> just for completeness can you post the dump of ethtool -e eth0 and
>>>> lspci -vvv?
>>> Yup, we'll give that info also.
>
> n0002:~# ethtool -e eth1
> Offset Values
> ------ ------
> 0x0000 00 30 48 93 94 2d 20 0d 46 f7 57 00 ff ff ff ff
> 0x0010 ff ff ff ff 6b 02 9a 10 d9 15 9a 10 86 80 df 80
> 0x0020 00 00 00 20 54 7e 00 00 00 10 da 00 04 00 00 27
> 0x0030 c9 6c 50 31 32 07 0b 04 84 29 00 00 00 c0 06 07
> 0x0040 08 10 00 00 04 0f ff 7f 01 4d ff ff ff ff ff ff
> 0x0050 14 00 1d 00 14 00 1d 00 af aa 1e 00 00 00 1d 00
> 0x0060 00 01 00 40 1e 12 ff ff ff ff ff ff ff ff ff ff
> 0x0070 ff ff ff ff ff ff ff ff ff ff ff ff ff ff cf 2f
this looks fine.
> lspci -vvv for this card:
> 0e:00.0 Ethernet controller: Intel Corporation 82573L Gigabit Ethernet
> Controller
> Subsystem: Super Micro Computer Inc Unknown device 109a
> Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop-
> ParErr- Stepping- SERR+ FastB2B-
> Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast
> >TAbort- <TAbort- <MAbort- >SERR- <PERR-
> Latency: 0, Cache Line Size: 64 bytes
> Interrupt: pin A routed to IRQ 378
> Region 0: Memory at ee200000 (32-bit, non-prefetchable)
> [size=128K] Region 2: I/O ports at 5000 [size=32]
> Capabilities: [c8] Power Management version 2
> Flags: PMEClk- DSI+ D1- D2- AuxCurrent=0mA
> PME(D0+,D1-,D2-,D3hot+,D3cold+)
> Status: D0 PME-Enable- DSel=0 DScale=1 PME-
> Capabilities: [d0] Message Signalled Interrupts: Mask- 64bit+
> Queue=0/0 Enable+
> Address: 00000000fee0f00c Data: 41b9
> Capabilities: [e0] Express Endpoint IRQ 0
> Device: Supported: MaxPayload 256 bytes, PhantFunc 0,
> ExtTag-
> Device: Latency L0s <512ns, L1 <64us
> Device: AtnBtn- AtnInd- PwrInd-
> Device: Errors: Correctable- Non-Fatal- Fatal-
> Unsupported- Device: RlxdOrd+ ExtTag- PhantFunc-
> AuxPwr- NoSnoop+ Device: MaxPayload 128 bytes,
> MaxReadReq 512 bytes Link: Supported Speed 2.5Gb/s,
> Width x1, ASPM unknown,
> Port 0
> Link: Latency L0s <128ns, L1 <64us
> Link: ASPM Disabled RCB 64 bytes CommClk- ExtSynch-
> Link: Speed 2.5Gb/s, Width x1
> Capabilities: [100] Advanced Error Reporting
> Capabilities: [140] Device Serial Number
> 2d-94-93-ff-ff-48-30-00
this also looks good, no APSM, MSI enabled,
^ permalink raw reply
* [PATCH 1/1]: Add support for aes-ctr to ipsec
From: Joy Latten @ 2008-01-31 16:59 UTC (permalink / raw)
To: netdev; +Cc: davem, herbert
Very sorry, re-posting as first patch was incomplete.
The below patch allows IPsec to use CTR mode with
AES encryption algorithm. Tested this using setkey
in ipsec-tools.
regards,
Joy
Signed-off-by: Joy Latten <latten@austin.ibm.com>
--
diff -urpN net-2.6.25/include/linux/pfkeyv2.h net-2.6.25.patch/include/linux/pfkeyv2.h
--- net-2.6.25/include/linux/pfkeyv2.h 2008-01-29 11:48:00.000000000 -0600
+++ net-2.6.25.patch/include/linux/pfkeyv2.h 2008-01-29 13:43:59.000000000 -0600
@@ -298,6 +298,7 @@ struct sadb_x_sec_ctx {
#define SADB_X_EALG_BLOWFISHCBC 7
#define SADB_EALG_NULL 11
#define SADB_X_EALG_AESCBC 12
+#define SADB_X_EALG_AESCTR 13
#define SADB_X_EALG_CAMELLIACBC 22
#define SADB_EALG_MAX 253 /* last EALG */
/* private allocations should use 249-255 (RFC2407) */
diff -urpN net-2.6.25/net/xfrm/xfrm_algo.c net-2.6.25.patch/net/xfrm/xfrm_algo.c
--- net-2.6.25/net/xfrm/xfrm_algo.c 2008-01-29 11:48:03.000000000 -0600
+++ net-2.6.25.patch/net/xfrm/xfrm_algo.c 2008-01-29 13:42:43.000000000 -0600
@@ -300,6 +300,23 @@ static struct xfrm_algo_desc ealg_list[]
.sadb_alg_maxbits = 256
}
},
+{
+ .name = "rfc3686(ctr(aes))",
+
+ .uinfo = {
+ .encr = {
+ .blockbits = 128,
+ .defkeybits = 160, /* 128-bit key + 32-bit nonce */
+ }
+ },
+
+ .desc = {
+ .sadb_alg_id = SADB_X_EALG_AESCTR,
+ .sadb_alg_ivlen = 8,
+ .sadb_alg_minbits = 128,
+ .sadb_alg_maxbits = 256
+ }
+},
};
static struct xfrm_algo_desc calg_list[] = {
^ permalink raw reply
* Re: [PATCH] [1/1] Deprecate tcp_tw_{reuse,recycle}
From: Andi Kleen @ 2008-01-31 16:49 UTC (permalink / raw)
To: Ben Greear; +Cc: Andi Kleen, netdev
In-Reply-To: <47A1FA42.4070503@candelatech.com>
On Thu, Jan 31, 2008 at 08:41:38AM -0800, Ben Greear wrote:
> I don't know exactly how the tcp_tw_recycle works, but it seems like it
> could be made to only
> take affect when all local ports are used up in TIME_WAIT.
TIME-WAIT does not actually use up local ports; it uses up remote ports
because it is done on the LISTEN socket which has always a fixed
local port. And it has no idea how many ports the other end has left.
-Andi
^ permalink raw reply
* Re: [PATCH 0/6] preparations to enable netdevice notifiers inside a namespace (resend)
From: Benjamin Thery @ 2008-01-31 16:47 UTC (permalink / raw)
To: Daniel Lezcano; +Cc: Linux Containers, netdev, David Miller, Denis V. Lunev
In-Reply-To: <47A1E21C.40909-GANU6spQydw@public.gmane.org>
On Jan 31, 2008 3:58 PM, Daniel Lezcano <daniel.lezcano-GANU6spQydw@public.gmane.org> wrote:
> Denis V. Lunev wrote:
> > Here are some preparations and cleanups to enable network device/inet
> > address notifiers inside a namespace.
> >
> > This set of patches has been originally sent last Friday. One cleanup
> > patch from the original series is dropped as wrong, thanks to Daniel
> > Lezcano.
>
> Can you explain please.
I think Denis refers to the patch called "3/7 Prohibit assignment of
0.0.0.0as interface address." ,
he dropped because it was inappropriate, no?
-- Benjamin
--
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
^ permalink raw reply
* Re: [PATCH] [1/1] Deprecate tcp_tw_{reuse,recycle}
From: Ben Greear @ 2008-01-31 16:41 UTC (permalink / raw)
To: Andi Kleen; +Cc: netdev
In-Reply-To: <200801310755.02110.ak@suse.de>
Andi Kleen wrote:
>> I believe the problem was that all of my ports were used up with
>> TIME_WAIT sockets and so it couldn't create more. My test
>> case was similar to this:
>>
>
> Ah that's simple to solve then :- use more IP addresses and bind
> to them in RR in your user program.
>
> Arguably the Linux TCP code should be able to do this by itself
> when enough IP addresses are available, but it's not very hard
> to do in user space using bind(2)
>
> BTW it's also an very unusual case -- in most cases there are more
> remote IP addresses
>
This could be done, but it does decrease our options for testing certain
scenarios.
>> So, is there a better way to max out the connections per second without
>> having to use tcp_tw_recycle?
>>
>
> Well did you profile where the bottle necks were?
>
> Perhaps also just increase the memory allowed for TCP sockets.
>
I may be missing something, but I believe the issue is that the sockets
wait around a while (maybe 30 seconds
or so) in TIME_WAIT state. So, even if we use all 64k of the local port
range, that will limit us to about 2000 new sockets
per second, as we have to wait for old ones to transition out of TIME_WAIT.
I guess I could probably decrease TIME_WAIT, but then all of my
connections would be affected, not just the
ones on the ports creating very large numbers of connections per
second. From 'man tcp', it does not seem
I can set the TIME_WAIT on a per-socket basis.
I don't know exactly how the tcp_tw_recycle works, but it seems like it
could be made to only
take affect when all local ports are used up in TIME_WAIT. It could
then recycle the oldest one
as a new socket is requested. For any normal program, it would be very
unlikely to ever need to
recycle in this case because there would be enough free IP/port pairs
available. But, for weird things
like my own, at least it could be made to work w/out hacking the global
TIME_WAIT.
Thanks,
Ben
--
Ben Greear <greearb@candelatech.com>
Candela Technologies Inc http://www.candelatech.com
^ permalink raw reply
* Re: e1000 full-duplex TCP performance well below wire speed
From: Carsten Aulbert @ 2008-01-31 16:09 UTC (permalink / raw)
To: Andi Kleen
Cc: Bruce Allen, Brandeburg, Jesse, netdev, Henning Fehrmann,
Bruce Allen
In-Reply-To: <p738x265p7p.fsf@bingen.suse.de>
Hi Andi,
Andi Kleen wrote:
> Another issue with full duplex TCP not mentioned yet is that if TSO is used
> the output will be somewhat bursty and might cause problems with the
> TCP ACK clock of the other direction because the ACKs would need
> to squeeze in between full TSO bursts.
>
> You could try disabling TSO with ethtool.
I just tried that:
https://n0.aei.uni-hannover.de/wiki/index.php/NetworkTestNetperf3
It seems that the numbers do get better (sweet-spot seems to be MTU6000
with 914 MBit/s and 927 MBit/s), however for other settings the results
vary a lot so I'm not sure how large the statistical fluctuations are.
Next test I'll try if it makes sense to enlarge the ring buffers.
Thanks
Carsten
^ permalink raw reply
* Re: rtl8150: use default MTU of 1500
From: Lennert Buytenhek @ 2008-01-31 16:05 UTC (permalink / raw)
To: Petko Manolov; +Cc: netdev, jgarzik
In-Reply-To: <alpine.DEB.1.00.0801311741400.4476@bender.nucleusys.com>
On Thu, Jan 31, 2008 at 05:42:34PM +0200, Petko Manolov wrote:
> > The RTL8150 driver uses an MTU of 1540 by default, which causes a
> > bunch of problems -- it prevents booting from NFS root, for one.
>
> Agreed, although it is a bit strange how this particular bug has
> sneaked up for so long...
I posted this patch sometime in 2006, and you asked me a question
about it then (why we don't just set RTL8150_MTU to 1500 -- the
answer would be that RTL8150_MTU is used in a couple more places
in the driver, including for allocing skbuffs), but I failed to
follow up to that question at the time, which is why I assume it got
dropped.
I have been carrying the patch in my own tree since then, and only
noticed recently that the patch never made it upstream.
cheers,
Lennert
> >Signed-off-by: Lennert Buytenhek <buytenh@wantstofly.org>
> >Cc: Petko Manolov <petkan@nucleusys.com>
> >
> >--- linux-2.6.24-git7.orig/drivers/net/usb/rtl8150.c 2008-01-24
> >23:58:37.000000000 +0100
> >+++ linux-2.6.24-git7/drivers/net/usb/rtl8150.c 2008-01-30
> >20:29:00.000000000 +0100
> >@@ -925,9 +925,8 @@
> > netdev->hard_start_xmit = rtl8150_start_xmit;
> > netdev->set_multicast_list = rtl8150_set_multicast;
> > netdev->set_mac_address = rtl8150_set_mac_address;
> > netdev->get_stats = rtl8150_netdev_stats;
> >- netdev->mtu = RTL8150_MTU;
> > SET_ETHTOOL_OPS(netdev, &ops);
> > dev->intr_interval = 100; /* 100ms */
> >
> > if (!alloc_all_urbs(dev)) {
> >
^ permalink raw reply
* Re: e1000 full-duplex TCP performance well below wire speed
From: Bruce Allen @ 2008-01-31 15:57 UTC (permalink / raw)
To: David Acker
Cc: Bill Fink, SANGTAE HA, Linux Kernel Mailing List, netdev,
Stephen Hemminger
In-Reply-To: <47A1E026.2070805@roinet.com>
Hi David,
> Could this be an issue with pause frames? At a previous job I remember
> having issues with a similar configuration using two broadcom sb1250 3
> gigE port devices. If I ran bidirectional tests on a single pair of
> ports connected via cross over, it was slower than when I gave each
> direction its own pair of ports. The problem turned out to be that
> pause frame generation and handling was not configured correctly.
We had PAUSE frames turned off for our testing. The idea is to let TCP
do the flow and congestion control.
The problem with PAUSE+TCP is that it can cause head-of-line blocking,
where a single oversubscribed output port on a switch can PAUSE a large
number of flows on other paths.
Cheers,
Bruce
^ permalink raw reply
* Re: e1000 full-duplex TCP performance well below wire speed
From: Bruce Allen @ 2008-01-31 15:54 UTC (permalink / raw)
To: Bill Fink
Cc: SANGTAE HA, Linux Kernel Mailing List, netdev, Stephen Hemminger
In-Reply-To: <20080131064533.ef0ae932.billfink@mindspring.com>
Hi Bill,
> I see similar results on my test systems
Thanks for this report and for confirming our observations. Could you
please confirm that a single-port bidrectional UDP link runs at wire
speed? This helps to localize the problem to the TCP stack or interaction
of the TCP stack with the e1000 driver and hardware.
Cheers,
Bruce
^ permalink raw reply
* Re: rtl8150: use default MTU of 1500
From: Petko Manolov @ 2008-01-31 15:42 UTC (permalink / raw)
To: Lennert Buytenhek; +Cc: netdev, jgarzik
In-Reply-To: <20080130193742.GA13631@xi.wantstofly.org>
On Wed, 30 Jan 2008, Lennert Buytenhek wrote:
> The RTL8150 driver uses an MTU of 1540 by default, which causes a
> bunch of problems -- it prevents booting from NFS root, for one.
Agreed, although it is a bit strange how this particular bug has sneaked
up for so long...
cheers,
Petko
> Signed-off-by: Lennert Buytenhek <buytenh@wantstofly.org>
> Cc: Petko Manolov <petkan@nucleusys.com>
>
> --- linux-2.6.24-git7.orig/drivers/net/usb/rtl8150.c 2008-01-24 23:58:37.000000000 +0100
> +++ linux-2.6.24-git7/drivers/net/usb/rtl8150.c 2008-01-30 20:29:00.000000000 +0100
> @@ -925,9 +925,8 @@
> netdev->hard_start_xmit = rtl8150_start_xmit;
> netdev->set_multicast_list = rtl8150_set_multicast;
> netdev->set_mac_address = rtl8150_set_mac_address;
> netdev->get_stats = rtl8150_netdev_stats;
> - netdev->mtu = RTL8150_MTU;
> SET_ETHTOOL_OPS(netdev, &ops);
> dev->intr_interval = 100; /* 100ms */
>
> if (!alloc_all_urbs(dev)) {
>
^ permalink raw reply
* Re: [PATCH 2/6][INET]: Consolidate inet(6)_hash_connect.
From: Arnaldo Carvalho de Melo @ 2008-01-31 15:42 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, Pavel Emelyanov, David Miller,
Linux Netdev List, devel
In-Reply-To: <20080131133954.GU1819@ghostprotocols.net>
Em Thu, Jan 31, 2008 at 11:39:55AM -0200, Arnaldo Carvalho de Melo escreveu:
> Em Thu, Jan 31, 2008 at 04:18:51PM +0300, Pavel Emelyanov escreveu:
> > Arnaldo Carvalho de Melo wrote:
> > > Em Thu, Jan 31, 2008 at 03:32:09PM +0300, Pavel Emelyanov escreveu:
> > >> These two functions are the same except for what they call
> > >> to "check_established" and "hash" for a socket.
> > >>
> > >> This saves half-a-kilo for ipv4 and ipv6.
> > >
> > > Good stuff!
> > >
> > > Yesterday I was perusing tcp_hash and I think we could have the hashinfo
> > > pointer stored perhaps in sk->sk_prot.
> > >
> > > That way we would be able to kill tcp_hash(), inet_put_port() could
> > > receive just sk, etc.
> >
> > But each proto will still have its own hashfn, so proto's
> > callbacks will be called to hash/unhash sockets, so this will
> > give us just one extra dereference. No?
> >
> > > What do you think?
> >
> > Hmmm... Even raw_hash, etc may become simpler. On the other hand
> > maybe this is a good idea, but I'm not very common with this code
> > yet to foresee such things in advance... I think that we should
> > try to prepare a patch and look, but if you have smth ready, then
> > it's better to review your stuff first.
>
> gimme some minutes
A bit more than minutes tho, but here it is, I'm testing it now.
Take a look and if testing is ok I'll submit it with a proper
description.
- Arnaldo
diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index fdff630..62a5b69 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -49,7 +49,7 @@ static inline int inet6_sk_ehashfn(const struct sock *sk)
return inet6_ehashfn(laddr, lport, faddr, fport);
}
-extern void __inet6_hash(struct inet_hashinfo *hashinfo, struct sock *sk);
+extern void __inet6_hash(struct sock *sk);
/*
* Sockets in TCP_CLOSE state are _always_ taken out of the hash, so
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 133cf30..f00f057 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -29,7 +29,6 @@
#undef INET_CSK_CLEAR_TIMERS
struct inet_bind_bucket;
-struct inet_hashinfo;
struct tcp_congestion_ops;
/*
@@ -59,6 +58,8 @@ struct inet_connection_sock_af_ops {
int level, int optname,
char __user *optval, int __user *optlen);
void (*addr2sockaddr)(struct sock *sk, struct sockaddr *);
+ int (*bind_conflict)(const struct sock *sk,
+ const struct inet_bind_bucket *tb);
};
/** inet_connection_sock - INET connection oriented sock
@@ -244,10 +245,7 @@ extern struct request_sock *inet_csk_search_req(const struct sock *sk,
const __be32 laddr);
extern int inet_csk_bind_conflict(const struct sock *sk,
const struct inet_bind_bucket *tb);
-extern int inet_csk_get_port(struct inet_hashinfo *hashinfo,
- struct sock *sk, unsigned short snum,
- int (*bind_conflict)(const struct sock *sk,
- const struct inet_bind_bucket *tb));
+extern int inet_csk_get_port(struct sock *sk, unsigned short snum);
extern struct dst_entry* inet_csk_route_req(struct sock *sk,
const struct request_sock *req);
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index c23c4ed..48ac620 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -221,9 +221,9 @@ static inline int inet_sk_listen_hashfn(const struct sock *sk)
}
/* Caller must disable local BH processing. */
-static inline void __inet_inherit_port(struct inet_hashinfo *table,
- struct sock *sk, struct sock *child)
+static inline void __inet_inherit_port(struct sock *sk, struct sock *child)
{
+ struct inet_hashinfo *table = sk->sk_prot->hashinfo;
const int bhash = inet_bhashfn(inet_sk(child)->num, table->bhash_size);
struct inet_bind_hashbucket *head = &table->bhash[bhash];
struct inet_bind_bucket *tb;
@@ -235,15 +235,14 @@ static inline void __inet_inherit_port(struct inet_hashinfo *table,
spin_unlock(&head->lock);
}
-static inline void inet_inherit_port(struct inet_hashinfo *table,
- struct sock *sk, struct sock *child)
+static inline void inet_inherit_port(struct sock *sk, struct sock *child)
{
local_bh_disable();
- __inet_inherit_port(table, sk, child);
+ __inet_inherit_port(sk, child);
local_bh_enable();
}
-extern void inet_put_port(struct inet_hashinfo *table, struct sock *sk);
+extern void inet_put_port(struct sock *sk);
extern void inet_listen_wlock(struct inet_hashinfo *hashinfo);
@@ -266,41 +265,9 @@ static inline void inet_listen_unlock(struct inet_hashinfo *hashinfo)
wake_up(&hashinfo->lhash_wait);
}
-extern void __inet_hash(struct inet_hashinfo *hashinfo, struct sock *sk);
-extern void __inet_hash_nolisten(struct inet_hashinfo *hinfo, struct sock *sk);
-
-static inline void inet_hash(struct inet_hashinfo *hashinfo, struct sock *sk)
-{
- if (sk->sk_state != TCP_CLOSE) {
- local_bh_disable();
- __inet_hash(hashinfo, sk);
- local_bh_enable();
- }
-}
-
-static inline void inet_unhash(struct inet_hashinfo *hashinfo, struct sock *sk)
-{
- rwlock_t *lock;
-
- if (sk_unhashed(sk))
- goto out;
-
- if (sk->sk_state == TCP_LISTEN) {
- local_bh_disable();
- inet_listen_wlock(hashinfo);
- lock = &hashinfo->lhash_lock;
- } else {
- lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
- write_lock_bh(lock);
- }
-
- if (__sk_del_node_init(sk))
- sock_prot_inuse_add(sk->sk_prot, -1);
- write_unlock_bh(lock);
-out:
- if (sk->sk_state == TCP_LISTEN)
- wake_up(&hashinfo->lhash_wait);
-}
+extern void __inet_hash_nolisten(struct sock *sk);
+extern void inet_hash(struct sock *sk);
+extern void inet_unhash(struct sock *sk);
extern struct sock *__inet_lookup_listener(struct net *net,
struct inet_hashinfo *hashinfo,
@@ -425,7 +392,7 @@ extern int __inet_hash_connect(struct inet_timewait_death_row *death_row,
struct sock *sk,
int (*check_established)(struct inet_timewait_death_row *,
struct sock *, __u16, struct inet_timewait_sock **),
- void (*hash)(struct inet_hashinfo *, struct sock *));
+ void (*hash)(struct sock *sk));
extern int inet_hash_connect(struct inet_timewait_death_row *death_row,
struct sock *sk);
#endif /* _INET_HASHTABLES_H */
diff --git a/include/net/sock.h b/include/net/sock.h
index e3fb4c0..8a7889b 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -496,6 +496,7 @@ extern int sk_wait_data(struct sock *sk, long *timeo);
struct request_sock_ops;
struct timewait_sock_ops;
+struct inet_hashinfo;
/* Networking protocol blocks we attach to sockets.
* socket layer -> transport layer interface
@@ -578,6 +579,8 @@ struct proto {
struct request_sock_ops *rsk_prot;
struct timewait_sock_ops *twsk_prot;
+ struct inet_hashinfo *hashinfo;
+
struct module *owner;
char name[32];
diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index ebe59d9..287a62b 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -271,8 +271,6 @@ extern struct sk_buff *dccp_make_response(struct sock *sk,
extern int dccp_connect(struct sock *sk);
extern int dccp_disconnect(struct sock *sk, int flags);
-extern void dccp_hash(struct sock *sk);
-extern void dccp_unhash(struct sock *sk);
extern int dccp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen);
extern int dccp_setsockopt(struct sock *sk, int level, int optname,
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index c982ad8..474075a 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -38,12 +38,6 @@
*/
static struct socket *dccp_v4_ctl_socket;
-static int dccp_v4_get_port(struct sock *sk, const unsigned short snum)
-{
- return inet_csk_get_port(&dccp_hashinfo, sk, snum,
- inet_csk_bind_conflict);
-}
-
int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
struct inet_sock *inet = inet_sk(sk);
@@ -408,8 +402,8 @@ struct sock *dccp_v4_request_recv_sock(struct sock *sk, struct sk_buff *skb,
dccp_sync_mss(newsk, dst_mtu(dst));
- __inet_hash_nolisten(&dccp_hashinfo, newsk);
- __inet_inherit_port(&dccp_hashinfo, sk, newsk);
+ __inet_hash_nolisten(newsk);
+ __inet_inherit_port(sk, newsk);
return newsk;
@@ -898,6 +892,7 @@ static struct inet_connection_sock_af_ops dccp_ipv4_af_ops = {
.getsockopt = ip_getsockopt,
.addr2sockaddr = inet_csk_addr2sockaddr,
.sockaddr_len = sizeof(struct sockaddr_in),
+ .bind_conflict = inet_csk_bind_conflict,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_ip_setsockopt,
.compat_getsockopt = compat_ip_getsockopt,
@@ -937,10 +932,10 @@ static struct proto dccp_v4_prot = {
.sendmsg = dccp_sendmsg,
.recvmsg = dccp_recvmsg,
.backlog_rcv = dccp_v4_do_rcv,
- .hash = dccp_hash,
- .unhash = dccp_unhash,
+ .hash = inet_hash,
+ .unhash = inet_unhash,
.accept = inet_csk_accept,
- .get_port = dccp_v4_get_port,
+ .get_port = inet_csk_get_port,
.shutdown = dccp_shutdown,
.destroy = dccp_destroy_sock,
.orphan_count = &dccp_orphan_count,
@@ -948,6 +943,7 @@ static struct proto dccp_v4_prot = {
.obj_size = sizeof(struct dccp_sock),
.rsk_prot = &dccp_request_sock_ops,
.twsk_prot = &dccp_timewait_sock_ops,
+ .hashinfo = &dccp_hashinfo,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_dccp_setsockopt,
.compat_getsockopt = compat_dccp_getsockopt,
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index ed0a005..490333d 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -39,21 +39,15 @@ static struct socket *dccp_v6_ctl_socket;
static struct inet_connection_sock_af_ops dccp_ipv6_mapped;
static struct inet_connection_sock_af_ops dccp_ipv6_af_ops;
-static int dccp_v6_get_port(struct sock *sk, unsigned short snum)
-{
- return inet_csk_get_port(&dccp_hashinfo, sk, snum,
- inet6_csk_bind_conflict);
-}
-
static void dccp_v6_hash(struct sock *sk)
{
if (sk->sk_state != DCCP_CLOSED) {
if (inet_csk(sk)->icsk_af_ops == &dccp_ipv6_mapped) {
- dccp_hash(sk);
+ inet_hash(sk);
return;
}
local_bh_disable();
- __inet6_hash(&dccp_hashinfo, sk);
+ __inet6_hash(sk);
local_bh_enable();
}
}
@@ -630,8 +624,8 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
newinet->daddr = newinet->saddr = newinet->rcv_saddr = LOOPBACK4_IPV6;
- __inet6_hash(&dccp_hashinfo, newsk);
- inet_inherit_port(&dccp_hashinfo, sk, newsk);
+ __inet6_hash(newsk);
+ inet_inherit_port(sk, newsk);
return newsk;
@@ -1054,6 +1048,7 @@ static struct inet_connection_sock_af_ops dccp_ipv6_af_ops = {
.getsockopt = ipv6_getsockopt,
.addr2sockaddr = inet6_csk_addr2sockaddr,
.sockaddr_len = sizeof(struct sockaddr_in6),
+ .bind_conflict = inet6_csk_bind_conflict,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_ipv6_setsockopt,
.compat_getsockopt = compat_ipv6_getsockopt,
@@ -1123,9 +1118,9 @@ static struct proto dccp_v6_prot = {
.recvmsg = dccp_recvmsg,
.backlog_rcv = dccp_v6_do_rcv,
.hash = dccp_v6_hash,
- .unhash = dccp_unhash,
+ .unhash = inet_unhash,
.accept = inet_csk_accept,
- .get_port = dccp_v6_get_port,
+ .get_port = inet_csk_get_port,
.shutdown = dccp_shutdown,
.destroy = dccp_v6_destroy_sock,
.orphan_count = &dccp_orphan_count,
@@ -1133,6 +1128,7 @@ static struct proto dccp_v6_prot = {
.obj_size = sizeof(struct dccp6_sock),
.rsk_prot = &dccp6_request_sock_ops,
.twsk_prot = &dccp6_timewait_sock_ops,
+ .hashinfo = &dccp_hashinfo,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_dccp_setsockopt,
.compat_getsockopt = compat_dccp_getsockopt,
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 0bed4a6..e3f5d37 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -78,7 +78,7 @@ void dccp_set_state(struct sock *sk, const int state)
sk->sk_prot->unhash(sk);
if (inet_csk(sk)->icsk_bind_hash != NULL &&
!(sk->sk_userlocks & SOCK_BINDPORT_LOCK))
- inet_put_port(&dccp_hashinfo, sk);
+ inet_put_port(sk);
/* fall through */
default:
if (oldstate == DCCP_OPEN)
@@ -173,20 +173,6 @@ const char *dccp_state_name(const int state)
EXPORT_SYMBOL_GPL(dccp_state_name);
-void dccp_hash(struct sock *sk)
-{
- inet_hash(&dccp_hashinfo, sk);
-}
-
-EXPORT_SYMBOL_GPL(dccp_hash);
-
-void dccp_unhash(struct sock *sk)
-{
- inet_unhash(&dccp_hashinfo, sk);
-}
-
-EXPORT_SYMBOL_GPL(dccp_unhash);
-
int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized)
{
struct dccp_sock *dp = dccp_sk(sk);
@@ -268,7 +254,7 @@ int dccp_destroy_sock(struct sock *sk)
/* Clean up a referenced DCCP bind bucket. */
if (inet_csk(sk)->icsk_bind_hash != NULL)
- inet_put_port(&dccp_hashinfo, sk);
+ inet_put_port(sk);
kfree(dp->dccps_service_list);
dp->dccps_service_list = NULL;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index de5a41d..b189278 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -78,11 +78,9 @@ EXPORT_SYMBOL_GPL(inet_csk_bind_conflict);
/* Obtain a reference to a local port for the given sock,
* if snum is zero it means select any available local port.
*/
-int inet_csk_get_port(struct inet_hashinfo *hashinfo,
- struct sock *sk, unsigned short snum,
- int (*bind_conflict)(const struct sock *sk,
- const struct inet_bind_bucket *tb))
+int inet_csk_get_port(struct sock *sk, unsigned short snum)
{
+ struct inet_hashinfo *hashinfo = sk->sk_prot->hashinfo;
struct inet_bind_hashbucket *head;
struct hlist_node *node;
struct inet_bind_bucket *tb;
@@ -142,7 +140,7 @@ tb_found:
goto success;
} else {
ret = 1;
- if (bind_conflict(sk, tb))
+ if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb))
goto fail_unlock;
}
}
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 48d4500..90f422c 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -66,8 +66,9 @@ void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
/*
* Get rid of any references to a local port held by the given sock.
*/
-static void __inet_put_port(struct inet_hashinfo *hashinfo, struct sock *sk)
+static void __inet_put_port(struct sock *sk)
{
+ struct inet_hashinfo *hashinfo = sk->sk_prot->hashinfo;
const int bhash = inet_bhashfn(inet_sk(sk)->num, hashinfo->bhash_size);
struct inet_bind_hashbucket *head = &hashinfo->bhash[bhash];
struct inet_bind_bucket *tb;
@@ -81,10 +82,10 @@ static void __inet_put_port(struct inet_hashinfo *hashinfo, struct sock *sk)
spin_unlock(&head->lock);
}
-void inet_put_port(struct inet_hashinfo *hashinfo, struct sock *sk)
+void inet_put_port(struct sock *sk)
{
local_bh_disable();
- __inet_put_port(hashinfo, sk);
+ __inet_put_port(sk);
local_bh_enable();
}
@@ -317,8 +318,9 @@ static inline u32 inet_sk_port_offset(const struct sock *sk)
inet->dport);
}
-void __inet_hash_nolisten(struct inet_hashinfo *hashinfo, struct sock *sk)
+void __inet_hash_nolisten(struct sock *sk)
{
+ struct inet_hashinfo *hashinfo = sk->sk_prot->hashinfo;
struct hlist_head *list;
rwlock_t *lock;
struct inet_ehash_bucket *head;
@@ -337,13 +339,14 @@ void __inet_hash_nolisten(struct inet_hashinfo *hashinfo, struct sock *sk)
}
EXPORT_SYMBOL_GPL(__inet_hash_nolisten);
-void __inet_hash(struct inet_hashinfo *hashinfo, struct sock *sk)
+static void __inet_hash(struct sock *sk)
{
+ struct inet_hashinfo *hashinfo = sk->sk_prot->hashinfo;
struct hlist_head *list;
rwlock_t *lock;
if (sk->sk_state != TCP_LISTEN) {
- __inet_hash_nolisten(hashinfo, sk);
+ __inet_hash_nolisten(sk);
return;
}
@@ -357,13 +360,48 @@ void __inet_hash(struct inet_hashinfo *hashinfo, struct sock *sk)
write_unlock(lock);
wake_up(&hashinfo->lhash_wait);
}
-EXPORT_SYMBOL_GPL(__inet_hash);
+
+void inet_hash(struct sock *sk)
+{
+ if (sk->sk_state != TCP_CLOSE) {
+ local_bh_disable();
+ __inet_hash(sk);
+ local_bh_enable();
+ }
+}
+EXPORT_SYMBOL_GPL(inet_hash);
+
+void inet_unhash(struct sock *sk)
+{
+ rwlock_t *lock;
+ struct inet_hashinfo *hashinfo = sk->sk_prot->hashinfo;
+
+ if (sk_unhashed(sk))
+ goto out;
+
+ if (sk->sk_state == TCP_LISTEN) {
+ local_bh_disable();
+ inet_listen_wlock(hashinfo);
+ lock = &hashinfo->lhash_lock;
+ } else {
+ lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
+ write_lock_bh(lock);
+ }
+
+ if (__sk_del_node_init(sk))
+ sock_prot_inuse_add(sk->sk_prot, -1);
+ write_unlock_bh(lock);
+out:
+ if (sk->sk_state == TCP_LISTEN)
+ wake_up(&hashinfo->lhash_wait);
+}
+EXPORT_SYMBOL_GPL(inet_unhash);
int __inet_hash_connect(struct inet_timewait_death_row *death_row,
struct sock *sk,
int (*check_established)(struct inet_timewait_death_row *,
struct sock *, __u16, struct inet_timewait_sock **),
- void (*hash)(struct inet_hashinfo *, struct sock *))
+ void (*hash)(struct sock *sk))
{
struct inet_hashinfo *hinfo = death_row->hashinfo;
const unsigned short snum = inet_sk(sk)->num;
@@ -427,7 +465,7 @@ ok:
inet_bind_hash(sk, tb, port);
if (sk_unhashed(sk)) {
inet_sk(sk)->sport = htons(port);
- hash(hinfo, sk);
+ hash(sk);
}
spin_unlock(&head->lock);
@@ -444,7 +482,7 @@ ok:
tb = inet_csk(sk)->icsk_bind_hash;
spin_lock_bh(&head->lock);
if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) {
- hash(hinfo, sk);
+ hash(sk);
spin_unlock_bh(&head->lock);
return 0;
} else {
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a0d373b..071e83a 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1669,7 +1669,7 @@ void tcp_set_state(struct sock *sk, int state)
sk->sk_prot->unhash(sk);
if (inet_csk(sk)->icsk_bind_hash &&
!(sk->sk_userlocks & SOCK_BINDPORT_LOCK))
- inet_put_port(&tcp_hashinfo, sk);
+ inet_put_port(sk);
/* fall through */
default:
if (oldstate==TCP_ESTABLISHED)
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 77c1939..63414ea 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -108,22 +108,6 @@ struct inet_hashinfo __cacheline_aligned tcp_hashinfo = {
.lhash_wait = __WAIT_QUEUE_HEAD_INITIALIZER(tcp_hashinfo.lhash_wait),
};
-static int tcp_v4_get_port(struct sock *sk, unsigned short snum)
-{
- return inet_csk_get_port(&tcp_hashinfo, sk, snum,
- inet_csk_bind_conflict);
-}
-
-static void tcp_v4_hash(struct sock *sk)
-{
- inet_hash(&tcp_hashinfo, sk);
-}
-
-void tcp_unhash(struct sock *sk)
-{
- inet_unhash(&tcp_hashinfo, sk);
-}
-
static inline __u32 tcp_v4_init_sequence(struct sk_buff *skb)
{
return secure_tcp_sequence_number(ip_hdr(skb)->daddr,
@@ -1478,8 +1462,8 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
}
#endif
- __inet_hash_nolisten(&tcp_hashinfo, newsk);
- __inet_inherit_port(&tcp_hashinfo, sk, newsk);
+ __inet_hash_nolisten(newsk);
+ __inet_inherit_port(sk, newsk);
return newsk;
@@ -1827,6 +1811,7 @@ struct inet_connection_sock_af_ops ipv4_specific = {
.getsockopt = ip_getsockopt,
.addr2sockaddr = inet_csk_addr2sockaddr,
.sockaddr_len = sizeof(struct sockaddr_in),
+ .bind_conflict = inet_csk_bind_conflict,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_ip_setsockopt,
.compat_getsockopt = compat_ip_getsockopt,
@@ -1926,7 +1911,7 @@ int tcp_v4_destroy_sock(struct sock *sk)
/* Clean up a referenced TCP bind bucket. */
if (inet_csk(sk)->icsk_bind_hash)
- inet_put_port(&tcp_hashinfo, sk);
+ inet_put_port(sk);
/*
* If sendmsg cached page exists, toss it.
@@ -2435,9 +2420,9 @@ struct proto tcp_prot = {
.getsockopt = tcp_getsockopt,
.recvmsg = tcp_recvmsg,
.backlog_rcv = tcp_v4_do_rcv,
- .hash = tcp_v4_hash,
- .unhash = tcp_unhash,
- .get_port = tcp_v4_get_port,
+ .hash = inet_hash,
+ .unhash = inet_unhash,
+ .get_port = inet_csk_get_port,
.enter_memory_pressure = tcp_enter_memory_pressure,
.sockets_allocated = &tcp_sockets_allocated,
.orphan_count = &tcp_orphan_count,
@@ -2450,6 +2435,7 @@ struct proto tcp_prot = {
.obj_size = sizeof(struct tcp_sock),
.twsk_prot = &tcp_timewait_sock_ops,
.rsk_prot = &tcp_request_sock_ops,
+ .hashinfo = &tcp_hashinfo,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_tcp_setsockopt,
.compat_getsockopt = compat_tcp_getsockopt,
@@ -2467,7 +2453,6 @@ void __init tcp_v4_init(struct net_proto_family *ops)
EXPORT_SYMBOL(ipv4_specific);
EXPORT_SYMBOL(tcp_hashinfo);
EXPORT_SYMBOL(tcp_prot);
-EXPORT_SYMBOL(tcp_unhash);
EXPORT_SYMBOL(tcp_v4_conn_request);
EXPORT_SYMBOL(tcp_v4_connect);
EXPORT_SYMBOL(tcp_v4_do_rcv);
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index d325a99..43f3993 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -22,9 +22,9 @@
#include <net/inet6_hashtables.h>
#include <net/ip.h>
-void __inet6_hash(struct inet_hashinfo *hashinfo,
- struct sock *sk)
+void __inet6_hash(struct sock *sk)
{
+ struct inet_hashinfo *hashinfo = sk->sk_prot->hashinfo;
struct hlist_head *list;
rwlock_t *lock;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 59d0029..12750f2 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -86,12 +86,6 @@ static struct tcp_sock_af_ops tcp_sock_ipv6_specific;
static struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific;
#endif
-static int tcp_v6_get_port(struct sock *sk, unsigned short snum)
-{
- return inet_csk_get_port(&tcp_hashinfo, sk, snum,
- inet6_csk_bind_conflict);
-}
-
static void tcp_v6_hash(struct sock *sk)
{
if (sk->sk_state != TCP_CLOSE) {
@@ -100,7 +94,7 @@ static void tcp_v6_hash(struct sock *sk)
return;
}
local_bh_disable();
- __inet6_hash(&tcp_hashinfo, sk);
+ __inet6_hash(sk);
local_bh_enable();
}
}
@@ -1504,8 +1498,8 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
}
#endif
- __inet6_hash(&tcp_hashinfo, newsk);
- inet_inherit_port(&tcp_hashinfo, sk, newsk);
+ __inet6_hash(newsk);
+ inet_inherit_port(sk, newsk);
return newsk;
@@ -1833,6 +1827,7 @@ static struct inet_connection_sock_af_ops ipv6_specific = {
.getsockopt = ipv6_getsockopt,
.addr2sockaddr = inet6_csk_addr2sockaddr,
.sockaddr_len = sizeof(struct sockaddr_in6),
+ .bind_conflict = inet6_csk_bind_conflict,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_ipv6_setsockopt,
.compat_getsockopt = compat_ipv6_getsockopt,
@@ -1864,6 +1859,7 @@ static struct inet_connection_sock_af_ops ipv6_mapped = {
.getsockopt = ipv6_getsockopt,
.addr2sockaddr = inet6_csk_addr2sockaddr,
.sockaddr_len = sizeof(struct sockaddr_in6),
+ .bind_conflict = inet6_csk_bind_conflict,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_ipv6_setsockopt,
.compat_getsockopt = compat_ipv6_getsockopt,
@@ -2127,8 +2123,8 @@ struct proto tcpv6_prot = {
.recvmsg = tcp_recvmsg,
.backlog_rcv = tcp_v6_do_rcv,
.hash = tcp_v6_hash,
- .unhash = tcp_unhash,
- .get_port = tcp_v6_get_port,
+ .unhash = inet_unhash,
+ .get_port = inet_csk_get_port,
.enter_memory_pressure = tcp_enter_memory_pressure,
.sockets_allocated = &tcp_sockets_allocated,
.memory_allocated = &tcp_memory_allocated,
@@ -2141,6 +2137,7 @@ struct proto tcpv6_prot = {
.obj_size = sizeof(struct tcp6_sock),
.twsk_prot = &tcp6_timewait_sock_ops,
.rsk_prot = &tcp6_request_sock_ops,
+ .hashinfo = &tcp_hashinfo,
#ifdef CONFIG_COMPAT
.compat_setsockopt = compat_tcp_setsockopt,
.compat_getsockopt = compat_tcp_getsockopt,
^ permalink raw reply related
* Re: e1000 full-duplex TCP performance well below wire speed
From: Carsten Aulbert @ 2008-01-31 15:18 UTC (permalink / raw)
To: Brandeburg, Jesse; +Cc: Bruce Allen, netdev, Henning Fehrmann, Bruce Allen
In-Reply-To: <36D9DB17C6DE9E40B059440DB8D95F52044F8BA3@orsmsx418.amr.corp.intel.com>
Brief question I forgot to ask:
Right now we are using the "old" version 7.3.20-k2. To save some effort
on your end, shall we upgrade this to 7.6.15 or should our version be
good enough?
Thanks
Carsten
^ permalink raw reply
* Re: e1000 full-duplex TCP performance well below wire speed
From: Carsten Aulbert @ 2008-01-31 15:12 UTC (permalink / raw)
To: Brandeburg, Jesse; +Cc: Bruce Allen, netdev, Henning Fehrmann, Bruce Allen
In-Reply-To: <36D9DB17C6DE9E40B059440DB8D95F52044F8BA3@orsmsx418.amr.corp.intel.com>
[-- Attachment #1: Type: text/plain, Size: 5687 bytes --]
Hi all, slowly crawling through the mails.
Brandeburg, Jesse wrote:
>>>> The test was done with various mtu sizes ranging from 1500 to 9000,
>>>> with ethernet flow control switched on and off, and using reno and
>>>> cubic as a TCP congestion control.
>>> As asked in LKML thread, please post the exact netperf command used
>>> to start the client/server, whether or not you're using irqbalanced
>>> (aka irqbalance) and what cat /proc/interrupts looks like (you ARE
>>> using MSI, right?)
We are using MSI, /proc/interrupts look like:
n0003:~# cat /proc/interrupts
CPU0 CPU1 CPU2 CPU3
0: 6536963 0 0 0 IO-APIC-edge timer
1: 2 0 0 0 IO-APIC-edge i8042
3: 1 0 0 0 IO-APIC-edge serial
8: 0 0 0 0 IO-APIC-edge rtc
9: 0 0 0 0 IO-APIC-fasteoi acpi
14: 32321 0 0 0 IO-APIC-edge libata
15: 0 0 0 0 IO-APIC-edge libata
16: 0 0 0 0 IO-APIC-fasteoi
uhci_hcd:usb5
18: 0 0 0 0 IO-APIC-fasteoi
uhci_hcd:usb4
19: 0 0 0 0 IO-APIC-fasteoi
uhci_hcd:usb3
23: 0 0 0 0 IO-APIC-fasteoi
ehci_hcd:usb1, uhci_hcd:usb2
378: 17234866 0 0 0 PCI-MSI-edge eth1
379: 129826 0 0 0 PCI-MSI-edge eth0
NMI: 0 0 0 0
LOC: 6537181 6537326 6537149 6537052
ERR: 0
(sorry for the line break).
What we don't understand is why only core0 gets the interrupts, since
the affinity is set to f:
# cat /proc/irq/378/smp_affinity
f
Right now, irqbalance is not running, though I can give it shot if
people think this will make a difference.
> I would suggest you try TCP_RR with a command line something like this:
> netperf -t TCP_RR -H <hostname> -C -c -- -b 4 -r 64K
I did that and the results can be found here:
https://n0.aei.uni-hannover.de/wiki/index.php/NetworkTest
The results with netperf running like
netperf -t TCP_STREAM -H <host> -l 20
can be found here:
https://n0.aei.uni-hannover.de/wiki/index.php/NetworkTestNetperf1
I reran the tests with
netperf -t <test> -H <host> -l 20 -c -C
or in the case of TCP_RR with the suggested burst settings -b 4 -r 64k
> Yes, InterruptThrottleRate=8000 means there will be no more than 8000
> ints/second from that adapter, and if interrupts are generated faster
> than that they are "aggregated."
>
> Interestingly since you are interested in ultra low latency, and may be
> willing to give up some cpu for it during bulk transfers you should try
> InterruptThrottleRate=1 (can generate up to 70000 ints/s)
>
On the web page you'll see that there are about 4000 interrupts/s for
most tests and up to 20,000/s for the TCP_RR test. Shall I change the
throttle rate?
>>> just for completeness can you post the dump of ethtool -e eth0 and
>>> lspci -vvv?
>> Yup, we'll give that info also.
n0002:~# ethtool -e eth1
Offset Values
------ ------
0x0000 00 30 48 93 94 2d 20 0d 46 f7 57 00 ff ff ff ff
0x0010 ff ff ff ff 6b 02 9a 10 d9 15 9a 10 86 80 df 80
0x0020 00 00 00 20 54 7e 00 00 00 10 da 00 04 00 00 27
0x0030 c9 6c 50 31 32 07 0b 04 84 29 00 00 00 c0 06 07
0x0040 08 10 00 00 04 0f ff 7f 01 4d ff ff ff ff ff ff
0x0050 14 00 1d 00 14 00 1d 00 af aa 1e 00 00 00 1d 00
0x0060 00 01 00 40 1e 12 ff ff ff ff ff ff ff ff ff ff
0x0070 ff ff ff ff ff ff ff ff ff ff ff ff ff ff cf 2f
lspci -vvv for this card:
0e:00.0 Ethernet controller: Intel Corporation 82573L Gigabit Ethernet
Controller
Subsystem: Super Micro Computer Inc Unknown device 109a
Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop-
ParErr- Stepping- SERR+ FastB2B-
Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort-
<TAbort- <MAbort- >SERR- <PERR-
Latency: 0, Cache Line Size: 64 bytes
Interrupt: pin A routed to IRQ 378
Region 0: Memory at ee200000 (32-bit, non-prefetchable) [size=128K]
Region 2: I/O ports at 5000 [size=32]
Capabilities: [c8] Power Management version 2
Flags: PMEClk- DSI+ D1- D2- AuxCurrent=0mA
PME(D0+,D1-,D2-,D3hot+,D3cold+)
Status: D0 PME-Enable- DSel=0 DScale=1 PME-
Capabilities: [d0] Message Signalled Interrupts: Mask- 64bit+
Queue=0/0 Enable+
Address: 00000000fee0f00c Data: 41b9
Capabilities: [e0] Express Endpoint IRQ 0
Device: Supported: MaxPayload 256 bytes, PhantFunc 0,
ExtTag-
Device: Latency L0s <512ns, L1 <64us
Device: AtnBtn- AtnInd- PwrInd-
Device: Errors: Correctable- Non-Fatal- Fatal- Unsupported-
Device: RlxdOrd+ ExtTag- PhantFunc- AuxPwr- NoSnoop+
Device: MaxPayload 128 bytes, MaxReadReq 512 bytes
Link: Supported Speed 2.5Gb/s, Width x1, ASPM unknown,
Port 0
Link: Latency L0s <128ns, L1 <64us
Link: ASPM Disabled RCB 64 bytes CommClk- ExtSynch-
Link: Speed 2.5Gb/s, Width x1
Capabilities: [100] Advanced Error Reporting
Capabilities: [140] Device Serial Number 2d-94-93-ff-ff-48-30-00
(all lspci-vvv output as attachment)
Thanks a lot, open for suggestions
Carsten
[-- Attachment #2: lspci --]
[-- Type: text/plain, Size: 16537 bytes --]
00:00.0 Host bridge: Intel Corporation E7230 Memory Controller Hub (rev c0)
Subsystem: Super Micro Computer Inc Unknown device 8580
Control: I/O- Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR+ FastB2B-
Status: Cap+ 66MHz- UDF- FastB2B+ ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort+ >SERR- <PERR-
Latency: 0
Capabilities: [e0] Vendor Specific Information
00:01.0 PCI bridge: Intel Corporation E7230 PCI Express Root Port (rev c0) (prog-if 00 [Normal decode])
Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR+ FastB2B-
Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR-
Latency: 0, Cache Line Size: 32 bytes
Bus: primary=00, secondary=01, subordinate=01, sec-latency=0
I/O behind bridge: 0000f000-00000fff
Memory behind bridge: fff00000-000fffff
Prefetchable memory behind bridge: 00000000fff00000-00000000000fffff
Secondary status: 66MHz- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- <SERR- <PERR-
BridgeCtl: Parity+ SERR- NoISA+ VGA- MAbort- >Reset+ FastB2B-
Capabilities: [88] Subsystem: Super Micro Computer Inc Unknown device 8580
Capabilities: [80] Power Management version 2
Flags: PMEClk- DSI- D1- D2- AuxCurrent=0mA PME(D0+,D1-,D2-,D3hot+,D3cold+)
Status: D0 PME-Enable- DSel=0 DScale=0 PME-
Capabilities: [90] Message Signalled Interrupts: Mask- 64bit- Queue=0/0 Enable+
Address: fee0f00c Data: 4159
Capabilities: [a0] Express Root Port (Slot+) IRQ 0
Device: Supported: MaxPayload 128 bytes, PhantFunc 0, ExtTag-
Device: Latency L0s <64ns, L1 <1us
Device: Errors: Correctable- Non-Fatal- Fatal- Unsupported-
Device: RlxdOrd- ExtTag- PhantFunc- AuxPwr- NoSnoop-
Device: MaxPayload 128 bytes, MaxReadReq 128 bytes
Link: Supported Speed 2.5Gb/s, Width x8, ASPM L0s, Port 2
Link: Latency L0s <1us, L1 <4us
Link: ASPM Disabled RCB 64 bytes Disabled CommClk- ExtSynch-
Link: Speed 2.5Gb/s, Width x0
Slot: AtnBtn- PwrCtrl- MRL- AtnInd- PwrInd- HotPlug- Surpise-
Slot: Number 0, PowerLimit 0.000000
Slot: Enabled AtnBtn- PwrFlt- MRL- PresDet- CmdCplt- HPIrq-
Slot: AttnInd Off, PwrInd On, Power-
Root: Correctable- Non-Fatal- Fatal- PME-
Capabilities: [100] Virtual Channel
Capabilities: [140] Unknown (5)
00:1c.0 PCI bridge: Intel Corporation 82801G (ICH7 Family) PCI Express Port 1 (rev 01) (prog-if 00 [Normal decode])
Control: I/O- Mem- BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B-
Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR-
Latency: 0, Cache Line Size: 32 bytes
Bus: primary=00, secondary=09, subordinate=09, sec-latency=0
I/O behind bridge: 0000f000-00000fff
Memory behind bridge: fff00000-000fffff
Prefetchable memory behind bridge: 00000000fff00000-00000000000fffff
Secondary status: 66MHz- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort+ <SERR- <PERR-
BridgeCtl: Parity- SERR- NoISA- VGA- MAbort- >Reset- FastB2B-
Capabilities: [40] Express Root Port (Slot+) IRQ 0
Device: Supported: MaxPayload 128 bytes, PhantFunc 0, ExtTag-
Device: Latency L0s unlimited, L1 unlimited
Device: Errors: Correctable- Non-Fatal- Fatal+ Unsupported-
Device: RlxdOrd- ExtTag- PhantFunc- AuxPwr- NoSnoop-
Device: MaxPayload 128 bytes, MaxReadReq 128 bytes
Link: Supported Speed 2.5Gb/s, Width x4, ASPM L0s L1, Port 1
Link: Latency L0s <256ns, L1 <4us
Link: ASPM Disabled RCB 64 bytes CommClk+ ExtSynch-
Link: Speed 2.5Gb/s, Width x0
Slot: AtnBtn- PwrCtrl- MRL- AtnInd- PwrInd- HotPlug+ Surpise+
Slot: Number 0, PowerLimit 0.000000
Slot: Enabled AtnBtn- PwrFlt- MRL- PresDet- CmdCplt- HPIrq-
Slot: AttnInd Unknown, PwrInd Unknown, Power-
Root: Correctable- Non-Fatal- Fatal- PME-
Capabilities: [80] Message Signalled Interrupts: Mask- 64bit- Queue=0/0 Enable+
Address: fee0f00c Data: 4161
Capabilities: [90] Subsystem: Super Micro Computer Inc Unknown device 8580
Capabilities: [a0] Power Management version 2
Flags: PMEClk- DSI- D1- D2- AuxCurrent=0mA PME(D0+,D1-,D2-,D3hot+,D3cold+)
Status: D0 PME-Enable- DSel=0 DScale=0 PME-
Capabilities: [100] Virtual Channel
Capabilities: [180] Unknown (5)
00:1c.4 PCI bridge: Intel Corporation 82801GR/GH/GHM (ICH7 Family) PCI Express Port 5 (rev 01) (prog-if 00 [Normal decode])
Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B-
Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR-
Latency: 0, Cache Line Size: 32 bytes
Bus: primary=00, secondary=0d, subordinate=0d, sec-latency=0
I/O behind bridge: 00004000-00004fff
Memory behind bridge: ee100000-ee1fffff
Prefetchable memory behind bridge: 00000000fff00000-00000000000fffff
Secondary status: 66MHz- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- <SERR- <PERR-
BridgeCtl: Parity- SERR- NoISA+ VGA- MAbort- >Reset- FastB2B-
Capabilities: [40] Express Root Port (Slot+) IRQ 0
Device: Supported: MaxPayload 128 bytes, PhantFunc 0, ExtTag-
Device: Latency L0s unlimited, L1 unlimited
Device: Errors: Correctable- Non-Fatal- Fatal+ Unsupported-
Device: RlxdOrd- ExtTag- PhantFunc- AuxPwr- NoSnoop-
Device: MaxPayload 128 bytes, MaxReadReq 128 bytes
Link: Supported Speed 2.5Gb/s, Width x1, ASPM L0s L1, Port 5
Link: Latency L0s <256ns, L1 <4us
Link: ASPM Disabled RCB 64 bytes CommClk+ ExtSynch-
Link: Speed 2.5Gb/s, Width x1
Slot: AtnBtn- PwrCtrl- MRL- AtnInd- PwrInd- HotPlug+ Surpise+
Slot: Number 5, PowerLimit 10.000000
Slot: Enabled AtnBtn- PwrFlt- MRL- PresDet- CmdCplt- HPIrq-
Slot: AttnInd Unknown, PwrInd Unknown, Power-
Root: Correctable- Non-Fatal- Fatal- PME-
Capabilities: [80] Message Signalled Interrupts: Mask- 64bit- Queue=0/0 Enable+
Address: fee0f00c Data: 4169
Capabilities: [90] Subsystem: Super Micro Computer Inc Unknown device 8580
Capabilities: [a0] Power Management version 2
Flags: PMEClk- DSI- D1- D2- AuxCurrent=0mA PME(D0+,D1-,D2-,D3hot+,D3cold+)
Status: D0 PME-Enable- DSel=0 DScale=0 PME-
Capabilities: [100] Virtual Channel
Capabilities: [180] Unknown (5)
00:1c.5 PCI bridge: Intel Corporation 82801GR/GH/GHM (ICH7 Family) PCI Express Port 6 (rev 01) (prog-if 00 [Normal decode])
Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B-
Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR-
Latency: 0, Cache Line Size: 32 bytes
Bus: primary=00, secondary=0e, subordinate=0e, sec-latency=0
I/O behind bridge: 00005000-00005fff
Memory behind bridge: ee200000-ee2fffff
Prefetchable memory behind bridge: 00000000fff00000-00000000000fffff
Secondary status: 66MHz- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- <SERR- <PERR-
BridgeCtl: Parity- SERR- NoISA+ VGA- MAbort- >Reset- FastB2B-
Capabilities: [40] Express Root Port (Slot+) IRQ 0
Device: Supported: MaxPayload 128 bytes, PhantFunc 0, ExtTag-
Device: Latency L0s unlimited, L1 unlimited
Device: Errors: Correctable- Non-Fatal- Fatal+ Unsupported-
Device: RlxdOrd- ExtTag- PhantFunc- AuxPwr- NoSnoop-
Device: MaxPayload 128 bytes, MaxReadReq 128 bytes
Link: Supported Speed 2.5Gb/s, Width x1, ASPM L0s L1, Port 6
Link: Latency L0s <256ns, L1 <4us
Link: ASPM Disabled RCB 64 bytes CommClk+ ExtSynch-
Link: Speed 2.5Gb/s, Width x1
Slot: AtnBtn- PwrCtrl- MRL- AtnInd- PwrInd- HotPlug+ Surpise+
Slot: Number 6, PowerLimit 10.000000
Slot: Enabled AtnBtn- PwrFlt- MRL- PresDet- CmdCplt- HPIrq-
Slot: AttnInd Unknown, PwrInd Unknown, Power-
Root: Correctable- Non-Fatal- Fatal- PME-
Capabilities: [80] Message Signalled Interrupts: Mask- 64bit- Queue=0/0 Enable+
Address: fee0f00c Data: 4171
Capabilities: [90] Subsystem: Super Micro Computer Inc Unknown device 8580
Capabilities: [a0] Power Management version 2
Flags: PMEClk- DSI- D1- D2- AuxCurrent=0mA PME(D0+,D1-,D2-,D3hot+,D3cold+)
Status: D0 PME-Enable- DSel=0 DScale=0 PME-
Capabilities: [100] Virtual Channel
Capabilities: [180] Unknown (5)
00:1d.0 USB Controller: Intel Corporation 82801G (ICH7 Family) USB UHCI #1 (rev 01) (prog-if 00 [UHCI])
Subsystem: Super Micro Computer Inc Unknown device 8580
Control: I/O+ Mem- BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B-
Status: Cap- 66MHz- UDF- FastB2B+ ParErr- DEVSEL=medium >TAbort- <TAbort- <MAbort- >SERR- <PERR-
Latency: 0
Interrupt: pin A routed to IRQ 23
Region 4: I/O ports at 3000 [size=32]
00:1d.1 USB Controller: Intel Corporation 82801G (ICH7 Family) USB UHCI #2 (rev 01) (prog-if 00 [UHCI])
Subsystem: Super Micro Computer Inc Unknown device 8580
Control: I/O+ Mem- BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B-
Status: Cap- 66MHz- UDF- FastB2B+ ParErr- DEVSEL=medium >TAbort- <TAbort- <MAbort- >SERR- <PERR-
Latency: 0
Interrupt: pin B routed to IRQ 19
Region 4: I/O ports at 3020 [size=32]
00:1d.2 USB Controller: Intel Corporation 82801G (ICH7 Family) USB UHCI #3 (rev 01) (prog-if 00 [UHCI])
Subsystem: Super Micro Computer Inc Unknown device 8580
Control: I/O+ Mem- BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B-
Status: Cap- 66MHz- UDF- FastB2B+ ParErr- DEVSEL=medium >TAbort- <TAbort- <MAbort- >SERR- <PERR-
Latency: 0
Interrupt: pin C routed to IRQ 18
Region 4: I/O ports at 3040 [size=32]
00:1d.3 USB Controller: Intel Corporation 82801G (ICH7 Family) USB UHCI #4 (rev 01) (prog-if 00 [UHCI])
Subsystem: Super Micro Computer Inc Unknown device 8580
Control: I/O+ Mem- BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B-
Status: Cap- 66MHz- UDF- FastB2B+ ParErr- DEVSEL=medium >TAbort- <TAbort- <MAbort- >SERR- <PERR-
Latency: 0
Interrupt: pin D routed to IRQ 16
Region 4: I/O ports at 3060 [size=32]
00:1d.7 USB Controller: Intel Corporation 82801G (ICH7 Family) USB2 EHCI Controller (rev 01) (prog-if 20 [EHCI])
Subsystem: Super Micro Computer Inc Unknown device 8580
Control: I/O- Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR+ FastB2B-
Status: Cap+ 66MHz- UDF- FastB2B+ ParErr- DEVSEL=medium >TAbort- <TAbort- <MAbort- >SERR- <PERR-
Latency: 0
Interrupt: pin A routed to IRQ 23
Region 0: Memory at ee000000 (32-bit, non-prefetchable) [size=1K]
Capabilities: [50] Power Management version 2
Flags: PMEClk- DSI- D1- D2- AuxCurrent=375mA PME(D0+,D1-,D2-,D3hot+,D3cold+)
Status: D0 PME-Enable- DSel=0 DScale=0 PME-
Capabilities: [58] Debug port
00:1e.0 PCI bridge: Intel Corporation 82801 PCI Bridge (rev e1) (prog-if 01 [Subtractive decode])
Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR+ FastB2B-
Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR-
Latency: 0
Bus: primary=00, secondary=0f, subordinate=0f, sec-latency=32
I/O behind bridge: 00006000-00006fff
Memory behind bridge: ee300000-ee3fffff
Prefetchable memory behind bridge: 00000000ef000000-00000000efffffff
Secondary status: 66MHz- FastB2B+ ParErr- DEVSEL=medium >TAbort- <TAbort- <MAbort+ <SERR- <PERR-
BridgeCtl: Parity- SERR- NoISA+ VGA+ MAbort- >Reset- FastB2B-
Capabilities: [50] Subsystem: Super Micro Computer Inc Unknown device 8580
00:1f.0 ISA bridge: Intel Corporation 82801GB/GR (ICH7 Family) LPC Interface Bridge (rev 01)
Subsystem: Super Micro Computer Inc Unknown device 8580
Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B-
Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=medium >TAbort- <TAbort- <MAbort- >SERR- <PERR-
Latency: 0
Capabilities: [e0] Vendor Specific Information
00:1f.2 IDE interface: Intel Corporation 82801GB/GR/GH (ICH7 Family) Serial ATA Storage Controller IDE (rev 01) (prog-if 8a [Master SecP PriP])
Subsystem: Super Micro Computer Inc Unknown device 8580
Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B-
Status: Cap+ 66MHz+ UDF- FastB2B+ ParErr- DEVSEL=medium >TAbort- <TAbort- <MAbort- >SERR- <PERR-
Latency: 0
Interrupt: pin B routed to IRQ 19
Region 0: I/O ports at 01f0 [size=8]
Region 1: I/O ports at 03f4 [size=1]
Region 2: I/O ports at 0170 [size=8]
Region 3: I/O ports at 0374 [size=1]
Region 4: I/O ports at 30a0 [size=16]
Region 5: Memory at f5000000 (32-bit, non-prefetchable) [size=1K]
Capabilities: [70] Power Management version 2
Flags: PMEClk- DSI- D1- D2- AuxCurrent=0mA PME(D0-,D1-,D2-,D3hot+,D3cold-)
Status: D0 PME-Enable- DSel=0 DScale=0 PME-
00:1f.3 SMBus: Intel Corporation 82801G (ICH7 Family) SMBus Controller (rev 01)
Subsystem: Super Micro Computer Inc Unknown device 8580
Control: I/O+ Mem- BusMaster- SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR+ FastB2B-
Status: Cap- 66MHz- UDF- FastB2B+ ParErr- DEVSEL=medium >TAbort- <TAbort- <MAbort- >SERR- <PERR-
Interrupt: pin B routed to IRQ 19
Region 4: I/O ports at 1100 [size=32]
0d:00.0 Ethernet controller: Intel Corporation 82573E Gigabit Ethernet Controller (Copper) (rev 03)
Subsystem: Super Micro Computer Inc Unknown device 108c
Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR+ FastB2B-
Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR-
Latency: 0, Cache Line Size: 64 bytes
Interrupt: pin A routed to IRQ 379
Region 0: Memory at ee100000 (32-bit, non-prefetchable) [size=128K]
Region 2: I/O ports at 4000 [size=32]
Capabilities: [c8] Power Management version 2
Flags: PMEClk- DSI+ D1- D2- AuxCurrent=0mA PME(D0+,D1-,D2-,D3hot+,D3cold+)
Status: D0 PME-Enable- DSel=0 DScale=1 PME-
Capabilities: [d0] Message Signalled Interrupts: Mask- 64bit+ Queue=0/0 Enable+
Address: 00000000fee0f00c Data: 41b1
Capabilities: [e0] Express Endpoint IRQ 0
Device: Supported: MaxPayload 256 bytes, PhantFunc 0, ExtTag-
Device: Latency L0s <512ns, L1 <64us
Device: AtnBtn- AtnInd- PwrInd-
Device: Errors: Correctable- Non-Fatal- Fatal- Unsupported-
Device: RlxdOrd+ ExtTag- PhantFunc- AuxPwr- NoSnoop+
Device: MaxPayload 128 bytes, MaxReadReq 512 bytes
Link: Supported Speed 2.5Gb/s, Width x1, ASPM unknown, Port 0
Link: Latency L0s <128ns, L1 <64us
Link: ASPM Disabled RCB 64 bytes CommClk- ExtSynch-
Link: Speed 2.5Gb/s, Width x1
Capabilities: [100] Advanced Error Reporting
Capabilities: [140] Device Serial Number 2c-94-93-ff-ff-48-30-00
0e:00.0 Ethernet controller: Intel Corporation 82573L Gigabit Ethernet Controller
Subsystem: Super Micro Computer Inc Unknown device 109a
Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR+ FastB2B-
Status: Cap+ 66MHz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR-
Latency: 0, Cache Line Size: 64 bytes
Interrupt: pin A routed to IRQ 378
Region 0: Memory at ee200000 (32-bit, non-prefetchable) [size=128K]
Region 2: I/O ports at 5000 [size=32]
Capabilities: [c8] Power Management version 2
Flags: PMEClk- DSI+ D1- D2- AuxCurrent=0mA PME(D0+,D1-,D2-,D3hot+,D3cold+)
Status: D0 PME-Enable- DSel=0 DScale=1 PME-
Capabilities: [d0] Message Signalled Interrupts: Mask- 64bit+ Queue=0/0 Enable+
Address: 00000000fee0f00c Data: 41b9
Capabilities: [e0] Express Endpoint IRQ 0
Device: Supported: MaxPayload 256 bytes, PhantFunc 0, ExtTag-
Device: Latency L0s <512ns, L1 <64us
Device: AtnBtn- AtnInd- PwrInd-
Device: Errors: Correctable- Non-Fatal- Fatal- Unsupported-
Device: RlxdOrd+ ExtTag- PhantFunc- AuxPwr- NoSnoop+
Device: MaxPayload 128 bytes, MaxReadReq 512 bytes
Link: Supported Speed 2.5Gb/s, Width x1, ASPM unknown, Port 0
Link: Latency L0s <128ns, L1 <64us
Link: ASPM Disabled RCB 64 bytes CommClk- ExtSynch-
Link: Speed 2.5Gb/s, Width x1
Capabilities: [100] Advanced Error Reporting
Capabilities: [140] Device Serial Number 2d-94-93-ff-ff-48-30-00
0f:00.0 VGA compatible controller: XGI - Xabre Graphics Inc Volari Z7 (prog-if 00 [VGA])
Subsystem: Super Micro Computer Inc Unknown device 8580
Control: I/O+ Mem+ BusMaster- SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B-
Status: Cap+ 66MHz+ UDF- FastB2B- ParErr- DEVSEL=medium >TAbort- <TAbort- <MAbort- >SERR- <PERR-
BIST result: 00
Region 0: Memory at ef000000 (32-bit, prefetchable) [size=16M]
Region 1: Memory at ee300000 (32-bit, non-prefetchable) [size=256K]
Region 2: I/O ports at 6000 [size=128]
Capabilities: [40] Power Management version 2
Flags: PMEClk- DSI- D1+ D2+ AuxCurrent=0mA PME(D0-,D1-,D2-,D3hot-,D3cold-)
Status: D0 PME-Enable- DSel=0 DScale=0 PME-
^ permalink raw reply
* Re: hard hang through qdisc
From: Patrick McHardy @ 2008-01-31 15:12 UTC (permalink / raw)
To: Andi Kleen; +Cc: hadi, netdev
In-Reply-To: <200801311604.28110.ak@suse.de>
Andi Kleen wrote:
>> Works for me:
>>
>> qdisc tbf 8001: root rate 1000bit burst 10b/8 mpu 0b lat 720.0ms
>> Sent 0 bytes 0 pkt (dropped 9, overlimits 0 requeues 0)
>> rate 0bit 0pps backlog 0b 0p requeues 0
>>
>> Packets are dropped as expected.
>
> I can still reproduce it on 64bit with http://halobates.de/config-qdisc
> (all qdiscs etc. compiled in for testing)
> with latest git tip (8af03e782cae1e0a0f530ddd22301cdd12cf9dc0)
>
> The command line above causes an instant hang. Also tried it with
> newer iproute2 (the original one was quite old), but it didn't make
> a difference.
>
> Perhaps it's related to what qdiscs are enabled?
I'm also testing on 64 bit, with all qdiscs enabled as modules.
> Can you please try with the above config?
I'll give it a try later.
^ permalink raw reply
* [PATCH][NETFILTER]: Ipv6-related xt_hashlimit compilation fix.
From: Pavel Emelyanov @ 2008-01-31 15:11 UTC (permalink / raw)
To: Patrick McHardy; +Cc: Linux Netdev List, devel
The hashlimit_ipv6_mask() is called from under IP6_NF_IPTABLES
config option, but is not under it by itself.
gcc warns us about it :) :
net/netfilter/xt_hashlimit.c:473: warning: ‘hashlimit_ipv6_mask’ defined but not used
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
---
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index 54aaf5b..744c7f2 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -469,6 +469,7 @@ static inline __be32 maskl(__be32 a, unsigned int l)
return htonl(ntohl(a) & ~(~(u_int32_t)0 >> l));
}
+#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
static void hashlimit_ipv6_mask(__be32 *i, unsigned int p)
{
switch (p) {
@@ -503,6 +504,7 @@ static void hashlimit_ipv6_mask(__be32 *i, unsigned int p)
break;
}
}
+#endif
static int
hashlimit_init_dst(const struct xt_hashlimit_htable *hinfo,
^ permalink raw reply related
* Re: hard hang through qdisc
From: Andi Kleen @ 2008-01-31 15:04 UTC (permalink / raw)
To: Patrick McHardy; +Cc: hadi, netdev
In-Reply-To: <47A1D4F2.6080904@trash.net>
> Works for me:
>
> qdisc tbf 8001: root rate 1000bit burst 10b/8 mpu 0b lat 720.0ms
> Sent 0 bytes 0 pkt (dropped 9, overlimits 0 requeues 0)
> rate 0bit 0pps backlog 0b 0p requeues 0
>
> Packets are dropped as expected.
I can still reproduce it on 64bit with http://halobates.de/config-qdisc
(all qdiscs etc. compiled in for testing)
with latest git tip (8af03e782cae1e0a0f530ddd22301cdd12cf9dc0)
The command line above causes an instant hang. Also tried it with
newer iproute2 (the original one was quite old), but it didn't make
a difference.
Perhaps it's related to what qdiscs are enabled? Can you please
try with the above config?
If everything fails I can do a bisect later.
-Andi
^ permalink raw reply
* Re: [PATCH 0/6] preparations to enable netdevice notifiers inside a namespace (resend)
From: Daniel Lezcano @ 2008-01-31 14:58 UTC (permalink / raw)
To: Denis V. Lunev; +Cc: David Miller, Linux Containers, netdev
In-Reply-To: <47A1B835.7050600@sw.ru>
Denis V. Lunev wrote:
> Here are some preparations and cleanups to enable network device/inet
> address notifiers inside a namespace.
>
> This set of patches has been originally sent last Friday. One cleanup
> patch from the original series is dropped as wrong, thanks to Daniel
> Lezcano.
Can you explain please.
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox