android_kernel_motorola_sm6225/net/core
Ilpo Järvinen 832d11c5cd tcp: Try to restore large SKBs while SACK processing
During SACK processing, most of the benefits of TSO are eaten by
the SACK blocks that one-by-one fragment SKBs to MSS sized chunks.
Then we're in problems when cleanup work for them has to be done
when a large cumulative ACK comes. Try to return back to pre-split
state already while more and more SACK info gets discovered by
combining newly discovered SACK areas with the previous skb if
that's SACKed as well.

This approach has a number of benefits:

1) The processing overhead is spread more equally over the RTT
2) Write queue has less skbs to process (affect everything
   which has to walk in the queue past the sacked areas)
3) Write queue is consistent whole the time, so no other parts
   of TCP has to be aware of this (this was not the case with
   some other approach that was, well, quite intrusive all
   around).
4) Clean_rtx_queue can release most of the pages using single
   put_page instead of previous PAGE_SIZE/mss+1 calls

In case a hole is fully filled by the new SACK block, we attempt
to combine the next skb too which allows construction of skbs
that are even larger than what tso split them to and it handles
hole per on every nth patterns that often occur during slow start
overshoot pretty nicely. Though this to be really useful also
a retransmission would have to get lost since cumulative ACKs
advance one hole at a time in the most typical case.

TODO: handle upwards only merging. That should be rather easy
when segment is fully sacked but I'm leaving that as future
work item (it won't make very large difference anyway since
this current approach already covers quite a lot of normal
cases).

I was earlier thinking of some sophisticated way of tracking
timestamps of the first and the last segment but later on
realized that it won't be that necessary at all to store the
timestamp of the last segment. The cases that can occur are
basically either:
  1) ambiguous => no sensible measurement can be taken anyway
  2) non-ambiguous is due to reordering => having the timestamp
     of the last segment there is just skewing things more off
     than does some good since the ack got triggered by one of
     the holes (besides some substle issues that would make
     determining right hole/skb even harder problem). Anyway,
     it has nothing to do with this change then.

I choose to route some abnormal looking cases with goto noop,
some could be handled differently (eg., by stopping the
walking at that skb but again). In general, they either
shouldn't happen at all or are rare enough to make no difference
in practice.

In theory this change (as whole) could cause some macroscale
regression (global) because of cache misses that are taken over
the round-trip time but it gets very likely better because of much
less (local) cache misses per other write queue walkers and the
big recovery clearing cumulative ack.

Worth to note that these benefits would be very easy to get also
without TSO/GSO being on as long as the data is in pages so that
we can merge them. Currently I won't let that happen because
DSACK splitting at fragment that would mess up pcounts due to
sk_can_gso in tcp_set_skb_tso_segs. Once DSACKs fragments gets
avoided, we have some conditions that can be made less strict.

TODO: I will probably have to convert the excessive pointer
passing to struct sacktag_state... :-)

My testing revealed that considerable amount of skbs couldn't
be shifted because they were cloned (most likely still awaiting
tx reclaim)...

[The rest is considering future work instead since I got
repeatably EFAULT to tcpdump's recvfrom when I added
pskb_expand_head to deal with clones, so I separated that
into another, later patch]

...To counter that, I gave up on the fifth advantage:

5) When growing previous SACK block, less allocs for new skbs
   are done, basically a new alloc is needed only when new hole
   is detected and when the previous skb runs out of frags space

...which now only happens of if reclaim is fast enough to dispose
the clone before the SACK block comes in (the window is RTT long),
otherwise we'll have to alloc some.

With clones being handled I got these numbers (will be somewhat
worse without that), taken with fine-grained mibs:

                  TCPSackShifted 398
                   TCPSackMerged 877
            TCPSackShiftFallback 320
      TCPSACKCOLLAPSEFALLBACKGSO 0
  TCPSACKCOLLAPSEFALLBACKSKBBITS 0
  TCPSACKCOLLAPSEFALLBACKSKBDATA 0
    TCPSACKCOLLAPSEFALLBACKBELOW 0
    TCPSACKCOLLAPSEFALLBACKFIRST 1
 TCPSACKCOLLAPSEFALLBACKPREVBITS 318
      TCPSACKCOLLAPSEFALLBACKMSS 1
   TCPSACKCOLLAPSEFALLBACKNOHEAD 0
    TCPSACKCOLLAPSEFALLBACKSHIFT 0
          TCPSACKCOLLAPSENOOPSEQ 0
  TCPSACKCOLLAPSENOOPSMALLPCOUNT 0
     TCPSACKCOLLAPSENOOPSMALLLEN 0
             TCPSACKCOLLAPSEHOLE 12

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-24 21:20:15 -08:00
..
datagram.c net: sk_free_datagram() should use sk_mem_reclaim_partial() 2008-11-05 01:38:06 -08:00
dev.c netdev: add more functions to netdevice ops 2008-11-20 20:14:53 -08:00
dev_mcast.c net: Rationalise email address: Network Specific Parts 2008-10-13 19:01:08 -07:00
dst.c net: speedup dst_release() 2008-11-14 00:53:54 -08:00
ethtool.c netdev: Add support for rx flow hash configuration, using ethtool. 2008-07-02 03:47:41 -07:00
fib_rules.c net: fib_rules ordering fixes. 2008-11-07 22:52:34 -08:00
filter.c filter: add SKF_AD_NLATTR_NEST to look for nested attributes 2008-11-20 00:49:27 -08:00
flow.c net: mark flow_cache_cpu_prepare() as __init 2008-11-06 23:06:44 -08:00
gen_estimator.c net: gen_estimator: Fix gen_kill_estimator() lookups 2008-11-24 15:48:05 -08:00
gen_stats.c
iovec.c net: Use standard structures for generic socket address structures. 2008-07-19 22:35:47 -07:00
kmap_skb.h
link_watch.c net: Clean up explicit ->tx_queue references in link watch. 2008-07-08 23:01:06 -07:00
Makefile net: Add SKB DMA mapping helper functions. 2008-09-11 04:51:14 -07:00
neighbour.c netdev: add more functions to netdevice ops 2008-11-20 20:14:53 -08:00
net-sysfs.c netdev: introduce dev_get_stats() 2008-11-19 21:40:23 -08:00
net-sysfs.h netns: Fix device renaming for sysfs 2008-05-02 17:00:58 -07:00
net_namespace.c Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6 2008-10-31 00:17:34 -07:00
netevent.c
netpoll.c netdev: add more functions to netdevice ops 2008-11-20 20:14:53 -08:00
pktgen.c netdev: add more functions to netdevice ops 2008-11-20 20:14:53 -08:00
request_sock.c net: convert BUG_TRAP to generic WARN_ON 2008-07-25 21:43:18 -07:00
rtnetlink.c netdev: introduce dev_get_stats() 2008-11-19 21:40:23 -08:00
scm.c scm: fix scm_fp_list->list initialization made in wrong place 2008-11-14 14:51:45 -08:00
skb_dma_map.c net: Fix off-by-one in skb_dma_map 2008-10-12 21:07:34 -07:00
skbuff.c tcp: Try to restore large SKBs while SACK processing 2008-11-24 21:20:15 -08:00
sock.c net: make /proc/net/protocols namespace aware 2008-11-19 15:14:01 -08:00
stream.c net: Rationalise email address: Network Specific Parts 2008-10-13 19:01:08 -07:00
sysctl_net_core.c net: '&' redux 2008-11-03 18:21:05 -08:00
user_dma.c Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6 2008-07-26 20:17:56 -07:00
utils.c printk ratelimiting rewrite 2008-07-25 10:53:29 -07:00