Skip to content

L
linux-davinci
Switch branch/tag
  1. 15 Jul, 2008 10 commits
    • Eli Cohen's avatar
      IPoIB: Copy small received SKBs in connected mode · f89271da
      Eli Cohen authored 
      The connected mode implementation in the IPoIB driver has a large
overhead in the way SKBs are handled in the receive flow.  It usually
allocates an SKB with as big as was used in the currently received SKB
and moves unused fragments from the old SKB to the new one. This
involves a loop on all the remaining fragments and incurs overhead on
the CPU.  This patch, for small SKBs, allocates an SKB just large
enough to contain the received data and copies to it the data from the
received SKB.  The newly allocated SKB is passed to the stack and the
old SKB is reposted.

When running netperf, UDP small messages, without this pach I get:

    UDP UNIDIRECTIONAL SEND TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to
    14.4.3.178 (14.4.3.178) port 0 AF_INET
    Socket  Message  Elapsed      Messages
    Size    Size     Time         Okay Errors   Throughput
    bytes   bytes    secs            #      #   10^6bits/sec

    114688     128   10.00     5142034      0     526.31
    114688           10.00     1130489            115.71

With this patch I get both send and receive at ~315 mbps.

The reason that send performance actually slows down is as follows:
When using this patch, the overhead of the CPU for handling RX packets
is dramatically reduced.  As a result, we do not experience RNR NAK
messages from the receiver which cause the connection to be closed and
reopened again; when the patch is not used, the receiver cannot handle
the packets fast enough so there is less time to post new buffers and
hence the mentioned RNR NACKs.  So what happens is that the
application *thinks* it posted a certain number of packets for
transmission but these packets are flushed and do not really get
transmitted.  Since the connection gets opened and closed many times,
each time netperf gets the CPU time that otherwise would have been
given to IPoIB to actually transmit the packets.  This can be verified
when looking at the port counters -- the output of ifconfig and the
oputput of netperf (this is for the case without the patch):

    tx packets
    ==========
    port counter:   1,543,996
    ifconfig:       1,581,426
    netperf:        5,142,034

    rx packets
    ==========
    netperf         1,1304,089
Signed-off-by: default avatarEli Cohen <eli@mellanox.co.il>
      f89271da
    • Roland Dreier's avatar
      RDMA: Remove subversion $Id tags · f3781d2e
      Roland Dreier authored 
      They don't get updated by git and so they're worse than useless.
Signed-off-by: default avatarRoland Dreier <rolandd@cisco.com>
      f3781d2e
    • Dotan Barak's avatar
      RDMA: Improve include file coding style · 4deccd6d
      Dotan Barak authored 
      Remove subversion $Id lines and improve readability by fixing other
coding style problems pointed out by checkpatch.pl.
Signed-off-by: default avatarDotan Barak <dotanba@gmail.com>
Signed-off-by: default avatarRoland Dreier <rolandd@cisco.com>
      4deccd6d
    • Robert P. J. Day's avatar
      IB/ipath: Simplify code using ARRAY_SIZE() macro · fd91b1bf
      Robert P. J. Day authored 
      Signed-off-by: default avatarRobert P. J. Day <rpjday@crashcourse.ca>
Signed-off-by: default avatarRoland Dreier <rolandd@cisco.com>
      fd91b1bf
    • Eli Cohen's avatar
      IB/mlx4: Optimize QP stamping · 9670e553
      Eli Cohen authored 
      The idea is that for QPs with fixed size work requests (eg selective
signaling QPs), before stamping the WQE, we read the value of the DS
field, which gives the effective size of the descriptor as used in the
previous post.  Then we stamp only that area, since the rest of the
descriptor is already stamped.

When initializing the send queue buffer, make sure the DS field is
initialized to the max descriptor size so that the subsequent stamping
will be done on the entire descriptor area.
Signed-off-by: default avatarEli Cohen <eli@mellanox.co.il>
Signed-off-by: default avatarRoland Dreier <rolandd@cisco.com>
      9670e553
    • Moni Shoua's avatar
      IB/sa: Fail requests made while creating new SM AH · 164ba089
      Moni Shoua authored 
      This patch solves a race that occurs after an event occurs that causes
the SA query module to flush its SM address handle (AH).  When SM AH
becomes invalid and needs an update it is handled by the global
workqueue.  On the other hand this event is also handled in the IPoIB
driver by queuing work in the ipoib_workqueue that does multicast
joins.  Although queuing is in the right order, it is done to 2
different workqueues and so there is no guarantee that the first to be
queued is the first to be executed.

This causes a problem because IPoIB may end up sending an request to
the old SM, which will take a long time to time out (since the old SM
is gone); this leads to a much longer than necessary interruption in
multicast traffer.

The patch sets the SA query module's SM AH to NULL when the event
occurs, and until update_sm_ah() is done, any request that needs sm_ah
fails with -EAGAIN return status.

For consumers, the patch doesn't make things worse.  Before the patch,
MADs are sent to the wrong SM so the request gets lost.  Consumers can
be improved if they examine the return code and respond to EAGAIN
properly but even without an improvement the situation is not getting
worse.
Signed-off-by: default avatarMoni Levy <monil@voltaire.com>
Signed-off-by: default avatarMoni Shoua <monis@voltaire.com>
Signed-off-by: default avatarRoland Dreier <rolandd@cisco.com>
      164ba089
    • Sean Hefty's avatar
      RDMA: Fix license text · a9474917
      Sean Hefty authored 
      The license text for several files references a third software license
that was inadvertently copied in.  Update the license to what was
intended.  This update was based on a request from HP.
Signed-off-by: default avatarSean Hefty <sean.hefty@intel.com>
Signed-off-by: default avatarRoland Dreier <rolandd@cisco.com>
      a9474917
    • Christophe Jaillet's avatar
      RDMA/nes: Remove unnecessary memset() · 929555a2
      Christophe Jaillet authored 
      Remove an explicit memset(..., 0, ...) of a 'listener' structure
allocated with kzalloc().
Signed-off-by: default avatarChristophe Jaillet <christophe.jaillet@wanadoo.fr>
Acked-by: default avatarFaisal Latif <faisal@neteffect.com>
Signed-off-by: default avatarRoland Dreier <rolandd@cisco.com>
      929555a2
    • Roland Dreier's avatar
      IB/srp: Remove use of cached P_Key/GID queries · 969a60f9
      Roland Dreier authored 
      The SRP initiator is currently using ib_find_cached_pkey() and
ib_get_cached_gid() in situations where the uncached ib_find_pkey()
and ib_query_gid() functions serve just as well: sleeping is allowed
and performance is not an issue.  Since we want to eliminate the
cached operations in the long term, convert SRP to use the uncached
variants.
Signed-off-by: default avatarRoland Dreier <rolandd@cisco.com>
      969a60f9
    • David Woodhouse's avatar
      firmware: Correct dependency on CONFIG_EXTRA_FIRMWARE_DIR · 50515af2
      David Woodhouse authored 
      When CONFIG_EXTRA_FIRMWARE_DIR gets changed, the filename in the .S file
(which uses .incbin to include the binary) needs to change. When we
renamed the BUILTIN_FIRMWARE_DIR option to EXTRA_FIRMWARE_DIR, we forgot
to update the manual dependency in firmware/Makefile, so it was
depending on a non-existent file in include/config/
Signed-off-by: default avatarDavid Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
      50515af2
  3. 14 Jul, 2008 30 commits