[jira] [Created] (TS-3164) why the load of trafficserver occurrs a abrupt rise on a occasion ?
taoyunxing created TS-3164: -- Summary: why the load of trafficserver occurrs a abrupt rise on a occasion ? Key: TS-3164 URL: https://issues.apache.org/jira/browse/TS-3164 Project: Traffic Server Issue Type: Bug Components: Core Reporter: taoyunxing I use Tsar to monitor the traffic status of the ATS 4.2.0, and come across the following problem: Time ---cpu-- ---mem-- ---tcp-- -traffic --sda--- --sdb--- --sdc--- ---load- Time util util retranbytin bytout util util util load1 03/11/14-18:20 40.6787.19 3.3624.5M 43.9M13.0294.68 0.00 5.34 03/11/14-18:25 40.3087.20 3.2722.5M 42.6M12.3894.87 0.00 5.79 03/11/14-18:30 40.8484.67 3.4421.4M 42.0M13.2995.37 0.00 6.28 03/11/14-18:35 43.6387.36 3.2123.8M 45.0M13.2393.99 0.00 7.37 03/11/14-18:40 42.2587.37 3.0924.2M 44.8M12.8495.77 0.00 7.25 03/11/14-18:45 42.9687.44 3.4623.3M 46.0M12.9695.84 0.00 7.10 03/11/14-18:50 44.0087.42 3.4922.3M 43.0M14.1794.99 0.00 6.57 03/11/14-18:55 42.2087.44 3.4622.3M 43.6M13.1996.05 0.00 6.09 03/11/14-19:00 44.9087.53 3.6023.6M 46.5M13.6196.67 0.00 8.06 03/11/14-19:05 46.2687.73 3.2425.8M 49.1M15.3994.05 0.00 9.98 03/11/14-19:10 43.8587.69 3.1925.4M 50.9M12.8897.80 0.00 7.99 03/11/14-19:15 45.2887.69 3.3625.6M 49.6M13.1096.86 0.00 7.47 03/11/14-19:20 44.1185.20 3.2924.1M 47.8M14.2496.75 0.00 5.82 03/11/14-19:25 45.2687.78 3.5224.4M 47.7M13.2195.44 0.00 7.61 03/11/14-19:30 44.8387.80 3.6425.7M 50.8M13.2798.02 0.00 6.85 03/11/14-19:35 44.8987.78 3.6123.9M 49.0M13.3497.42 0.00 7.04 03/11/14-19:40 69.2188.88 0.5518.3M 33.7M11.3971.23 0.00 65.80 03/11/14-19:45 72.4788.66 0.2715.4M 31.6M11.5172.31 0.00 11.56 03/11/14-19:50 44.8788.72 4.1122.7M 46.3M12.9997.33 0.00 8.29 in addition, top command show hi:0 ni:0 si:45.56 st:0 sy:13.92 us:12.58 wa:14.3 id:15.96 who help me ? think in advance. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-3164) why the load of trafficserver occurrs a abrupt rise on a occasion ?
[ https://issues.apache.org/jira/browse/TS-3164?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] taoyunxing updated TS-3164: --- Description: I use Tsar to monitor the traffic status of the ATS 4.2.0, and come across the following problem: Time ---cpu-- ---mem-- ---tcp-- -traffic --sda--- --sdb--- --sdc--- ---load- Time util util retranbytin bytout util util util load1 03/11/14-18:20 40.6787.19 3.3624.5M 43.9M13.0294.68 0.00 5.34 03/11/14-18:25 40.3087.20 3.2722.5M 42.6M12.3894.87 0.00 5.79 03/11/14-18:30 40.8484.67 3.4421.4M 42.0M13.2995.37 0.00 6.28 03/11/14-18:35 43.6387.36 3.2123.8M 45.0M13.2393.99 0.00 7.37 03/11/14-18:40 42.2587.37 3.0924.2M 44.8M12.8495.77 0.00 7.25 03/11/14-18:45 42.9687.44 3.4623.3M 46.0M12.9695.84 0.00 7.10 03/11/14-18:50 44.0087.42 3.4922.3M 43.0M14.1794.99 0.00 6.57 03/11/14-18:55 42.2087.44 3.4622.3M 43.6M13.1996.05 0.00 6.09 03/11/14-19:00 44.9087.53 3.6023.6M 46.5M13.6196.67 0.00 8.06 03/11/14-19:05 46.2687.73 3.2425.8M 49.1M15.3994.05 0.00 9.98 03/11/14-19:10 43.8587.69 3.1925.4M 50.9M12.8897.80 0.00 7.99 03/11/14-19:15 45.2887.69 3.3625.6M 49.6M13.1096.86 0.00 7.47 03/11/14-19:20 44.1185.20 3.2924.1M 47.8M14.2496.75 0.00 5.82 03/11/14-19:25 45.2687.78 3.5224.4M 47.7M13.2195.44 0.00 7.61 03/11/14-19:30 44.8387.80 3.6425.7M 50.8M13.2798.02 0.00 6.85 03/11/14-19:35 44.8987.78 3.6123.9M 49.0M13.3497.42 0.00 7.04 03/11/14-19:40 69.2188.88 0.5518.3M 33.7M11.3971.23 0.00 65.80 03/11/14-19:45 72.4788.66 0.2715.4M 31.6M11.5172.31 0.00 11.56 03/11/14-19:50 44.8788.72 4.1122.7M 46.3M12.9997.33 0.00 8.29 in addition, top command show hi:0 ni:0 si:45.56 st:0 sy:13.92 us:12.58 wa:14.3 id:15.96 who help me ? thanks in advance. was: I use Tsar to monitor the traffic status of the ATS 4.2.0, and come across the following problem: Time ---cpu-- ---mem-- ---tcp-- -traffic --sda--- --sdb--- --sdc--- ---load- Time util util retranbytin bytout util util util load1 03/11/14-18:20 40.6787.19 3.3624.5M 43.9M13.0294.68 0.00 5.34 03/11/14-18:25 40.3087.20 3.2722.5M 42.6M12.3894.87 0.00 5.79 03/11/14-18:30 40.8484.67 3.4421.4M 42.0M13.2995.37 0.00 6.28 03/11/14-18:35 43.6387.36 3.2123.8M 45.0M13.2393.99 0.00 7.37 03/11/14-18:40 42.2587.37 3.0924.2M 44.8M12.8495.77 0.00 7.25 03/11/14-18:45 42.9687.44 3.4623.3M 46.0M12.9695.84 0.00 7.10 03/11/14-18:50 44.0087.42 3.4922.3M 43.0M14.1794.99 0.00 6.57 03/11/14-18:55 42.2087.44 3.4622.3M 43.6M13.1996.05 0.00 6.09 03/11/14-19:00 44.9087.53 3.6023.6M 46.5M13.6196.67 0.00 8.06 03/11/14-19:05 46.2687.73 3.2425.8M 49.1M15.3994.05 0.00 9.98 03/11/14-19:10 43.8587.69 3.1925.4M 50.9M12.8897.80 0.00 7.99 03/11/14-19:15 45.2887.69 3.3625.6M 49.6M13.1096.86 0.00 7.47 03/11/14-19:20 44.1185.20 3.2924.1M 47.8M14.2496.75 0.00 5.82 03/11/14-19:25 45.2687.78 3.5224.4M 47.7M13.2195.44 0.00 7.61 03/11/14-19:30 44.8387.80 3.6425.7M 50.8M13.2798.02 0.00 6.85 03/11/14-19:35 44.8987.78 3.6123.9M 49.0M13.3497.42 0.00 7.04 03/11/14-19:40 69.2188.88 0.5518.3M 33.7M11.3971.23 0.00 65.80 03/11/14-19:45 72.4788.66 0.2715.4M 31.6M11.5172.31 0.00 11.56 03/11/14-19:50 44.8788.72 4.1122.7M 46.3M12.9997.33 0.00 8.29 in addition, top command show hi:0 ni:0 si:45.56 st:0 sy:13.92 us:12.58 wa:14.3 id:15.96 who help me ? think in advance. Environment: CentOS 6.3 64bit, 8 cores, 128G mem why the load of trafficserver occurrs a abrupt rise on a occasion ? --- Key: TS-3164
[jira] [Assigned] (TS-60) support writing large buffers via zero-copy
[ https://issues.apache.org/jira/browse/TS-60?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Alan M. Carroll reassigned TS-60: - Assignee: Alan M. Carroll (was: John Plevyak) support writing large buffers via zero-copy --- Key: TS-60 URL: https://issues.apache.org/jira/browse/TS-60 Project: Traffic Server Issue Type: Improvement Components: Cache Affects Versions: 3.0.0 Environment: all Reporter: John Plevyak Assignee: Alan M. Carroll Fix For: sometime Original Estimate: 48h Remaining Estimate: 48h Currently all write data is written from the aggregation buffer. In order to support large buffer writes efficiently it would be nice to be able to write directly from page aligned memory. This would be bother more efficient and would help support large objects. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-54) UnixNet cleanup, encapsulation of event subsystem
[ https://issues.apache.org/jira/browse/TS-54?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-54: - Assignee: Phil Sorber (was: John Plevyak) UnixNet cleanup, encapsulation of event subsystem - Key: TS-54 URL: https://issues.apache.org/jira/browse/TS-54 Project: Traffic Server Issue Type: Improvement Components: Cleanup Environment: all unixesque Reporter: John Plevyak Assignee: Phil Sorber Fix For: sometime Attachments: proposed-jp-v1-List.h, ts-List-net-cleanup-jp-v2.patch, ts-List_and_net-cleanup-jp-v1.patch Original Estimate: 72h Remaining Estimate: 72h The UnixNet subsystem was modified for epoll, but lots of the old data structures, data members and code remain for the old bucket approach. The epoll code should also be encapsulated to simplify support for other platforms and a possible move to an event library. The current code is complicated by limitations in Queue which require specifying the link field for every use, but which can be fixed by in the template. Finally, the current code does an unnecessary allocation for the epoll struct which should be part of the NetVConnection etc. and it takes a lock for the enable_queue which can be avoided by using the non-locking AtomicSSL. This work is also good preparation for evaluating libev or libevent as it will reduce the amount of code which will have to be changed. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (TS-61) multiple do_io_pread on a CacheVConnection
[ https://issues.apache.org/jira/browse/TS-61?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14196303#comment-14196303 ] Alan M. Carroll commented on TS-61: --- I think I'll roll this in to the partial object caching. multiple do_io_pread on a CacheVConnection -- Key: TS-61 URL: https://issues.apache.org/jira/browse/TS-61 Project: Traffic Server Issue Type: Improvement Components: Cache Affects Versions: 3.0.0 Reporter: John Plevyak Assignee: Alan M. Carroll Fix For: sometime Attachments: pread-2.patch Original Estimate: 48h Remaining Estimate: 48h The current TS-46 patch includes do_io_pread support but allows only a single do_io_pread. In order to efficiently support range requests with multiple ranges it would be helpful to be able to do multiple do_io_pread's on a single open CacheVConnection. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-81) Have one single place to store and lookup remap rules irrespective of type
[ https://issues.apache.org/jira/browse/TS-81?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-81: - Fix Version/s: (was: 5.3.0) sometime Have one single place to store and lookup remap rules irrespective of type -- Key: TS-81 URL: https://issues.apache.org/jira/browse/TS-81 Project: Traffic Server Issue Type: Improvement Components: Core Affects Versions: 2.0.0a Reporter: Manjesh Nilange Priority: Minor Labels: A Fix For: sometime Currently, remap rules are stored in different structures and looked up separately based on type (forward, reverse, etc.). It'd be better design and more maintainable to process (store, search) all rules in one structure and then use type to determine action. A fundamental problem with our current implementation is that the order in remap.config is not honored. E.g. a map directive always takes precedence over any redirect directives (if both matches). -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-110) Improve regex remap to allow substitutions in path field
[ https://issues.apache.org/jira/browse/TS-110?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-110: -- Fix Version/s: (was: 5.3.0) sometime Improve regex remap to allow substitutions in path field Key: TS-110 URL: https://issues.apache.org/jira/browse/TS-110 Project: Traffic Server Issue Type: Improvement Components: Core Affects Versions: 3.0.0 Reporter: Manjesh Nilange Assignee: Brian Geffon Priority: Minor Fix For: sometime Currently, regex support covers only the host field of the remap rules. It'd be nice to extend this to allow substitutions into the path field as well. This will allow rules like: regex_map http://www.example-(.*).com/ http://real-example.com/$1 -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-81) Have one single place to store and lookup remap rules irrespective of type
[ https://issues.apache.org/jira/browse/TS-81?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-81: - Labels: (was: A) Have one single place to store and lookup remap rules irrespective of type -- Key: TS-81 URL: https://issues.apache.org/jira/browse/TS-81 Project: Traffic Server Issue Type: Improvement Components: Core Affects Versions: 2.0.0a Reporter: Manjesh Nilange Priority: Minor Fix For: sometime Currently, remap rules are stored in different structures and looked up separately based on type (forward, reverse, etc.). It'd be better design and more maintainable to process (store, search) all rules in one structure and then use type to determine action. A fundamental problem with our current implementation is that the order in remap.config is not honored. E.g. a map directive always takes precedence over any redirect directives (if both matches). -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (TS-110) Improve regex remap to allow substitutions in path field
[ https://issues.apache.org/jira/browse/TS-110?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14196312#comment-14196312 ] Susan Hinrichs commented on TS-110: --- Brian, are you still working on this? Any target for ETA? Improve regex remap to allow substitutions in path field Key: TS-110 URL: https://issues.apache.org/jira/browse/TS-110 Project: Traffic Server Issue Type: Improvement Components: Core Affects Versions: 3.0.0 Reporter: Manjesh Nilange Assignee: Brian Geffon Priority: Minor Fix For: sometime Currently, regex support covers only the host field of the remap rules. It'd be nice to extend this to allow substitutions into the path field as well. This will allow rules like: regex_map http://www.example-(.*).com/ http://real-example.com/$1 -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (TS-119) RAM only caching
[ https://issues.apache.org/jira/browse/TS-119?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14196314#comment-14196314 ] Alan M. Carroll commented on TS-119: This may end up being part of the Cache API toolkit (which is also tiered caching). RAM only caching Key: TS-119 URL: https://issues.apache.org/jira/browse/TS-119 Project: Traffic Server Issue Type: Improvement Components: Cache Reporter: John Plevyak Priority: Minor Fix For: sometime It would be nice if we could run with a RAM only cache. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-119) RAM only caching
[ https://issues.apache.org/jira/browse/TS-119?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-119: -- Assignee: (was: Phil Sorber) RAM only caching Key: TS-119 URL: https://issues.apache.org/jira/browse/TS-119 Project: Traffic Server Issue Type: Improvement Components: Cache Reporter: John Plevyak Priority: Minor Fix For: sometime It would be nice if we could run with a RAM only cache. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-203) config files ownership
[ https://issues.apache.org/jira/browse/TS-203?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-203: -- Fix Version/s: (was: 5.2.0) 6.0.0 config files ownership -- Key: TS-203 URL: https://issues.apache.org/jira/browse/TS-203 Project: Traffic Server Issue Type: Bug Components: Build Reporter: Leif Hedstrom Priority: Minor Fix For: 6.0.0 It's semi-odd that the admin user (nobody) is also the user as to which traffic_server process changes it's euid to. This means that the traffic_server process has write permissions on the config files. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-228) Cleanup usage of long in all code
[ https://issues.apache.org/jira/browse/TS-228?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-228: -- Assignee: (was: James Peach) Cleanup usage of long in all code --- Key: TS-228 URL: https://issues.apache.org/jira/browse/TS-228 Project: Traffic Server Issue Type: Bug Components: Cleanup Affects Versions: 2.1.0 Reporter: John Plevyak Priority: Critical Fix For: 5.2.0 Solaris 64-bit SunPro long is 64-bit while for g++ 64-bit long is 32-bit. This is a potential can of worms which at the least is making records.snap incompatible but at worse could be the cause of other bugs. In any case we should not be using long in the TS code, but instead use either int which is always 32-bits or inkXXX of a particular size. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-228) Cleanup usage of long in all code
[ https://issues.apache.org/jira/browse/TS-228?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-228: -- Fix Version/s: (was: 5.2.0) 5.3.0 Cleanup usage of long in all code --- Key: TS-228 URL: https://issues.apache.org/jira/browse/TS-228 Project: Traffic Server Issue Type: Bug Components: Cleanup Affects Versions: 2.1.0 Reporter: John Plevyak Priority: Critical Fix For: 5.3.0 Solaris 64-bit SunPro long is 64-bit while for g++ 64-bit long is 32-bit. This is a potential can of worms which at the least is making records.snap incompatible but at worse could be the cause of other bugs. In any case we should not be using long in the TS code, but instead use either int which is always 32-bits or inkXXX of a particular size. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-242) Connect timeout doesn't reset until first byte is received from server
[ https://issues.apache.org/jira/browse/TS-242?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-242: -- Fix Version/s: (was: 5.3.0) sometime Connect timeout doesn't reset until first byte is received from server -- Key: TS-242 URL: https://issues.apache.org/jira/browse/TS-242 Project: Traffic Server Issue Type: Bug Components: Core Reporter: Steve Jiang Assignee: Alan M. Carroll Priority: Minor Fix For: sometime proxy.config.http.connect_attempts_timeout proxy.config.http.parent_proxy.connect_attempts_timeout proxy.config.http.post_connect_attempts_timeout These timeouts are implemented with inactivity timeout on the netvc and don't behave as expected. If the connect succeeds (the remote server successfully accepted) but the remote server does not respond with any bytes within the timeout period, TS still treats it as a connect timeout. If retries are enabled and the origin server is slow to start sending responses (but not down), it will keep sending requests and closing the connection after getting no response within the connect timeout. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-275) API: TSHttpTxnConnectTimeoutSet isn't documented
[ https://issues.apache.org/jira/browse/TS-275?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-275: -- Labels: Docs (was: ) API: TSHttpTxnConnectTimeoutSet isn't documented Key: TS-275 URL: https://issues.apache.org/jira/browse/TS-275 Project: Traffic Server Issue Type: Bug Components: Documentation, TS API Reporter: Miles Libbey Priority: Minor Labels: Docs Fix For: Docs Someone had a question about INKHttpTxnConnectTimeoutSet -- it's not documented in the SDK guide. Can someone please provide: - Where it should live (ie, Function Reference/HTTP Functions/ HTTP Transaction Functions) - suggested text in a similar format to http://incubator.apache.org/trafficserver/docs/sdk/HTTPFunctions.html (ie, what it does; prototype; description; returns, and possibly an example) (Bryan also mentioned that a few timeout apis were added last year, but, I don't see any others with timeout in them (except for https://issues.apache.org/jira/browse/TS-256 -- INKHttpSchedule -- are we missing others?) -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-302) -fstrict-aliasing optimizer generates bad code
[ https://issues.apache.org/jira/browse/TS-302?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-302: -- Assignee: (was: Phil Sorber) -fstrict-aliasing optimizer generates bad code -- Key: TS-302 URL: https://issues.apache.org/jira/browse/TS-302 Project: Traffic Server Issue Type: Improvement Components: Cleanup Reporter: Miles Libbey Priority: Minor Fix For: sometime Attachments: no-no-fstrict-alias.patch, ts-302.patch (moving from yahoo bug 525119) Original description by Leif Hedstrom 4 years ago at 2005-12-16 08:41 Not sure if this is a compiler bug or a code issue on our side, but enabling the -fstrict-aliasing optimization option generates faulty code. This optimization technique is enabled implicitly with -Os, -O2 and -O3, so for now I'm explicitly turning it off with -O3 -fno-strict-aliasing This solves the problem where the traffic server would return data of 0 or 1 length out of the cache. This initially looked like the cache corruption problem, but is completely different and unrelated. The cache corruption problem has been fixed and closed. I'm opening this bug as a reminder, at some point we should isolate which code triggers the strict-aliasing problem, and confirm if it's a compiler bug or a problem in our code. Comment 1 by Michael Bigby 4 years ago at 2005-12-16 09:07:40 I'm recommending that we get Ed's input on this. He may some insight compiler issues... Comment 2 by Leif Hedstrom 4 years ago at 2005-12-16 10:02:07 That'd be great! We haven't had a chance yet to review the code that might be affecting this, it's obviously something with unions and how the compiler handles storage/alignment on the members. Comment 3 by Ed Hall 4 years ago at 2006-03-03 11:46:52 This is with gcc 2.95.3, correct? There have been a number of complaints around the 'net about problems with -fstrict-aliasing. I've not really looked very deeply into it, though I should mention that certain C code was known at the time to malfunction when by-the-standard aliasing rules were enforced (starting with the Linux kernel). In essense, the -fstrict-aliasing optimizations assume that any particular part of memory accessed via a specific type of pointer won't be accessed as another type. There are a set of optimizations that are safe only when it can be guaranteed that a given bit of memory hasn't been manipulated via pointer; if the compiler assumes that the rather arcane C aliasing rules have been followed (aliasing in this case meaning accessing a given bit of memory with more than one type of pointer), there are more situations where such optimizations can be applied. Code which uses type casts where unions might be more appropriate is the most likely to break aliasing rules. In any case, gcc 3/4 is less aggressive (and perhaps less buggy) in applying the C aliasing rules, and has added warnings for obvious violations. It's never been clear to me if gcc 2.95.3 was actually broken or not, or if there simply was a lot of code out there that ran afoul of the standard. Comment 4 by Leif Hedstrom 4 years ago at 2006-03-03 12:50:22 Actually, the problem only occured after we converted the code from gcc-2.9x to gcc-3.4.4. We have since cleared out a *lot* of compiler warnings (thousands and thousands), so maybe we should try again to compile without the -fno-strict-aliasing, and see if gcc will point us to some places where we do dangerous things. The code does some very scary things manipulating objects directly, by byte-offsets for instance. I think it's pretty easy to reproduce the problem, it basically renders the cache completely useless, returning objects of size 0 or 1. Comment 5 by Ed Hall 4 years ago at 2006-03-03 16:44:04 Ah, that makes sense. I just checked, and the -fstrict-aliasing option wasn't part of the -O2 optimizations on gcc 2.95, but got added sometime during gcc 3 development. Comment 6 by Ed Hall 4 years ago at 2006-03-03 16:46:43 (Just to be clear, -fstrict-aliasing was *available* with gcc 2.95.3, it just wasn't activated by the -O optimization flags.) -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-306) enable log rotation for diags.log
[ https://issues.apache.org/jira/browse/TS-306?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-306: -- Assignee: kang li enable log rotation for diags.log - Key: TS-306 URL: https://issues.apache.org/jira/browse/TS-306 Project: Traffic Server Issue Type: Improvement Components: Logging Reporter: Miles Libbey Assignee: kang li Priority: Critical Fix For: 5.3.0 (from yahoo bug 913896) Original description by Leif Hedstrom 3 years ago at 2006-12-04 12:42 There might be reasons why this file might get filled up, e.g. libraries used by plugins producing output on STDOUT/STDERR. A few suggestions have been made, to somehow rotate traffic.out. One possible solution (suggested by Ryan) is to use cronolog (http://cronolog.org/), which seems like a fine idea. Comment 1 by Joseph Rothrock 2 years ago at 2007-10-17 09:13:24 Maybe consider rolling diags.log as well. -Feature enhancement. Comment 2 by Kevin Dalley 13 months ago at 2009-03-04 15:32:18 When traffic.out gets filled up, error.log stops filing up, even though rotation is turned on. This is counter-intuitive. Rotation does not control traffic.out, but a large traffic.out will stop error.log from being written. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-315) Add switch to disable config file generation/runtime behavior changing
[ https://issues.apache.org/jira/browse/TS-315?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-315: -- Fix Version/s: (was: 5.2.0) sometime Add switch to disable config file generation/runtime behavior changing -- Key: TS-315 URL: https://issues.apache.org/jira/browse/TS-315 Project: Traffic Server Issue Type: Sub-task Components: Configuration Reporter: Miles Libbey Priority: Minor Fix For: sometime (was yahoo bug 1863676) Original description by Michael S. Fischer 2 years ago at 2008-04-09 09:52 In production, in order to improve site stability, it is imperative that TS never accidentally overwrite its own configuration files. For this reason, we'd like to request a switch be added to TS, preferably via the command line, that disables all automatic configuration file generation or other runtime behavioral changes initiated by any form of IPC other than 'traffic_line -x' (including the web interface, etc.) Comment 1 by Bjornar Sandvik 2 years ago at 2008-04-09 09:57:17 A very crucial request, in my opinion. If TS needs to be able to read command-line config changes on the fly, these changes should be stored in another config file (for example remap.config.local instead of remap.config). We have a patch config package that overwrites 4 of the config files under /home/conf/ts/, and with all packages we'd like to think that the content of these files can't change outside our control. Comment 2 by Bryan Call 2 years ago at 2008-04-09 11:02:46 traffic_line -x doesn't modify the configuration, it reloads the configuration files. If we want to have an option for this it would be good to have it as an option configuration file (CONFIG proxy.config.write_protect INT 1). It would be an equivalent of write protecting floppies (ahh the memories)... Comment 3 by Michael S. Fischer 2 years ago at 2008-04-09 11:09:09 I don't think it would be a good idea to have this in the configuration file, as it would introduce a chicken/egg problem. Comment 4 by Leif Hedstrom 19 months ago at 2008-08-27 12:43:17 So I'm not 100% positive that this isn't just a bad interaction. Now, it's only triggered when trafficserver is running, but usually what ends up happening is that we get a records.config which looks like it's the default config that comes with the trafficserver package. It's possible it's all one and the same issue, or we might have two issues. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Assigned] (TS-337) Cache Replacement Algorithm plug-in API
[ https://issues.apache.org/jira/browse/TS-337?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs reassigned TS-337: - Assignee: Susan Hinrichs Cache Replacement Algorithm plug-in API --- Key: TS-337 URL: https://issues.apache.org/jira/browse/TS-337 Project: Traffic Server Issue Type: New Feature Components: TS API Affects Versions: 2.0.0 Reporter: Mark Nottingham Assignee: Susan Hinrichs Fix For: sometime New cache replacement algorithms are often proposed, and often it's not a one size fits all problem; different workloads require different approaches. To facilitate this, TS should have a pluggable cache replacement policy API, both for the memory and disk cache. Squid has done this to good effect; see http://www.squid-cache.org/cgi-bin/cvsweb.cgi/squid/src/repl/ -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-337) Cache Replacement Algorithm plug-in API
[ https://issues.apache.org/jira/browse/TS-337?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-337: -- Assignee: Alan M. Carroll (was: Susan Hinrichs) Cache Replacement Algorithm plug-in API --- Key: TS-337 URL: https://issues.apache.org/jira/browse/TS-337 Project: Traffic Server Issue Type: New Feature Components: TS API Affects Versions: 2.0.0 Reporter: Mark Nottingham Assignee: Alan M. Carroll Fix For: sometime New cache replacement algorithms are often proposed, and often it's not a one size fits all problem; different workloads require different approaches. To facilitate this, TS should have a pluggable cache replacement policy API, both for the memory and disk cache. Squid has done this to good effect; see http://www.squid-cache.org/cgi-bin/cvsweb.cgi/squid/src/repl/ -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-3164) why the load of trafficserver occurrs a abrupt rise on a occasion ?
[ https://issues.apache.org/jira/browse/TS-3164?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] James Peach updated TS-3164: Description: I use Tsar to monitor the traffic status of the ATS 4.2.0, and come across the following problem: {code} Time ---cpu-- ---mem-- ---tcp-- -traffic --sda--- --sdb--- --sdc--- ---load- Time util util retranbytin bytout util util util load1 03/11/14-18:20 40.6787.19 3.3624.5M 43.9M13.0294.68 0.00 5.34 03/11/14-18:25 40.3087.20 3.2722.5M 42.6M12.3894.87 0.00 5.79 03/11/14-18:30 40.8484.67 3.4421.4M 42.0M13.2995.37 0.00 6.28 03/11/14-18:35 43.6387.36 3.2123.8M 45.0M13.2393.99 0.00 7.37 03/11/14-18:40 42.2587.37 3.0924.2M 44.8M12.8495.77 0.00 7.25 03/11/14-18:45 42.9687.44 3.4623.3M 46.0M12.9695.84 0.00 7.10 03/11/14-18:50 44.0087.42 3.4922.3M 43.0M14.1794.99 0.00 6.57 03/11/14-18:55 42.2087.44 3.4622.3M 43.6M13.1996.05 0.00 6.09 03/11/14-19:00 44.9087.53 3.6023.6M 46.5M13.6196.67 0.00 8.06 03/11/14-19:05 46.2687.73 3.2425.8M 49.1M15.3994.05 0.00 9.98 03/11/14-19:10 43.8587.69 3.1925.4M 50.9M12.8897.80 0.00 7.99 03/11/14-19:15 45.2887.69 3.3625.6M 49.6M13.1096.86 0.00 7.47 03/11/14-19:20 44.1185.20 3.2924.1M 47.8M14.2496.75 0.00 5.82 03/11/14-19:25 45.2687.78 3.5224.4M 47.7M13.2195.44 0.00 7.61 03/11/14-19:30 44.8387.80 3.6425.7M 50.8M13.2798.02 0.00 6.85 03/11/14-19:35 44.8987.78 3.6123.9M 49.0M13.3497.42 0.00 7.04 03/11/14-19:40 69.2188.88 0.5518.3M 33.7M11.3971.23 0.00 65.80 03/11/14-19:45 72.4788.66 0.2715.4M 31.6M11.5172.31 0.00 11.56 03/11/14-19:50 44.8788.72 4.1122.7M 46.3M12.9997.33 0.00 8.29 {code} in addition, top command show {code} hi:0 ni:0 si:45.56 st:0 sy:13.92 us:12.58 wa:14.3 id:15.96 {code} who help me ? thanks in advance. was: I use Tsar to monitor the traffic status of the ATS 4.2.0, and come across the following problem: Time ---cpu-- ---mem-- ---tcp-- -traffic --sda--- --sdb--- --sdc--- ---load- Time util util retranbytin bytout util util util load1 03/11/14-18:20 40.6787.19 3.3624.5M 43.9M13.0294.68 0.00 5.34 03/11/14-18:25 40.3087.20 3.2722.5M 42.6M12.3894.87 0.00 5.79 03/11/14-18:30 40.8484.67 3.4421.4M 42.0M13.2995.37 0.00 6.28 03/11/14-18:35 43.6387.36 3.2123.8M 45.0M13.2393.99 0.00 7.37 03/11/14-18:40 42.2587.37 3.0924.2M 44.8M12.8495.77 0.00 7.25 03/11/14-18:45 42.9687.44 3.4623.3M 46.0M12.9695.84 0.00 7.10 03/11/14-18:50 44.0087.42 3.4922.3M 43.0M14.1794.99 0.00 6.57 03/11/14-18:55 42.2087.44 3.4622.3M 43.6M13.1996.05 0.00 6.09 03/11/14-19:00 44.9087.53 3.6023.6M 46.5M13.6196.67 0.00 8.06 03/11/14-19:05 46.2687.73 3.2425.8M 49.1M15.3994.05 0.00 9.98 03/11/14-19:10 43.8587.69 3.1925.4M 50.9M12.8897.80 0.00 7.99 03/11/14-19:15 45.2887.69 3.3625.6M 49.6M13.1096.86 0.00 7.47 03/11/14-19:20 44.1185.20 3.2924.1M 47.8M14.2496.75 0.00 5.82 03/11/14-19:25 45.2687.78 3.5224.4M 47.7M13.2195.44 0.00 7.61 03/11/14-19:30 44.8387.80 3.6425.7M 50.8M13.2798.02 0.00 6.85 03/11/14-19:35 44.8987.78 3.6123.9M 49.0M13.3497.42 0.00 7.04 03/11/14-19:40 69.2188.88 0.5518.3M 33.7M11.3971.23 0.00 65.80 03/11/14-19:45 72.4788.66 0.2715.4M 31.6M11.5172.31 0.00 11.56 03/11/14-19:50 44.8788.72 4.1122.7M 46.3M12.9997.33 0.00 8.29 in addition, top command show hi:0 ni:0 si:45.56 st:0 sy:13.92 us:12.58 wa:14.3 id:15.96 who help me ? thanks in advance. why the load of trafficserver occurrs a abrupt rise on a occasion ? --- Key: TS-3164 URL:
[jira] [Assigned] (TS-357) Compiling with -Wconversion generates a lot of errors
[ https://issues.apache.org/jira/browse/TS-357?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs reassigned TS-357: - Assignee: Susan Hinrichs Compiling with -Wconversion generates a lot of errors - Key: TS-357 URL: https://issues.apache.org/jira/browse/TS-357 Project: Traffic Server Issue Type: Improvement Components: Cleanup Affects Versions: 2.1.0 Reporter: Bryan Call Assignee: Susan Hinrichs Fix For: sometime After adding -Wconversion to CFLAGS and CXXFLAGS I got 11k errors: [bcall@snowball traffic.git]$ gmake -k 2 /dev/stdout | grep -c ' error: ' 11432 -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (TS-357) Compiling with -Wconversion generates a lot of errors
[ https://issues.apache.org/jira/browse/TS-357?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14196331#comment-14196331 ] Susan Hinrichs commented on TS-357: --- Bryan will check this out, because a number of these have been fixed in other efforts. Compiling with -Wconversion generates a lot of errors - Key: TS-357 URL: https://issues.apache.org/jira/browse/TS-357 Project: Traffic Server Issue Type: Improvement Components: Cleanup Affects Versions: 2.1.0 Reporter: Bryan Call Assignee: Bryan Call Fix For: sometime After adding -Wconversion to CFLAGS and CXXFLAGS I got 11k errors: [bcall@snowball traffic.git]$ gmake -k 2 /dev/stdout | grep -c ' error: ' 11432 -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-357) Compiling with -Wconversion generates a lot of errors
[ https://issues.apache.org/jira/browse/TS-357?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-357: -- Assignee: Bryan Call (was: Susan Hinrichs) Compiling with -Wconversion generates a lot of errors - Key: TS-357 URL: https://issues.apache.org/jira/browse/TS-357 Project: Traffic Server Issue Type: Improvement Components: Cleanup Affects Versions: 2.1.0 Reporter: Bryan Call Assignee: Bryan Call Fix For: sometime After adding -Wconversion to CFLAGS and CXXFLAGS I got 11k errors: [bcall@snowball traffic.git]$ gmake -k 2 /dev/stdout | grep -c ' error: ' 11432 -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (TS-3164) why the load of trafficserver occurrs a abrupt rise on a occasion ?
[ https://issues.apache.org/jira/browse/TS-3164?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14196335#comment-14196335 ] James Peach commented on TS-3164: - I suggest using standard Linux tools to investigate this. {strace} and {perf} could show you interesting data. why the load of trafficserver occurrs a abrupt rise on a occasion ? --- Key: TS-3164 URL: https://issues.apache.org/jira/browse/TS-3164 Project: Traffic Server Issue Type: Bug Components: Core Environment: CentOS 6.3 64bit, 8 cores, 128G mem Reporter: taoyunxing I use Tsar to monitor the traffic status of the ATS 4.2.0, and come across the following problem: {code} Time ---cpu-- ---mem-- ---tcp-- -traffic --sda--- --sdb--- --sdc--- ---load- Time util util retranbytin bytout util util util load1 03/11/14-18:20 40.6787.19 3.3624.5M 43.9M13.0294.68 0.00 5.34 03/11/14-18:25 40.3087.20 3.2722.5M 42.6M12.3894.87 0.00 5.79 03/11/14-18:30 40.8484.67 3.4421.4M 42.0M13.2995.37 0.00 6.28 03/11/14-18:35 43.6387.36 3.2123.8M 45.0M13.2393.99 0.00 7.37 03/11/14-18:40 42.2587.37 3.0924.2M 44.8M12.8495.77 0.00 7.25 03/11/14-18:45 42.9687.44 3.4623.3M 46.0M12.9695.84 0.00 7.10 03/11/14-18:50 44.0087.42 3.4922.3M 43.0M14.1794.99 0.00 6.57 03/11/14-18:55 42.2087.44 3.4622.3M 43.6M13.1996.05 0.00 6.09 03/11/14-19:00 44.9087.53 3.6023.6M 46.5M13.6196.67 0.00 8.06 03/11/14-19:05 46.2687.73 3.2425.8M 49.1M15.3994.05 0.00 9.98 03/11/14-19:10 43.8587.69 3.1925.4M 50.9M12.8897.80 0.00 7.99 03/11/14-19:15 45.2887.69 3.3625.6M 49.6M13.1096.86 0.00 7.47 03/11/14-19:20 44.1185.20 3.2924.1M 47.8M14.2496.75 0.00 5.82 03/11/14-19:25 45.2687.78 3.5224.4M 47.7M13.2195.44 0.00 7.61 03/11/14-19:30 44.8387.80 3.6425.7M 50.8M13.2798.02 0.00 6.85 03/11/14-19:35 44.8987.78 3.6123.9M 49.0M13.3497.42 0.00 7.04 03/11/14-19:40 69.2188.88 0.5518.3M 33.7M11.3971.23 0.00 65.80 03/11/14-19:45 72.4788.66 0.2715.4M 31.6M11.5172.31 0.00 11.56 03/11/14-19:50 44.8788.72 4.1122.7M 46.3M12.9997.33 0.00 8.29 {code} in addition, top command show {code} hi:0 ni:0 si:45.56 st:0 sy:13.92 us:12.58 wa:14.3 id:15.96 {code} who help me ? thanks in advance. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-382) socket option cleanup (and bug fixes)
[ https://issues.apache.org/jira/browse/TS-382?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-382: -- Assignee: (was: Alan M. Carroll) socket option cleanup (and bug fixes) --- Key: TS-382 URL: https://issues.apache.org/jira/browse/TS-382 Project: Traffic Server Issue Type: Bug Components: Network Reporter: Leif Hedstrom Fix For: sometime This is a bug moved from Y! Bugzilla, I'm posting the original bug description and a few comments separately. Note that the bug description is fairly limited, but while looking at this code, I noticed a lot of oddities with the socket option support (lots of hardcoded stuff, and most of it is not configurable). Note that the original bug should have been fixed already in Apache TS, but the other comments are still applicable. From Bugzilla (posted by Leif): We have two socket option config options in records.config: proxy.config.net.sock_option_flag_in proxy.config.net.sock_option_flag_out With accept thread enabled, at least the _in option isn't honored. There are possibly other cases in UnixNetAccept.cc that we don't honor these flags either. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-454) Dynamic resizing API stats
[ https://issues.apache.org/jira/browse/TS-454?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-454: -- Assignee: (was: Phil Sorber) Dynamic resizing API stats -- Key: TS-454 URL: https://issues.apache.org/jira/browse/TS-454 Project: Traffic Server Issue Type: Bug Components: Metrics Reporter: Leif Hedstrom Fix For: sometime This is a new bug, as introduced with TS-390. We do not properly allow to resize the librecords container, not allowing API (plugins) to create the requested number of stats slots. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Assigned] (TS-3165) Cache Toolkit API
[ https://issues.apache.org/jira/browse/TS-3165?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Alan M. Carroll reassigned TS-3165: --- Assignee: Alan M. Carroll Cache Toolkit API - Key: TS-3165 URL: https://issues.apache.org/jira/browse/TS-3165 Project: Traffic Server Issue Type: Improvement Components: Cache Reporter: Alan M. Carroll Assignee: Alan M. Carroll Implement the Cache Toolkit API as described in https://cwiki.apache.org/confluence/download/attachments/47384310/ApacheCon-2014-Cache-Toolkit.pdf?version=1modificationDate=1414085058000api=v2. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Created] (TS-3165) Cache Toolkit API
Alan M. Carroll created TS-3165: --- Summary: Cache Toolkit API Key: TS-3165 URL: https://issues.apache.org/jira/browse/TS-3165 Project: Traffic Server Issue Type: Improvement Components: Cache Reporter: Alan M. Carroll Implement the Cache Toolkit API as described in https://cwiki.apache.org/confluence/download/attachments/47384310/ApacheCon-2014-Cache-Toolkit.pdf?version=1modificationDate=1414085058000api=v2. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (TS-454) Dynamic resizing API stats
[ https://issues.apache.org/jira/browse/TS-454?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14196345#comment-14196345 ] Susan Hinrichs commented on TS-454: --- Related to work for reducing number of callbacks for states. Not sure there is a bug created for that work yet. [~jtblatt] is directing that effort. Dynamic resizing API stats -- Key: TS-454 URL: https://issues.apache.org/jira/browse/TS-454 Project: Traffic Server Issue Type: Bug Components: Metrics Reporter: Leif Hedstrom Fix For: sometime This is a new bug, as introduced with TS-390. We do not properly allow to resize the librecords container, not allowing API (plugins) to create the requested number of stats slots. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-464) Chunked response with bad Content-Length header to HTTP/1.0 client is broken
[ https://issues.apache.org/jira/browse/TS-464?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-464: -- Fix Version/s: (was: sometime) 5.3.0 Chunked response with bad Content-Length header to HTTP/1.0 client is broken Key: TS-464 URL: https://issues.apache.org/jira/browse/TS-464 Project: Traffic Server Issue Type: Bug Components: HTTP Reporter: Leif Hedstrom Assignee: Leif Hedstrom Labels: HTTP, Violation Fix For: 5.3.0 A client sends an HTTP/1.0 request through ATS, which gets proxied with HTTP/1.1 to the origin. The origin (which is at fault here, but nonetheless) returns with both Content-Length: 10 Transfer-Encoding: chunked and a chunked body which is 10 bytes long. In this case, ATS should still respond with an HTTP/1.0 response, undoing the chunking, and return with an appropriate CL: header. We do everything, except set the correct Content-Length header, we simply return the erroneous CL header that the Origin provided. This is not allowed in the RFC. (Originally discovered using Coadvisor). -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-464) Chunked response with bad Content-Length header to HTTP/1.0 client is broken
[ https://issues.apache.org/jira/browse/TS-464?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-464: -- Assignee: Leif Hedstrom Chunked response with bad Content-Length header to HTTP/1.0 client is broken Key: TS-464 URL: https://issues.apache.org/jira/browse/TS-464 Project: Traffic Server Issue Type: Bug Components: HTTP Reporter: Leif Hedstrom Assignee: Leif Hedstrom Labels: HTTP, Violation Fix For: 5.3.0 A client sends an HTTP/1.0 request through ATS, which gets proxied with HTTP/1.1 to the origin. The origin (which is at fault here, but nonetheless) returns with both Content-Length: 10 Transfer-Encoding: chunked and a chunked body which is 10 bytes long. In this case, ATS should still respond with an HTTP/1.0 response, undoing the chunking, and return with an appropriate CL: header. We do everything, except set the correct Content-Length header, we simply return the erroneous CL header that the Origin provided. This is not allowed in the RFC. (Originally discovered using Coadvisor). -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (TS-337) Cache Replacement Algorithm plug-in API
[ https://issues.apache.org/jira/browse/TS-337?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14196348#comment-14196348 ] Alan M. Carroll commented on TS-337: I will look at this as part of the Cache Toolkit work. Cache Replacement Algorithm plug-in API --- Key: TS-337 URL: https://issues.apache.org/jira/browse/TS-337 Project: Traffic Server Issue Type: New Feature Components: TS API Affects Versions: 2.0.0 Reporter: Mark Nottingham Assignee: Alan M. Carroll Fix For: sometime New cache replacement algorithms are often proposed, and often it's not a one size fits all problem; different workloads require different approaches. To facilitate this, TS should have a pluggable cache replacement policy API, both for the memory and disk cache. Squid has done this to good effect; see http://www.squid-cache.org/cgi-bin/cvsweb.cgi/squid/src/repl/ -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Assigned] (TS-467) Proxy should not forward request headers that matches a Connection token
[ https://issues.apache.org/jira/browse/TS-467?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs reassigned TS-467: - Assignee: Susan Hinrichs Proxy should not forward request headers that matches a Connection token Key: TS-467 URL: https://issues.apache.org/jira/browse/TS-467 Project: Traffic Server Issue Type: Bug Components: HTTP Reporter: Leif Hedstrom Assignee: Susan Hinrichs Labels: CoAdvisor Fix For: 5.3.0 If a client sends a request like X-foobar: fum Connection: ,,X-foobar,, the proxy (Traffic Server) MUST remove the header X-foobar before forwarding the request. From the RFC: HTTP/1.1 proxies MUST parse the Connection header field before a message is forwarded and, for each connection-token in this field, remove any header field(s) from the message with the same name as the connection-token. and A system receiving an HTTP/1.0 (or lower-version) message that includes a Connection header MUST, for each connection-token in this field, remove and ignore any header field(s) from the message with the same name as the connection-token. (Originally discovered with Coadvisor). -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-467) Proxy should not forward request headers that matches a Connection token
[ https://issues.apache.org/jira/browse/TS-467?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-467: -- Fix Version/s: (was: sometime) 5.3.0 Proxy should not forward request headers that matches a Connection token Key: TS-467 URL: https://issues.apache.org/jira/browse/TS-467 Project: Traffic Server Issue Type: Bug Components: HTTP Reporter: Leif Hedstrom Assignee: Susan Hinrichs Labels: CoAdvisor Fix For: 5.3.0 If a client sends a request like X-foobar: fum Connection: ,,X-foobar,, the proxy (Traffic Server) MUST remove the header X-foobar before forwarding the request. From the RFC: HTTP/1.1 proxies MUST parse the Connection header field before a message is forwarded and, for each connection-token in this field, remove any header field(s) from the message with the same name as the connection-token. and A system receiving an HTTP/1.0 (or lower-version) message that includes a Connection header MUST, for each connection-token in this field, remove and ignore any header field(s) from the message with the same name as the connection-token. (Originally discovered with Coadvisor). -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-469) A PUT request should invalidate a previously cached object with the same URI
[ https://issues.apache.org/jira/browse/TS-469?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-469: -- Assignee: (was: Bryan Call) A PUT request should invalidate a previously cached object with the same URI Key: TS-469 URL: https://issues.apache.org/jira/browse/TS-469 Project: Traffic Server Issue Type: Bug Components: HTTP Affects Versions: 2.1.6 Reporter: Leif Hedstrom Labels: CoAdvisor Fix For: sometime If the client first fetches an object with GET, and TS caches it, a subsequent PUT request for the same URL should invalidate the cached object. Update: This is a problem with PUT/POST when the response from the origin is a 201, and there is a Location: header. We then must also invalidate any cached object for the URL which the Location header refers to (Originally discovered with Coadvisor). -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-469) A PUT request should invalidate a previously cached object with the same URI
[ https://issues.apache.org/jira/browse/TS-469?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-469: -- Fix Version/s: (was: 5.2.0) sometime A PUT request should invalidate a previously cached object with the same URI Key: TS-469 URL: https://issues.apache.org/jira/browse/TS-469 Project: Traffic Server Issue Type: Bug Components: HTTP Affects Versions: 2.1.6 Reporter: Leif Hedstrom Labels: CoAdvisor Fix For: sometime If the client first fetches an object with GET, and TS caches it, a subsequent PUT request for the same URL should invalidate the cached object. Update: This is a problem with PUT/POST when the response from the origin is a 201, and there is a Location: header. We then must also invalidate any cached object for the URL which the Location header refers to (Originally discovered with Coadvisor). -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Assigned] (TS-481) Missing remap support for two cases
[ https://issues.apache.org/jira/browse/TS-481?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs reassigned TS-481: - Assignee: Susan Hinrichs Missing remap support for two cases --- Key: TS-481 URL: https://issues.apache.org/jira/browse/TS-481 Project: Traffic Server Issue Type: Bug Components: HTTP Reporter: Leif Hedstrom Assignee: Susan Hinrichs Fix For: sometime There are two cases where the remap processor is not used, but it should. As of v2.1.4, the broken support was removed (broken code is worse than no code), making two cases not use / support remap features. Both cases currently call request_url_remap() which is now set to return false. The two cases are 1) If you configure remap mode to be URL_REMAP_FOR_OS (2). This is an undocumented feature, I don't even know when or why you'd want to use it. The setting in RecordsConfig.cc is proxy.config.url_remap.url_remap_mode, which defaults to 1. 2) If TS uses raw connections, I think for example when using the CONNECT method, we will not do remap rules. This would be in a forward proxy mode, primarily for things like HTTPS afaik. I don't think either case are critical to get support for the remap processor for v2.2, but please adjust the fix version if necessary. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-481) Missing remap support for two cases
[ https://issues.apache.org/jira/browse/TS-481?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-481: -- Assignee: Leif Hedstrom (was: Susan Hinrichs) Missing remap support for two cases --- Key: TS-481 URL: https://issues.apache.org/jira/browse/TS-481 Project: Traffic Server Issue Type: Bug Components: HTTP Reporter: Leif Hedstrom Assignee: Leif Hedstrom Fix For: sometime There are two cases where the remap processor is not used, but it should. As of v2.1.4, the broken support was removed (broken code is worse than no code), making two cases not use / support remap features. Both cases currently call request_url_remap() which is now set to return false. The two cases are 1) If you configure remap mode to be URL_REMAP_FOR_OS (2). This is an undocumented feature, I don't even know when or why you'd want to use it. The setting in RecordsConfig.cc is proxy.config.url_remap.url_remap_mode, which defaults to 1. 2) If TS uses raw connections, I think for example when using the CONNECT method, we will not do remap rules. This would be in a forward proxy mode, primarily for things like HTTPS afaik. I don't think either case are critical to get support for the remap processor for v2.2, but please adjust the fix version if necessary. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Assigned] (TS-510) API: Add documentation for HTTP Status code counters in stats (TS-509)
[ https://issues.apache.org/jira/browse/TS-510?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs reassigned TS-510: - Assignee: Susan Hinrichs API: Add documentation for HTTP Status code counters in stats (TS-509) -- Key: TS-510 URL: https://issues.apache.org/jira/browse/TS-510 Project: Traffic Server Issue Type: Bug Components: Documentation, TS API Affects Versions: 2.1.6 Reporter: Theo Schlossnagle Assignee: Susan Hinrichs Fix For: Docs -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Assigned] (TS-518) Close UA connection early if the origin sent Connection close:, there's a bad Content-Length header, and the UA connection has Keep-Alive.
[ https://issues.apache.org/jira/browse/TS-518?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs reassigned TS-518: - Assignee: Susan Hinrichs (was: James Peach) Close UA connection early if the origin sent Connection close:, there's a bad Content-Length header, and the UA connection has Keep-Alive. -- Key: TS-518 URL: https://issues.apache.org/jira/browse/TS-518 Project: Traffic Server Issue Type: Bug Components: HTTP Reporter: Leif Hedstrom Assignee: Susan Hinrichs Fix For: 5.2.0 In a very special case, we could improve the user experience by forcefully closing the connection early. The case is 1) The origin server sends a Content-Length: header that is wrong, where the CL: value exceeds the actually body size. 2) The origin server either sends a Connection: close, or it uses HTTP/1.0 without keep-alive. 3) The client (and TS) uses Keep-Alive to the UA. In this case, we can end up stalling the UA until either the UA or the TS connection times out. It might make sense to prematurely disconnect the client when this case is detected. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (TS-518) Close UA connection early if the origin sent Connection close:, there's a bad Content-Length header, and the UA connection has Keep-Alive.
[ https://issues.apache.org/jira/browse/TS-518?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14196370#comment-14196370 ] Alan M. Carroll commented on TS-518: Is it presumed the origin server has sent a FIN or RST on the connection? Close UA connection early if the origin sent Connection close:, there's a bad Content-Length header, and the UA connection has Keep-Alive. -- Key: TS-518 URL: https://issues.apache.org/jira/browse/TS-518 Project: Traffic Server Issue Type: Bug Components: HTTP Reporter: Leif Hedstrom Assignee: Susan Hinrichs Fix For: 5.2.0 In a very special case, we could improve the user experience by forcefully closing the connection early. The case is 1) The origin server sends a Content-Length: header that is wrong, where the CL: value exceeds the actually body size. 2) The origin server either sends a Connection: close, or it uses HTTP/1.0 without keep-alive. 3) The client (and TS) uses Keep-Alive to the UA. In this case, we can end up stalling the UA until either the UA or the TS connection times out. It might make sense to prematurely disconnect the client when this case is detected. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-608) Is HttpSessionManager::purge_keepalives() too aggressive?
[ https://issues.apache.org/jira/browse/TS-608?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-608: -- Assignee: (was: Bin Chen) Is HttpSessionManager::purge_keepalives() too aggressive? -- Key: TS-608 URL: https://issues.apache.org/jira/browse/TS-608 Project: Traffic Server Issue Type: Bug Components: HTTP Reporter: Leif Hedstrom Fix For: 5.2.0 Attachments: TS-608.patch It seems that if we trigger the max server connections, we call this purge function in the session manager, which will close all currently open keep-alive connections. This seems very aggressive, why not limit it to say only removing 10% of each bucket or some such? Also, how does this work together with per-origin limits? Ideally, if the per-origin limits are in place, we would only purge sessions that are for the IP we wish to connect to ? -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-608) Is HttpSessionManager::purge_keepalives() too aggressive?
[ https://issues.apache.org/jira/browse/TS-608?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-608: -- Assignee: Bryan Call Is HttpSessionManager::purge_keepalives() too aggressive? -- Key: TS-608 URL: https://issues.apache.org/jira/browse/TS-608 Project: Traffic Server Issue Type: Bug Components: HTTP Reporter: Leif Hedstrom Assignee: Bryan Call Fix For: 5.2.0 Attachments: TS-608.patch It seems that if we trigger the max server connections, we call this purge function in the session manager, which will close all currently open keep-alive connections. This seems very aggressive, why not limit it to say only removing 10% of each bucket or some such? Also, how does this work together with per-origin limits? Ideally, if the per-origin limits are in place, we would only purge sessions that are for the IP we wish to connect to ? -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-641) WebUI: Kill it with fire.
[ https://issues.apache.org/jira/browse/TS-641?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-641: -- Assignee: Leif Hedstrom WebUI: Kill it with fire. - Key: TS-641 URL: https://issues.apache.org/jira/browse/TS-641 Project: Traffic Server Issue Type: Improvement Components: Web UI Reporter: Igor Galić Assignee: Leif Hedstrom Fix For: sometime Original Estimate: 14m Remaining Estimate: 14m Get rid of proxy/mgmt/html2 Get rid of all code in proxy/mgmt/web2 that is not used Merge used code into proxy/mgmt/utils/WebMgmtUtils.* -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-654) request for support of Layer7 http health checking for Origin Servers
[ https://issues.apache.org/jira/browse/TS-654?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-654: -- Assignee: Alan M. Carroll (was: portl4t) request for support of Layer7 http health checking for Origin Servers - Key: TS-654 URL: https://issues.apache.org/jira/browse/TS-654 Project: Traffic Server Issue Type: New Feature Components: HTTP Affects Versions: 3.0.0 Reporter: Zhao Yongming Assignee: Alan M. Carroll Attachments: HCUtil.cc, hc.patch this ticket is for the L7 health checking project: https://cwiki.apache.org/confluence/display/TS/HttpHealthCheck -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-654) request for support of Layer7 http health checking for Origin Servers
[ https://issues.apache.org/jira/browse/TS-654?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-654: -- Fix Version/s: (was: 5.3.0) request for support of Layer7 http health checking for Origin Servers - Key: TS-654 URL: https://issues.apache.org/jira/browse/TS-654 Project: Traffic Server Issue Type: New Feature Components: HTTP Affects Versions: 3.0.0 Reporter: Zhao Yongming Assignee: Alan M. Carroll Attachments: HCUtil.cc, hc.patch this ticket is for the L7 health checking project: https://cwiki.apache.org/confluence/display/TS/HttpHealthCheck -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Created] (TS-3166) HostDB Upgrade
Alan M. Carroll created TS-3166: --- Summary: HostDB Upgrade Key: TS-3166 URL: https://issues.apache.org/jira/browse/TS-3166 Project: Traffic Server Issue Type: Improvement Components: HostDB, DNS Reporter: Alan M. Carroll Implement the HostDB upgrade as described in https://cwiki.apache.org/confluence/download/attachments/47384310/ApacheCon-2014-Host-Resolution.pdf?version=1modificationDate=1414085058000api=v2 -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-658) HTTP SM holds the cache write lock for too long
[ https://issues.apache.org/jira/browse/TS-658?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-658: -- Assignee: Alan M. Carroll (was: Phil Sorber) HTTP SM holds the cache write lock for too long --- Key: TS-658 URL: https://issues.apache.org/jira/browse/TS-658 Project: Traffic Server Issue Type: Bug Components: HTTP Reporter: Leif Hedstrom Assignee: Alan M. Carroll Labels: A Fix For: 5.2.0 It seems we open the cache for write very early on in the HTTP SM, which can have very bad effect on performance if the object is not cacheable. It's not totally clear as to why this is done this way, but we should examine this for v3.1, and try to minimize how long we hold the lock. It's possible this is related to read_while_writer, but then it should be modified IMO. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Closed] (TS-656) reimplement Connection Collapsing in a smooth way
[ https://issues.apache.org/jira/browse/TS-656?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs closed TS-656. - Resolution: Duplicate Addressed via documentation. Remainder addressed by ts-2604. reimplement Connection Collapsing in a smooth way - Key: TS-656 URL: https://issues.apache.org/jira/browse/TS-656 Project: Traffic Server Issue Type: Improvement Components: HTTP Affects Versions: 2.1.6 Environment: per discussed in IRC, we'd like to clean the current CC codes from trunk. Reporter: Zhao Yongming Fix For: 5.3.0 we should figure out how to implement the Connection Collapsing that not so ugly. target for V3.1 or so. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-656) reimplement Connection Collapsing in a smooth way
[ https://issues.apache.org/jira/browse/TS-656?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-656: -- Fix Version/s: (was: 5.3.0) reimplement Connection Collapsing in a smooth way - Key: TS-656 URL: https://issues.apache.org/jira/browse/TS-656 Project: Traffic Server Issue Type: Improvement Components: HTTP Affects Versions: 2.1.6 Environment: per discussed in IRC, we'd like to clean the current CC codes from trunk. Reporter: Zhao Yongming we should figure out how to implement the Connection Collapsing that not so ugly. target for V3.1 or so. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-658) HTTP SM holds the cache write lock for too long
[ https://issues.apache.org/jira/browse/TS-658?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-658: -- Fix Version/s: (was: 5.2.0) sometime HTTP SM holds the cache write lock for too long --- Key: TS-658 URL: https://issues.apache.org/jira/browse/TS-658 Project: Traffic Server Issue Type: Bug Components: HTTP Reporter: Leif Hedstrom Assignee: Alan M. Carroll Labels: A Fix For: sometime It seems we open the cache for write very early on in the HTTP SM, which can have very bad effect on performance if the object is not cacheable. It's not totally clear as to why this is done this way, but we should examine this for v3.1, and try to minimize how long we hold the lock. It's possible this is related to read_while_writer, but then it should be modified IMO. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Closed] (TS-727) Do we need support for streams partitions?
[ https://issues.apache.org/jira/browse/TS-727?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs closed TS-727. - Resolution: Duplicate Do we need support for streams partitions? Key: TS-727 URL: https://issues.apache.org/jira/browse/TS-727 Project: Traffic Server Issue Type: Improvement Components: Cache Reporter: Leif Hedstrom Assignee: Alan M. Carroll Labels: CacheToolKit Fix For: 6.0.0 There's code in the cache related to MIXT streams volumes (caches). Since we don't support streams, I'm thinking this code could be removed? Or alternatively, we should expose APIs so that someone writing a plugin and wish to store a different protocol (e.g. QT) can register this media type with the API and core. The idea being that the core only contains protocols that are in the core, but expose the cache core so that plugins can take advantage of it. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-727) Do we need support for streams partitions?
[ https://issues.apache.org/jira/browse/TS-727?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-727: -- Fix Version/s: (was: 6.0.0) Do we need support for streams partitions? Key: TS-727 URL: https://issues.apache.org/jira/browse/TS-727 Project: Traffic Server Issue Type: Improvement Components: Cache Reporter: Leif Hedstrom Assignee: Alan M. Carroll Labels: CacheToolKit There's code in the cache related to MIXT streams volumes (caches). Since we don't support streams, I'm thinking this code could be removed? Or alternatively, we should expose APIs so that someone writing a plugin and wish to store a different protocol (e.g. QT) can register this media type with the API and core. The idea being that the core only contains protocols that are in the core, but expose the cache core so that plugins can take advantage of it. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Closed] (TS-767) Make the cluster interface configurable
[ https://issues.apache.org/jira/browse/TS-767?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs closed TS-767. - Resolution: Duplicate Fix Version/s: (was: sometime) Already addressed by Http proxy port issues. Make the cluster interface configurable --- Key: TS-767 URL: https://issues.apache.org/jira/browse/TS-767 Project: Traffic Server Issue Type: Improvement Components: Configuration, Network Affects Versions: 2.1.8 Reporter: Arno Toell Priority: Minor I consider the way how Traffic Server opens listening ports dangerous, or at least more risky than necessary. Currently ATS allows to configure port numbers for the related services, but not the listening interface. Instead it binds to 0.0.0.0. Therefore I'd like to suggest * -Allow the user to specify a listening interface, don't assume 0.0.0.0 suits for all setups.- * -Disable the autoconfiguration port (i.e. 8083 by default) unless proxy.local.cluster.type is set to enable clustering (!= 3). I think _traffic_shell_ and eventually _traffic_line_ use this port to configure ATS locally. If so it should be bound to the loop back at least or using Unix Domain Sockets or whatever local socket method you prefer.- * Disable the reliable service port (i.e. 8088 by default) unless proxy.local.cluster.type enables clustering. Similar to the autoconfiguration port. If _traffic_cop_ (or something else on the local machine) is using this port, the same suggestions apply as above. * -The internal communication port (8084) should not open a public socket at all. Instead use Unix Domain Sockets or something similar.- n.b. striked through issues are obsolete or tracked in TS-765. For the remaining issue is worth to be added the comment from TS-765: 8088 is no problem anymore until clustering is enabled, so there is only the TS-766 improvement left there. However if enabled, I think it is still fairly useful to allow the user to bind to a specific IP. Say, you run a public facing proxy in cluster mode where you want to communicate in between on private IPs between cluster peers. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-777) Increasing logbuffer size makes us drop log entries
[ https://issues.apache.org/jira/browse/TS-777?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-777: -- Fix Version/s: (was: 5.2.0) 5.3.0 Increasing logbuffer size makes us drop log entries - Key: TS-777 URL: https://issues.apache.org/jira/browse/TS-777 Project: Traffic Server Issue Type: Bug Components: Logging Affects Versions: 2.1.8 Reporter: Leif Hedstrom Assignee: Leif Hedstrom Labels: A Fix For: 5.3.0 Setting proxy.config.log.log_buffer_size higher than somewhere around 24KB makes us start losing log entries. This is bad, since increasing this setting could be a way to increase performance for busy systems. I've for now set the defaults to 16KB, which seems to be stable. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-795) Clean up definitions and usage of buffer size indexes vs buffer sizes
[ https://issues.apache.org/jira/browse/TS-795?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-795: -- Fix Version/s: (was: 5.2.0) sometime Clean up definitions and usage of buffer size indexes vs buffer sizes - Key: TS-795 URL: https://issues.apache.org/jira/browse/TS-795 Project: Traffic Server Issue Type: Improvement Components: Core Reporter: Leif Hedstrom Fix For: sometime Right now, we have a set of defines, and APIs, which can take either a index to a size (used e.g. for an allocator index), or a real size. Both of these are currently int64_t in all APIs and member variables, and in the implementations, the usage are sometimes overloaded (i.e. we do size calculations on top of the indexes, making for real confusing code). There's also a lack of proper identification of what is an size index type (or parameter), and what is a size. This makes for risky code. I think we should clean up all the implementations and APIs, as follow 1) Make proper names of all APIs and macros, clearly indicating if it's working on a size index or a size. 2) Keep only the size types, parameters and macros using int64_t. Do not overload real size over the size indexes. 3) We either make the size indexes an int (or even a short), or perhaps even better an enum (like below). All APIs, parameters, and member variables that refer to such size indexes would use this appropriate type. {code} enum BufferSizeIndex { BUFFER_SIZE_INDEX_128 = 0, BUFFER_SIZE_INDEX_256, /* 1 */ BUFFER_SIZE_INDEX_512, /* 2 */ BUFFER_SIZE_INDEX_1K,/* 3 */ BUFFER_SIZE_INDEX_2K,/* 4 */ BUFFER_SIZE_INDEX_4K,/* 5 */ BUFFER_SIZE_INDEX_8K,/* 6 */ BUFFER_SIZE_INDEX_16K, /* 7 */ BUFFER_SIZE_INDEX_32K, /* 8 */ BUFFER_SIZE_INDEX_64K, /* 9 */ BUFFER_SIZE_INDEX_128K, /* 10 */ BUFFER_SIZE_INDEX_256K, /* 11 */ BUFFER_SIZE_INDEX_512K, /* 12 */ BUFFER_SIZE_INDEX_1M,/* 13 */ BUFFER_SIZE_INDEX_2M,/* 14 */ /* These have special semantics */ BUFFER_SIZE_NOT_ALLOCATED, }; {code} -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (TS-795) Clean up definitions and usage of buffer size indexes vs buffer sizes
[ https://issues.apache.org/jira/browse/TS-795?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14196430#comment-14196430 ] Alan M. Carroll commented on TS-795: I should contribute my NumericTypeId class for this. Clean up definitions and usage of buffer size indexes vs buffer sizes - Key: TS-795 URL: https://issues.apache.org/jira/browse/TS-795 Project: Traffic Server Issue Type: Improvement Components: Core Reporter: Leif Hedstrom Fix For: sometime Right now, we have a set of defines, and APIs, which can take either a index to a size (used e.g. for an allocator index), or a real size. Both of these are currently int64_t in all APIs and member variables, and in the implementations, the usage are sometimes overloaded (i.e. we do size calculations on top of the indexes, making for real confusing code). There's also a lack of proper identification of what is an size index type (or parameter), and what is a size. This makes for risky code. I think we should clean up all the implementations and APIs, as follow 1) Make proper names of all APIs and macros, clearly indicating if it's working on a size index or a size. 2) Keep only the size types, parameters and macros using int64_t. Do not overload real size over the size indexes. 3) We either make the size indexes an int (or even a short), or perhaps even better an enum (like below). All APIs, parameters, and member variables that refer to such size indexes would use this appropriate type. {code} enum BufferSizeIndex { BUFFER_SIZE_INDEX_128 = 0, BUFFER_SIZE_INDEX_256, /* 1 */ BUFFER_SIZE_INDEX_512, /* 2 */ BUFFER_SIZE_INDEX_1K,/* 3 */ BUFFER_SIZE_INDEX_2K,/* 4 */ BUFFER_SIZE_INDEX_4K,/* 5 */ BUFFER_SIZE_INDEX_8K,/* 6 */ BUFFER_SIZE_INDEX_16K, /* 7 */ BUFFER_SIZE_INDEX_32K, /* 8 */ BUFFER_SIZE_INDEX_64K, /* 9 */ BUFFER_SIZE_INDEX_128K, /* 10 */ BUFFER_SIZE_INDEX_256K, /* 11 */ BUFFER_SIZE_INDEX_512K, /* 12 */ BUFFER_SIZE_INDEX_1M,/* 13 */ BUFFER_SIZE_INDEX_2M,/* 14 */ /* These have special semantics */ BUFFER_SIZE_NOT_ALLOCATED, }; {code} -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Closed] (TS-802) Unique KA pools for SOCKS/src IP parameters
[ https://issues.apache.org/jira/browse/TS-802?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs closed TS-802. - Resolution: Duplicate Unique KA pools for SOCKS/src IP parameters --- Key: TS-802 URL: https://issues.apache.org/jira/browse/TS-802 Project: Traffic Server Issue Type: Wish Components: HTTP Reporter: M. Nunberg Fix For: sometime From what I've observed, ATS' keepalive/connection cache only indexes by the OS server or next proxy server, but not by other types of connection/transport/socket parameters, specifically in my case, negotiated SOCKS connections and outgoing connections which are bound to a specific source IP Is it possible to have such functionality in the near future? Currently I've been forced to write my own 'KA gateway' which pretends to be an HTTP server (to which ATS can maintain unique connections) and have that do SOCKS/source ip bind()ing for me. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-802) Unique KA pools for SOCKS/src IP parameters
[ https://issues.apache.org/jira/browse/TS-802?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-802: -- Fix Version/s: (was: sometime) Unique KA pools for SOCKS/src IP parameters --- Key: TS-802 URL: https://issues.apache.org/jira/browse/TS-802 Project: Traffic Server Issue Type: Wish Components: HTTP Reporter: M. Nunberg From what I've observed, ATS' keepalive/connection cache only indexes by the OS server or next proxy server, but not by other types of connection/transport/socket parameters, specifically in my case, negotiated SOCKS connections and outgoing connections which are bound to a specific source IP Is it possible to have such functionality in the near future? Currently I've been forced to write my own 'KA gateway' which pretends to be an HTTP server (to which ATS can maintain unique connections) and have that do SOCKS/source ip bind()ing for me. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Closed] (TS-803) Fix SOCKS breakage and allow for setting next-hop SOCKS
[ https://issues.apache.org/jira/browse/TS-803?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs closed TS-803. - Resolution: Won't Fix Fix Version/s: (was: sometime) If someone wishes to fix, please provide a patch against the current master. Fix SOCKS breakage and allow for setting next-hop SOCKS --- Key: TS-803 URL: https://issues.apache.org/jira/browse/TS-803 Project: Traffic Server Issue Type: New Feature Components: Network Affects Versions: 3.0.0 Environment: Wherever ATS might run Reporter: M. Nunberg Here is a patch I drew up a few months ago against a snapshot of ATS/2.1.7 unstable/git. There are some quirks here, and I'm not that sure any more what this patch does exactly. However it: 1) Does fix SOCKS connections in general 2) Allows setting next-hop SOCKS proxy via the API Problems: See https://issues.apache.org/jira/browse/TS-802 This has no effect on connections which are drawn from the connection pool, as it seems ATS currently doesn't maintain unique identities for peripheral connection params (source IP, SOCKS etc); i.e. this only affects new TCP connections to an OS. diff -x '*.o' -ru tsorig/iocore/net/I_NetVConnection.h tsgit217/iocore/net/I_NetVConnection.h --- tsorig/iocore/net/I_NetVConnection.h2011-03-09 21:43:58.0 + +++ tsgit217/iocore/net/I_NetVConnection.h2011-03-17 14:37:18.0 + @@ -120,6 +120,13 @@ /// Version of SOCKS to use. unsigned char socks_version; + struct { + unsigned int ip; + int port; + char *username; + char *password; + } socks_override; + int socket_recv_bufsize; int socket_send_bufsize; Only in tsgit217/iocore/net: Makefile Only in tsgit217/iocore/net: Makefile.in diff -x '*.o' -ru tsorig/iocore/net/P_Socks.h tsgit217/iocore/net/P_Socks.h --- tsorig/iocore/net/P_Socks.h2011-03-09 21:43:58.0 + +++ tsgit217/iocore/net/P_Socks.h2011-03-17 13:17:20.0 + @@ -126,7 +126,7 @@ unsigned char version; bool write_done; - + bool manual_parent_selection; SocksAuthHandler auth_handler; unsigned char socks_cmd; @@ -145,7 +145,8 @@ SocksEntry():Continuation(NULL), netVConnection(0), ip(0), port(0), server_ip(0), server_port(0), nattempts(0), -lerrno(0), timeout(0), version(5), write_done(false), auth_handler(NULL), socks_cmd(NORMAL_SOCKS) +lerrno(0), timeout(0), version(5), write_done(false), manual_parent_selection(false), +auth_handler(NULL), socks_cmd(NORMAL_SOCKS) { } }; diff -x '*.o' -ru tsorig/iocore/net/Socks.cc tsgit217/iocore/net/Socks.cc --- tsorig/iocore/net/Socks.cc2011-03-09 21:43:58.0 + +++ tsgit217/iocore/net/Socks.cc2011-03-17 13:46:07.0 + @@ -73,7 +73,8 @@ nattempts = 0; findServer(); - timeout = this_ethread()-schedule_in(this, HRTIME_SECONDS(netProcessor.socks_conf_stuff-server_connect_timeout)); +// timeout = this_ethread()-schedule_in(this, HRTIME_SECONDS(netProcessor.socks_conf_stuff-server_connect_timeout)); + timeout = this_ethread()-schedule_in(this, HRTIME_SECONDS(5)); write_done = false; } @@ -81,6 +82,15 @@ SocksEntry::findServer() { nattempts++; + if(manual_parent_selection) { + if(nattempts 1) { + //Nullify IP and PORT + server_ip = -1; + server_port = 0; + } + Debug(mndebug(Socks), findServer() is a noop with manual socks selection); + return; + } #ifdef SOCKS_WITH_TS if (nattempts == 1) { @@ -187,7 +197,6 @@ } Debug(Socks, Failed to connect to %u.%u.%u.%u:%d, PRINT_IP(server_ip), server_port); - findServer(); if (server_ip == (uint32_t) - 1) { diff -x '*.o' -ru tsorig/iocore/net/UnixNetProcessor.cc tsgit217/iocore/net/UnixNetProcessor.cc --- tsorig/iocore/net/UnixNetProcessor.cc2011-03-09 21:43:58.0 + +++ tsgit217/iocore/net/UnixNetProcessor.cc2011-03-17 15:48:38.0 + @@ -228,6 +228,11 @@ !socks_conf_stuff-ip_range.match(ip)) #endif ); + if(opt-socks_override.ip = 1) { + using_socks = true; + Debug(mndebug, trying to set using_socks to true); + } + SocksEntry *socksEntry = NULL; #endif NET_SUM_GLOBAL_DYN_STAT(net_connections_currently_open_stat, 1); @@ -242,6 +247,16 @@ if (using_socks) { Debug(Socks, Using Socks ip: %u.%u.%u.%u:%d\n, PRINT_IP(ip), port); socksEntry = socksAllocator.alloc(); + +if (opt-socks_override.ip) { +//Needs to be done before socksEntry-init() +socksEntry-server_ip = opt-socks_override.ip; +socksEntry-server_port = opt-socks_override.port; +socksEntry-manual_parent_selection
[jira] [Closed] (TS-817) TSFetchUrl/TSFetchPages does not work with HTTP/1.1 requests
[ https://issues.apache.org/jira/browse/TS-817?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs closed TS-817. - Resolution: Invalid Fix Version/s: (was: 5.2.0) TSFetchUrl/TSFetchPages does not work with HTTP/1.1 requests Key: TS-817 URL: https://issues.apache.org/jira/browse/TS-817 Project: Traffic Server Issue Type: Bug Components: TS API Affects Versions: 3.0.0 Reporter: Naveen Labels: api-change, function The API calls TSFetchUrl/TSFetchPages do not work with HTTP/1.1 requests. The implementation seems to use the end of the connection to signal the user callback function, which is not the case on persistent connections. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-829) socks stats cleanup - some stats are registered, but not used
[ https://issues.apache.org/jira/browse/TS-829?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-829: -- Fix Version/s: (was: sometime) 5.3.0 socks stats cleanup - some stats are registered, but not used - Key: TS-829 URL: https://issues.apache.org/jira/browse/TS-829 Project: Traffic Server Issue Type: Bug Components: Network Affects Versions: 3.0.0 Reporter: Bryan Call Priority: Minor Fix For: 5.3.0 From reviewing TS-818 I noticed that the stats that were being double resisted are not used. Some cleanup work should be done for the socks stats. Stats that are registered, but not used in the code: [bcall@snowball traffic.git]$ grep -r proxy.process.socks iocore/net/Net.cc proxy.process.socks.connections_successful, proxy.process.socks.connections_unsuccessful, proxy.process.socks.connections_currently_open, These stats are used some tests, so maybe they should be added back into the code. [bcall@snowball traffic.git]$ grep -rl --binary-files=without-match proxy.process.socks.connections_ * iocore/net/Net.cc mgmt/api/remote/APITestCliRemote.cc test/plugin/test-mgmt/test-mgmt.c I did however see these stats being used: [bcall@snowball traffic.git]$ grep -r SOCKSPROXY_ * proxy/SocksProxy.cc:#define SOCKSPROXY_INC_STAT(x) \ proxy/SocksProxy.cc: SOCKSPROXY_INC_STAT(socksproxy_http_connections_stat); proxy/SocksProxy.cc: SOCKSPROXY_INC_STAT(socksproxy_tunneled_connections_stat); -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-829) socks stats cleanup - some stats are registered, but not used
[ https://issues.apache.org/jira/browse/TS-829?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-829: -- Assignee: Bryan Call socks stats cleanup - some stats are registered, but not used - Key: TS-829 URL: https://issues.apache.org/jira/browse/TS-829 Project: Traffic Server Issue Type: Bug Components: Network Affects Versions: 3.0.0 Reporter: Bryan Call Assignee: Bryan Call Priority: Minor Fix For: 5.3.0 From reviewing TS-818 I noticed that the stats that were being double resisted are not used. Some cleanup work should be done for the socks stats. Stats that are registered, but not used in the code: [bcall@snowball traffic.git]$ grep -r proxy.process.socks iocore/net/Net.cc proxy.process.socks.connections_successful, proxy.process.socks.connections_unsuccessful, proxy.process.socks.connections_currently_open, These stats are used some tests, so maybe they should be added back into the code. [bcall@snowball traffic.git]$ grep -rl --binary-files=without-match proxy.process.socks.connections_ * iocore/net/Net.cc mgmt/api/remote/APITestCliRemote.cc test/plugin/test-mgmt/test-mgmt.c I did however see these stats being used: [bcall@snowball traffic.git]$ grep -r SOCKSPROXY_ * proxy/SocksProxy.cc:#define SOCKSPROXY_INC_STAT(x) \ proxy/SocksProxy.cc: SOCKSPROXY_INC_STAT(socksproxy_http_connections_stat); proxy/SocksProxy.cc: SOCKSPROXY_INC_STAT(socksproxy_tunneled_connections_stat); -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-852) hostdb and dns system hangup
[ https://issues.apache.org/jira/browse/TS-852?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-852: -- Fix Version/s: (was: sometime) hostdb and dns system hangup Key: TS-852 URL: https://issues.apache.org/jira/browse/TS-852 Project: Traffic Server Issue Type: Bug Components: Core, DNS Affects Versions: 3.1.0 Reporter: Zhao Yongming Assignee: Phil Sorber Priority: Minor Labels: dns, hostdb Fix For: 3.1.0 Attachments: TS-852.patch in my testing, all request that need go OS, fails with 30s timeout, and the slow query shows data from dns missed: {code} [Jun 22 15:33:47.183] Server {1106880832} ERROR: [8122411] Slow Request: url: http://download.im.alisoft.com/aliim/AliIM6/update/packages//2011-5-4-10-10-40/0/modulesproxy/8203.xml.wwzip status: 0 unique id: bytes: 0 fd: 0 client state: 6 server state: 0 ua_begin: 0.000 ua_read_header_done: 0.000 cache_open_read_begin: 0.000 cache_open_read_end: 0.000 dns_lookup_begin: 0.000 dns_lookup_end: -1.000 server_connect: -1.000 server_first_read: -1.000 server_read_header_done: -1.000 server_close: -1.000 ua_close: 30.667 sm_finish: 30.667 [Jun 22 15:33:47.220] Server {1099663680} ERROR: [8122422] Slow Request: url: http://img.uu1001.cn/materials/original/2010-11-22/22-48/a302876929a9c40a8272ac439a16ad25e74edf71.png status: 0 unique id: bytes: 0 fd: 0 client state: 6 server state: 0 ua_begin: 0.000 ua_read_header_done: 0.000 cache_open_read_begin: 0.000 cache_open_read_end: 0.000 dns_lookup_begin: 0.000 dns_lookup_end: -1.000 server_connect: -1.000 server_first_read: -1.000 server_read_header_done: -1.000 server_close: -1.000 ua_close: 30.318 sm_finish: 30.318 [Jun 22 15:33:47.441] Server {1098611008} ERROR: [8122421] Slow Request: url: http://img02.taobaocdn.com/bao/uploaded/i2/T1mp8QXopdXXblNIZ6_061203.jpg_b.jpg status: 0 unique id: bytes: 0 fd: 0 client state: 6 server state: 0 ua_begin: 0.000 ua_read_header_done: 0.000 cache_open_read_begin: 0.000 cache_open_read_end: 0.000 dns_lookup_begin: 0.000 dns_lookup_end: -1.000 server_connect: -1.000 server_first_read: -1.000 server_read_header_done: -1.000 server_close: -1.000 ua_close: 30.597 sm_finish: 30.597 [Jun 22 15:33:47.441] Server {1098611008} ERROR: [8122409] Slow Request: url: http://img04.taobaocdn.com/tps/i4/T1EM9gXltt-440-135.jpg status: 0 unique id: bytes: 0 fd: 0 client state: 6 server state: 0 ua_begin: 0.000 ua_read_header_done: 0.000 cache_open_read_begin: 0.000 cache_open_read_end: 0.000 dns_lookup_begin: 0.000 dns_lookup_end: -1.000 server_connect: -1.000 server_first_read: -1.000 server_read_header_done: -1.000 server_close: -1.000 ua_close: 30.948 sm_finish: 30.948 {code} all http SM show from {http} in DNS_LOOKUP and traffic.out show nothing with error, when I enable debug on hostdb.*|dns.*: {code} [Jun 22 15:27:42.391] Server {1108986176} DEBUG: (hostdb) probe img03.taobaocdn.com DB357D60B8247DC7 1 [ignore_timeout = 0] [Jun 22 15:27:42.391] Server {1108986176} DEBUG: (hostdb) timeout 64204 1308663404 300 [Jun 22 15:27:42.391] Server {1108986176} DEBUG: (hostdb) delaying force 0 answer for img03.taobaocdn.com [timeout 0] [Jun 22 15:27:42.411] Server {1108986176} DEBUG: (hostdb) probe img03.taobaocdn.com DB357D60B8247DC7 1 [ignore_timeout = 0] [Jun 22 15:27:42.411] Server {1108986176} DEBUG: (hostdb) timeout 64204 1308663404 300 [Jun 22 15:27:42.411] Server {1108986176} DEBUG: (hostdb) DNS img03.taobaocdn.com [Jun 22 15:27:42.411] Server {1108986176} DEBUG: (hostdb) enqueuing additional request [Jun 22 15:27:42.416] Server {47177168876656} DEBUG: (hostdb) probe 127.0.0.1 E9B7563422C93608 1 [ignore_timeout = 0] [Jun 22 15:27:42.416] Server {47177168876656} DEBUG: (hostdb) immediate answer for 127.0.0.1 [Jun 22 15:27:42.422] Server {1098611008} DEBUG: (hostdb) probe img08.taobaocdn.com 945198AE9AE37481 1 [ignore_timeout = 0] [Jun 22 15:27:42.422] Server {1098611008} DEBUG: (hostdb) timeout 64281 1308663327 300 [Jun 22 15:27:42.422] Server {1098611008} DEBUG: (hostdb) delaying force 0 answer for img08.taobaocdn.com [timeout 0] [Jun 22 15:27:42.441] Server {1098611008} DEBUG: (hostdb) probe img08.taobaocdn.com 945198AE9AE37481 1 [ignore_timeout = 0] [Jun 22 15:27:42.441] Server {1098611008} DEBUG: (hostdb) timeout 64281 1308663327 300 [Jun 22 15:27:42.441] Server {1098611008} DEBUG: (hostdb) DNS img08.taobaocdn.com [Jun 22 15:27:42.441] Server {1098611008} DEBUG: (hostdb) enqueuing additional request [Jun 22 15:27:42.470] Server {1099663680} DEBUG: (hostdb) probe 127.0.0.1 E9B7563422C93608 1 [ignore_timeout = 0] [Jun 22 15:27:42.470] Server {1099663680} DEBUG: (hostdb) immediate answer for 127.0.0.1 [Jun 22
[jira] [Updated] (TS-852) hostdb and dns system hangup
[ https://issues.apache.org/jira/browse/TS-852?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Alan M. Carroll updated TS-852: --- Fix Version/s: sometime hostdb and dns system hangup Key: TS-852 URL: https://issues.apache.org/jira/browse/TS-852 Project: Traffic Server Issue Type: Bug Components: Core, DNS Affects Versions: 3.1.0 Reporter: Zhao Yongming Assignee: Phil Sorber Priority: Minor Labels: dns, hostdb Fix For: 3.1.0, sometime Attachments: TS-852.patch in my testing, all request that need go OS, fails with 30s timeout, and the slow query shows data from dns missed: {code} [Jun 22 15:33:47.183] Server {1106880832} ERROR: [8122411] Slow Request: url: http://download.im.alisoft.com/aliim/AliIM6/update/packages//2011-5-4-10-10-40/0/modulesproxy/8203.xml.wwzip status: 0 unique id: bytes: 0 fd: 0 client state: 6 server state: 0 ua_begin: 0.000 ua_read_header_done: 0.000 cache_open_read_begin: 0.000 cache_open_read_end: 0.000 dns_lookup_begin: 0.000 dns_lookup_end: -1.000 server_connect: -1.000 server_first_read: -1.000 server_read_header_done: -1.000 server_close: -1.000 ua_close: 30.667 sm_finish: 30.667 [Jun 22 15:33:47.220] Server {1099663680} ERROR: [8122422] Slow Request: url: http://img.uu1001.cn/materials/original/2010-11-22/22-48/a302876929a9c40a8272ac439a16ad25e74edf71.png status: 0 unique id: bytes: 0 fd: 0 client state: 6 server state: 0 ua_begin: 0.000 ua_read_header_done: 0.000 cache_open_read_begin: 0.000 cache_open_read_end: 0.000 dns_lookup_begin: 0.000 dns_lookup_end: -1.000 server_connect: -1.000 server_first_read: -1.000 server_read_header_done: -1.000 server_close: -1.000 ua_close: 30.318 sm_finish: 30.318 [Jun 22 15:33:47.441] Server {1098611008} ERROR: [8122421] Slow Request: url: http://img02.taobaocdn.com/bao/uploaded/i2/T1mp8QXopdXXblNIZ6_061203.jpg_b.jpg status: 0 unique id: bytes: 0 fd: 0 client state: 6 server state: 0 ua_begin: 0.000 ua_read_header_done: 0.000 cache_open_read_begin: 0.000 cache_open_read_end: 0.000 dns_lookup_begin: 0.000 dns_lookup_end: -1.000 server_connect: -1.000 server_first_read: -1.000 server_read_header_done: -1.000 server_close: -1.000 ua_close: 30.597 sm_finish: 30.597 [Jun 22 15:33:47.441] Server {1098611008} ERROR: [8122409] Slow Request: url: http://img04.taobaocdn.com/tps/i4/T1EM9gXltt-440-135.jpg status: 0 unique id: bytes: 0 fd: 0 client state: 6 server state: 0 ua_begin: 0.000 ua_read_header_done: 0.000 cache_open_read_begin: 0.000 cache_open_read_end: 0.000 dns_lookup_begin: 0.000 dns_lookup_end: -1.000 server_connect: -1.000 server_first_read: -1.000 server_read_header_done: -1.000 server_close: -1.000 ua_close: 30.948 sm_finish: 30.948 {code} all http SM show from {http} in DNS_LOOKUP and traffic.out show nothing with error, when I enable debug on hostdb.*|dns.*: {code} [Jun 22 15:27:42.391] Server {1108986176} DEBUG: (hostdb) probe img03.taobaocdn.com DB357D60B8247DC7 1 [ignore_timeout = 0] [Jun 22 15:27:42.391] Server {1108986176} DEBUG: (hostdb) timeout 64204 1308663404 300 [Jun 22 15:27:42.391] Server {1108986176} DEBUG: (hostdb) delaying force 0 answer for img03.taobaocdn.com [timeout 0] [Jun 22 15:27:42.411] Server {1108986176} DEBUG: (hostdb) probe img03.taobaocdn.com DB357D60B8247DC7 1 [ignore_timeout = 0] [Jun 22 15:27:42.411] Server {1108986176} DEBUG: (hostdb) timeout 64204 1308663404 300 [Jun 22 15:27:42.411] Server {1108986176} DEBUG: (hostdb) DNS img03.taobaocdn.com [Jun 22 15:27:42.411] Server {1108986176} DEBUG: (hostdb) enqueuing additional request [Jun 22 15:27:42.416] Server {47177168876656} DEBUG: (hostdb) probe 127.0.0.1 E9B7563422C93608 1 [ignore_timeout = 0] [Jun 22 15:27:42.416] Server {47177168876656} DEBUG: (hostdb) immediate answer for 127.0.0.1 [Jun 22 15:27:42.422] Server {1098611008} DEBUG: (hostdb) probe img08.taobaocdn.com 945198AE9AE37481 1 [ignore_timeout = 0] [Jun 22 15:27:42.422] Server {1098611008} DEBUG: (hostdb) timeout 64281 1308663327 300 [Jun 22 15:27:42.422] Server {1098611008} DEBUG: (hostdb) delaying force 0 answer for img08.taobaocdn.com [timeout 0] [Jun 22 15:27:42.441] Server {1098611008} DEBUG: (hostdb) probe img08.taobaocdn.com 945198AE9AE37481 1 [ignore_timeout = 0] [Jun 22 15:27:42.441] Server {1098611008} DEBUG: (hostdb) timeout 64281 1308663327 300 [Jun 22 15:27:42.441] Server {1098611008} DEBUG: (hostdb) DNS img08.taobaocdn.com [Jun 22 15:27:42.441] Server {1098611008} DEBUG: (hostdb) enqueuing additional request [Jun 22 15:27:42.470] Server {1099663680} DEBUG: (hostdb) probe 127.0.0.1 E9B7563422C93608 1 [ignore_timeout = 0] [Jun 22 15:27:42.470] Server {1099663680} DEBUG: (hostdb) immediate answer for 127.0.0.1 [Jun 22
[jira] [Updated] (TS-871) Subversion (1.7) with serf fails with ATS in forward and reverse proxy mode
[ https://issues.apache.org/jira/browse/TS-871?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Bryan Call updated TS-871: -- Assignee: Leif Hedstrom Subversion (1.7) with serf fails with ATS in forward and reverse proxy mode --- Key: TS-871 URL: https://issues.apache.org/jira/browse/TS-871 Project: Traffic Server Issue Type: Bug Components: HTTP Affects Versions: 3.0.0 Reporter: Igor Galić Assignee: Leif Hedstrom Fix For: sometime Attachments: TS-871-20121107.diff, TS-871.diff, ats_Thttp.debug.notime.txt, ats_Thttp.debug.txt, revats_Thttp.debug.notime.txt, revats_Thttp.debug.txt, serf_proxy.cap, serf_revproxy.cap, stats.diff When accessing a remote subversion repository via http or https with svn 1.7, it will currently timeout: {noformat} igalic@tynix ~/src/asf % svn co http://svn.apache.org/repos/asf/trafficserver/plugins/stats_over_http/ svn: E020014: Unable to connect to a repository at URL 'http://svn.apache.org/repos/asf/trafficserver/plugins/stats_over_http' svn: E020014: Unspecified error message: 504 Connection Timed Out 1 igalic@tynix ~/src/asf % {noformat} I have started traffic_server -Thttp and captured the output, which I'm attaching. There's also a capture from the network. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (TS-871) Subversion (1.7) with serf fails with ATS in forward and reverse proxy mode
[ https://issues.apache.org/jira/browse/TS-871?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14196463#comment-14196463 ] Bryan Call commented on TS-871: --- @Leif Can you test again and see if it works with subversion? Subversion (1.7) with serf fails with ATS in forward and reverse proxy mode --- Key: TS-871 URL: https://issues.apache.org/jira/browse/TS-871 Project: Traffic Server Issue Type: Bug Components: HTTP Affects Versions: 3.0.0 Reporter: Igor Galić Assignee: Leif Hedstrom Fix For: sometime Attachments: TS-871-20121107.diff, TS-871.diff, ats_Thttp.debug.notime.txt, ats_Thttp.debug.txt, revats_Thttp.debug.notime.txt, revats_Thttp.debug.txt, serf_proxy.cap, serf_revproxy.cap, stats.diff When accessing a remote subversion repository via http or https with svn 1.7, it will currently timeout: {noformat} igalic@tynix ~/src/asf % svn co http://svn.apache.org/repos/asf/trafficserver/plugins/stats_over_http/ svn: E020014: Unable to connect to a repository at URL 'http://svn.apache.org/repos/asf/trafficserver/plugins/stats_over_http' svn: E020014: Unspecified error message: 504 Connection Timed Out 1 igalic@tynix ~/src/asf % {noformat} I have started traffic_server -Thttp and captured the output, which I'm attaching. There's also a capture from the network. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Comment Edited] (TS-871) Subversion (1.7) with serf fails with ATS in forward and reverse proxy mode
[ https://issues.apache.org/jira/browse/TS-871?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14196463#comment-14196463 ] Bryan Call edited comment on TS-871 at 11/4/14 5:59 PM: [~zwoop] Can you test again and see if it works with subversion? was (Author: bcall): @Leif Can you test again and see if it works with subversion? Subversion (1.7) with serf fails with ATS in forward and reverse proxy mode --- Key: TS-871 URL: https://issues.apache.org/jira/browse/TS-871 Project: Traffic Server Issue Type: Bug Components: HTTP Affects Versions: 3.0.0 Reporter: Igor Galić Assignee: Leif Hedstrom Fix For: sometime Attachments: TS-871-20121107.diff, TS-871.diff, ats_Thttp.debug.notime.txt, ats_Thttp.debug.txt, revats_Thttp.debug.notime.txt, revats_Thttp.debug.txt, serf_proxy.cap, serf_revproxy.cap, stats.diff When accessing a remote subversion repository via http or https with svn 1.7, it will currently timeout: {noformat} igalic@tynix ~/src/asf % svn co http://svn.apache.org/repos/asf/trafficserver/plugins/stats_over_http/ svn: E020014: Unable to connect to a repository at URL 'http://svn.apache.org/repos/asf/trafficserver/plugins/stats_over_http' svn: E020014: Unspecified error message: 504 Connection Timed Out 1 igalic@tynix ~/src/asf % {noformat} I have started traffic_server -Thttp and captured the output, which I'm attaching. There's also a capture from the network. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Closed] (TS-879) Seek on cached file
[ https://issues.apache.org/jira/browse/TS-879?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Alan M. Carroll closed TS-879. -- Resolution: Duplicate Seek on cached file --- Key: TS-879 URL: https://issues.apache.org/jira/browse/TS-879 Project: Traffic Server Issue Type: Bug Components: Cache, TS API Affects Versions: 3.0.0 Reporter: Nelson Pérez Assignee: Alan M. Carroll Labels: api-addition, cache, trafficserver Fix For: sometime I want a custom written plugin to be able to seek to any point in a cached file. According to John Plevyak (http://www.mail-archive.com/dev@trafficserver.apache.org/msg02785.html) this feature is new in the cache, but not yet available to the API. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Resolved] (TS-892) request for bulk setting in remap.config for refer filter
[ https://issues.apache.org/jira/browse/TS-892?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Leif Hedstrom resolved TS-892. -- Resolution: Won't Fix Closing in liu of future configuration refactoring. request for bulk setting in remap.config for refer filter - Key: TS-892 URL: https://issues.apache.org/jira/browse/TS-892 Project: Traffic Server Issue Type: Improvement Components: Configuration, HTTP Affects Versions: 3.1.0 Reporter: Zhao Yongming Labels: remap when we put our TS online, we find out we are complex when handling squid's default filter rule such as: {code} acl ctoc referer_regex -i XXXa\.com\/ XXXb\.com\/ XXXc\.com\/ http_access deny ctoc {code} we have to convert every map rule to map_with_referer, and get very ugly. if we can get the referer filter config in the bulk way as IP based filter in the remap.config, it will make the config file clear and clean -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-892) request for bulk setting in remap.config for refer filter
[ https://issues.apache.org/jira/browse/TS-892?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Leif Hedstrom updated TS-892: - Fix Version/s: (was: sometime) request for bulk setting in remap.config for refer filter - Key: TS-892 URL: https://issues.apache.org/jira/browse/TS-892 Project: Traffic Server Issue Type: Improvement Components: Configuration, HTTP Affects Versions: 3.1.0 Reporter: Zhao Yongming Labels: remap when we put our TS online, we find out we are complex when handling squid's default filter rule such as: {code} acl ctoc referer_regex -i XXXa\.com\/ XXXb\.com\/ XXXc\.com\/ http_access deny ctoc {code} we have to convert every map rule to map_with_referer, and get very ugly. if we can get the referer filter config in the bulk way as IP based filter in the remap.config, it will make the config file clear and clean -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-893) the prefetch function in codes need more love to show up
[ https://issues.apache.org/jira/browse/TS-893?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Leif Hedstrom updated TS-893: - Assignee: (was: Zhao Yongming) the prefetch function in codes need more love to show up Key: TS-893 URL: https://issues.apache.org/jira/browse/TS-893 Project: Traffic Server Issue Type: Improvement Components: Cache, HTTP Affects Versions: 3.0.0 Reporter: Zhao Yongming Fix For: sometime the prefetch function in proxy is a good solution when you really need to faster up your user download time, it can parse any allowed plean html file, get all resource tags out and do batch loading from OS. I am going to preload my site before we put it online, as it will get about 1 month to get the disk full and hit rate stable. it is a cool feature but it have the following issues: 1, the prefetch config file is not managed well. ie, it is not managed by cluster 2, the it does not any document in the admin guide or old pdf file. 3, prefetching just care plean html file, without compressing, should we do some decompressing? is that possible? hopes this is the starting of make prefetch really useful for some cutting edge situation. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (TS-852) hostdb and dns system hangup
[ https://issues.apache.org/jira/browse/TS-852?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14196472#comment-14196472 ] Susan Hinrichs commented on TS-852: --- [~psudaemon] any additional thoughts on this. hostdb and dns system hangup Key: TS-852 URL: https://issues.apache.org/jira/browse/TS-852 Project: Traffic Server Issue Type: Bug Components: Core, DNS Affects Versions: 3.1.0 Reporter: Zhao Yongming Assignee: Phil Sorber Priority: Minor Labels: dns, hostdb Fix For: 3.1.0, sometime Attachments: TS-852.patch in my testing, all request that need go OS, fails with 30s timeout, and the slow query shows data from dns missed: {code} [Jun 22 15:33:47.183] Server {1106880832} ERROR: [8122411] Slow Request: url: http://download.im.alisoft.com/aliim/AliIM6/update/packages//2011-5-4-10-10-40/0/modulesproxy/8203.xml.wwzip status: 0 unique id: bytes: 0 fd: 0 client state: 6 server state: 0 ua_begin: 0.000 ua_read_header_done: 0.000 cache_open_read_begin: 0.000 cache_open_read_end: 0.000 dns_lookup_begin: 0.000 dns_lookup_end: -1.000 server_connect: -1.000 server_first_read: -1.000 server_read_header_done: -1.000 server_close: -1.000 ua_close: 30.667 sm_finish: 30.667 [Jun 22 15:33:47.220] Server {1099663680} ERROR: [8122422] Slow Request: url: http://img.uu1001.cn/materials/original/2010-11-22/22-48/a302876929a9c40a8272ac439a16ad25e74edf71.png status: 0 unique id: bytes: 0 fd: 0 client state: 6 server state: 0 ua_begin: 0.000 ua_read_header_done: 0.000 cache_open_read_begin: 0.000 cache_open_read_end: 0.000 dns_lookup_begin: 0.000 dns_lookup_end: -1.000 server_connect: -1.000 server_first_read: -1.000 server_read_header_done: -1.000 server_close: -1.000 ua_close: 30.318 sm_finish: 30.318 [Jun 22 15:33:47.441] Server {1098611008} ERROR: [8122421] Slow Request: url: http://img02.taobaocdn.com/bao/uploaded/i2/T1mp8QXopdXXblNIZ6_061203.jpg_b.jpg status: 0 unique id: bytes: 0 fd: 0 client state: 6 server state: 0 ua_begin: 0.000 ua_read_header_done: 0.000 cache_open_read_begin: 0.000 cache_open_read_end: 0.000 dns_lookup_begin: 0.000 dns_lookup_end: -1.000 server_connect: -1.000 server_first_read: -1.000 server_read_header_done: -1.000 server_close: -1.000 ua_close: 30.597 sm_finish: 30.597 [Jun 22 15:33:47.441] Server {1098611008} ERROR: [8122409] Slow Request: url: http://img04.taobaocdn.com/tps/i4/T1EM9gXltt-440-135.jpg status: 0 unique id: bytes: 0 fd: 0 client state: 6 server state: 0 ua_begin: 0.000 ua_read_header_done: 0.000 cache_open_read_begin: 0.000 cache_open_read_end: 0.000 dns_lookup_begin: 0.000 dns_lookup_end: -1.000 server_connect: -1.000 server_first_read: -1.000 server_read_header_done: -1.000 server_close: -1.000 ua_close: 30.948 sm_finish: 30.948 {code} all http SM show from {http} in DNS_LOOKUP and traffic.out show nothing with error, when I enable debug on hostdb.*|dns.*: {code} [Jun 22 15:27:42.391] Server {1108986176} DEBUG: (hostdb) probe img03.taobaocdn.com DB357D60B8247DC7 1 [ignore_timeout = 0] [Jun 22 15:27:42.391] Server {1108986176} DEBUG: (hostdb) timeout 64204 1308663404 300 [Jun 22 15:27:42.391] Server {1108986176} DEBUG: (hostdb) delaying force 0 answer for img03.taobaocdn.com [timeout 0] [Jun 22 15:27:42.411] Server {1108986176} DEBUG: (hostdb) probe img03.taobaocdn.com DB357D60B8247DC7 1 [ignore_timeout = 0] [Jun 22 15:27:42.411] Server {1108986176} DEBUG: (hostdb) timeout 64204 1308663404 300 [Jun 22 15:27:42.411] Server {1108986176} DEBUG: (hostdb) DNS img03.taobaocdn.com [Jun 22 15:27:42.411] Server {1108986176} DEBUG: (hostdb) enqueuing additional request [Jun 22 15:27:42.416] Server {47177168876656} DEBUG: (hostdb) probe 127.0.0.1 E9B7563422C93608 1 [ignore_timeout = 0] [Jun 22 15:27:42.416] Server {47177168876656} DEBUG: (hostdb) immediate answer for 127.0.0.1 [Jun 22 15:27:42.422] Server {1098611008} DEBUG: (hostdb) probe img08.taobaocdn.com 945198AE9AE37481 1 [ignore_timeout = 0] [Jun 22 15:27:42.422] Server {1098611008} DEBUG: (hostdb) timeout 64281 1308663327 300 [Jun 22 15:27:42.422] Server {1098611008} DEBUG: (hostdb) delaying force 0 answer for img08.taobaocdn.com [timeout 0] [Jun 22 15:27:42.441] Server {1098611008} DEBUG: (hostdb) probe img08.taobaocdn.com 945198AE9AE37481 1 [ignore_timeout = 0] [Jun 22 15:27:42.441] Server {1098611008} DEBUG: (hostdb) timeout 64281 1308663327 300 [Jun 22 15:27:42.441] Server {1098611008} DEBUG: (hostdb) DNS img08.taobaocdn.com [Jun 22 15:27:42.441] Server {1098611008} DEBUG: (hostdb) enqueuing additional request [Jun 22 15:27:42.470] Server {1099663680} DEBUG: (hostdb) probe 127.0.0.1 E9B7563422C93608 1 [ignore_timeout = 0] [Jun 22 15:27:42.470] Server
[jira] [Created] (TS-3167) Remove the prefetch feature
Susan Hinrichs created TS-3167: -- Summary: Remove the prefetch feature Key: TS-3167 URL: https://issues.apache.org/jira/browse/TS-3167 Project: Traffic Server Issue Type: Task Reporter: Susan Hinrichs In discussions with [~amc] and [~zwoop] and [~bcall], it was decided to remove the prefetch feature. It currently does not work. It would be best to remove the broken feature. If someone really needs this feature, then they can build a working feature. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-3167) Remove the prefetch feature
[ https://issues.apache.org/jira/browse/TS-3167?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-3167: --- Assignee: Leif Hedstrom Remove the prefetch feature --- Key: TS-3167 URL: https://issues.apache.org/jira/browse/TS-3167 Project: Traffic Server Issue Type: Task Reporter: Susan Hinrichs Assignee: Leif Hedstrom In discussions with [~amc] and [~zwoop] and [~bcall], it was decided to remove the prefetch feature. It currently does not work. It would be best to remove the broken feature. If someone really needs this feature, then they can build a working feature. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-898) fix potential problems from coverity scan
[ https://issues.apache.org/jira/browse/TS-898?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-898: -- Assignee: Leif Hedstrom fix potential problems from coverity scan - Key: TS-898 URL: https://issues.apache.org/jira/browse/TS-898 Project: Traffic Server Issue Type: Improvement Components: Core Affects Versions: 3.0.0 Environment: RHEL5 Reporter: Bryan Call Assignee: Leif Hedstrom Fix For: 5.2.0 Ran Coverity over the code and it reported 856 potential problems with the code. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-898) fix potential problems from coverity scan
[ https://issues.apache.org/jira/browse/TS-898?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-898: -- Fix Version/s: (was: sometime) 5.2.0 fix potential problems from coverity scan - Key: TS-898 URL: https://issues.apache.org/jira/browse/TS-898 Project: Traffic Server Issue Type: Improvement Components: Core Affects Versions: 3.0.0 Environment: RHEL5 Reporter: Bryan Call Assignee: Leif Hedstrom Fix For: 5.2.0 Ran Coverity over the code and it reported 856 potential problems with the code. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Closed] (TS-904) when doing custom logging, it would be nice if we can set dedicate sampling rate for each rule
[ https://issues.apache.org/jira/browse/TS-904?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs closed TS-904. - Resolution: Invalid Fix Version/s: (was: sometime) when doing custom logging, it would be nice if we can set dedicate sampling rate for each rule -- Key: TS-904 URL: https://issues.apache.org/jira/browse/TS-904 Project: Traffic Server Issue Type: New Feature Components: Logging Affects Versions: 3.0.0 Reporter: Zhao Yongming Priority: Minor the sampling is a global config in logging, we want to get it custom-able. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Closed] (TS-905) Improve state machine around DNS lookups and handling of URL_REMAP_FOR_OS
[ https://issues.apache.org/jira/browse/TS-905?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs closed TS-905. - Resolution: Duplicate Fix Version/s: (was: sometime) Improve state machine around DNS lookups and handling of URL_REMAP_FOR_OS - Key: TS-905 URL: https://issues.apache.org/jira/browse/TS-905 Project: Traffic Server Issue Type: Improvement Components: DNS, HTTP Reporter: Leif Hedstrom The code around DNS lookups in the HTTP state machine is somewhat odd. The same state is revisited at least twice in the case of a parent proxy lookup for example, and the internal state is not reset in between such lookups. This caused breakage of parent proxy when we added an API to bypass origin DNS lookup, as a very obscure side effect. Also, there's code in there for a remapping mode URL_REMAP_FOR_OS (2), which I believe we have crippled, and it's unclear exactly when it would be used. We should examine this, and either fix this mode, or disable it completely. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Created] (TS-3168) Remove Log Collation
Susan Hinrichs created TS-3168: -- Summary: Remove Log Collation Key: TS-3168 URL: https://issues.apache.org/jira/browse/TS-3168 Project: Traffic Server Issue Type: Task Components: Logging Reporter: Susan Hinrichs In discussion with [~amc], [~zwoop], and [~bcall], decided to remove this feature. Does not work. Better to use newer dedicated log sub systems and syslog-ng -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Closed] (TS-910) log collation in custom log will make dedicate connection to the same collation server
[ https://issues.apache.org/jira/browse/TS-910?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs closed TS-910. - Resolution: Invalid Fix Version/s: (was: sometime) Removing feature. log collation in custom log will make dedicate connection to the same collation server -- Key: TS-910 URL: https://issues.apache.org/jira/browse/TS-910 Project: Traffic Server Issue Type: Improvement Components: Logging Affects Versions: 3.1.0 Reporter: Zhao Yongming Assignee: Zhao Yongming Priority: Trivial when you define LogObject in logs_xml.config, and set CollationHosts, it will open connections for each LogObject, despite you put the same host in CollationHosts. it will affect the default squid logging too. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (TS-935) Should EVENT_INTERNAL really be the same as TS_EVENT_TIMEOUT
[ https://issues.apache.org/jira/browse/TS-935?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14196504#comment-14196504 ] Susan Hinrichs commented on TS-935: --- [~briang] unassign yourself unless you are still working on it. Should EVENT_INTERNAL really be the same as TS_EVENT_TIMEOUT Key: TS-935 URL: https://issues.apache.org/jira/browse/TS-935 Project: Traffic Server Issue Type: Bug Components: TS API Affects Versions: 3.0.1 Reporter: Brian Geffon Assignee: Brian Geffon Labels: api-change Fix For: sometime When trying to use TSContCall with event = TS_EVENT_TIMEOUT I stumbled upon the fact that the API will decrement the event count for EVENT_INTERNAL or EVENT_IMMEDIATE (see INKContInternal::handle_event_count), but shouldn't we be able to do a TSContCall with TS_EVENT_IMMEDIAITE or TS_EVENT_TIMEOUT because as of now doing so would cause m_event_count to become -1 or shouldn't these defined values be something different? -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-946) Scheduling a continuation on all threads of a specific type
[ https://issues.apache.org/jira/browse/TS-946?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-946: -- Fix Version/s: (was: 5.2.0) 5.3.0 Scheduling a continuation on all threads of a specific type --- Key: TS-946 URL: https://issues.apache.org/jira/browse/TS-946 Project: Traffic Server Issue Type: New Feature Components: Core Affects Versions: 3.0.0 Reporter: Leif Hedstrom Fix For: 5.3.0 It would be incredibly useful, both in the core and in plugin APIs, to be able to schedule a continuation to run on all threads of a specific type. E.g. in a plugin, something like TSAction TSContScheduleOnThreads(TSCont cont, TSThreadPool tp); This would be useful for e.g. setting up per-thread specifics from a plugin, but quite possibly also from the core. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-966) cache.config dest_domain= dest_hostname= dest_ip= do not match anything
[ https://issues.apache.org/jira/browse/TS-966?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-966: -- Fix Version/s: (was: 5.2.0) 5.3.0 cache.config dest_domain= dest_hostname= dest_ip= do not match anything --- Key: TS-966 URL: https://issues.apache.org/jira/browse/TS-966 Project: Traffic Server Issue Type: Bug Components: Cache Affects Versions: 3.1.0, 3.0.1 Reporter: Igor Galić Labels: A Fix For: 5.3.0 Caching policies are not applied when using these options to match targets. It is also not very clear *what* dest_domain= vs dest_hostname= can match. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-946) Scheduling a continuation on all threads of a specific type
[ https://issues.apache.org/jira/browse/TS-946?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-946: -- Assignee: Leif Hedstrom Scheduling a continuation on all threads of a specific type --- Key: TS-946 URL: https://issues.apache.org/jira/browse/TS-946 Project: Traffic Server Issue Type: New Feature Components: Core Affects Versions: 3.0.0 Reporter: Leif Hedstrom Assignee: Leif Hedstrom Fix For: 5.3.0 It would be incredibly useful, both in the core and in plugin APIs, to be able to schedule a continuation to run on all threads of a specific type. E.g. in a plugin, something like TSAction TSContScheduleOnThreads(TSCont cont, TSThreadPool tp); This would be useful for e.g. setting up per-thread specifics from a plugin, but quite possibly also from the core. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-965) cache.config can't deal with both revalidate= and ttl-in-cache= specified
[ https://issues.apache.org/jira/browse/TS-965?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-965: -- Fix Version/s: (was: 5.2.0) 5.3.0 cache.config can't deal with both revalidate= and ttl-in-cache= specified - Key: TS-965 URL: https://issues.apache.org/jira/browse/TS-965 Project: Traffic Server Issue Type: Bug Components: Cache Affects Versions: 3.1.0, 3.0.1 Reporter: Igor Galić Labels: A Fix For: 5.3.0 If both of these options are specified (with the same time?), nothing is cached at all. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-965) cache.config can't deal with both revalidate= and ttl-in-cache= specified
[ https://issues.apache.org/jira/browse/TS-965?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-965: -- Assignee: Alan M. Carroll cache.config can't deal with both revalidate= and ttl-in-cache= specified - Key: TS-965 URL: https://issues.apache.org/jira/browse/TS-965 Project: Traffic Server Issue Type: Bug Components: Cache Affects Versions: 3.1.0, 3.0.1 Reporter: Igor Galić Assignee: Alan M. Carroll Labels: A Fix For: 5.3.0 If both of these options are specified (with the same time?), nothing is cached at all. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-974) TS should have a mode to hold partial objects in cache
[ https://issues.apache.org/jira/browse/TS-974?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-974: -- Assignee: Alan M. Carroll TS should have a mode to hold partial objects in cache -- Key: TS-974 URL: https://issues.apache.org/jira/browse/TS-974 Project: Traffic Server Issue Type: Improvement Components: Cache Affects Versions: 3.0.1 Reporter: William Bardwell Assignee: Alan M. Carroll Labels: A Fix For: sometime For ATS to do an excelent job caching large files like video it would need to be able to hold partial objects for a large file. This could be done in a plugin or in the core. This would need to be integrated with the Range handling code to serve requests out of the partial objects and to get more parts of a file to satisfy a Range request. An intermediate step (also do-able in the core or in a plugin) would be to have some settings to let the Range handling code be able to trigger a full file download either asynchronously when a Range response indicates that the file isn't larger than some threshold, or synchronously when a Range request could reasonably be answered quickly from a full request. (Right now Range requests are tunneled if there is not full cached content as far as I can tell.) -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-974) TS should have a mode to hold partial objects in cache
[ https://issues.apache.org/jira/browse/TS-974?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-974: -- Fix Version/s: (was: sometime) 5.3.0 TS should have a mode to hold partial objects in cache -- Key: TS-974 URL: https://issues.apache.org/jira/browse/TS-974 Project: Traffic Server Issue Type: Improvement Components: Cache Affects Versions: 3.0.1 Reporter: William Bardwell Assignee: Alan M. Carroll Labels: A Fix For: 5.3.0 For ATS to do an excelent job caching large files like video it would need to be able to hold partial objects for a large file. This could be done in a plugin or in the core. This would need to be integrated with the Range handling code to serve requests out of the partial objects and to get more parts of a file to satisfy a Range request. An intermediate step (also do-able in the core or in a plugin) would be to have some settings to let the Range handling code be able to trigger a full file download either asynchronously when a Range response indicates that the file isn't larger than some threshold, or synchronously when a Range request could reasonably be answered quickly from a full request. (Right now Range requests are tunneled if there is not full cached content as far as I can tell.) -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-966) cache.config dest_domain= dest_hostname= dest_ip= do not match anything
[ https://issues.apache.org/jira/browse/TS-966?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-966: -- Assignee: Alan M. Carroll cache.config dest_domain= dest_hostname= dest_ip= do not match anything --- Key: TS-966 URL: https://issues.apache.org/jira/browse/TS-966 Project: Traffic Server Issue Type: Bug Components: Cache Affects Versions: 3.1.0, 3.0.1 Reporter: Igor Galić Assignee: Alan M. Carroll Labels: A Fix For: 5.3.0 Caching policies are not applied when using these options to match targets. It is also not very clear *what* dest_domain= vs dest_hostname= can match. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (TS-974) TS should have a mode to hold partial objects in cache
[ https://issues.apache.org/jira/browse/TS-974?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14196518#comment-14196518 ] Alan M. Carroll commented on TS-974: This is now under active development. TS should have a mode to hold partial objects in cache -- Key: TS-974 URL: https://issues.apache.org/jira/browse/TS-974 Project: Traffic Server Issue Type: Improvement Components: Cache Affects Versions: 3.0.1 Reporter: William Bardwell Assignee: Alan M. Carroll Labels: A Fix For: 5.3.0 For ATS to do an excelent job caching large files like video it would need to be able to hold partial objects for a large file. This could be done in a plugin or in the core. This would need to be integrated with the Range handling code to serve requests out of the partial objects and to get more parts of a file to satisfy a Range request. An intermediate step (also do-able in the core or in a plugin) would be to have some settings to let the Range handling code be able to trigger a full file download either asynchronously when a Range response indicates that the file isn't larger than some threshold, or synchronously when a Range request could reasonably be answered quickly from a full request. (Right now Range requests are tunneled if there is not full cached content as far as I can tell.) -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Closed] (TS-980) change client_session schedule from global to thread local, and reduce the try_locks in UnixNetVConnection::reenable
[ https://issues.apache.org/jira/browse/TS-980?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs closed TS-980. - Resolution: Invalid Fix Version/s: (was: 5.2.0) Consensus of [~zwoop] and [~amc] is that this optimization will not work. change client_session schedule from global to thread local, and reduce the try_locks in UnixNetVConnection::reenable - Key: TS-980 URL: https://issues.apache.org/jira/browse/TS-980 Project: Traffic Server Issue Type: Improvement Components: Network, Performance Affects Versions: 3.1.0, 3.0.0 Environment: all Reporter: weijin Assignee: weijin Attachments: ts-980.diff I did some performance test on ats last days(disable cache, set share_server session 2, pure proxy mode), I did see significant improvement on low load, but it dropped rapidly when load is high. meanwhile, some stability problems happened. Through gdb, I found the client_session`s mutex can be acquired by two or more threads, I believe some schedules happened during the sm life_time. May be we need do some work to find these eventProcessor.schedules and change them to thread schedules. UnixVConnecton::reenable { if (nh-mutex-thread_holding == t) { // put into ready_list } else { MUTEX_TRY_LOCK(lock, nh-mutex, t); if (!lock) { // put into enable_list; } else { // put into ready_list; } } remove UnixNetVConnection::reenable try_lock operations, 3 reasons 1. try_lock operation means obj allocation and deallocation operation. frequently 2. try_lock hardly can lock the net-handler`s mutex.(net-handler is schedule by as soon as possible) 3. try_lock should not acquire the net-handler`s mutex. That may lead more net io latency if it is an epoll event need to be processed in other threads. If it is not an epoll event(time event), I don`t think putting vc in ready_list has any advantage than in enable_list. may be we can change reenale function like this: UnixVConnecton::reenable { if (nh-mutex-thread_holding == t) { // put into ready_list; } else { // put into enable_list; } my buddies, any advice? -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Updated] (TS-990) IPv6 support for clustering
[ https://issues.apache.org/jira/browse/TS-990?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs updated TS-990: -- Assignee: (was: Alan M. Carroll) IPv6 support for clustering --- Key: TS-990 URL: https://issues.apache.org/jira/browse/TS-990 Project: Traffic Server Issue Type: Improvement Components: Clustering Affects Versions: 3.1.0 Reporter: Alan M. Carroll Priority: Minor Labels: clustering, ipv6 Fix For: sometime Update clustering to be IPv6 compatible. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Closed] (TS-983) prefetch: the documents
[ https://issues.apache.org/jira/browse/TS-983?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs closed TS-983. - Resolution: Invalid Fix Version/s: (was: sometime) prefetch: the documents --- Key: TS-983 URL: https://issues.apache.org/jira/browse/TS-983 Project: Traffic Server Issue Type: Sub-task Components: HTTP Reporter: Zhao Yongming Assignee: Zhao Yongming -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (TS-993) Add OpenBSD support.
[ https://issues.apache.org/jira/browse/TS-993?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14196525#comment-14196525 ] Susan Hinrichs commented on TS-993: --- [~piotrsikora] Are you still interested? If not, we will close as 'Won't fix'. Add OpenBSD support. Key: TS-993 URL: https://issues.apache.org/jira/browse/TS-993 Project: Traffic Server Issue Type: Improvement Components: Build Environment: OpenBSD Reporter: Piotr Sikora Fix For: sometime Attachments: 0001-Add-OpenBSD-support.patch, freebsd.patch Add OpenBSD support. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Commented] (TS-935) Should EVENT_INTERNAL really be the same as TS_EVENT_TIMEOUT
[ https://issues.apache.org/jira/browse/TS-935?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14196531#comment-14196531 ] Brian Geffon commented on TS-935: - [~shinrich], I think we should just close this as WONT FIX. Should EVENT_INTERNAL really be the same as TS_EVENT_TIMEOUT Key: TS-935 URL: https://issues.apache.org/jira/browse/TS-935 Project: Traffic Server Issue Type: Bug Components: TS API Affects Versions: 3.0.1 Reporter: Brian Geffon Assignee: Brian Geffon Labels: api-change Fix For: sometime When trying to use TSContCall with event = TS_EVENT_TIMEOUT I stumbled upon the fact that the API will decrement the event count for EVENT_INTERNAL or EVENT_IMMEDIATE (see INKContInternal::handle_event_count), but shouldn't we be able to do a TSContCall with TS_EVENT_IMMEDIAITE or TS_EVENT_TIMEOUT because as of now doing so would cause m_event_count to become -1 or shouldn't these defined values be something different? -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Closed] (TS-1001) reload the changes in dns.resolv_conf
[ https://issues.apache.org/jira/browse/TS-1001?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs closed TS-1001. -- Resolution: Duplicate reload the changes in dns.resolv_conf - Key: TS-1001 URL: https://issues.apache.org/jira/browse/TS-1001 Project: Traffic Server Issue Type: Wish Components: DNS Reporter: Conan Wang Assignee: Leif Hedstrom Priority: Trivial Labels: A Fix For: 5.2.0 a trivial wish: ATS can reload (traffic_line -x) resolv.conf if nameserver changed. -- This message was sent by Atlassian JIRA (v6.3.4#6332)
[jira] [Assigned] (TS-1007) SSN Close called before TXN Close
[ https://issues.apache.org/jira/browse/TS-1007?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Susan Hinrichs reassigned TS-1007: -- Assignee: Susan Hinrichs SSN Close called before TXN Close - Key: TS-1007 URL: https://issues.apache.org/jira/browse/TS-1007 Project: Traffic Server Issue Type: Bug Components: TS API Affects Versions: 3.0.1 Reporter: Nick Kew Assignee: Susan Hinrichs Priority: Critical Fix For: 5.3.0 Where a plugin implements both SSN_CLOSE_HOOK and TXN_CLOSE_HOOK, the SSN_CLOSE_HOOK is called first of the two. This messes up normal cleanups! Details: Register a SSN_START event globally In the SSN START, add a TXN_START and a SSN_CLOSE In the TXN START, add a TXN_CLOSE Stepping through, I see the order of events actually called, for the simple case of a one-off HTTP request with no keepalive: SSN_START TXN_START SSN_END TXN_END Whoops, SSN_END cleaned up the SSN context, leaving dangling pointers in the TXN! -- This message was sent by Atlassian JIRA (v6.3.4#6332)