You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@trafficserver.apache.org by "bettydramit (JIRA)" <ji...@apache.org> on 2011/09/14 05:10:11 UTC
[jira] [Created] (TS-951) ats can't save large object in memory
ats can't save large object in memory
-------------------------------------
Key: TS-951
URL: https://issues.apache.org/jira/browse/TS-951
Project: Traffic Server
Issue Type: Bug
Affects Versions: 3.1.0
Environment: centos 6.0 x86_64 ats 3.1.0 build from svn
Reporter: bettydramit
1. The record.config is follow
# Cache
#
##############################################################################
CONFIG proxy.config.cache.permit.pinning INT 0
# default the ram cache size to AUTO_SIZE (-1) based on cache size
# (approximately 1 MB of RAM cache per GB of disk cache)
# alternatively, set to a fixed value such as 20971520 (20MB)
CONFIG proxy.config.cache.ram_cache.size INT -1
#CONFIG proxy.config.cache.ram_cache_cutoff INT 4194304
CONFIG proxy.config.cache.ram_cache_cutoff INT 314572800
# Replacement algorithm
# 0 : Clocked Least Frequently Used by Size (CLFUS) w/optional compression
# 1 : LRU w/o optional compression - trivially simple
CONFIG proxy.config.cache.ram_cache.algorithm INT 0
# Compress the content of the ram cache:
# 0 : no compression
# 1 : fastlz (extremely fast, relatively low compression)
# 2 : libz (moderate speed, reasonable compression)
# 3 : liblzma (very slow, high compression)
# NOTE: compression runs on task threads. To use more cores for
# compression, increase proxy.config.task_threads.
CONFIG proxy.config.cache.ram_cache.compress INT 0
# The maximum number of alternates that are allowed for any given URL.
# It is not possible to strictly enforce this if the variable
# 'proxy.config.cache.vary_on_user_agent' is set to 1.
# The default value for 'proxy.config.cache.vary_on_user_agent' is 0.
# (0 disables the maximum number of alts check)
CONFIG proxy.config.cache.limits.http.max_alts INT 5
I get the file from ats proxy.
wget -S -O /dev/null -e http_proxy=127.0.0.1 http://www.test.com/CentOS-6.0-x86_64-netinstall.iso
--2011-09-14 10:31:24-- http://www.test.com/CentOS-6.0-x86_64-netinstall.iso
Connecting to 127.0.0.1:80... connected.
Proxy request sent, awaiting response...
HTTP/1.0 200 OK
Date: Wed, 14 Sep 2011 02:24:13 GMT
Server: ATS/3.0.1
Last-Modified: Wed, 14 Sep 2011 02:23:35 GMT
ETag: "201480-d300000-4acdd7285324b"
Accept-Ranges: bytes
Content-Length: 221249536
Content-Type: application/octet-stream
Age: 431
Length: 221249536 (211M) [application/octet-stream]
Saving to: "/dev/null"
100%[====================================================================================>] 221,249,536 90.6M/s in 2.3s
2011-09-14 10:31:26 (90.6 MB/s) - "/dev/null" saved [221249536/221249536]
I request the file more than 3,at the same time i use the dstat to monitor the disk.the follwing info is
----total-cpu-usage---- -dsk/total- -net/total- ---paging-- ---system--
usr sys idl wai hiq siq| read writ| recv send| in out | int csw
0 0 100 0 0 0| 0 0 | 120B 452B| 0 0 | 493 1759
0 0 100 0 0 0| 0 0 | 180B 826B| 0 0 | 542 1825
0 0 99 1 0 0| 0 208k| 120B 346B| 0 0 | 665 1897
2 2 95 0 0 0| 0 0 | 496B 542B| 0 0 |1817 2300
0 0 100 0 0 0| 0 0 | 316B 542B| 0 0 | 874 1987
0 0 100 0 0 0| 0 0 | 316B 542B| 0 0 | 742 2005
0 0 100 0 0 0| 0 0 | 602B 596B| 0 0 | 625 1927
0 0 99 1 0 0| 0 624k|1372B 1626B| 0 0 | 928 2106
0 0 100 0 0 0| 0 160k|3204B 2389B| 0 0 | 950 2049
0 1 99 0 0 0| 0 0 | 890B 1052B| 0 0 | 716 1935
2 0 98 0 0 0| 0 0 | 512B 792B| 0 0 | 839 1943
12 3 80 6 0 0| 163M 0 | 772B 3787B| 0 0 |2652 4345
7 3 82 8 0 0| 155M 336k| 646B 1680B| 0 0 |2375 6258
0 1 96 3 0 0| 54M 672k| 632B 1218B| 0 0 |1067 3438
0 0 99 0 0 0| 0 0 | 286B 702B| 0 0 | 715 1947
0 0 100 0 0 0| 0 0 | 236B 346B| 0 0 | 668 1992
Why the object hit from disk ???
is it bug??
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (TS-951) ats can't save large object in memory
Posted by "bettydramit (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/TS-951?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13104315#comment-13104315 ]
bettydramit commented on TS-951:
--------------------------------
thanks ming_zym
> ats can't save large object in memory
> -------------------------------------
>
> Key: TS-951
> URL: https://issues.apache.org/jira/browse/TS-951
> Project: Traffic Server
> Issue Type: Bug
> Affects Versions: 3.1.0
> Environment: centos 6.0 x86_64 ats 3.1.0 build from svn
> Reporter: bettydramit
>
> 1. The record.config is follow
> # Cache
> #
> ##############################################################################
> CONFIG proxy.config.cache.permit.pinning INT 0
> # default the ram cache size to AUTO_SIZE (-1) based on cache size
> # (approximately 1 MB of RAM cache per GB of disk cache)
> # alternatively, set to a fixed value such as 20971520 (20MB)
> CONFIG proxy.config.cache.ram_cache.size INT -1
> #CONFIG proxy.config.cache.ram_cache_cutoff INT 4194304
> CONFIG proxy.config.cache.ram_cache_cutoff INT 314572800
> # Replacement algorithm
> # 0 : Clocked Least Frequently Used by Size (CLFUS) w/optional compression
> # 1 : LRU w/o optional compression - trivially simple
> CONFIG proxy.config.cache.ram_cache.algorithm INT 0
> # Compress the content of the ram cache:
> # 0 : no compression
> # 1 : fastlz (extremely fast, relatively low compression)
> # 2 : libz (moderate speed, reasonable compression)
> # 3 : liblzma (very slow, high compression)
> # NOTE: compression runs on task threads. To use more cores for
> # compression, increase proxy.config.task_threads.
> CONFIG proxy.config.cache.ram_cache.compress INT 0
> # The maximum number of alternates that are allowed for any given URL.
> # It is not possible to strictly enforce this if the variable
> # 'proxy.config.cache.vary_on_user_agent' is set to 1.
> # The default value for 'proxy.config.cache.vary_on_user_agent' is 0.
> # (0 disables the maximum number of alts check)
> CONFIG proxy.config.cache.limits.http.max_alts INT 5
> I get the file from ats proxy.
> wget -S -O /dev/null -e http_proxy=127.0.0.1 http://www.test.com/CentOS-6.0-x86_64-netinstall.iso
> --2011-09-14 10:31:24-- http://www.test.com/CentOS-6.0-x86_64-netinstall.iso
> Connecting to 127.0.0.1:80... connected.
> Proxy request sent, awaiting response...
> HTTP/1.0 200 OK
> Date: Wed, 14 Sep 2011 02:24:13 GMT
> Server: ATS/3.0.1
> Last-Modified: Wed, 14 Sep 2011 02:23:35 GMT
> ETag: "201480-d300000-4acdd7285324b"
> Accept-Ranges: bytes
> Content-Length: 221249536
> Content-Type: application/octet-stream
> Age: 431
> Length: 221249536 (211M) [application/octet-stream]
> Saving to: "/dev/null"
>
> 100%[====================================================================================>] 221,249,536 90.6M/s in 2.3s
>
> 2011-09-14 10:31:26 (90.6 MB/s) - "/dev/null" saved [221249536/221249536]
> I request the file more than 3,at the same time i use the dstat to monitor the disk.the follwing info is
> ----total-cpu-usage---- -dsk/total- -net/total- ---paging-- ---system--
> usr sys idl wai hiq siq| read writ| recv send| in out | int csw
> 0 0 100 0 0 0| 0 0 | 120B 452B| 0 0 | 493 1759
> 0 0 100 0 0 0| 0 0 | 180B 826B| 0 0 | 542 1825
> 0 0 99 1 0 0| 0 208k| 120B 346B| 0 0 | 665 1897
> 2 2 95 0 0 0| 0 0 | 496B 542B| 0 0 |1817 2300
> 0 0 100 0 0 0| 0 0 | 316B 542B| 0 0 | 874 1987
> 0 0 100 0 0 0| 0 0 | 316B 542B| 0 0 | 742 2005
> 0 0 100 0 0 0| 0 0 | 602B 596B| 0 0 | 625 1927
> 0 0 99 1 0 0| 0 624k|1372B 1626B| 0 0 | 928 2106
> 0 0 100 0 0 0| 0 160k|3204B 2389B| 0 0 | 950 2049
> 0 1 99 0 0 0| 0 0 | 890B 1052B| 0 0 | 716 1935
> 2 0 98 0 0 0| 0 0 | 512B 792B| 0 0 | 839 1943
> 12 3 80 6 0 0| 163M 0 | 772B 3787B| 0 0 |2652 4345
> 7 3 82 8 0 0| 155M 336k| 646B 1680B| 0 0 |2375 6258
> 0 1 96 3 0 0| 54M 672k| 632B 1218B| 0 0 |1067 3438
> 0 0 99 0 0 0| 0 0 | 286B 702B| 0 0 | 715 1947
> 0 0 100 0 0 0| 0 0 | 236B 346B| 0 0 | 668 1992
>
> Why the object hit from disk ???
> is it bug??
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Resolved] (TS-951) ats can't save large object in memory
Posted by "bettydramit (JIRA)" <ji...@apache.org>.
[ https://issues.apache.org/jira/browse/TS-951?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
bettydramit resolved TS-951.
----------------------------
Resolution: Fixed
traffic_line -s proxy.config.cache.ram_cache.size -v 500000000;traffic_line -x;traffic_line -L
> ats can't save large object in memory
> -------------------------------------
>
> Key: TS-951
> URL: https://issues.apache.org/jira/browse/TS-951
> Project: Traffic Server
> Issue Type: Bug
> Affects Versions: 3.1.0
> Environment: centos 6.0 x86_64 ats 3.1.0 build from svn
> Reporter: bettydramit
>
> 1. The record.config is follow
> # Cache
> #
> ##############################################################################
> CONFIG proxy.config.cache.permit.pinning INT 0
> # default the ram cache size to AUTO_SIZE (-1) based on cache size
> # (approximately 1 MB of RAM cache per GB of disk cache)
> # alternatively, set to a fixed value such as 20971520 (20MB)
> CONFIG proxy.config.cache.ram_cache.size INT -1
> #CONFIG proxy.config.cache.ram_cache_cutoff INT 4194304
> CONFIG proxy.config.cache.ram_cache_cutoff INT 314572800
> # Replacement algorithm
> # 0 : Clocked Least Frequently Used by Size (CLFUS) w/optional compression
> # 1 : LRU w/o optional compression - trivially simple
> CONFIG proxy.config.cache.ram_cache.algorithm INT 0
> # Compress the content of the ram cache:
> # 0 : no compression
> # 1 : fastlz (extremely fast, relatively low compression)
> # 2 : libz (moderate speed, reasonable compression)
> # 3 : liblzma (very slow, high compression)
> # NOTE: compression runs on task threads. To use more cores for
> # compression, increase proxy.config.task_threads.
> CONFIG proxy.config.cache.ram_cache.compress INT 0
> # The maximum number of alternates that are allowed for any given URL.
> # It is not possible to strictly enforce this if the variable
> # 'proxy.config.cache.vary_on_user_agent' is set to 1.
> # The default value for 'proxy.config.cache.vary_on_user_agent' is 0.
> # (0 disables the maximum number of alts check)
> CONFIG proxy.config.cache.limits.http.max_alts INT 5
> I get the file from ats proxy.
> wget -S -O /dev/null -e http_proxy=127.0.0.1 http://www.test.com/CentOS-6.0-x86_64-netinstall.iso
> --2011-09-14 10:31:24-- http://www.test.com/CentOS-6.0-x86_64-netinstall.iso
> Connecting to 127.0.0.1:80... connected.
> Proxy request sent, awaiting response...
> HTTP/1.0 200 OK
> Date: Wed, 14 Sep 2011 02:24:13 GMT
> Server: ATS/3.0.1
> Last-Modified: Wed, 14 Sep 2011 02:23:35 GMT
> ETag: "201480-d300000-4acdd7285324b"
> Accept-Ranges: bytes
> Content-Length: 221249536
> Content-Type: application/octet-stream
> Age: 431
> Length: 221249536 (211M) [application/octet-stream]
> Saving to: "/dev/null"
>
> 100%[====================================================================================>] 221,249,536 90.6M/s in 2.3s
>
> 2011-09-14 10:31:26 (90.6 MB/s) - "/dev/null" saved [221249536/221249536]
> I request the file more than 3,at the same time i use the dstat to monitor the disk.the follwing info is
> ----total-cpu-usage---- -dsk/total- -net/total- ---paging-- ---system--
> usr sys idl wai hiq siq| read writ| recv send| in out | int csw
> 0 0 100 0 0 0| 0 0 | 120B 452B| 0 0 | 493 1759
> 0 0 100 0 0 0| 0 0 | 180B 826B| 0 0 | 542 1825
> 0 0 99 1 0 0| 0 208k| 120B 346B| 0 0 | 665 1897
> 2 2 95 0 0 0| 0 0 | 496B 542B| 0 0 |1817 2300
> 0 0 100 0 0 0| 0 0 | 316B 542B| 0 0 | 874 1987
> 0 0 100 0 0 0| 0 0 | 316B 542B| 0 0 | 742 2005
> 0 0 100 0 0 0| 0 0 | 602B 596B| 0 0 | 625 1927
> 0 0 99 1 0 0| 0 624k|1372B 1626B| 0 0 | 928 2106
> 0 0 100 0 0 0| 0 160k|3204B 2389B| 0 0 | 950 2049
> 0 1 99 0 0 0| 0 0 | 890B 1052B| 0 0 | 716 1935
> 2 0 98 0 0 0| 0 0 | 512B 792B| 0 0 | 839 1943
> 12 3 80 6 0 0| 163M 0 | 772B 3787B| 0 0 |2652 4345
> 7 3 82 8 0 0| 155M 336k| 646B 1680B| 0 0 |2375 6258
> 0 1 96 3 0 0| 54M 672k| 632B 1218B| 0 0 |1067 3438
> 0 0 99 0 0 0| 0 0 | 286B 702B| 0 0 | 715 1947
> 0 0 100 0 0 0| 0 0 | 236B 346B| 0 0 | 668 1992
>
> Why the object hit from disk ???
> is it bug??
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira