语音服务器端内存泄露

INFO: cmd_ln.c(691): Parsing command line:
\
    -nfilt 20 \
    -lowerf 1 \
    -upperf 4000 \
    -wlen 0.025 \
    -transform dct \
    -round_filters no \
    -remove_dc yes \
    -feat 1s_c_d_dd \
    -svspec 0-12/13-25/26-38 \
    -agc none \
    -cmn current \
    -cmninit 54,-1,2 \
    -varnorm no

Current configuration:
[NAME]        [DEFLT]        [VALUE]
-agc        none        none
-agcthresh    2.0        2.000000e+00
-alpha        0.97        9.700000e-01
-ceplen        13        13
-cmn        current        current
-cmninit    8.0        54,-1,2
-dither        no        no
-doublebw    no        no
-feat        1s_c_d_dd    1s_c_d_dd
-frate        100        100
-input_endian    little        little
-lda                
-ldadim        0        0
-lifter        0        0
-logspec    no        no
-lowerf        133.33334    1.000000e+00
-ncep        13        13
-nfft        512        256
-nfilt        40        20
-remove_dc    no        yes
-round_filters    yes        no
-samprate    16000        8.000000e+03
-seed        -1        -1
-smoothspec    no        no
-svspec                0-12/13-25/26-38
-transform    legacy        dct
-unit_area    yes        yes
-upperf        6855.4976    4.000000e+03
-varnorm    no        no
-verbose    no        no
-warp_params            
-warp_type    inverse_linear    inverse_linear
-wlen        0.025625    2.500000e-02

INFO: acmod.c(242): Parsed model-specific feature parameters from /usr/local/share/pocketsphinx/model/hmm/tdt_sc_8kadapt/feat.params
INFO: feat.c(684): Initializing feature stream to type: '1s_c_d_dd', ceplen=13, CMN='current', VARNORM='no', AGC='none'
INFO: cmn.c(142): mean[0]= 12.00, mean[1..12]= 0.0
INFO: acmod.c(163): Using subvector specification 0-12/13-25/26-38
INFO: mdef.c(520): Reading model definition: /usr/local/share/pocketsphinx/model/hmm/tdt_sc_8kadapt/mdef
INFO: mdef.c(531): Found byte-order mark BMDF, assuming this is a binary mdef file
INFO: bin_mdef.c(330): Reading binary model definition: /usr/local/share/pocketsphinx/model/hmm/tdt_sc_8kadapt/mdef
INFO: bin_mdef.c(507): 70 CI-phone, 65021 CD-phone, 3 emitstate/phone, 210 CI-sen, 5210 Sen, 11271 Sen-Seq
INFO: tmat.c(205): Reading HMM transition probability matrices: /usr/local/share/pocketsphinx/model/hmm/tdt_sc_8kadapt/transition_matrices
INFO: acmod.c(117): Attempting to use SCHMM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /usr/local/share/pocketsphinx/model/hmm/tdt_sc_8kadapt/means
INFO: ms_gauden.c(292): 1 codebook, 3 feature, size:
INFO: ms_gauden.c(294):  256x13
INFO: ms_gauden.c(294):  256x13
INFO: ms_gauden.c(294):  256x13
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /usr/local/share/pocketsphinx/model/hmm/tdt_sc_8kadapt/variances
INFO: ms_gauden.c(292): 1 codebook, 3 feature, size:
INFO: ms_gauden.c(294):  256x13
INFO: ms_gauden.c(294):  256x13
INFO: ms_gauden.c(294):  256x13
INFO: ms_gauden.c(354): 0 variance values floored
INFO: s2_semi_mgau.c(908): Loading senones from dump file /usr/local/share/pocketsphinx/model/hmm/tdt_sc_8kadapt/sendump
INFO: s2_semi_mgau.c(932): BEGIN FILE FORMAT DESCRIPTION
INFO: s2_semi_mgau.c(995): Rows: 256, Columns: 5210
INFO: s2_semi_mgau.c(1027): Using memory-mapped I/O for senones
SYSTEM_ERROR: "mmio.c", line 224: Failed to mmap 4001920 bytes; 无法分配内存
calloc(4001280,1) failed from s2_semi_mgau.c(1068)
[recognizer_cn-2] process has died [pid 21859, exit code 255, cmd /home/yuyin/ros_workspace/src/pocketsphinx/nodes/recognizer_cn_wav.py __name:=recognizer_cn __log:=/home/yuyin/.ros/log/ee64ad4c-97da-11e4-8935-005056890008/recognizer_cn-2.log].
log file: /home/yuyin/.ros/log/ee64ad4c-97da-11e4-8935-005056890008/recognizer_cn-2*.log

-/+ buffers/cache:       1863        151
yuyin@yuyin-runji:~/serverwav$ free -m |grep cache:
-/+ buffers/cache:       1863        151
yuyin@yuyin-runji:~/serverwav$ free -m |grep cache:
-/+ buffers/cache:       1865        149
yuyin@yuyin-runji:~/serverwav$ free -m |grep cache:
-/+ buffers/cache:       1855        159
yuyin@yuyin-runji:~/serverwav$ free -m |grep cache:
-/+ buffers/cache:       1855        159
yuyin@yuyin-runji:~/serverwav$ free -m |grep cache:
-/+ buffers/cache:       1857        157
yuyin@yuyin-runji:~/serverwav$ free -m |grep cache:
-/+ buffers/cache:        345       1669
yuyin@yuyin-runji:~/serverwav$

1.内存急剧减小，少到15０左右时不再减小。

2.内存小到最后，先是识别不成功，最后才报无法分配内存的错误。

待解决。