diff options
| author | Eric Dumazet <edumazet@google.com> | 2014-10-27 21:45:24 -0700 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2014-10-29 15:05:15 -0400 |
| commit | dca145ffaa8d39ea1904491ac81b92b7049372c0 (patch) | |
| tree | ebe67ece694b9e54281047a6037b7d5776f9f56b /Documentation | |
| parent | 7aef06db0f91c7b48305d07b62edf43179adb28c (diff) | |
| download | blackbird-op-linux-dca145ffaa8d39ea1904491ac81b92b7049372c0.tar.gz blackbird-op-linux-dca145ffaa8d39ea1904491ac81b92b7049372c0.zip | |
tcp: allow for bigger reordering level
While testing upcoming Yaogong patch (converting out of order queue
into an RB tree), I hit the max reordering level of linux TCP stack.
Reordering level was limited to 127 for no good reason, and some
network setups [1] can easily reach this limit and get limited
throughput.
Allow a new max limit of 300, and add a sysctl to allow admins to even
allow bigger (or lower) values if needed.
[1] Aggregation of links, per packet load balancing, fabrics not doing
deep packet inspections, alternative TCP congestion modules...
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yaogong Wang <wygivan@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'Documentation')
| -rw-r--r-- | Documentation/networking/bonding.txt | 7 | ||||
| -rw-r--r-- | Documentation/networking/ip-sysctl.txt | 10 |
2 files changed, 11 insertions, 6 deletions
diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt index eeb5b2e97bed..83bf4986baea 100644 --- a/Documentation/networking/bonding.txt +++ b/Documentation/networking/bonding.txt @@ -2230,11 +2230,8 @@ balance-rr: This mode is the only mode that will permit a single It is possible to adjust TCP/IP's congestion limits by altering the net.ipv4.tcp_reordering sysctl parameter. The - usual default value is 3, and the maximum useful value is 127. - For a four interface balance-rr bond, expect that a single - TCP/IP stream will utilize no more than approximately 2.3 - interface's worth of throughput, even after adjusting - tcp_reordering. + usual default value is 3. But keep in mind TCP stack is able + to automatically increase this when it detects reorders. Note that the fraction of packets that will be delivered out of order is highly variable, and is unlikely to be zero. The level diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 0307e2875f21..9028b879a97b 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -376,9 +376,17 @@ tcp_orphan_retries - INTEGER may consume significant resources. Cf. tcp_max_orphans. tcp_reordering - INTEGER - Maximal reordering of packets in a TCP stream. + Initial reordering level of packets in a TCP stream. + TCP stack can then dynamically adjust flow reordering level + between this initial value and tcp_max_reordering Default: 3 +tcp_max_reordering - INTEGER + Maximal reordering level of packets in a TCP stream. + 300 is a fairly conservative value, but you might increase it + if paths are using per packet load balancing (like bonding rr mode) + Default: 300 + tcp_retrans_collapse - BOOLEAN Bug-to-bug compatibility with some broken printers. On retransmit try to send bigger packets to work around bugs in |
