diff for duplicates of <52D8D544.5050501@nsn.com> diff --git a/a/1.txt b/N1/1.txt index 9b2f28f..629a4b2 100644 --- a/a/1.txt +++ b/N1/1.txt @@ -19,7 +19,7 @@ message in 4G (LTE) network). On B data is left in buffer by not reading socket in userspace. Lets examine when we will hit pressure state and declare rwnd to be 0 for -scenario with above stated parameters (rwnd = 10000, chunk size = 43, each +scenario with above stated parameters (rwnd == 10000, chunk size == 43, each chunk is sent in separate sctp packet) Logic is implemented in sctp_assoc_rwnd_decrease: @@ -108,7 +108,7 @@ size less then sizeof(struct sk_buff) and receiver keeping them in its buffers. 2) Minute size window for associations sharing the same socket buffer In case multiple associations share the same socket, and same socket buffer -(sctp.rcvbuf_policy = 0), different scenarios exist in which congestion on one +(sctp.rcvbuf_policy == 0), different scenarios exist in which congestion on one of the associations can permanently drop rwnd of other association(s). Situation will be typically observed as one association suddenly having rwnd @@ -131,8 +131,8 @@ Scenario happened in the field and labs frequently after congestion state (link breaks, different probabilities of packet drop, packet reordering) and with scenario 1) preceding. Here is given a deterministic scenario for reproduction: -From node A establish two associations on the same socket, with rcvbuf_policy -being set to share one common buffer (sctp.rcvbuf_policy = 0). On association 1 +>From node A establish two associations on the same socket, with rcvbuf_policy +being set to share one common buffer (sctp.rcvbuf_policy == 0). On association 1 repeat scenario from 1), that is, bring it down to 0 and restore up. Observe scenario 1). Use small payload size (here we use 43). Once rwnd is 'recovered', bring it down close to 0, as in just one more packet would close it. This has as diff --git a/a/content_digest b/N1/content_digest index 1188b68..1be82c9 100644 --- a/a/content_digest +++ b/N1/content_digest @@ -1,6 +1,6 @@ "From\0Matija Glavinic Pecotic <matija.glavinic-pecotic.ext@nsn.com>\0" "Subject\0[PATCH] net: sctp: Fix a_rwnd/rwnd management to reflect real state of the receiver's buffer\0" - "Date\0Fri, 17 Jan 2014 07:01:24 +0000\0" + "Date\0Fri, 17 Jan 2014 08:01:24 +0100\0" "To\0linux-sctp@vger.kernel.org\0" "Cc\0Alexander Sverdlin <alexander.sverdlin@nsn.com>" " netdev@vger.kernel.org\0" @@ -27,7 +27,7 @@ "in userspace.\n" "\n" "Lets examine when we will hit pressure state and declare rwnd to be 0 for\n" - "scenario with above stated parameters (rwnd = 10000, chunk size = 43, each\n" + "scenario with above stated parameters (rwnd == 10000, chunk size == 43, each\n" "chunk is sent in separate sctp packet)\n" "\n" "Logic is implemented in sctp_assoc_rwnd_decrease:\n" @@ -116,7 +116,7 @@ "2) Minute size window for associations sharing the same socket buffer\n" "\n" "In case multiple associations share the same socket, and same socket buffer\n" - "(sctp.rcvbuf_policy = 0), different scenarios exist in which congestion on one\n" + "(sctp.rcvbuf_policy == 0), different scenarios exist in which congestion on one\n" "of the associations can permanently drop rwnd of other association(s).\n" "\n" "Situation will be typically observed as one association suddenly having rwnd\n" @@ -139,8 +139,8 @@ "breaks, different probabilities of packet drop, packet reordering) and with \n" "scenario 1) preceding. Here is given a deterministic scenario for reproduction:\n" "\n" - "From node A establish two associations on the same socket, with rcvbuf_policy\n" - "being set to share one common buffer (sctp.rcvbuf_policy = 0). On association 1\n" + ">From node A establish two associations on the same socket, with rcvbuf_policy\n" + "being set to share one common buffer (sctp.rcvbuf_policy == 0). On association 1\n" "repeat scenario from 1), that is, bring it down to 0 and restore up. Observe\n" "scenario 1). Use small payload size (here we use 43). Once rwnd is 'recovered',\n" "bring it down close to 0, as in just one more packet would close it. This has as\n" @@ -437,4 +437,4 @@ " \tsctp_ulpevent_release_owner(event);\n" } -6b9691919915594aed9a43230ce3407a4d76daff49ed75538b9d1a88f9ac4267 +751154cfb3cc157c3afc5a2474405740f680ccd3dd936e5094915d9ce11b0e8d
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.