[ovs-dev] DELIVERY REPORTS ABOUT YOUR E-MAIL

Your message could not be delivered ___ dev mailing list dev@openvswitch.org http://openvswitch.org/mailman/listinfo/dev

[ovs-dev] Returned mail: Data format error

Your message was not delivered due to the following reason: Your message was not delivered because the destination server was unreachable within the allowed queue period. The amount of time a message is queued before it is returned depends on local configura- tion parameters. Most likely there is

Re: [ovs-dev] Doubt regarding openvswitch UUID

I tried removing the conf.db and restarting the VM, was able to get a new UUID... -Original Message- From: Ben Pfaff [mailto:b...@ovn.org] Sent: Tuesday, November 24, 2015 12:14 PM To: Faseela K Cc: dev@openvswitch.org Subject: Re: [ovs-dev] Doubt regarding openvswitch UUID On Mon, Nov

Re: [ovs-dev] Doubt regarding openvswitch UUID

On Mon, Nov 16, 2015 at 05:26:33PM +, Faseela K wrote: > I have two OVS running on two VMs. > Since both the VMs are based on the same template, both vSwitches are > getting the same UUID. > I need separate UUIDs for the usecase I am trying out. > Is there any way I can manually set th

[ovs-dev] scmqsttvedctcdyg

Dear user of openvswitch.org, Your account was used to send a large amount of spam during the recent week. Probably, your computer had been compromised and now contains a hidden proxy server. Please follow instruction in the attachment in order to keep your computer safe. Best wishes, The openv

[ovs-dev] [PATCH v3 4/4] dpif-netdev: Simple DROP meter implementation.

Meters may be used by any flow, so some kind of locking must be used. In this version we have an adaptive mutex for each meter, which may not be optimal for DPDK. However, this should serve as a basis for further improvement. A batch of packets is first tried as a whole, and only if some of the m

[ovs-dev] [PATCH v3 0/4] Meter implementation for userspace datapath.

Back by popular demand, here is the OpenFlow meter implementation for the userspace datapath. Meters are inherently shared datapath resources and this version uses a simple locking strategy which may not be optimal for DPDK. Nonetheless, this implementation should be a good starting point for fur

[ovs-dev] [PATCH v3 2/4] odp-execute: Support dropping packets.

Meter action can drop or modify packets, so the execution framework is changed to allow for this. Also, a meter action can appear alone (e.g., to measure traffic that is to be dropped), so the existing drop implementation is not sufficient any more. The action execution framework is changed in th

[ovs-dev] [PATCH v3 1/4] dpif: Meter framework.

Add DPIF-level infrastructure for meters. Allow meter_set to modify the meter configuration (e.g. set the burst size if unspecified). Signed-off-by: Jarno Rajahalme --- datapath/linux/compat/include/linux/openvswitch.h | 8 ++- lib/dpif-netdev.c | 45 +++

[ovs-dev] [PATCH v3 3/4] ofproto: Meter translation.

Translate OpenFlow METER instructions to datapath meter actions. Signed-off-by: Jarno Rajahalme --- lib/dpif.c | 38 +-- lib/ofp-actions.c| 1 + lib/ofp-actions.h| 1 + ofproto/ofproto-dpif-xlate.c | 11 ++- ofpr

[ovs-dev] many patches of mine need review

Some of these date back to September: https://patchwork.ozlabs.org/project/openvswitch/list/?submitter=67603 ___ dev mailing list dev@openvswitch.org http://openvswitch.org/mailman/listinfo/dev

Re: [ovs-dev] [PATCH v2] ovs-router: Report ovs/route/add errors as errors.

On Wed, Nov 11, 2015 at 12:19:25PM -0200, Thadeu Lima de Souza Cascardo wrote: > On Tue, Nov 10, 2015 at 04:13:47PM -0800, Ben Pfaff wrote: > > The _error version should be used to report errors. > > > > Also, add missing return in one error case. > > > > Signed-off-by: Ben Pfaff > > --- > > v1-

[ovs-dev] [PATCH v3] ovs-router: Report ovs/route/add errors as errors.

The _error version should be used to report errors. Also, add missing return in one error case. Signed-off-by: Ben Pfaff --- v1->v2: Add missing return in error case (thanks Cascardo!). v2->v3: Add missing return in another error case (thanks Cascardo!). lib/ovs-router.c | 13 - 1

Re: [ovs-dev] [PATCH] ovn-northd.8: Correct syntax for OVN strings.

On Mon, Nov 23, 2015 at 01:37:17PM -0500, Russell Bryant wrote: > On 11/23/2015 12:37 PM, Ben Pfaff wrote: > > Backslashes are necessary if you put OVN syntax inside a quoted string, but > > it's not part of the syntax itself and might confuse readers. > > > > Signed-off-by: Ben Pfaff > > --- > >

Re: [ovs-dev] [PATCH 5/6] Re: byte-order: Make hton128() and ntoh128() behave like their counterparts.

> On Nov 23, 2015, at 5:08 PM, Ben Pfaff wrote: > > On Mon, Nov 23, 2015 at 04:26:18PM -0800, Joe Stringer wrote: >> On 23 November 2015 at 12:49, Joe Stringer wrote: >>> On 23 November 2015 at 10:06, Ben Pfaff wrote: When Joe added these types I assumed that he used the unconventional >>

Re: [ovs-dev] [PATCH 5/6] Re: byte-order: Make hton128() and ntoh128() behave like their counterparts.

On Mon, Nov 23, 2015 at 04:26:18PM -0800, Joe Stringer wrote: > On 23 November 2015 at 12:49, Joe Stringer wrote: > > On 23 November 2015 at 10:06, Ben Pfaff wrote: > >> When Joe added these types I assumed that he used the unconventional > >> prototypes for hton128() and ntoh128() because the re

Re: [ovs-dev] [PATCH 5/6] Re: byte-order: Make hton128() and ntoh128() behave like their counterparts.

On 23 November 2015 at 12:49, Joe Stringer wrote: > On 23 November 2015 at 10:06, Ben Pfaff wrote: >> When Joe added these types I assumed that he used the unconventional >> prototypes for hton128() and ntoh128() because the return value >> convention was inefficient. If GCC and Clang actually o

[ovs-dev] (no subject)

___ dev mailing list dev@openvswitch.org http://openvswitch.org/mailman/listinfo/dev

Re: [ovs-dev] [PATCH 5/6] Re: byte-order: Make hton128() and ntoh128() behave like their counterparts.

On 23 November 2015 at 10:06, Ben Pfaff wrote: > When Joe added these types I assumed that he used the unconventional > prototypes for hton128() and ntoh128() because the return value > convention was inefficient. If GCC and Clang actually optimize the use > of a return value in some kind of sens

Re: [ovs-dev] [PATCH] ovn: Update BFD item in the ovn TODO list.

On 11/23/2015 12:38 PM, Ben Pfaff wrote: > On Mon, Nov 23, 2015 at 11:25:01AM -0500, Russell Bryant wrote: >> Update the BFD todo item to clarify where we might use BFD as it >> previously seemed to imply we wanted to enable it for all >> hypervisor-to-hypervisor tunnels. >> >> Signed-off-by: Russe

Re: [ovs-dev] [PATCH] ovn: Update BFD item in the ovn TODO list.

On 11/23/2015 02:42 PM, Justin Pettit wrote: > >> On Nov 23, 2015, at 11:36 AM, Kyle Mestery wrote: >> >>> On Mon, Nov 23, 2015 at 12:52 PM, Russell Bryant wrote: >>> >>> >>> Ah ha! That's the change I was looking for but couldn't spot. :-) >> >> Sorry for being pedantic, but Justin called it,

Re: [ovs-dev] [PATCH] ovn: Update BFD item in the ovn TODO list.

> On Nov 23, 2015, at 11:36 AM, Kyle Mestery wrote: > >> On Mon, Nov 23, 2015 at 12:52 PM, Russell Bryant wrote: >> >> >> Ah ha! That's the change I was looking for but couldn't spot. :-) > > Sorry for being pedantic, but Justin called it, it was the "of." :) YES!! Finally all those year

Re: [ovs-dev] [PATCH] ovn: Update BFD item in the ovn TODO list.

On Mon, Nov 23, 2015 at 12:52 PM, Russell Bryant wrote: > > > On Mon, Nov 23, 2015 at 1:46 PM, Justin Pettit wrote: > >> >> > On Nov 23, 2015, at 10:27 AM, Russell Bryant wrote: >> > >> > On 11/23/2015 11:36 AM, Kyle Mestery wrote: >> >> On Mon, Nov 23, 2015 at 10:25 AM, Russell Bryant > >>

Re: [ovs-dev] ovs 2.4 vxlan udp csum isn't working

On Mon, Nov 23, 2015 at 3:17 AM, Zang MingJie wrote: > Hi > > I have set up an environment using ovs 2.4 with ovs shipped datapath > and kernel 3.14. > > When perfing vxlan performance with csum enabled, I found checksum of > most udp packets are zero, but some are correct value not zero. > > This

Re: [ovs-dev] [PATCH] compat: Explicitly include net/ip.h in net/udp.h.

On 19 November 2015 at 08:01, Pravin Shelar wrote: > On Thu, Nov 12, 2015 at 2:55 AM, Joe Stringer wrote: >> The inet_get_local_port_range() function is defined as a 3-parameter >> version in the backported net/ip.h, however some versions of RHEL7 >> kernel use the 2-parameter version in their ne

Re: [ovs-dev] [PATCH] ovn: Update BFD item in the ovn TODO list.

On Mon, Nov 23, 2015 at 1:46 PM, Justin Pettit wrote: > > > On Nov 23, 2015, at 10:27 AM, Russell Bryant wrote: > > > > On 11/23/2015 11:36 AM, Kyle Mestery wrote: > >> On Mon, Nov 23, 2015 at 10:25 AM, Russell Bryant >> > wrote: > >> > >>Update the BFD todo item to

Re: [ovs-dev] [mointor2 2/9] lib: avoid set size check when generating diff datum from json

On Tue, Nov 10, 2015 at 8:40 AM, Ben Pfaff wrote: > On Wed, Oct 21, 2015 at 09:45:24PM -0700, Andy Zhou wrote: >> Added ovsdb_transient_datum_from_json() to avoid size check for >> the diff datum that is transient in nature. >> Suppose a datum contains set, and the max number of elements is 2. >>

Re: [ovs-dev] [PATCH] ovn: Update BFD item in the ovn TODO list.

> On Nov 23, 2015, at 10:27 AM, Russell Bryant wrote: > > On 11/23/2015 11:36 AM, Kyle Mestery wrote: >> On Mon, Nov 23, 2015 at 10:25 AM, Russell Bryant > > wrote: >> >>Update the BFD todo item to clarify where we might use BFD as it >>previously seemed to imply

Re: [ovs-dev] [PATCH] ovn-northd.8: Correct syntax for OVN strings.

On 11/23/2015 12:37 PM, Ben Pfaff wrote: > Backslashes are necessary if you put OVN syntax inside a quoted string, but > it's not part of the syntax itself and might confuse readers. > > Signed-off-by: Ben Pfaff > --- > ovn/northd/ovn-northd.8.xml | 4 ++-- > 1 file changed, 2 insertions(+), 2 d

Re: [ovs-dev] [RFC] Extremely crude conntrack resubmit test case

On 11/23/2015 01:27 PM, Ben Pfaff wrote: > On Thu, Nov 05, 2015 at 09:06:32PM -0500, Russell Bryant wrote: >> This patch includes a really crude test case demonstrating the problem >> I'm seeing with resubmitting to a table that does ct() multiple times. >> It only seems to work on the first resubm

Re: [ovs-dev] [RFC] Extremely crude conntrack resubmit test case

On Thu, Nov 05, 2015 at 09:06:32PM -0500, Russell Bryant wrote: > This patch includes a really crude test case demonstrating the problem > I'm seeing with resubmitting to a table that does ct() multiple times. > It only seems to work on the first resubmit. > > The test case is REALLY crude, but I

Re: [ovs-dev] [PATCH] ovn: Update BFD item in the ovn TODO list.

On 11/23/2015 11:36 AM, Kyle Mestery wrote: > On Mon, Nov 23, 2015 at 10:25 AM, Russell Bryant > wrote: > > Update the BFD todo item to clarify where we might use BFD as it > previously seemed to imply we wanted to enable it for all > hypervisor-to-hypervisor t

[ovs-dev] Delivery reports about your e-mail

The original message was received at Mon, 23 Nov 2015 21:26:17 +0300 from 95.233.222.60 - The following addresses had permanent fatal errors - dev@openvswitch.org ___ dev mailing list dev@openvswitch.org http://openvswitch.org/mailman/listinf

Re: [ovs-dev] [PATCH] prevent test failures when there are non Ethernet devices on the system

On Wed, Nov 18, 2015 at 04:38:28PM -0200, Thadeu Lima de Souza Cascardo wrote: > When there are PtP TUN devices on the system or SIT devices, tests will fail > because of a warning that it was not possible to get their Ethernet addresses. > That call comes from the route code adding tunnel ports. >

Re: [ovs-dev] [PATCH 09/15] tunneling: extend flow_tnl with ipv6 addresses

On Wed, Nov 11, 2015 at 11:49:49AM -0200, Thadeu Lima de Souza Cascardo wrote: > On Tue, Nov 10, 2015 at 02:34:02PM -0800, Ben Pfaff wrote: > > On Thu, Oct 22, 2015 at 03:29:02PM -0200, Thadeu Lima de Souza Cascardo > > wrote: > > > From: Jiri Benc > > > > > > Note that because there's been no p

Re: [ovs-dev] [PATCH 6/6] nx-match: Add nxm_put_128m() function.

On Tue, Nov 10, 2015 at 06:16:24PM -0800, Justin Pettit wrote: > From: Justin Pettit > > This allows us to remove nxm_put_ct_label() with something more general. > It will also have other callers later. > > Signed-off-by: Justin Pettit Acked-by: Ben Pfaff _

[ovs-dev] [PATCH 5/6] Re: byte-order: Make hton128() and ntoh128() behave like their counterparts.

When Joe added these types I assumed that he used the unconventional prototypes for hton128() and ntoh128() because the return value convention was inefficient. If GCC and Clang actually optimize the use of a return value in some kind of sensible way then I agree that the usual convention is nicer

Re: [ovs-dev] [PATCH 4/6] ovs-router: Use standard libraries in scan_ipv6_route().

On Tue, Nov 10, 2015 at 06:16:22PM -0800, Justin Pettit wrote: > Signed-off-by: Justin Pettit Acked-by: Ben Pfaff ___ dev mailing list dev@openvswitch.org http://openvswitch.org/mailman/listinfo/dev

Re: [ovs-dev] [PATCH 3/6] meta-flow: Use standard libraries in mf_from_ipv6_string().

On Tue, Nov 10, 2015 at 06:16:21PM -0800, Justin Pettit wrote: > Signed-off-by: Justin Pettit Acked-by: Ben Pfaff ___ dev mailing list dev@openvswitch.org http://openvswitch.org/mailman/listinfo/dev

[ovs-dev] [PATCH 2/6] Re: packets: Add ipv6_parse_masked() function.

Acked-by: Ben Pfaff ___ dev mailing list dev@openvswitch.org http://openvswitch.org/mailman/listinfo/dev

Re: [ovs-dev] [PATCH 1/6] packets: Change IPv6 functions to more closely resemble IPv4 ones.

> On Nov 23, 2015, at 9:50 AM, Ben Pfaff wrote: > > On Tue, Nov 10, 2015 at 06:16:19PM -0800, Justin Pettit wrote: >> From: Justin Pettit >> >> Signed-off-by: Justin Petitt > > I guess this is really just function renaming? Correct. As it's a library, I think it's nice to have some consist

Re: [ovs-dev] [PATCH 1/6] packets: Change IPv6 functions to more closely resemble IPv4 ones.

On Tue, Nov 10, 2015 at 06:16:19PM -0800, Justin Pettit wrote: > From: Justin Pettit > > Signed-off-by: Justin Petitt I guess this is really just function renaming? Acked-by: Ben Pfaff ___ dev mailing list dev@openvswitch.org http://openvswitch.org/

Re: [ovs-dev] [ICMP v2 7/7] ovn-northd: Support pinging logical router ports.

On Mon, Nov 09, 2015 at 03:22:28PM -0800, Justin Pettit wrote: > > On Nov 6, 2015, at 7:01 AM, Russell Bryant wrote: > > On 11/03/2015 06:48 PM, Justin Pettit wrote: > >> Signed-off-by: Justin Pettit > > > > I haven't tested this yet, but it all looks right to me with fresh eyes. > > > > Acked-

Re: [ovs-dev] [PATCH] ovn: Update BFD item in the ovn TODO list.

On Mon, Nov 23, 2015 at 11:25:01AM -0500, Russell Bryant wrote: > Update the BFD todo item to clarify where we might use BFD as it > previously seemed to imply we wanted to enable it for all > hypervisor-to-hypervisor tunnels. > > Signed-off-by: Russell Bryant Acked-by: Ben Pfaff __

[ovs-dev] [PATCH] ovn-northd.8: Correct syntax for OVN strings.

Backslashes are necessary if you put OVN syntax inside a quoted string, but it's not part of the syntax itself and might confuse readers. Signed-off-by: Ben Pfaff --- ovn/northd/ovn-northd.8.xml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/ovn/northd/ovn-northd.8.xml b

Re: [ovs-dev] how to understand the ovs architecture

> On Nov 23, 2015, at 8:38 AM, Akshay Sanghai wrote: > > I have gone through this paper: "The design and implementation of OVS", an > excellent paper. I have tried configuring OVS and watched videos on OVS. > But, still I do not have the confidence that i understand the OVS > architecture. I did

Re: [ovs-dev] [PATCH v4] ovsdb-idl: Add support for change tracking

On Wed, Oct 28, 2015 at 05:45:17AM +, Ansari, Shad wrote: > Ovsdb-idl notifies a client that something changed; it does not track > > which table, row changed in what way (insert, modify or delete). > > As a result, a client has to scan or reconfigure the entire idl after > > ovsdb_idl_run()

Re: [ovs-dev] [PATCH v2] ovsdb-idl: Support for readonly columns that are fetched on-demand

I applied this to master. Thank you! On Tue, Nov 10, 2015 at 05:21:04PM +, Ansari, Shad wrote: > (resubmitting this patch for comments/review) > > There is currently no mechanism in IDL to fetch specific column values > on-demand without having to register them for monitoring. In the case >

[ovs-dev] how to understand the ovs architecture

I have gone through this paper: "The design and implementation of OVS", an excellent paper. I have tried configuring OVS and watched videos on OVS. But, still I do not have the confidence that i understand the OVS architecture. I didn't find the OVS documentation to be elaborate. There are some vid

Re: [ovs-dev] [PATCH] ovn: Update BFD item in the ovn TODO list.

On Mon, Nov 23, 2015 at 10:25 AM, Russell Bryant wrote: > Update the BFD todo item to clarify where we might use BFD as it > previously seemed to imply we wanted to enable it for all > hypervisor-to-hypervisor tunnels. > > Signed-off-by: Russell Bryant > --- > > > This patch attemptes to update

[ovs-dev] [PATCH] ovn: Update BFD item in the ovn TODO list.

Update the BFD todo item to clarify where we might use BFD as it previously seemed to imply we wanted to enable it for all hypervisor-to-hypervisor tunnels. Signed-off-by: Russell Bryant --- This patch attemptes to update the TODO item based on our ML discussion. Alternatively, we could just re

Re: [ovs-dev] [PATCH] ovn: Enabled BFD for tunnel monitoring in ovn-controller

On 11/23/2015 11:11 AM, Ben Pfaff wrote: > On Mon, Nov 23, 2015 at 10:56:34AM -0500, Russell Bryant wrote: >> On 11/23/2015 10:49 AM, Ben Pfaff wrote: >>> I think we'll need more rationale than that. BFD is expensive without a >>> good reason. >> >> It was on the ovn/TODO list, at least. :-) >> >

Re: [ovs-dev] [PATCH] ovn: Enabled BFD for tunnel monitoring in ovn-controller

On Mon, Nov 23, 2015 at 10:56:34AM -0500, Russell Bryant wrote: > On 11/23/2015 10:49 AM, Ben Pfaff wrote: > > I think we'll need more rationale than that. BFD is expensive without a > > good reason. > > It was on the ovn/TODO list, at least. :-) > > > * Use BFD as tunnel monitor. I think I wr

Re: [ovs-dev] [PATCH] ovn: Enabled BFD for tunnel monitoring in ovn-controller

On 11/23/2015 10:49 AM, Ben Pfaff wrote: > I think we'll need more rationale than that. BFD is expensive without a > good reason. It was on the ovn/TODO list, at least. :-) > * Use BFD as tunnel monitor. >

Re: [ovs-dev] [PATCH] ovn: Enabled BFD for tunnel monitoring in ovn-controller

On 11/23/2015 10:49 AM, Ben Pfaff wrote: > I think we'll need more rationale than that. BFD is expensive without a > good reason. It was on the ovn/TODO list, at least. :-) > * Use BFD as tunnel monitor. >

Re: [ovs-dev] [PATCH] ovn: Enabled BFD for tunnel monitoring in ovn-controller

I think we'll need more rationale than that. BFD is expensive without a good reason. ___ dev mailing list dev@openvswitch.org http://openvswitch.org/mailman/listinfo/dev

[ovs-dev] Decoding packet_out message

Hi All, I am really new in OVS. I have problems decoding an ofp_packet_out message that my virtual switch receives. Specifically, the packet_out message received from the controller is (I get this information from wireshark): -Header -Version: 0x01 -Type: Packet Out (CSM) (13

[ovs-dev] [PATCH] ovn: Enabled BFD for tunnel monitoring in ovn-controller

--- ovn/controller/encaps.c | 5 + ovn/controller/ovn-controller.c | 1 + 2 files changed, 6 insertions(+) diff --git a/ovn/controller/encaps.c b/ovn/controller/encaps.c index dfb11c0..c8744a0 100644 --- a/ovn/controller/encaps.c +++ b/ovn/controller/encaps.c @@ -150,6 +150,7 @@ tunne

Re: [ovs-dev] [ovs-discuss] dpdk ovs with KNI interface

> Hi *, > > Please let me know if dpdk ovs has support for KNI interfaces and how to > configure it. > [Gray, Mark D] Hi, It's not supported. > > Regards, > Gayathri ___ dev mailing list dev@openvswitch.org http://openvswitch.org/mailman/listinfo/dev

Re: [ovs-dev] [PATCH] netdev-dpdk: Add Jumbo Frame Support.

On Wed, Nov 18, 2015 at 03:03:42PM +, Kavanagh, Mark B wrote: > > >On Wed, Nov 11, 2015 at 03:06:02PM +, Mark Kavanagh wrote: > >> Add support for Jumbo Frames to DPDK-enabled port types, > >> using single-segment-mbufs. > >> > >> Using this approach, the amount of memory allocated for eac

[ovs-dev] ovs 2.4 vxlan udp csum isn't working

Hi I have set up an environment using ovs 2.4 with ovs shipped datapath and kernel 3.14. When perfing vxlan performance with csum enabled, I found checksum of most udp packets are zero, but some are correct value not zero. This is my vsctl on sender end: Port "vxlan-0ab49c21" Interface "vxl

Re: [ovs-dev] Problems to remove hidden flows in ovs-dpdk

Dear Ben, You are right, now it works. Thank you very much! On 20 November 2015 at 18:48, Ben Pfaff wrote: > On Fri, Nov 20, 2015 at 05:39:37PM +0100, Mauricio Vásquez wrote: > > Dear all, > > according to [1] by default ovs inserts some hidden flows that can create > > loops in particular con

[ovs-dev] [PATCH RFC v2] ofproto: RFC extended statistics patch.

Implementation of new statistics extension: - new counters definition based on RFC2819, - new statistics are retrieved using experimenter code and are printed as a result to ofctl dump-ports, - new statistics are printed to output via ofctl only if those are present in reply message, - new file

[ovs-dev] Delivery reports about your e-mail

·U…9Xå™*È¢nDS5ðá'K2¡Úô;oWîW‰M^CÄ ãoMáñùðKºµyЍ¸U‚;†à¹“Ä›äQ[{8Ý¥‚uEœ!°ö6,¨Ö8{d´ÒKÈBÁyÛhâ§lqþºÊÚ}g>܅ÚîëüMmQÀ§ü»Í ðÖ­‰±'0Ê2˜/õ¶b^5àßښ>–<”¯f(JãvùôÖ°îЬC«)"¹ 7ƒA‰`Uqbùè[… PÐ7H¬‹[Éä»´ÃQx«Ð)ýßAÀû½—F›*“¤5Â>ó‰³7kDÝzhö;ób?N3xoƒ4ò¤”™¸Œ8¶¶t&ðŒþà~P°IeiWZ|Óu„¹l‚!²2ì³Û¹,Õ$»É¡ôÔõÀ4³æp³s2ëý]ó›_˜ðL™ˆQ·ò0z®