[Top][All Lists]

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: Feature request for md5sum

From: Pádraig Brady
Subject: Re: Feature request for md5sum
Date: Wed, 24 Feb 2010 16:44:41 +0000
User-agent: Mozilla/5.0 (X11; U; Linux i686; en-US; rv: Gecko/20100111 Thunderbird/3.0.1

On 19/02/10 22:41, Pádraig Brady wrote:
Note the linux nfs client should be doing adaptive
read ahead to abstract you from this latency issue.
Check the rsize nfs setting as that may limit the
size of read ahead done.

I just noticed the following message which
shows some of the current Linux knobs in this area:

-------- Original Message --------
Subject: [RFC] nfs: use 2*rsize readahead size
Date: Wed, 24 Feb 2010 10:41:01 +0800
From: Wu Fengguang <address@hidden>
To: Trond Myklebust <address@hidden>
CC: address@hidden, address@hidden,     Linux Memory Management List 
<address@hidden>,    LKML <address@hidden>

With default rsize=512k and NFS_MAX_READAHEAD=15, the current NFS
readahead size 512k*15=7680k is too large than necessary for typical

On a e1000e--e1000e connection, I got the following numbers

        readahead size          throughput
                   16k           35.5 MB/s
                   32k           54.3 MB/s
                   64k           64.1 MB/s
                  128k           70.5 MB/s
                  256k           74.6 MB/s
rsize ==>      512k           77.4 MB/s
                 1024k           85.5 MB/s
                 2048k           86.8 MB/s
                 4096k           87.9 MB/s
                 8192k           89.0 MB/s
                16384k           87.7 MB/s

So it seems that readahead_size=2*rsize (ie. keep two RPC requests in flight)
can already get near full NFS bandwidth.

The test script is:



for rasize in 16 32 64 128 256 512 1024 2048 4096 8192 16384
        echo 3 > /proc/sys/vm/drop_caches
        echo $rasize > /sys/devices/virtual/bdi/$BDI/read_ahead_kb
        echo readahead_size=${rasize}k
        dd if=$file of=/dev/null bs=4k count=1024000

reply via email to

[Prev in Thread] Current Thread [Next in Thread]