diff options
author | Vlad Yasevich <vladislav.yasevich@hp.com> | 2009-08-07 13:23:28 -0400 |
---|---|---|
committer | Vlad Yasevich <vladislav.yasevich@hp.com> | 2009-09-04 18:20:56 -0400 |
commit | 5d7ff261ef497c62f54c39effc259910a28b313d (patch) | |
tree | 78eca9144bafc85c65cfdf19e5c8c5dffbd271f4 /net/sctp/chunk.c | |
parent | e83963b769a2c38b436f5dcf82309f5cbc2f6012 (diff) | |
download | kernel_samsung_espresso10-5d7ff261ef497c62f54c39effc259910a28b313d.zip kernel_samsung_espresso10-5d7ff261ef497c62f54c39effc259910a28b313d.tar.gz kernel_samsung_espresso10-5d7ff261ef497c62f54c39effc259910a28b313d.tar.bz2 |
sctp: Try to encourage SACK bundling with DATA.
If the association has a SACK timer pending and now DATA queued
to be send, we'll try to bundle the SACK with the next application send.
As such, try encourage bundling by accounting for SACK in the size
of the first chunk fragment.
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>
Diffstat (limited to 'net/sctp/chunk.c')
-rw-r--r-- | net/sctp/chunk.c | 21 |
1 files changed, 16 insertions, 5 deletions
diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index 9292294..7acaf15 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -207,14 +207,25 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, whole = 0; first_len = max; + /* Check to see if we have a pending SACK and try to let it be bundled + * with this message. Do this if we don't have any data queued already. + * To check that, look at out_qlen and retransmit list. + * NOTE: we will not reduce to account for SACK, if the message would + * not have been fragmented. + */ + if (timer_pending(&asoc->timers[SCTP_EVENT_TIMEOUT_SACK]) && + asoc->outqueue.out_qlen == 0 && + list_empty(&asoc->outqueue.retransmit) && + msg_len > max) + max_data -= WORD_ROUND(sizeof(sctp_sack_chunk_t)); + /* Encourage Cookie-ECHO bundling. */ - if (asoc->state < SCTP_STATE_COOKIE_ECHOED) { + if (asoc->state < SCTP_STATE_COOKIE_ECHOED) max_data -= SCTP_ARBITRARY_COOKIE_ECHO_LEN; - /* This is the biggesr first_len we can have */ - if (first_len > max_data) - first_len = max_data; - } + /* Now that we adjusted completely, reset first_len */ + if (first_len > max_data) + first_len = max_data; /* Account for a different sized first fragment */ if (msg_len >= first_len) { |