[jira] [Commented] (TS-3032) FATAL: ats_malloc: couldn't allocate XXXXXX bytes
[ https://issues.apache.org/jira/browse/TS-3032?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14116551#comment-14116551 ] Nikolai Gorchilov commented on TS-3032: --- This is to confirm, FATAL: ats_malloc: couldn't allocate bytes is due to reaching vm.max_map_count limit. Closing the ticket as non-ATS issue. FATAL: ats_malloc: couldn't allocate XX bytes - Key: TS-3032 URL: https://issues.apache.org/jira/browse/TS-3032 Project: Traffic Server Issue Type: Bug Components: Core Affects Versions: 5.0.1 Reporter: Nikolai Gorchilov Assignee: Brian Geffon Labels: crash Fix For: 5.2.0 Attachments: memory.d.png ATS 5.0.1 under Unbuntu 12.04.4 running happily for days suddenly crashes due to memory allocation issue. Happens once or twice a week. Server is having plenty of RAM - 128G - out of which 64G+ are free. Nothing suspicious in dmesg. {noformat} FATAL: ats_malloc: couldn't allocate 155648 bytes /z/bin/traffic_server - STACK TRACE: /z/lib/libtsutil.so.5(+0x1e837)[0x2b6251b3d837] /z/lib/libtsutil.so.5(ats_malloc+0x30)[0x2b6251b40c50] /z/bin/traffic_server(HdrHeap::coalesce_str_heaps(int)+0x34)[0x62e834] /z/bin/traffic_server(http_hdr_clone(HTTPHdrImpl*, HdrHeap*, HdrHeap*)+0x8f)[0x62a54f] /z/bin/traffic_server(HttpTransactHeaders::copy_header_fields(HTTPHdr*, HTTPHdr*, bool, long)+0x1ae)[0x5d08de] /z/bin/traffic_server(HttpTransact::build_request(HttpTransact::State*, HTTPHdr*, HTTPHdr*, HTTPVersion)+0x5c)[0x5b280c] /z/bin/traffic_server(HttpTransact::HandleCacheOpenReadMiss(HttpTransact::State*)+0x2c8)[0x5c2ce8] /z/bin/traffic_server(HttpSM::call_transact_and_set_next_state(void (*)(HttpTransact::State*))+0x66)[0x58e356] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::do_hostdb_lookup()+0x27a)[0x58e84a] /z/bin/traffic_server(HttpSM::set_next_state()+0xd48)[0x5a1038] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/x3me_dscp.so(http_txn_hook(tsapi_cont*, TSEvent, void*)+0x236)[0x2b626342b508] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_cache_open_read(int, void*)+0x180)[0x59b070] /z/bin/traffic_server(HttpSM::main_handler(int, void*)+0xd8)[0x59ad98] /z/bin/traffic_server(HttpCacheSM::state_cache_open_read(int, void*)+0x173)[0x57bbb3] /z/bin/traffic_server(Cache::open_read(Continuation*, INK_MD5*, HTTPHdr*, CacheLookupHttpConfig*, CacheFragType, char*, int)+0x616)[0x6d65a6] /z/bin/traffic_server(CacheProcessor::open_read(Continuation*, URL*, bool, HTTPHdr*, CacheLookupHttpConfig*, long, CacheFragType)+0xb0)[0x6b1af0] /z/bin/traffic_server(HttpCacheSM::open_read(URL*, HTTPHdr*, CacheLookupHttpConfig*, long)+0x83)[0x57c2d3] /z/bin/traffic_server(HttpSM::do_cache_lookup_and_read()+0xfb)[0x58baeb] /z/bin/traffic_server(HttpSM::set_next_state()+0x888)[0x5a0b78] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::set_next_state()+0x7e2)[0x5a0ad2] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/cacheurl.so(+0x17dc)[0x2b6263a477dc] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/tslua.so(+0x596f)[0x2b626363396f] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/stats_over_http.so(+0x1235)[0x2b6263228235] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_read_client_request_header(int, void*)+0x22b)[0x59270b] /z/bin/traffic_server(HttpSM::main_handler(int, void*)+0xd8)[0x59ad98] /z/bin/traffic_server[0x714a60] /z/bin/traffic_server(NetHandler::mainNetEvent(int, Event*)+0x1ed)[0x7077cd]
[jira] [Commented] (TS-3032) FATAL: ats_malloc: couldn't allocate XXXXXX bytes
[ https://issues.apache.org/jira/browse/TS-3032?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14115168#comment-14115168 ] Nikolai Gorchilov commented on TS-3032: --- In the mean time, the smaller box, running with --enable-reclaimable-freelist buld, crashed with the following message: FATAL: Failed to mmap 12288 bytes, Out of memory, or the process's maximum number of mappings would have been exceeded(if so, you can enlarge 'vm.max_map_count' by sysctl in linux). During the crash free memory was above 10G and vm.max_map_count is 65530. Could vm.max_map_count be the actual reason for all crashes? FATAL: ats_malloc: couldn't allocate XX bytes - Key: TS-3032 URL: https://issues.apache.org/jira/browse/TS-3032 Project: Traffic Server Issue Type: Bug Components: Core Affects Versions: 5.0.1 Reporter: Nikolai Gorchilov Assignee: Brian Geffon Labels: crash Fix For: 5.2.0 ATS 5.0.1 under Unbuntu 12.04.4 running happily for days suddenly crashes due to memory allocation issue. Happens once or twice a week. Server is having plenty of RAM - 128G - out of which 64G+ are free. Nothing suspicious in dmesg. {noformat} FATAL: ats_malloc: couldn't allocate 155648 bytes /z/bin/traffic_server - STACK TRACE: /z/lib/libtsutil.so.5(+0x1e837)[0x2b6251b3d837] /z/lib/libtsutil.so.5(ats_malloc+0x30)[0x2b6251b40c50] /z/bin/traffic_server(HdrHeap::coalesce_str_heaps(int)+0x34)[0x62e834] /z/bin/traffic_server(http_hdr_clone(HTTPHdrImpl*, HdrHeap*, HdrHeap*)+0x8f)[0x62a54f] /z/bin/traffic_server(HttpTransactHeaders::copy_header_fields(HTTPHdr*, HTTPHdr*, bool, long)+0x1ae)[0x5d08de] /z/bin/traffic_server(HttpTransact::build_request(HttpTransact::State*, HTTPHdr*, HTTPHdr*, HTTPVersion)+0x5c)[0x5b280c] /z/bin/traffic_server(HttpTransact::HandleCacheOpenReadMiss(HttpTransact::State*)+0x2c8)[0x5c2ce8] /z/bin/traffic_server(HttpSM::call_transact_and_set_next_state(void (*)(HttpTransact::State*))+0x66)[0x58e356] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::do_hostdb_lookup()+0x27a)[0x58e84a] /z/bin/traffic_server(HttpSM::set_next_state()+0xd48)[0x5a1038] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/x3me_dscp.so(http_txn_hook(tsapi_cont*, TSEvent, void*)+0x236)[0x2b626342b508] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_cache_open_read(int, void*)+0x180)[0x59b070] /z/bin/traffic_server(HttpSM::main_handler(int, void*)+0xd8)[0x59ad98] /z/bin/traffic_server(HttpCacheSM::state_cache_open_read(int, void*)+0x173)[0x57bbb3] /z/bin/traffic_server(Cache::open_read(Continuation*, INK_MD5*, HTTPHdr*, CacheLookupHttpConfig*, CacheFragType, char*, int)+0x616)[0x6d65a6] /z/bin/traffic_server(CacheProcessor::open_read(Continuation*, URL*, bool, HTTPHdr*, CacheLookupHttpConfig*, long, CacheFragType)+0xb0)[0x6b1af0] /z/bin/traffic_server(HttpCacheSM::open_read(URL*, HTTPHdr*, CacheLookupHttpConfig*, long)+0x83)[0x57c2d3] /z/bin/traffic_server(HttpSM::do_cache_lookup_and_read()+0xfb)[0x58baeb] /z/bin/traffic_server(HttpSM::set_next_state()+0x888)[0x5a0b78] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::set_next_state()+0x7e2)[0x5a0ad2] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/cacheurl.so(+0x17dc)[0x2b6263a477dc] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/tslua.so(+0x596f)[0x2b626363396f] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/stats_over_http.so(+0x1235)[0x2b6263228235] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528]
[jira] [Commented] (TS-3032) FATAL: ats_malloc: couldn't allocate XXXXXX bytes
[ https://issues.apache.org/jira/browse/TS-3032?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14115401#comment-14115401 ] Zhao Yongming commented on TS-3032: --- yeah, 64k is too small for you, I'd suggest you 128K, you may use 256K I think. FATAL: ats_malloc: couldn't allocate XX bytes - Key: TS-3032 URL: https://issues.apache.org/jira/browse/TS-3032 Project: Traffic Server Issue Type: Bug Components: Core Affects Versions: 5.0.1 Reporter: Nikolai Gorchilov Assignee: Brian Geffon Labels: crash Fix For: 5.2.0 Attachments: memory.d.png ATS 5.0.1 under Unbuntu 12.04.4 running happily for days suddenly crashes due to memory allocation issue. Happens once or twice a week. Server is having plenty of RAM - 128G - out of which 64G+ are free. Nothing suspicious in dmesg. {noformat} FATAL: ats_malloc: couldn't allocate 155648 bytes /z/bin/traffic_server - STACK TRACE: /z/lib/libtsutil.so.5(+0x1e837)[0x2b6251b3d837] /z/lib/libtsutil.so.5(ats_malloc+0x30)[0x2b6251b40c50] /z/bin/traffic_server(HdrHeap::coalesce_str_heaps(int)+0x34)[0x62e834] /z/bin/traffic_server(http_hdr_clone(HTTPHdrImpl*, HdrHeap*, HdrHeap*)+0x8f)[0x62a54f] /z/bin/traffic_server(HttpTransactHeaders::copy_header_fields(HTTPHdr*, HTTPHdr*, bool, long)+0x1ae)[0x5d08de] /z/bin/traffic_server(HttpTransact::build_request(HttpTransact::State*, HTTPHdr*, HTTPHdr*, HTTPVersion)+0x5c)[0x5b280c] /z/bin/traffic_server(HttpTransact::HandleCacheOpenReadMiss(HttpTransact::State*)+0x2c8)[0x5c2ce8] /z/bin/traffic_server(HttpSM::call_transact_and_set_next_state(void (*)(HttpTransact::State*))+0x66)[0x58e356] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::do_hostdb_lookup()+0x27a)[0x58e84a] /z/bin/traffic_server(HttpSM::set_next_state()+0xd48)[0x5a1038] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/x3me_dscp.so(http_txn_hook(tsapi_cont*, TSEvent, void*)+0x236)[0x2b626342b508] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_cache_open_read(int, void*)+0x180)[0x59b070] /z/bin/traffic_server(HttpSM::main_handler(int, void*)+0xd8)[0x59ad98] /z/bin/traffic_server(HttpCacheSM::state_cache_open_read(int, void*)+0x173)[0x57bbb3] /z/bin/traffic_server(Cache::open_read(Continuation*, INK_MD5*, HTTPHdr*, CacheLookupHttpConfig*, CacheFragType, char*, int)+0x616)[0x6d65a6] /z/bin/traffic_server(CacheProcessor::open_read(Continuation*, URL*, bool, HTTPHdr*, CacheLookupHttpConfig*, long, CacheFragType)+0xb0)[0x6b1af0] /z/bin/traffic_server(HttpCacheSM::open_read(URL*, HTTPHdr*, CacheLookupHttpConfig*, long)+0x83)[0x57c2d3] /z/bin/traffic_server(HttpSM::do_cache_lookup_and_read()+0xfb)[0x58baeb] /z/bin/traffic_server(HttpSM::set_next_state()+0x888)[0x5a0b78] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::set_next_state()+0x7e2)[0x5a0ad2] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/cacheurl.so(+0x17dc)[0x2b6263a477dc] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/tslua.so(+0x596f)[0x2b626363396f] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/stats_over_http.so(+0x1235)[0x2b6263228235] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_read_client_request_header(int, void*)+0x22b)[0x59270b] /z/bin/traffic_server(HttpSM::main_handler(int, void*)+0xd8)[0x59ad98] /z/bin/traffic_server[0x714a60] /z/bin/traffic_server(NetHandler::mainNetEvent(int, Event*)+0x1ed)[0x7077cd] /z/bin/traffic_server(EThread::process_event(Event*, int)+0x91)[0x736111]
[jira] [Commented] (TS-3032) FATAL: ats_malloc: couldn't allocate XXXXXX bytes
[ https://issues.apache.org/jira/browse/TS-3032?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14115416#comment-14115416 ] Zhao Yongming commented on TS-3032: --- well, looks your memory is starting from 20G, I'd think that your index memory is nearly about 20G, that indicate you may have ~20TB storage, if you haven't change proxy.config.cache.min_average_object_size, is this right? FATAL: ats_malloc: couldn't allocate XX bytes - Key: TS-3032 URL: https://issues.apache.org/jira/browse/TS-3032 Project: Traffic Server Issue Type: Bug Components: Core Affects Versions: 5.0.1 Reporter: Nikolai Gorchilov Assignee: Brian Geffon Labels: crash Fix For: 5.2.0 Attachments: memory.d.png ATS 5.0.1 under Unbuntu 12.04.4 running happily for days suddenly crashes due to memory allocation issue. Happens once or twice a week. Server is having plenty of RAM - 128G - out of which 64G+ are free. Nothing suspicious in dmesg. {noformat} FATAL: ats_malloc: couldn't allocate 155648 bytes /z/bin/traffic_server - STACK TRACE: /z/lib/libtsutil.so.5(+0x1e837)[0x2b6251b3d837] /z/lib/libtsutil.so.5(ats_malloc+0x30)[0x2b6251b40c50] /z/bin/traffic_server(HdrHeap::coalesce_str_heaps(int)+0x34)[0x62e834] /z/bin/traffic_server(http_hdr_clone(HTTPHdrImpl*, HdrHeap*, HdrHeap*)+0x8f)[0x62a54f] /z/bin/traffic_server(HttpTransactHeaders::copy_header_fields(HTTPHdr*, HTTPHdr*, bool, long)+0x1ae)[0x5d08de] /z/bin/traffic_server(HttpTransact::build_request(HttpTransact::State*, HTTPHdr*, HTTPHdr*, HTTPVersion)+0x5c)[0x5b280c] /z/bin/traffic_server(HttpTransact::HandleCacheOpenReadMiss(HttpTransact::State*)+0x2c8)[0x5c2ce8] /z/bin/traffic_server(HttpSM::call_transact_and_set_next_state(void (*)(HttpTransact::State*))+0x66)[0x58e356] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::do_hostdb_lookup()+0x27a)[0x58e84a] /z/bin/traffic_server(HttpSM::set_next_state()+0xd48)[0x5a1038] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/x3me_dscp.so(http_txn_hook(tsapi_cont*, TSEvent, void*)+0x236)[0x2b626342b508] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_cache_open_read(int, void*)+0x180)[0x59b070] /z/bin/traffic_server(HttpSM::main_handler(int, void*)+0xd8)[0x59ad98] /z/bin/traffic_server(HttpCacheSM::state_cache_open_read(int, void*)+0x173)[0x57bbb3] /z/bin/traffic_server(Cache::open_read(Continuation*, INK_MD5*, HTTPHdr*, CacheLookupHttpConfig*, CacheFragType, char*, int)+0x616)[0x6d65a6] /z/bin/traffic_server(CacheProcessor::open_read(Continuation*, URL*, bool, HTTPHdr*, CacheLookupHttpConfig*, long, CacheFragType)+0xb0)[0x6b1af0] /z/bin/traffic_server(HttpCacheSM::open_read(URL*, HTTPHdr*, CacheLookupHttpConfig*, long)+0x83)[0x57c2d3] /z/bin/traffic_server(HttpSM::do_cache_lookup_and_read()+0xfb)[0x58baeb] /z/bin/traffic_server(HttpSM::set_next_state()+0x888)[0x5a0b78] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::set_next_state()+0x7e2)[0x5a0ad2] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/cacheurl.so(+0x17dc)[0x2b6263a477dc] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/tslua.so(+0x596f)[0x2b626363396f] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/stats_over_http.so(+0x1235)[0x2b6263228235] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_read_client_request_header(int, void*)+0x22b)[0x59270b] /z/bin/traffic_server(HttpSM::main_handler(int, void*)+0xd8)[0x59ad98] /z/bin/traffic_server[0x714a60]
[jira] [Commented] (TS-3032) FATAL: ats_malloc: couldn't allocate XXXXXX bytes
[ https://issues.apache.org/jira/browse/TS-3032?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14115442#comment-14115442 ] Nikolai Gorchilov commented on TS-3032: --- I prefer to keep only objects smaller than 64k in RAM, thus proxy.config.cache.ram_cache_cutoff = 65536. The question was about the possibility this limit to trigger the un-handled out-of-memory exception I'm facing. Total storage is just bellow 8TB and proxy.config.cache.min_average_object_size = 8000. RAM cache is 1G (proxy.config.cache.ram_cache.size = 1073741824) Here's the current ATS memory allocation on this box: {noformat} allocated |in-use | type size | free list name |||-- 67108864 | 10485760 |2097152 | memory/ioBufAllocator[14] 738197504 | 679477248 |1048576 | memory/ioBufAllocator[13] 100663296 | 58720256 | 524288 | memory/ioBufAllocator[12] 50331648 | 34340864 | 262144 | memory/ioBufAllocator[11] 50331648 | 35782656 | 131072 | memory/ioBufAllocator[10] 312475648 | 270270464 | 65536 | memory/ioBufAllocator[9] 1249902592 | 1039499264 | 32768 | memory/ioBufAllocator[8] 293601280 | 261799936 | 16384 | memory/ioBufAllocator[7] 418381824 | 397361152 | 8192 | memory/ioBufAllocator[6] 1760559104 | 1741463552 | 4096 | memory/ioBufAllocator[5] 786432 | 550912 | 2048 | memory/ioBufAllocator[4] 393216 | 275456 | 1024 | memory/ioBufAllocator[3] 3997696 |3930624 |512 | memory/ioBufAllocator[2] 5537792 | 273152 |256 | memory/ioBufAllocator[1] 13795328 |1084544 |128 | memory/ioBufAllocator[0] 2580480 | 320352 | 96 | memory/eventAllocator 29511680 | 29227040 | 80 | memory/mutexAllocator 38346752 | 31291840 | 64 | memory/ioBlockAllocator 27420672 | 26394288 | 48 | memory/ioDataAllocator 97720320 | 97719360 |240 | memory/ioAllocator 0 | 0 |384 | memory/socksAllocator 0 | 0 |128 | memory/udpReadContAllocator 0 | 0 |160 | memory/udpPacketAllocator 256929792 | 254691360 |672 | memory/netVCAllocator 0 | 0 |128 | memory/UDPIOEventAllocator 92160 | 2880 |720 | memory/sslNetVCAllocator 4546560 |4426496 | 64 | memory/RamCacheLRUEntry 0 | 0 | 96 | memory/RamCacheCLFUSEntry 983040 | 964960 |160 | memory/openDirEntry 14336 |112 |112 | memory/migrateToInterimCache 0 | 0 | 48 | memory/evacuationKey 6144 | 0 | 48 | memory/cacheRemoveCont 2691072 |2683968 | 96 | memory/evacuationBlock 7004160 |6917760 |960 | memory/cacheVConnection 0 | 0 | 32 | memory/byteBankAllocator 0 | 0 |592 | memory/clusterVCAllocator 0 | 0 |112 | memory/inControlAllocator 0 | 0 |112 | memory/outControlAllocator 0 | 0 | 48 | memory/ClusterVConnectionCache::Entry 0 | 0 |576 | memory/cacheContAllocator 0 | 0 | 16 | memory/DNSRequestDataAllocator 6364928 | 33856 | 33856 | memory/dnsBufAllocator 983040 | 21760 | 1280 | memory/dnsEntryAllocator 7372800 | 46080 | 2304 | memory/hostDBContAllocator 0 | 0 |112 | memory/OneWayTunnelAllocator 64225280 | 64210944 | 2048 | memory/hdrStrHeap 120848384 | 117352448 | 2048 | memory/hdrHeap 163840 | 144896 |256 | memory/httpCacheAltAllocator 0 | 0 | 48 | memory/CongestRequestParamAllocator 0 | 0 |144 | memory/CongestionDBContAllocator 0 | 0 |128 |
[jira] [Commented] (TS-3032) FATAL: ats_malloc: couldn't allocate XXXXXX bytes
[ https://issues.apache.org/jira/browse/TS-3032?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14115477#comment-14115477 ] Nikolai Gorchilov commented on TS-3032: --- I also suspect vm.max_map_count to be the reason behind the failure. Just checked the number of allocations at the other box and it stands at 50222 currently. Added crontab logging facility in order to track number of ATS memory maps: {noformat} * * * * * cat /proc/18455/maps | wc -l | xargs echo $(date): /tmp/maps.log {noformat} If I'm right ATS will crash soon and the last logged value would be just bellow vm.max_map_count (65530) FATAL: ats_malloc: couldn't allocate XX bytes - Key: TS-3032 URL: https://issues.apache.org/jira/browse/TS-3032 Project: Traffic Server Issue Type: Bug Components: Core Affects Versions: 5.0.1 Reporter: Nikolai Gorchilov Assignee: Brian Geffon Labels: crash Fix For: 5.2.0 Attachments: memory.d.png ATS 5.0.1 under Unbuntu 12.04.4 running happily for days suddenly crashes due to memory allocation issue. Happens once or twice a week. Server is having plenty of RAM - 128G - out of which 64G+ are free. Nothing suspicious in dmesg. {noformat} FATAL: ats_malloc: couldn't allocate 155648 bytes /z/bin/traffic_server - STACK TRACE: /z/lib/libtsutil.so.5(+0x1e837)[0x2b6251b3d837] /z/lib/libtsutil.so.5(ats_malloc+0x30)[0x2b6251b40c50] /z/bin/traffic_server(HdrHeap::coalesce_str_heaps(int)+0x34)[0x62e834] /z/bin/traffic_server(http_hdr_clone(HTTPHdrImpl*, HdrHeap*, HdrHeap*)+0x8f)[0x62a54f] /z/bin/traffic_server(HttpTransactHeaders::copy_header_fields(HTTPHdr*, HTTPHdr*, bool, long)+0x1ae)[0x5d08de] /z/bin/traffic_server(HttpTransact::build_request(HttpTransact::State*, HTTPHdr*, HTTPHdr*, HTTPVersion)+0x5c)[0x5b280c] /z/bin/traffic_server(HttpTransact::HandleCacheOpenReadMiss(HttpTransact::State*)+0x2c8)[0x5c2ce8] /z/bin/traffic_server(HttpSM::call_transact_and_set_next_state(void (*)(HttpTransact::State*))+0x66)[0x58e356] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::do_hostdb_lookup()+0x27a)[0x58e84a] /z/bin/traffic_server(HttpSM::set_next_state()+0xd48)[0x5a1038] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/x3me_dscp.so(http_txn_hook(tsapi_cont*, TSEvent, void*)+0x236)[0x2b626342b508] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_cache_open_read(int, void*)+0x180)[0x59b070] /z/bin/traffic_server(HttpSM::main_handler(int, void*)+0xd8)[0x59ad98] /z/bin/traffic_server(HttpCacheSM::state_cache_open_read(int, void*)+0x173)[0x57bbb3] /z/bin/traffic_server(Cache::open_read(Continuation*, INK_MD5*, HTTPHdr*, CacheLookupHttpConfig*, CacheFragType, char*, int)+0x616)[0x6d65a6] /z/bin/traffic_server(CacheProcessor::open_read(Continuation*, URL*, bool, HTTPHdr*, CacheLookupHttpConfig*, long, CacheFragType)+0xb0)[0x6b1af0] /z/bin/traffic_server(HttpCacheSM::open_read(URL*, HTTPHdr*, CacheLookupHttpConfig*, long)+0x83)[0x57c2d3] /z/bin/traffic_server(HttpSM::do_cache_lookup_and_read()+0xfb)[0x58baeb] /z/bin/traffic_server(HttpSM::set_next_state()+0x888)[0x5a0b78] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::set_next_state()+0x7e2)[0x5a0ad2] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/cacheurl.so(+0x17dc)[0x2b6263a477dc] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/tslua.so(+0x596f)[0x2b626363396f] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/stats_over_http.so(+0x1235)[0x2b6263228235] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528]
[jira] [Commented] (TS-3032) FATAL: ats_malloc: couldn't allocate XXXXXX bytes
[ https://issues.apache.org/jira/browse/TS-3032?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14115529#comment-14115529 ] Leif Hedstrom commented on TS-3032: --- Yeah, we need to document this better. It was unclear if we still needed this many mmap's, but apparently we do :). I wonder, does the interim cache consume more mmap areas? Fwiw, there's a setting in ATS as well for this, but we set it way, way high (such that the sysctl would always become the bottleneck): {code} {RECT_CONFIG, proxy.config.system.mmap_max, RECD_INT, 2097152, {code} FATAL: ats_malloc: couldn't allocate XX bytes - Key: TS-3032 URL: https://issues.apache.org/jira/browse/TS-3032 Project: Traffic Server Issue Type: Bug Components: Core Affects Versions: 5.0.1 Reporter: Nikolai Gorchilov Assignee: Brian Geffon Labels: crash Fix For: 5.2.0 Attachments: memory.d.png ATS 5.0.1 under Unbuntu 12.04.4 running happily for days suddenly crashes due to memory allocation issue. Happens once or twice a week. Server is having plenty of RAM - 128G - out of which 64G+ are free. Nothing suspicious in dmesg. {noformat} FATAL: ats_malloc: couldn't allocate 155648 bytes /z/bin/traffic_server - STACK TRACE: /z/lib/libtsutil.so.5(+0x1e837)[0x2b6251b3d837] /z/lib/libtsutil.so.5(ats_malloc+0x30)[0x2b6251b40c50] /z/bin/traffic_server(HdrHeap::coalesce_str_heaps(int)+0x34)[0x62e834] /z/bin/traffic_server(http_hdr_clone(HTTPHdrImpl*, HdrHeap*, HdrHeap*)+0x8f)[0x62a54f] /z/bin/traffic_server(HttpTransactHeaders::copy_header_fields(HTTPHdr*, HTTPHdr*, bool, long)+0x1ae)[0x5d08de] /z/bin/traffic_server(HttpTransact::build_request(HttpTransact::State*, HTTPHdr*, HTTPHdr*, HTTPVersion)+0x5c)[0x5b280c] /z/bin/traffic_server(HttpTransact::HandleCacheOpenReadMiss(HttpTransact::State*)+0x2c8)[0x5c2ce8] /z/bin/traffic_server(HttpSM::call_transact_and_set_next_state(void (*)(HttpTransact::State*))+0x66)[0x58e356] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::do_hostdb_lookup()+0x27a)[0x58e84a] /z/bin/traffic_server(HttpSM::set_next_state()+0xd48)[0x5a1038] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/x3me_dscp.so(http_txn_hook(tsapi_cont*, TSEvent, void*)+0x236)[0x2b626342b508] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_cache_open_read(int, void*)+0x180)[0x59b070] /z/bin/traffic_server(HttpSM::main_handler(int, void*)+0xd8)[0x59ad98] /z/bin/traffic_server(HttpCacheSM::state_cache_open_read(int, void*)+0x173)[0x57bbb3] /z/bin/traffic_server(Cache::open_read(Continuation*, INK_MD5*, HTTPHdr*, CacheLookupHttpConfig*, CacheFragType, char*, int)+0x616)[0x6d65a6] /z/bin/traffic_server(CacheProcessor::open_read(Continuation*, URL*, bool, HTTPHdr*, CacheLookupHttpConfig*, long, CacheFragType)+0xb0)[0x6b1af0] /z/bin/traffic_server(HttpCacheSM::open_read(URL*, HTTPHdr*, CacheLookupHttpConfig*, long)+0x83)[0x57c2d3] /z/bin/traffic_server(HttpSM::do_cache_lookup_and_read()+0xfb)[0x58baeb] /z/bin/traffic_server(HttpSM::set_next_state()+0x888)[0x5a0b78] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::set_next_state()+0x7e2)[0x5a0ad2] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/cacheurl.so(+0x17dc)[0x2b6263a477dc] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/tslua.so(+0x596f)[0x2b626363396f] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/stats_over_http.so(+0x1235)[0x2b6263228235] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528]
[jira] [Commented] (TS-3032) FATAL: ats_malloc: couldn't allocate XXXXXX bytes
[ https://issues.apache.org/jira/browse/TS-3032?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14115536#comment-14115536 ] Nikolai Gorchilov commented on TS-3032: --- I'm can't tell what is interim cache contribution to mmap exhaust as I don't have comparable size installations without interim storage. I can only say that all crashing setups do use interim storage. What is going to happen if I decrease proxy.config.system.mmap_max vm. max_map_count? FATAL: ats_malloc: couldn't allocate XX bytes - Key: TS-3032 URL: https://issues.apache.org/jira/browse/TS-3032 Project: Traffic Server Issue Type: Bug Components: Core Affects Versions: 5.0.1 Reporter: Nikolai Gorchilov Assignee: Brian Geffon Labels: crash Fix For: 5.2.0 Attachments: memory.d.png ATS 5.0.1 under Unbuntu 12.04.4 running happily for days suddenly crashes due to memory allocation issue. Happens once or twice a week. Server is having plenty of RAM - 128G - out of which 64G+ are free. Nothing suspicious in dmesg. {noformat} FATAL: ats_malloc: couldn't allocate 155648 bytes /z/bin/traffic_server - STACK TRACE: /z/lib/libtsutil.so.5(+0x1e837)[0x2b6251b3d837] /z/lib/libtsutil.so.5(ats_malloc+0x30)[0x2b6251b40c50] /z/bin/traffic_server(HdrHeap::coalesce_str_heaps(int)+0x34)[0x62e834] /z/bin/traffic_server(http_hdr_clone(HTTPHdrImpl*, HdrHeap*, HdrHeap*)+0x8f)[0x62a54f] /z/bin/traffic_server(HttpTransactHeaders::copy_header_fields(HTTPHdr*, HTTPHdr*, bool, long)+0x1ae)[0x5d08de] /z/bin/traffic_server(HttpTransact::build_request(HttpTransact::State*, HTTPHdr*, HTTPHdr*, HTTPVersion)+0x5c)[0x5b280c] /z/bin/traffic_server(HttpTransact::HandleCacheOpenReadMiss(HttpTransact::State*)+0x2c8)[0x5c2ce8] /z/bin/traffic_server(HttpSM::call_transact_and_set_next_state(void (*)(HttpTransact::State*))+0x66)[0x58e356] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::do_hostdb_lookup()+0x27a)[0x58e84a] /z/bin/traffic_server(HttpSM::set_next_state()+0xd48)[0x5a1038] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/x3me_dscp.so(http_txn_hook(tsapi_cont*, TSEvent, void*)+0x236)[0x2b626342b508] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_cache_open_read(int, void*)+0x180)[0x59b070] /z/bin/traffic_server(HttpSM::main_handler(int, void*)+0xd8)[0x59ad98] /z/bin/traffic_server(HttpCacheSM::state_cache_open_read(int, void*)+0x173)[0x57bbb3] /z/bin/traffic_server(Cache::open_read(Continuation*, INK_MD5*, HTTPHdr*, CacheLookupHttpConfig*, CacheFragType, char*, int)+0x616)[0x6d65a6] /z/bin/traffic_server(CacheProcessor::open_read(Continuation*, URL*, bool, HTTPHdr*, CacheLookupHttpConfig*, long, CacheFragType)+0xb0)[0x6b1af0] /z/bin/traffic_server(HttpCacheSM::open_read(URL*, HTTPHdr*, CacheLookupHttpConfig*, long)+0x83)[0x57c2d3] /z/bin/traffic_server(HttpSM::do_cache_lookup_and_read()+0xfb)[0x58baeb] /z/bin/traffic_server(HttpSM::set_next_state()+0x888)[0x5a0b78] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::set_next_state()+0x7e2)[0x5a0ad2] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/cacheurl.so(+0x17dc)[0x2b6263a477dc] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/tslua.so(+0x596f)[0x2b626363396f] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/stats_over_http.so(+0x1235)[0x2b6263228235] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_read_client_request_header(int, void*)+0x22b)[0x59270b] /z/bin/traffic_server(HttpSM::main_handler(int,
[jira] [Commented] (TS-3032) FATAL: ats_malloc: couldn't allocate XXXXXX bytes
[ https://issues.apache.org/jira/browse/TS-3032?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14115745#comment-14115745 ] Leif Hedstrom commented on TS-3032: --- Doing that change would not make things better. What you need to try is to try setting your vm.max_map_count bigger, and restart ATS. E.g. in sysctl.conf {code} vm.max_map_count = 2097152 {code} or, using sysctl from command line. FATAL: ats_malloc: couldn't allocate XX bytes - Key: TS-3032 URL: https://issues.apache.org/jira/browse/TS-3032 Project: Traffic Server Issue Type: Bug Components: Core Affects Versions: 5.0.1 Reporter: Nikolai Gorchilov Assignee: Brian Geffon Labels: crash Fix For: 5.2.0 Attachments: memory.d.png ATS 5.0.1 under Unbuntu 12.04.4 running happily for days suddenly crashes due to memory allocation issue. Happens once or twice a week. Server is having plenty of RAM - 128G - out of which 64G+ are free. Nothing suspicious in dmesg. {noformat} FATAL: ats_malloc: couldn't allocate 155648 bytes /z/bin/traffic_server - STACK TRACE: /z/lib/libtsutil.so.5(+0x1e837)[0x2b6251b3d837] /z/lib/libtsutil.so.5(ats_malloc+0x30)[0x2b6251b40c50] /z/bin/traffic_server(HdrHeap::coalesce_str_heaps(int)+0x34)[0x62e834] /z/bin/traffic_server(http_hdr_clone(HTTPHdrImpl*, HdrHeap*, HdrHeap*)+0x8f)[0x62a54f] /z/bin/traffic_server(HttpTransactHeaders::copy_header_fields(HTTPHdr*, HTTPHdr*, bool, long)+0x1ae)[0x5d08de] /z/bin/traffic_server(HttpTransact::build_request(HttpTransact::State*, HTTPHdr*, HTTPHdr*, HTTPVersion)+0x5c)[0x5b280c] /z/bin/traffic_server(HttpTransact::HandleCacheOpenReadMiss(HttpTransact::State*)+0x2c8)[0x5c2ce8] /z/bin/traffic_server(HttpSM::call_transact_and_set_next_state(void (*)(HttpTransact::State*))+0x66)[0x58e356] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::do_hostdb_lookup()+0x27a)[0x58e84a] /z/bin/traffic_server(HttpSM::set_next_state()+0xd48)[0x5a1038] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/x3me_dscp.so(http_txn_hook(tsapi_cont*, TSEvent, void*)+0x236)[0x2b626342b508] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_cache_open_read(int, void*)+0x180)[0x59b070] /z/bin/traffic_server(HttpSM::main_handler(int, void*)+0xd8)[0x59ad98] /z/bin/traffic_server(HttpCacheSM::state_cache_open_read(int, void*)+0x173)[0x57bbb3] /z/bin/traffic_server(Cache::open_read(Continuation*, INK_MD5*, HTTPHdr*, CacheLookupHttpConfig*, CacheFragType, char*, int)+0x616)[0x6d65a6] /z/bin/traffic_server(CacheProcessor::open_read(Continuation*, URL*, bool, HTTPHdr*, CacheLookupHttpConfig*, long, CacheFragType)+0xb0)[0x6b1af0] /z/bin/traffic_server(HttpCacheSM::open_read(URL*, HTTPHdr*, CacheLookupHttpConfig*, long)+0x83)[0x57c2d3] /z/bin/traffic_server(HttpSM::do_cache_lookup_and_read()+0xfb)[0x58baeb] /z/bin/traffic_server(HttpSM::set_next_state()+0x888)[0x5a0b78] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::set_next_state()+0x7e2)[0x5a0ad2] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/cacheurl.so(+0x17dc)[0x2b6263a477dc] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/tslua.so(+0x596f)[0x2b626363396f] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/stats_over_http.so(+0x1235)[0x2b6263228235] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_read_client_request_header(int, void*)+0x22b)[0x59270b] /z/bin/traffic_server(HttpSM::main_handler(int, void*)+0xd8)[0x59ad98] /z/bin/traffic_server[0x714a60]
[jira] [Commented] (TS-3032) FATAL: ats_malloc: couldn't allocate XXXXXX bytes
[ https://issues.apache.org/jira/browse/TS-3032?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14113762#comment-14113762 ] Zhao Yongming commented on TS-3032: --- any update? [~ngorchilov] FATAL: ats_malloc: couldn't allocate XX bytes - Key: TS-3032 URL: https://issues.apache.org/jira/browse/TS-3032 Project: Traffic Server Issue Type: Bug Components: Core Affects Versions: 5.0.1 Reporter: Nikolai Gorchilov Assignee: Brian Geffon Labels: crash Fix For: 5.2.0 ATS 5.0.1 under Unbuntu 12.04.4 running happily for days suddenly crashes due to memory allocation issue. Happens once or twice a week. Server is having plenty of RAM - 128G - out of which 64G+ are free. Nothing suspicious in dmesg. {noformat} FATAL: ats_malloc: couldn't allocate 155648 bytes /z/bin/traffic_server - STACK TRACE: /z/lib/libtsutil.so.5(+0x1e837)[0x2b6251b3d837] /z/lib/libtsutil.so.5(ats_malloc+0x30)[0x2b6251b40c50] /z/bin/traffic_server(HdrHeap::coalesce_str_heaps(int)+0x34)[0x62e834] /z/bin/traffic_server(http_hdr_clone(HTTPHdrImpl*, HdrHeap*, HdrHeap*)+0x8f)[0x62a54f] /z/bin/traffic_server(HttpTransactHeaders::copy_header_fields(HTTPHdr*, HTTPHdr*, bool, long)+0x1ae)[0x5d08de] /z/bin/traffic_server(HttpTransact::build_request(HttpTransact::State*, HTTPHdr*, HTTPHdr*, HTTPVersion)+0x5c)[0x5b280c] /z/bin/traffic_server(HttpTransact::HandleCacheOpenReadMiss(HttpTransact::State*)+0x2c8)[0x5c2ce8] /z/bin/traffic_server(HttpSM::call_transact_and_set_next_state(void (*)(HttpTransact::State*))+0x66)[0x58e356] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::do_hostdb_lookup()+0x27a)[0x58e84a] /z/bin/traffic_server(HttpSM::set_next_state()+0xd48)[0x5a1038] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/x3me_dscp.so(http_txn_hook(tsapi_cont*, TSEvent, void*)+0x236)[0x2b626342b508] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_cache_open_read(int, void*)+0x180)[0x59b070] /z/bin/traffic_server(HttpSM::main_handler(int, void*)+0xd8)[0x59ad98] /z/bin/traffic_server(HttpCacheSM::state_cache_open_read(int, void*)+0x173)[0x57bbb3] /z/bin/traffic_server(Cache::open_read(Continuation*, INK_MD5*, HTTPHdr*, CacheLookupHttpConfig*, CacheFragType, char*, int)+0x616)[0x6d65a6] /z/bin/traffic_server(CacheProcessor::open_read(Continuation*, URL*, bool, HTTPHdr*, CacheLookupHttpConfig*, long, CacheFragType)+0xb0)[0x6b1af0] /z/bin/traffic_server(HttpCacheSM::open_read(URL*, HTTPHdr*, CacheLookupHttpConfig*, long)+0x83)[0x57c2d3] /z/bin/traffic_server(HttpSM::do_cache_lookup_and_read()+0xfb)[0x58baeb] /z/bin/traffic_server(HttpSM::set_next_state()+0x888)[0x5a0b78] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::set_next_state()+0x7e2)[0x5a0ad2] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/cacheurl.so(+0x17dc)[0x2b6263a477dc] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/tslua.so(+0x596f)[0x2b626363396f] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/stats_over_http.so(+0x1235)[0x2b6263228235] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_read_client_request_header(int, void*)+0x22b)[0x59270b] /z/bin/traffic_server(HttpSM::main_handler(int, void*)+0xd8)[0x59ad98] /z/bin/traffic_server[0x714a60] /z/bin/traffic_server(NetHandler::mainNetEvent(int, Event*)+0x1ed)[0x7077cd] /z/bin/traffic_server(EThread::process_event(Event*, int)+0x91)[0x736111] /z/bin/traffic_server(EThread::execute()+0x4fc)[0x736bcc] /z/bin/traffic_server[0x7353aa]
[jira] [Commented] (TS-3032) FATAL: ats_malloc: couldn't allocate XXXXXX bytes
[ https://issues.apache.org/jira/browse/TS-3032?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14113798#comment-14113798 ] Nikolai Gorchilov commented on TS-3032: --- Unfortunately, I'm out of office this week. Will update you early next week. FATAL: ats_malloc: couldn't allocate XX bytes - Key: TS-3032 URL: https://issues.apache.org/jira/browse/TS-3032 Project: Traffic Server Issue Type: Bug Components: Core Affects Versions: 5.0.1 Reporter: Nikolai Gorchilov Assignee: Brian Geffon Labels: crash Fix For: 5.2.0 ATS 5.0.1 under Unbuntu 12.04.4 running happily for days suddenly crashes due to memory allocation issue. Happens once or twice a week. Server is having plenty of RAM - 128G - out of which 64G+ are free. Nothing suspicious in dmesg. {noformat} FATAL: ats_malloc: couldn't allocate 155648 bytes /z/bin/traffic_server - STACK TRACE: /z/lib/libtsutil.so.5(+0x1e837)[0x2b6251b3d837] /z/lib/libtsutil.so.5(ats_malloc+0x30)[0x2b6251b40c50] /z/bin/traffic_server(HdrHeap::coalesce_str_heaps(int)+0x34)[0x62e834] /z/bin/traffic_server(http_hdr_clone(HTTPHdrImpl*, HdrHeap*, HdrHeap*)+0x8f)[0x62a54f] /z/bin/traffic_server(HttpTransactHeaders::copy_header_fields(HTTPHdr*, HTTPHdr*, bool, long)+0x1ae)[0x5d08de] /z/bin/traffic_server(HttpTransact::build_request(HttpTransact::State*, HTTPHdr*, HTTPHdr*, HTTPVersion)+0x5c)[0x5b280c] /z/bin/traffic_server(HttpTransact::HandleCacheOpenReadMiss(HttpTransact::State*)+0x2c8)[0x5c2ce8] /z/bin/traffic_server(HttpSM::call_transact_and_set_next_state(void (*)(HttpTransact::State*))+0x66)[0x58e356] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::do_hostdb_lookup()+0x27a)[0x58e84a] /z/bin/traffic_server(HttpSM::set_next_state()+0xd48)[0x5a1038] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/x3me_dscp.so(http_txn_hook(tsapi_cont*, TSEvent, void*)+0x236)[0x2b626342b508] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_cache_open_read(int, void*)+0x180)[0x59b070] /z/bin/traffic_server(HttpSM::main_handler(int, void*)+0xd8)[0x59ad98] /z/bin/traffic_server(HttpCacheSM::state_cache_open_read(int, void*)+0x173)[0x57bbb3] /z/bin/traffic_server(Cache::open_read(Continuation*, INK_MD5*, HTTPHdr*, CacheLookupHttpConfig*, CacheFragType, char*, int)+0x616)[0x6d65a6] /z/bin/traffic_server(CacheProcessor::open_read(Continuation*, URL*, bool, HTTPHdr*, CacheLookupHttpConfig*, long, CacheFragType)+0xb0)[0x6b1af0] /z/bin/traffic_server(HttpCacheSM::open_read(URL*, HTTPHdr*, CacheLookupHttpConfig*, long)+0x83)[0x57c2d3] /z/bin/traffic_server(HttpSM::do_cache_lookup_and_read()+0xfb)[0x58baeb] /z/bin/traffic_server(HttpSM::set_next_state()+0x888)[0x5a0b78] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::set_next_state()+0x7e2)[0x5a0ad2] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/cacheurl.so(+0x17dc)[0x2b6263a477dc] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/tslua.so(+0x596f)[0x2b626363396f] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/stats_over_http.so(+0x1235)[0x2b6263228235] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_read_client_request_header(int, void*)+0x22b)[0x59270b] /z/bin/traffic_server(HttpSM::main_handler(int, void*)+0xd8)[0x59ad98] /z/bin/traffic_server[0x714a60] /z/bin/traffic_server(NetHandler::mainNetEvent(int, Event*)+0x1ed)[0x7077cd] /z/bin/traffic_server(EThread::process_event(Event*, int)+0x91)[0x736111]
[jira] [Commented] (TS-3032) FATAL: ats_malloc: couldn't allocate XXXXXX bytes
[ https://issues.apache.org/jira/browse/TS-3032?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14110941#comment-14110941 ] Zhao Yongming commented on TS-3032: --- I'd suggest you get some tool to log the memory usage and other history data. a tool we used very often in tracing issues like this is https://github.com/alibaba/tsar https://blog.zymlinux.net/index.php/archives/251 , any other tool that can find out the data to compare is great. when we deal with TS-1006, I even make some excel sheet to point out that the memory is a big problem, the more data the better FATAL: ats_malloc: couldn't allocate XX bytes - Key: TS-3032 URL: https://issues.apache.org/jira/browse/TS-3032 Project: Traffic Server Issue Type: Bug Components: Core Affects Versions: 5.0.1 Reporter: Nikolai Gorchilov Assignee: Brian Geffon Labels: crash Fix For: 5.2.0 ATS 5.0.1 under Unbuntu 12.04.4 running happily for days suddenly crashes due to memory allocation issue. Happens once or twice a week. Server is having plenty of RAM - 128G - out of which 64G+ are free. Nothing suspicious in dmesg. {noformat} FATAL: ats_malloc: couldn't allocate 155648 bytes /z/bin/traffic_server - STACK TRACE: /z/lib/libtsutil.so.5(+0x1e837)[0x2b6251b3d837] /z/lib/libtsutil.so.5(ats_malloc+0x30)[0x2b6251b40c50] /z/bin/traffic_server(HdrHeap::coalesce_str_heaps(int)+0x34)[0x62e834] /z/bin/traffic_server(http_hdr_clone(HTTPHdrImpl*, HdrHeap*, HdrHeap*)+0x8f)[0x62a54f] /z/bin/traffic_server(HttpTransactHeaders::copy_header_fields(HTTPHdr*, HTTPHdr*, bool, long)+0x1ae)[0x5d08de] /z/bin/traffic_server(HttpTransact::build_request(HttpTransact::State*, HTTPHdr*, HTTPHdr*, HTTPVersion)+0x5c)[0x5b280c] /z/bin/traffic_server(HttpTransact::HandleCacheOpenReadMiss(HttpTransact::State*)+0x2c8)[0x5c2ce8] /z/bin/traffic_server(HttpSM::call_transact_and_set_next_state(void (*)(HttpTransact::State*))+0x66)[0x58e356] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::do_hostdb_lookup()+0x27a)[0x58e84a] /z/bin/traffic_server(HttpSM::set_next_state()+0xd48)[0x5a1038] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/x3me_dscp.so(http_txn_hook(tsapi_cont*, TSEvent, void*)+0x236)[0x2b626342b508] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_cache_open_read(int, void*)+0x180)[0x59b070] /z/bin/traffic_server(HttpSM::main_handler(int, void*)+0xd8)[0x59ad98] /z/bin/traffic_server(HttpCacheSM::state_cache_open_read(int, void*)+0x173)[0x57bbb3] /z/bin/traffic_server(Cache::open_read(Continuation*, INK_MD5*, HTTPHdr*, CacheLookupHttpConfig*, CacheFragType, char*, int)+0x616)[0x6d65a6] /z/bin/traffic_server(CacheProcessor::open_read(Continuation*, URL*, bool, HTTPHdr*, CacheLookupHttpConfig*, long, CacheFragType)+0xb0)[0x6b1af0] /z/bin/traffic_server(HttpCacheSM::open_read(URL*, HTTPHdr*, CacheLookupHttpConfig*, long)+0x83)[0x57c2d3] /z/bin/traffic_server(HttpSM::do_cache_lookup_and_read()+0xfb)[0x58baeb] /z/bin/traffic_server(HttpSM::set_next_state()+0x888)[0x5a0b78] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::set_next_state()+0x7e2)[0x5a0ad2] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/cacheurl.so(+0x17dc)[0x2b6263a477dc] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/tslua.so(+0x596f)[0x2b626363396f] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/stats_over_http.so(+0x1235)[0x2b6263228235] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_read_client_request_header(int,
[jira] [Commented] (TS-3032) FATAL: ats_malloc: couldn't allocate XXXXXX bytes
[ https://issues.apache.org/jira/browse/TS-3032?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14109022#comment-14109022 ] Nikolai Gorchilov commented on TS-3032: --- * /proc/meminfo {noformat} MemTotal: 131999852 kB MemFree:81857040 kB Buffers: 357000 kB Cached: 25975284 kB SwapCached:0 kB Active: 30757792 kB Inactive: 15528096 kB Active(anon): 19953648 kB Inactive(anon): 292 kB Active(file): 10804144 kB Inactive(file): 15527804 kB Unevictable: 0 kB Mlocked: 0 kB SwapTotal: 0 kB SwapFree: 0 kB Dirty: 1800 kB Writeback: 0 kB AnonPages: 19956200 kB Mapped:47440 kB Shmem: 332 kB Slab:1794776 kB SReclaimable: 990372 kB SUnreclaim: 804404 kB KernelStack:4872 kB PageTables:43808 kB NFS_Unstable: 0 kB Bounce:0 kB WritebackTmp: 0 kB CommitLimit:6524 kB Committed_AS: 17297316 kB VmallocTotal: 34359738367 kB VmallocUsed: 488860 kB VmallocChunk: 34290894976 kB HardwareCorrupted: 0 kB AnonHugePages: 0 kB HugePages_Total: 0 HugePages_Free:0 HugePages_Rsvd:0 HugePages_Surp:0 Hugepagesize: 2048 kB DirectMap4k: 1125372 kB DirectMap2M:93210624 kB DirectMap1G:41943040 kB {noformat} * /proc/pid/status {noformat} Name: [ET_NET 0] State: S (sleeping) Tgid: 24037 Pid:24037 PPid: 24025 TracerPid: 0 Uid:13 13 13 13 Gid:13 13 13 13 FDSize: 262144 Groups: 0 VmPeak: 25063316 kB VmSize: 24999124 kB VmLck: 0 kB VmPin: 0 kB VmHWM: 19672548 kB VmRSS: 19672300 kB VmData: 24902004 kB VmStk: 136 kB VmExe: 4100 kB VmLib: 9684 kB VmPTE: 39768 kB VmSwap:0 kB Threads:145 SigQ: 0/1031099 SigPnd: ShdPnd: SigBlk: SigIgn: 00381000 SigCgt: 000180004e4f CapInh: CapPrm: 5402 CapEff: 5400 CapBnd: 001f Seccomp:0 Cpus_allowed: Cpus_allowed_list: 0-31 Mems_allowed: ,0003 Mems_allowed_list: 0-1 voluntary_ctxt_switches:130883732 nonvoluntary_ctxt_switches: 797084 {noformat} * configure options {noformat} --with-group=proxy \ --with-xml=libxml2 \ --disable-static \ --disable-static-libts \ --disable-spdy \ --enable-interim-cache \ --enable-tproxy \ --enable-hwloc \ --enable-experimental-plugins \ --enable-example-plugins {noformat} * other system logs - nothing memory related available FATAL: ats_malloc: couldn't allocate XX bytes - Key: TS-3032 URL: https://issues.apache.org/jira/browse/TS-3032 Project: Traffic Server Issue Type: Bug Components: Core Affects Versions: 5.0.1 Reporter: Nikolai Gorchilov Assignee: Brian Geffon Labels: crash Fix For: 5.2.0 ATS 5.0.1 under Unbuntu 12.04.4 running happily for days suddenly crashes due to memory allocation issue. Happens once or twice a week. Server is having plenty of RAM - 128G - out of which 64G+ are free. Nothing suspicious in dmesg. {noformat} FATAL: ats_malloc: couldn't allocate 155648 bytes /z/bin/traffic_server - STACK TRACE: /z/lib/libtsutil.so.5(+0x1e837)[0x2b6251b3d837] /z/lib/libtsutil.so.5(ats_malloc+0x30)[0x2b6251b40c50] /z/bin/traffic_server(HdrHeap::coalesce_str_heaps(int)+0x34)[0x62e834] /z/bin/traffic_server(http_hdr_clone(HTTPHdrImpl*, HdrHeap*, HdrHeap*)+0x8f)[0x62a54f] /z/bin/traffic_server(HttpTransactHeaders::copy_header_fields(HTTPHdr*, HTTPHdr*, bool, long)+0x1ae)[0x5d08de] /z/bin/traffic_server(HttpTransact::build_request(HttpTransact::State*, HTTPHdr*, HTTPHdr*, HTTPVersion)+0x5c)[0x5b280c] /z/bin/traffic_server(HttpTransact::HandleCacheOpenReadMiss(HttpTransact::State*)+0x2c8)[0x5c2ce8] /z/bin/traffic_server(HttpSM::call_transact_and_set_next_state(void (*)(HttpTransact::State*))+0x66)[0x58e356] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::do_hostdb_lookup()+0x27a)[0x58e84a] /z/bin/traffic_server(HttpSM::set_next_state()+0xd48)[0x5a1038] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/x3me_dscp.so(http_txn_hook(tsapi_cont*, TSEvent, void*)+0x236)[0x2b626342b508] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_cache_open_read(int,
[jira] [Commented] (TS-3032) FATAL: ats_malloc: couldn't allocate XXXXXX bytes
[ https://issues.apache.org/jira/browse/TS-3032?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14109133#comment-14109133 ] Zhao Yongming commented on TS-3032: --- looks nothing unusal, I think that 'Cached: 25975284 kB' is caused by the access logging, then we need more infomation on ATS: 1. your ram cache setting: proxy.config.cache.ram_cache.size, if not set please tell us your storage device usage, and cache min_average_object_size. 2. let us dump some memory details in the ATS itself: https://docs.trafficserver.apache.org/en/latest/sdk/troubleshooting-tips/debugging-memory-leaks.en.html and we should better get all those data the breaking point too :D FATAL: ats_malloc: couldn't allocate XX bytes - Key: TS-3032 URL: https://issues.apache.org/jira/browse/TS-3032 Project: Traffic Server Issue Type: Bug Components: Core Affects Versions: 5.0.1 Reporter: Nikolai Gorchilov Assignee: Brian Geffon Labels: crash Fix For: 5.2.0 ATS 5.0.1 under Unbuntu 12.04.4 running happily for days suddenly crashes due to memory allocation issue. Happens once or twice a week. Server is having plenty of RAM - 128G - out of which 64G+ are free. Nothing suspicious in dmesg. {noformat} FATAL: ats_malloc: couldn't allocate 155648 bytes /z/bin/traffic_server - STACK TRACE: /z/lib/libtsutil.so.5(+0x1e837)[0x2b6251b3d837] /z/lib/libtsutil.so.5(ats_malloc+0x30)[0x2b6251b40c50] /z/bin/traffic_server(HdrHeap::coalesce_str_heaps(int)+0x34)[0x62e834] /z/bin/traffic_server(http_hdr_clone(HTTPHdrImpl*, HdrHeap*, HdrHeap*)+0x8f)[0x62a54f] /z/bin/traffic_server(HttpTransactHeaders::copy_header_fields(HTTPHdr*, HTTPHdr*, bool, long)+0x1ae)[0x5d08de] /z/bin/traffic_server(HttpTransact::build_request(HttpTransact::State*, HTTPHdr*, HTTPHdr*, HTTPVersion)+0x5c)[0x5b280c] /z/bin/traffic_server(HttpTransact::HandleCacheOpenReadMiss(HttpTransact::State*)+0x2c8)[0x5c2ce8] /z/bin/traffic_server(HttpSM::call_transact_and_set_next_state(void (*)(HttpTransact::State*))+0x66)[0x58e356] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::do_hostdb_lookup()+0x27a)[0x58e84a] /z/bin/traffic_server(HttpSM::set_next_state()+0xd48)[0x5a1038] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/x3me_dscp.so(http_txn_hook(tsapi_cont*, TSEvent, void*)+0x236)[0x2b626342b508] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_cache_open_read(int, void*)+0x180)[0x59b070] /z/bin/traffic_server(HttpSM::main_handler(int, void*)+0xd8)[0x59ad98] /z/bin/traffic_server(HttpCacheSM::state_cache_open_read(int, void*)+0x173)[0x57bbb3] /z/bin/traffic_server(Cache::open_read(Continuation*, INK_MD5*, HTTPHdr*, CacheLookupHttpConfig*, CacheFragType, char*, int)+0x616)[0x6d65a6] /z/bin/traffic_server(CacheProcessor::open_read(Continuation*, URL*, bool, HTTPHdr*, CacheLookupHttpConfig*, long, CacheFragType)+0xb0)[0x6b1af0] /z/bin/traffic_server(HttpCacheSM::open_read(URL*, HTTPHdr*, CacheLookupHttpConfig*, long)+0x83)[0x57c2d3] /z/bin/traffic_server(HttpSM::do_cache_lookup_and_read()+0xfb)[0x58baeb] /z/bin/traffic_server(HttpSM::set_next_state()+0x888)[0x5a0b78] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::set_next_state()+0x7e2)[0x5a0ad2] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/cacheurl.so(+0x17dc)[0x2b6263a477dc] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/tslua.so(+0x596f)[0x2b626363396f] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/stats_over_http.so(+0x1235)[0x2b6263228235] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2]
[jira] [Commented] (TS-3032) FATAL: ats_malloc: couldn't allocate XXXXXX bytes
[ https://issues.apache.org/jira/browse/TS-3032?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14109151#comment-14109151 ] Nikolai Gorchilov commented on TS-3032: --- * traffic_line -r proxy.config.cache.ram_cache.size {noformat} 1073741824 {noformat} * traffic_line -s proxy.config.dump_mem_info_frequency -v 60 {noformat} allocated |in-use | type size | free list name |||-- 67108864 | 0 |2097152 | memory/ioBufAllocator[14] 268435456 | 80740352 |1048576 | memory/ioBufAllocator[13] 83886080 |7340032 | 524288 | memory/ioBufAllocator[12] 218103808 | 11272192 | 262144 | memory/ioBufAllocator[11] 88080384 |9568256 | 131072 | memory/ioBufAllocator[10] 243269632 | 36831232 | 65536 | memory/ioBufAllocator[9] 2797600768 | 2661744640 | 32768 | memory/ioBufAllocator[8] 443547648 | 184287232 | 16384 | memory/ioBufAllocator[7] 612630528 | 525918208 | 8192 | memory/ioBufAllocator[6] 1208483840 | 905179136 | 4096 | memory/ioBufAllocator[5] 4456448 |4358144 | 2048 | memory/ioBufAllocator[4] 1179648 |1078272 | 1024 | memory/ioBufAllocator[3] 9043968 |9004032 |512 | memory/ioBufAllocator[2] 4521984 |1761536 |256 | memory/ioBufAllocator[1] 39108608 |1824768 |128 | memory/ioBufAllocator[0] 120840192 | 249408 | 96 | memory/eventAllocator 10270720 |7616480 | 80 | memory/mutexAllocator 46039040 | 17172480 | 64 | memory/ioBlockAllocator 28323840 | 20658912 | 48 | memory/ioDataAllocator 55449600 | 40364640 |240 | memory/ioAllocator 0 | 0 |384 | memory/socksAllocator 0 | 0 |128 | memory/udpReadContAllocator 0 | 0 |160 | memory/udpPacketAllocator 105627648 | 71248800 |672 | memory/netVCAllocator 0 | 0 |128 | memory/UDPIOEventAllocator 92160 | 68400 |720 | memory/sslNetVCAllocator 0 | 0 | 64 | memory/RamCacheLRUEntry 32526336 | 32181984 | 96 | memory/RamCacheCLFUSEntry 1454080 |1420640 |160 | memory/openDirEntry 14336 | 0 |112 | memory/migrateToInterimCache 0 | 0 | 48 | memory/evacuationKey 6144 | 0 | 48 | memory/cacheRemoveCont 10936320 | 10875648 | 96 | memory/evacuationBlock 11673600 | 11447040 |960 | memory/cacheVConnection 0 | 0 | 32 | memory/byteBankAllocator 0 | 0 |592 | memory/clusterVCAllocator 0 | 0 |112 | memory/inControlAllocator 0 | 0 |112 | memory/outControlAllocator 0 | 0 | 48 | memory/ClusterVConnectionCache::Entry 0 | 0 |576 | memory/cacheContAllocator 0 | 0 | 16 | memory/DNSRequestDataAllocator 1354240 | 33856 | 33856 | memory/dnsBufAllocator 1146880 | 20480 | 1280 | memory/dnsEntryAllocator 24477696 | 73728 | 2304 | memory/hostDBContAllocator 0 | 0 |112 | memory/OneWayTunnelAllocator 168034304 | 47165440 | 2048 | memory/hdrStrHeap 217841664 | 75976704 | 2048 | memory/hdrHeap 229376 | 70400 |256 | memory/httpCacheAltAllocator 0 | 0 | 48 | memory/CongestRequestParamAllocator 0 | 0 |144 | memory/CongestionDBContAllocator 0 | 0 |128 | memory/RemapPluginsAlloc 0 | 0 | 7760 | memory/httpUpdateSMAllocator 0 | 0 | 48 | memory/CacheLookupHttpConfigAllocator 13848576 |9485280 |224 |
[jira] [Commented] (TS-3032) FATAL: ats_malloc: couldn't allocate XXXXXX bytes
[ https://issues.apache.org/jira/browse/TS-3032?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14109214#comment-14109214 ] Zhao Yongming commented on TS-3032: --- well, you have 7368964608 memory in the freelist, and 4893378608 in use, that is 66% in use. with about 8000 active connections. all sounds not so bad except that 7G is far smaller than that 19G from the pid summary, why? FATAL: ats_malloc: couldn't allocate XX bytes - Key: TS-3032 URL: https://issues.apache.org/jira/browse/TS-3032 Project: Traffic Server Issue Type: Bug Components: Core Affects Versions: 5.0.1 Reporter: Nikolai Gorchilov Assignee: Brian Geffon Labels: crash Fix For: 5.2.0 ATS 5.0.1 under Unbuntu 12.04.4 running happily for days suddenly crashes due to memory allocation issue. Happens once or twice a week. Server is having plenty of RAM - 128G - out of which 64G+ are free. Nothing suspicious in dmesg. {noformat} FATAL: ats_malloc: couldn't allocate 155648 bytes /z/bin/traffic_server - STACK TRACE: /z/lib/libtsutil.so.5(+0x1e837)[0x2b6251b3d837] /z/lib/libtsutil.so.5(ats_malloc+0x30)[0x2b6251b40c50] /z/bin/traffic_server(HdrHeap::coalesce_str_heaps(int)+0x34)[0x62e834] /z/bin/traffic_server(http_hdr_clone(HTTPHdrImpl*, HdrHeap*, HdrHeap*)+0x8f)[0x62a54f] /z/bin/traffic_server(HttpTransactHeaders::copy_header_fields(HTTPHdr*, HTTPHdr*, bool, long)+0x1ae)[0x5d08de] /z/bin/traffic_server(HttpTransact::build_request(HttpTransact::State*, HTTPHdr*, HTTPHdr*, HTTPVersion)+0x5c)[0x5b280c] /z/bin/traffic_server(HttpTransact::HandleCacheOpenReadMiss(HttpTransact::State*)+0x2c8)[0x5c2ce8] /z/bin/traffic_server(HttpSM::call_transact_and_set_next_state(void (*)(HttpTransact::State*))+0x66)[0x58e356] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::do_hostdb_lookup()+0x27a)[0x58e84a] /z/bin/traffic_server(HttpSM::set_next_state()+0xd48)[0x5a1038] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/x3me_dscp.so(http_txn_hook(tsapi_cont*, TSEvent, void*)+0x236)[0x2b626342b508] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_cache_open_read(int, void*)+0x180)[0x59b070] /z/bin/traffic_server(HttpSM::main_handler(int, void*)+0xd8)[0x59ad98] /z/bin/traffic_server(HttpCacheSM::state_cache_open_read(int, void*)+0x173)[0x57bbb3] /z/bin/traffic_server(Cache::open_read(Continuation*, INK_MD5*, HTTPHdr*, CacheLookupHttpConfig*, CacheFragType, char*, int)+0x616)[0x6d65a6] /z/bin/traffic_server(CacheProcessor::open_read(Continuation*, URL*, bool, HTTPHdr*, CacheLookupHttpConfig*, long, CacheFragType)+0xb0)[0x6b1af0] /z/bin/traffic_server(HttpCacheSM::open_read(URL*, HTTPHdr*, CacheLookupHttpConfig*, long)+0x83)[0x57c2d3] /z/bin/traffic_server(HttpSM::do_cache_lookup_and_read()+0xfb)[0x58baeb] /z/bin/traffic_server(HttpSM::set_next_state()+0x888)[0x5a0b78] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::set_next_state()+0x7e2)[0x5a0ad2] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/cacheurl.so(+0x17dc)[0x2b6263a477dc] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/tslua.so(+0x596f)[0x2b626363396f] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/stats_over_http.so(+0x1235)[0x2b6263228235] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_read_client_request_header(int, void*)+0x22b)[0x59270b] /z/bin/traffic_server(HttpSM::main_handler(int, void*)+0xd8)[0x59ad98] /z/bin/traffic_server[0x714a60] /z/bin/traffic_server(NetHandler::mainNetEvent(int,
[jira] [Commented] (TS-3032) FATAL: ats_malloc: couldn't allocate XXXXXX bytes
[ https://issues.apache.org/jira/browse/TS-3032?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14109216#comment-14109216 ] Zhao Yongming commented on TS-3032: --- I'd like you keep colect those data for some more days, the same time(to get the same load) if you can, to figure out which component is wasting more memories. FATAL: ats_malloc: couldn't allocate XX bytes - Key: TS-3032 URL: https://issues.apache.org/jira/browse/TS-3032 Project: Traffic Server Issue Type: Bug Components: Core Affects Versions: 5.0.1 Reporter: Nikolai Gorchilov Assignee: Brian Geffon Labels: crash Fix For: 5.2.0 ATS 5.0.1 under Unbuntu 12.04.4 running happily for days suddenly crashes due to memory allocation issue. Happens once or twice a week. Server is having plenty of RAM - 128G - out of which 64G+ are free. Nothing suspicious in dmesg. {noformat} FATAL: ats_malloc: couldn't allocate 155648 bytes /z/bin/traffic_server - STACK TRACE: /z/lib/libtsutil.so.5(+0x1e837)[0x2b6251b3d837] /z/lib/libtsutil.so.5(ats_malloc+0x30)[0x2b6251b40c50] /z/bin/traffic_server(HdrHeap::coalesce_str_heaps(int)+0x34)[0x62e834] /z/bin/traffic_server(http_hdr_clone(HTTPHdrImpl*, HdrHeap*, HdrHeap*)+0x8f)[0x62a54f] /z/bin/traffic_server(HttpTransactHeaders::copy_header_fields(HTTPHdr*, HTTPHdr*, bool, long)+0x1ae)[0x5d08de] /z/bin/traffic_server(HttpTransact::build_request(HttpTransact::State*, HTTPHdr*, HTTPHdr*, HTTPVersion)+0x5c)[0x5b280c] /z/bin/traffic_server(HttpTransact::HandleCacheOpenReadMiss(HttpTransact::State*)+0x2c8)[0x5c2ce8] /z/bin/traffic_server(HttpSM::call_transact_and_set_next_state(void (*)(HttpTransact::State*))+0x66)[0x58e356] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::do_hostdb_lookup()+0x27a)[0x58e84a] /z/bin/traffic_server(HttpSM::set_next_state()+0xd48)[0x5a1038] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/x3me_dscp.so(http_txn_hook(tsapi_cont*, TSEvent, void*)+0x236)[0x2b626342b508] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_cache_open_read(int, void*)+0x180)[0x59b070] /z/bin/traffic_server(HttpSM::main_handler(int, void*)+0xd8)[0x59ad98] /z/bin/traffic_server(HttpCacheSM::state_cache_open_read(int, void*)+0x173)[0x57bbb3] /z/bin/traffic_server(Cache::open_read(Continuation*, INK_MD5*, HTTPHdr*, CacheLookupHttpConfig*, CacheFragType, char*, int)+0x616)[0x6d65a6] /z/bin/traffic_server(CacheProcessor::open_read(Continuation*, URL*, bool, HTTPHdr*, CacheLookupHttpConfig*, long, CacheFragType)+0xb0)[0x6b1af0] /z/bin/traffic_server(HttpCacheSM::open_read(URL*, HTTPHdr*, CacheLookupHttpConfig*, long)+0x83)[0x57c2d3] /z/bin/traffic_server(HttpSM::do_cache_lookup_and_read()+0xfb)[0x58baeb] /z/bin/traffic_server(HttpSM::set_next_state()+0x888)[0x5a0b78] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::set_next_state()+0x7e2)[0x5a0ad2] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/cacheurl.so(+0x17dc)[0x2b6263a477dc] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/tslua.so(+0x596f)[0x2b626363396f] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/stats_over_http.so(+0x1235)[0x2b6263228235] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_read_client_request_header(int, void*)+0x22b)[0x59270b] /z/bin/traffic_server(HttpSM::main_handler(int, void*)+0xd8)[0x59ad98] /z/bin/traffic_server[0x714a60] /z/bin/traffic_server(NetHandler::mainNetEvent(int, Event*)+0x1ed)[0x7077cd]
[jira] [Commented] (TS-3032) FATAL: ats_malloc: couldn't allocate XXXXXX bytes
[ https://issues.apache.org/jira/browse/TS-3032?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14109225#comment-14109225 ] Zhao Yongming commented on TS-3032: --- and if you have more than one boxes with that issue, please consider test one box with the following tweak: 1. re-install with reclaim freelist enabled. and make sure reclaim is enabled in the records.config 2. use the standard LRU: set proxy.config.cache.ram_cache.algorithm to 1 and if you have more system that can do a release test, we can identify which release is proved to be correct. :D FATAL: ats_malloc: couldn't allocate XX bytes - Key: TS-3032 URL: https://issues.apache.org/jira/browse/TS-3032 Project: Traffic Server Issue Type: Bug Components: Core Affects Versions: 5.0.1 Reporter: Nikolai Gorchilov Assignee: Brian Geffon Labels: crash Fix For: 5.2.0 ATS 5.0.1 under Unbuntu 12.04.4 running happily for days suddenly crashes due to memory allocation issue. Happens once or twice a week. Server is having plenty of RAM - 128G - out of which 64G+ are free. Nothing suspicious in dmesg. {noformat} FATAL: ats_malloc: couldn't allocate 155648 bytes /z/bin/traffic_server - STACK TRACE: /z/lib/libtsutil.so.5(+0x1e837)[0x2b6251b3d837] /z/lib/libtsutil.so.5(ats_malloc+0x30)[0x2b6251b40c50] /z/bin/traffic_server(HdrHeap::coalesce_str_heaps(int)+0x34)[0x62e834] /z/bin/traffic_server(http_hdr_clone(HTTPHdrImpl*, HdrHeap*, HdrHeap*)+0x8f)[0x62a54f] /z/bin/traffic_server(HttpTransactHeaders::copy_header_fields(HTTPHdr*, HTTPHdr*, bool, long)+0x1ae)[0x5d08de] /z/bin/traffic_server(HttpTransact::build_request(HttpTransact::State*, HTTPHdr*, HTTPHdr*, HTTPVersion)+0x5c)[0x5b280c] /z/bin/traffic_server(HttpTransact::HandleCacheOpenReadMiss(HttpTransact::State*)+0x2c8)[0x5c2ce8] /z/bin/traffic_server(HttpSM::call_transact_and_set_next_state(void (*)(HttpTransact::State*))+0x66)[0x58e356] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::do_hostdb_lookup()+0x27a)[0x58e84a] /z/bin/traffic_server(HttpSM::set_next_state()+0xd48)[0x5a1038] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/x3me_dscp.so(http_txn_hook(tsapi_cont*, TSEvent, void*)+0x236)[0x2b626342b508] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_cache_open_read(int, void*)+0x180)[0x59b070] /z/bin/traffic_server(HttpSM::main_handler(int, void*)+0xd8)[0x59ad98] /z/bin/traffic_server(HttpCacheSM::state_cache_open_read(int, void*)+0x173)[0x57bbb3] /z/bin/traffic_server(Cache::open_read(Continuation*, INK_MD5*, HTTPHdr*, CacheLookupHttpConfig*, CacheFragType, char*, int)+0x616)[0x6d65a6] /z/bin/traffic_server(CacheProcessor::open_read(Continuation*, URL*, bool, HTTPHdr*, CacheLookupHttpConfig*, long, CacheFragType)+0xb0)[0x6b1af0] /z/bin/traffic_server(HttpCacheSM::open_read(URL*, HTTPHdr*, CacheLookupHttpConfig*, long)+0x83)[0x57c2d3] /z/bin/traffic_server(HttpSM::do_cache_lookup_and_read()+0xfb)[0x58baeb] /z/bin/traffic_server(HttpSM::set_next_state()+0x888)[0x5a0b78] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::set_next_state()+0x7e2)[0x5a0ad2] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/cacheurl.so(+0x17dc)[0x2b6263a477dc] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/tslua.so(+0x596f)[0x2b626363396f] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/stats_over_http.so(+0x1235)[0x2b6263228235] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_read_client_request_header(int,
[jira] [Commented] (TS-3032) FATAL: ats_malloc: couldn't allocate XXXXXX bytes
[ https://issues.apache.org/jira/browse/TS-3032?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14109294#comment-14109294 ] Nikolai Gorchilov commented on TS-3032: --- Yes, I have two boxes that have this issue and one of them is available for testing. Have in mind it has just 48G of RAM. Here's the relevant info on this box just after restarting the new build of traffic server with requested config changes: * cat /proc/meminfo {noformat} MemTotal: 49361540 kB MemFree:36481844 kB MemAvailable: 37318832 kB Buffers: 139888 kB Cached: 1174072 kB SwapCached:0 kB Active: 11619048 kB Inactive: 472492 kB Active(anon): 10944848 kB Inactive(anon):43404 kB Active(file): 674200 kB Inactive(file): 429088 kB Unevictable: 175688 kB Mlocked: 12852 kB SwapTotal: 0 kB SwapFree: 0 kB Dirty: 0 kB Writeback: 0 kB AnonPages: 10953252 kB Mapped:61956 kB Shmem: 44052 kB Slab: 513432 kB SReclaimable: 143176 kB SUnreclaim: 370256 kB KernelStack:7728 kB PageTables:29912 kB NFS_Unstable: 0 kB Bounce:0 kB WritebackTmp: 0 kB CommitLimit:24680768 kB Committed_AS: 11943052 kB VmallocTotal: 34359738367 kB VmallocUsed: 285388 kB VmallocChunk: 34359406432 kB AnonHugePages: 10416128 kB DirectMap4k: 13824 kB DirectMap2M: 4171776 kB DirectMap1G:48234496 kB {noformat} * /proc/pid/status after traffic_server restart {noformat} Name: [ET_NET 0] State: S (sleeping) Tgid: 24406 Ngid: 0 Pid:24406 PPid: 24397 TracerPid: 0 Uid:13 13 13 13 Gid:13 13 13 13 FDSize: 128 Groups: 0 VmPeak: 19229780 kB VmSize: 19229272 kB VmLck: 0 kB VmPin: 0 kB VmHWM: 10616928 kB VmRSS: 10616928 kB VmData: 19129068 kB VmStk: 136 kB VmExe: 4096 kB VmLib: 10736 kB VmPTE: 21840 kB VmSwap:0 kB Threads:162 SigQ: 0/192701 SigPnd: ShdPnd: SigBlk: SigIgn: 00381000 SigCgt: 000180004e4f CapInh: CapPrm: 5402 CapEff: 5400 CapBnd: 001f Cpus_allowed: Cpus_allowed_list: 0-15 voluntary_ctxt_switches:26618 nonvoluntary_ctxt_switches: 135 {noformat} * relevant records.config options: {noformat} CONFIG proxy.config.allocator.enable_reclaim INT 1 CONFIG proxy.config.cache.ram_cache_cutoff INT 65536 CONFIG proxy.config.cache.ram_cache.size INT 1073741824 CONFIG proxy.config.cache.ram_cache.algorithm INT 1 {noformat} NB! Could it be related to ram_cache_cutoff? Seems all crashes are for allocations above 64k. FATAL: ats_malloc: couldn't allocate XX bytes - Key: TS-3032 URL: https://issues.apache.org/jira/browse/TS-3032 Project: Traffic Server Issue Type: Bug Components: Core Affects Versions: 5.0.1 Reporter: Nikolai Gorchilov Assignee: Brian Geffon Labels: crash Fix For: 5.2.0 ATS 5.0.1 under Unbuntu 12.04.4 running happily for days suddenly crashes due to memory allocation issue. Happens once or twice a week. Server is having plenty of RAM - 128G - out of which 64G+ are free. Nothing suspicious in dmesg. {noformat} FATAL: ats_malloc: couldn't allocate 155648 bytes /z/bin/traffic_server - STACK TRACE: /z/lib/libtsutil.so.5(+0x1e837)[0x2b6251b3d837] /z/lib/libtsutil.so.5(ats_malloc+0x30)[0x2b6251b40c50] /z/bin/traffic_server(HdrHeap::coalesce_str_heaps(int)+0x34)[0x62e834] /z/bin/traffic_server(http_hdr_clone(HTTPHdrImpl*, HdrHeap*, HdrHeap*)+0x8f)[0x62a54f] /z/bin/traffic_server(HttpTransactHeaders::copy_header_fields(HTTPHdr*, HTTPHdr*, bool, long)+0x1ae)[0x5d08de] /z/bin/traffic_server(HttpTransact::build_request(HttpTransact::State*, HTTPHdr*, HTTPHdr*, HTTPVersion)+0x5c)[0x5b280c] /z/bin/traffic_server(HttpTransact::HandleCacheOpenReadMiss(HttpTransact::State*)+0x2c8)[0x5c2ce8] /z/bin/traffic_server(HttpSM::call_transact_and_set_next_state(void (*)(HttpTransact::State*))+0x66)[0x58e356] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::do_hostdb_lookup()+0x27a)[0x58e84a] /z/bin/traffic_server(HttpSM::set_next_state()+0xd48)[0x5a1038] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/x3me_dscp.so(http_txn_hook(tsapi_cont*, TSEvent, void*)+0x236)[0x2b626342b508]
[jira] [Commented] (TS-3032) FATAL: ats_malloc: couldn't allocate XXXXXX bytes
[ https://issues.apache.org/jira/browse/TS-3032?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14108393#comment-14108393 ] Nikolai Gorchilov commented on TS-3032: --- Another manifestation: {noformat} FATAL: ats_malloc: couldn't allocate 65536 bytes /z/bin/traffic_server - STACK TRACE: /z/lib/libtsutil.so.5(+0x1e837)[0x2b0203d6a837] /z/lib/libtsutil.so.5(ats_malloc+0x30)[0x2b0203d6dc50] /z/bin/traffic_server(HdrHeap::allocate_obj(int, int)+0xa4)[0x62e414] /z/bin/traffic_server(mime_hdr_copy_onto(MIMEHdrImpl*, HdrHeap*, MIMEHdrImpl*, HdrHeap*, bool)+0x102)[0x634bc2] /z/bin/traffic_server(http_hdr_copy_onto(HTTPHdrImpl*, HdrHeap*, HTTPHdrImpl*, HdrHeap*, bool)+0x87)[0x62a427] /z/bin/traffic_server(HttpSM::set_next_state()+0x9c1)[0x5a0cc1] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c13] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c82a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/x3me_dscp.so(http_txn_hook(tsapi_cont*, TSEvent, void*)+0x236)[0x2b0211806508] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999d2] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0538] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c13] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0538] /z/bin/traffic_server(HttpSM::state_cache_open_read(int, void*)+0x103)[0x59b003] /z/bin/traffic_server(HttpSM::main_handler(int, void*)+0xd8)[0x59ada8] /z/bin/traffic_server(HttpCacheSM::state_cache_open_read(int, void*)+0x1d6)[0x57bc16] /z/bin/traffic_server[0x6d56b8] /z/bin/traffic_server(CacheVC::openReadStartEarliest(int, Event*)+0x7d0)[0x6d9120] /z/bin/traffic_server(CacheVC::handleReadDone(int, Event*)+0x27b)[0x6b79cb] /z/bin/traffic_server(AIOCallbackInternal::io_complete(int, void*)+0x3d)[0x662e5d] /z/bin/traffic_server(EThread::process_event(Event*, int)+0x91)[0x736121] /z/bin/traffic_server(EThread::execute()+0x6a3)[0x736d83] /z/bin/traffic_server[0x7353ba] /lib64/libpthread.so.0(+0x7034)[0x2b0205370034] /lib64/libc.so.6(clone+0x6d)[0x2b02060b475d] {noformat} FATAL: ats_malloc: couldn't allocate XX bytes - Key: TS-3032 URL: https://issues.apache.org/jira/browse/TS-3032 Project: Traffic Server Issue Type: Bug Components: Core Affects Versions: 5.0.1 Reporter: Nikolai Gorchilov Assignee: Brian Geffon Labels: crash Fix For: 5.2.0 ATS 5.0.1 under Unbuntu 12.04.4 running happily for days suddenly crashes due to memory allocation issue. Happens once or twice a week. Server is having plenty of RAM - 128G - out of which 64G+ are free. Nothing suspicious in dmesg. {noformat} FATAL: ats_malloc: couldn't allocate 155648 bytes /z/bin/traffic_server - STACK TRACE: /z/lib/libtsutil.so.5(+0x1e837)[0x2b6251b3d837] /z/lib/libtsutil.so.5(ats_malloc+0x30)[0x2b6251b40c50] /z/bin/traffic_server(HdrHeap::coalesce_str_heaps(int)+0x34)[0x62e834] /z/bin/traffic_server(http_hdr_clone(HTTPHdrImpl*, HdrHeap*, HdrHeap*)+0x8f)[0x62a54f] /z/bin/traffic_server(HttpTransactHeaders::copy_header_fields(HTTPHdr*, HTTPHdr*, bool, long)+0x1ae)[0x5d08de] /z/bin/traffic_server(HttpTransact::build_request(HttpTransact::State*, HTTPHdr*, HTTPHdr*, HTTPVersion)+0x5c)[0x5b280c] /z/bin/traffic_server(HttpTransact::HandleCacheOpenReadMiss(HttpTransact::State*)+0x2c8)[0x5c2ce8] /z/bin/traffic_server(HttpSM::call_transact_and_set_next_state(void (*)(HttpTransact::State*))+0x66)[0x58e356] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::do_hostdb_lookup()+0x27a)[0x58e84a] /z/bin/traffic_server(HttpSM::set_next_state()+0xd48)[0x5a1038] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/x3me_dscp.so(http_txn_hook(tsapi_cont*, TSEvent, void*)+0x236)[0x2b626342b508] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_cache_open_read(int, void*)+0x180)[0x59b070] /z/bin/traffic_server(HttpSM::main_handler(int, void*)+0xd8)[0x59ad98] /z/bin/traffic_server(HttpCacheSM::state_cache_open_read(int, void*)+0x173)[0x57bbb3] /z/bin/traffic_server(Cache::open_read(Continuation*, INK_MD5*, HTTPHdr*, CacheLookupHttpConfig*, CacheFragType, char*, int)+0x616)[0x6d65a6] /z/bin/traffic_server(CacheProcessor::open_read(Continuation*, URL*, bool, HTTPHdr*, CacheLookupHttpConfig*, long, CacheFragType)+0xb0)[0x6b1af0] /z/bin/traffic_server(HttpCacheSM::open_read(URL*, HTTPHdr*,
[jira] [Commented] (TS-3032) FATAL: ats_malloc: couldn't allocate XXXXXX bytes
[ https://issues.apache.org/jira/browse/TS-3032?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14108410#comment-14108410 ] Zhao Yongming commented on TS-3032: --- I don't know who have any sucess story on BIG memory system, I'd like to hear if any. for the problem you have, please attach some more data such as: 1. /proc/meminfo 2. the traffic_server process status: /proc//status 3. more system log related to alloc and memory, such as dmesg syslog and, please tell us your configure options when building the binary too. hopes that will help us inspect the problem. FATAL: ats_malloc: couldn't allocate XX bytes - Key: TS-3032 URL: https://issues.apache.org/jira/browse/TS-3032 Project: Traffic Server Issue Type: Bug Components: Core Affects Versions: 5.0.1 Reporter: Nikolai Gorchilov Assignee: Brian Geffon Labels: crash Fix For: 5.2.0 ATS 5.0.1 under Unbuntu 12.04.4 running happily for days suddenly crashes due to memory allocation issue. Happens once or twice a week. Server is having plenty of RAM - 128G - out of which 64G+ are free. Nothing suspicious in dmesg. {noformat} FATAL: ats_malloc: couldn't allocate 155648 bytes /z/bin/traffic_server - STACK TRACE: /z/lib/libtsutil.so.5(+0x1e837)[0x2b6251b3d837] /z/lib/libtsutil.so.5(ats_malloc+0x30)[0x2b6251b40c50] /z/bin/traffic_server(HdrHeap::coalesce_str_heaps(int)+0x34)[0x62e834] /z/bin/traffic_server(http_hdr_clone(HTTPHdrImpl*, HdrHeap*, HdrHeap*)+0x8f)[0x62a54f] /z/bin/traffic_server(HttpTransactHeaders::copy_header_fields(HTTPHdr*, HTTPHdr*, bool, long)+0x1ae)[0x5d08de] /z/bin/traffic_server(HttpTransact::build_request(HttpTransact::State*, HTTPHdr*, HTTPHdr*, HTTPVersion)+0x5c)[0x5b280c] /z/bin/traffic_server(HttpTransact::HandleCacheOpenReadMiss(HttpTransact::State*)+0x2c8)[0x5c2ce8] /z/bin/traffic_server(HttpSM::call_transact_and_set_next_state(void (*)(HttpTransact::State*))+0x66)[0x58e356] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::do_hostdb_lookup()+0x27a)[0x58e84a] /z/bin/traffic_server(HttpSM::set_next_state()+0xd48)[0x5a1038] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/x3me_dscp.so(http_txn_hook(tsapi_cont*, TSEvent, void*)+0x236)[0x2b626342b508] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_cache_open_read(int, void*)+0x180)[0x59b070] /z/bin/traffic_server(HttpSM::main_handler(int, void*)+0xd8)[0x59ad98] /z/bin/traffic_server(HttpCacheSM::state_cache_open_read(int, void*)+0x173)[0x57bbb3] /z/bin/traffic_server(Cache::open_read(Continuation*, INK_MD5*, HTTPHdr*, CacheLookupHttpConfig*, CacheFragType, char*, int)+0x616)[0x6d65a6] /z/bin/traffic_server(CacheProcessor::open_read(Continuation*, URL*, bool, HTTPHdr*, CacheLookupHttpConfig*, long, CacheFragType)+0xb0)[0x6b1af0] /z/bin/traffic_server(HttpCacheSM::open_read(URL*, HTTPHdr*, CacheLookupHttpConfig*, long)+0x83)[0x57c2d3] /z/bin/traffic_server(HttpSM::do_cache_lookup_and_read()+0xfb)[0x58baeb] /z/bin/traffic_server(HttpSM::set_next_state()+0x888)[0x5a0b78] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::set_next_state()+0x7e2)[0x5a0ad2] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/cacheurl.so(+0x17dc)[0x2b6263a477dc] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/tslua.so(+0x596f)[0x2b626363396f] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/stats_over_http.so(+0x1235)[0x2b6263228235] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_read_client_request_header(int,
[jira] [Commented] (TS-3032) FATAL: ats_malloc: couldn't allocate XXXXXX bytes
[ https://issues.apache.org/jira/browse/TS-3032?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14105713#comment-14105713 ] Brian Geffon commented on TS-3032: -- Hmm 155k headers seem pretty large, do all of your previous stack traces have such large values? Also, are such header set sizes normal for you guys? FATAL: ats_malloc: couldn't allocate XX bytes - Key: TS-3032 URL: https://issues.apache.org/jira/browse/TS-3032 Project: Traffic Server Issue Type: Bug Components: Core Affects Versions: 5.0.1 Reporter: Nikolai Gorchilov Assignee: Brian Geffon Labels: crash Fix For: 5.2.0 ATS 5.0.1 under Unbuntu 12.04.4 running happily for days suddenly crashes due to memory allocation issue. Happens once or twice a week. Server is having plenty of RAM - 128G - out of which 64G+ are free. Nothing suspicious in dmesg. {noformat} FATAL: ats_malloc: couldn't allocate 155648 bytes /z/bin/traffic_server - STACK TRACE: /z/lib/libtsutil.so.5(+0x1e837)[0x2b6251b3d837] /z/lib/libtsutil.so.5(ats_malloc+0x30)[0x2b6251b40c50] /z/bin/traffic_server(HdrHeap::coalesce_str_heaps(int)+0x34)[0x62e834] /z/bin/traffic_server(http_hdr_clone(HTTPHdrImpl*, HdrHeap*, HdrHeap*)+0x8f)[0x62a54f] /z/bin/traffic_server(HttpTransactHeaders::copy_header_fields(HTTPHdr*, HTTPHdr*, bool, long)+0x1ae)[0x5d08de] /z/bin/traffic_server(HttpTransact::build_request(HttpTransact::State*, HTTPHdr*, HTTPHdr*, HTTPVersion)+0x5c)[0x5b280c] /z/bin/traffic_server(HttpTransact::HandleCacheOpenReadMiss(HttpTransact::State*)+0x2c8)[0x5c2ce8] /z/bin/traffic_server(HttpSM::call_transact_and_set_next_state(void (*)(HttpTransact::State*))+0x66)[0x58e356] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::do_hostdb_lookup()+0x27a)[0x58e84a] /z/bin/traffic_server(HttpSM::set_next_state()+0xd48)[0x5a1038] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/x3me_dscp.so(http_txn_hook(tsapi_cont*, TSEvent, void*)+0x236)[0x2b626342b508] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_cache_open_read(int, void*)+0x180)[0x59b070] /z/bin/traffic_server(HttpSM::main_handler(int, void*)+0xd8)[0x59ad98] /z/bin/traffic_server(HttpCacheSM::state_cache_open_read(int, void*)+0x173)[0x57bbb3] /z/bin/traffic_server(Cache::open_read(Continuation*, INK_MD5*, HTTPHdr*, CacheLookupHttpConfig*, CacheFragType, char*, int)+0x616)[0x6d65a6] /z/bin/traffic_server(CacheProcessor::open_read(Continuation*, URL*, bool, HTTPHdr*, CacheLookupHttpConfig*, long, CacheFragType)+0xb0)[0x6b1af0] /z/bin/traffic_server(HttpCacheSM::open_read(URL*, HTTPHdr*, CacheLookupHttpConfig*, long)+0x83)[0x57c2d3] /z/bin/traffic_server(HttpSM::do_cache_lookup_and_read()+0xfb)[0x58baeb] /z/bin/traffic_server(HttpSM::set_next_state()+0x888)[0x5a0b78] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::set_next_state()+0x7e2)[0x5a0ad2] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/cacheurl.so(+0x17dc)[0x2b6263a477dc] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/tslua.so(+0x596f)[0x2b626363396f] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/stats_over_http.so(+0x1235)[0x2b6263228235] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_read_client_request_header(int, void*)+0x22b)[0x59270b] /z/bin/traffic_server(HttpSM::main_handler(int, void*)+0xd8)[0x59ad98] /z/bin/traffic_server[0x714a60] /z/bin/traffic_server(NetHandler::mainNetEvent(int, Event*)+0x1ed)[0x7077cd] /z/bin/traffic_server(EThread::process_event(Event*,
[jira] [Commented] (TS-3032) FATAL: ats_malloc: couldn't allocate XXXXXX bytes
[ https://issues.apache.org/jira/browse/TS-3032?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=14106114#comment-14106114 ] Nikolai Gorchilov commented on TS-3032: --- This system is running on forward proxy mode, so we're not in a control of header sizes. Here's a backtrace from another location: {noformat} FATAL: ats_malloc: couldn't allocate 108896 bytes /z/bin/traffic_server - STACK TRACE: /z/lib/libtsutil.so.5(+0x1e837)[0x2b1605203837] /z/lib/libtsutil.so.5(ats_malloc+0x30)[0x2b1605206c50] /z/bin/traffic_server(ProcessManager::signalManager(int, char const*, int)+0x3a)[0x64b91a] /z/bin/traffic_server(RecMessageSend(RecMessageHdr*)+0x48)[0x72bda8] /z/bin/traffic_server(send_push_message()+0xdd)[0x7272ed] /z/bin/traffic_server(sync_cont::sync(int, Event*)+0xd)[0x72e67d] /z/bin/traffic_server(EThread::process_event(Event*, int)+0x91)[0x736111] /z/bin/traffic_server(EThread::execute()+0x2fb)[0x7369cb] /z/bin/traffic_server[0x7353aa] /lib64/libpthread.so.0(+0x7034)[0x2b1606809034] /lib64/libc.so.6(clone+0x6d)[0x2b160754d75d] {noformat} HTH FATAL: ats_malloc: couldn't allocate XX bytes - Key: TS-3032 URL: https://issues.apache.org/jira/browse/TS-3032 Project: Traffic Server Issue Type: Bug Components: Core Affects Versions: 5.0.1 Reporter: Nikolai Gorchilov Assignee: Brian Geffon Labels: crash Fix For: 5.2.0 ATS 5.0.1 under Unbuntu 12.04.4 running happily for days suddenly crashes due to memory allocation issue. Happens once or twice a week. Server is having plenty of RAM - 128G - out of which 64G+ are free. Nothing suspicious in dmesg. {noformat} FATAL: ats_malloc: couldn't allocate 155648 bytes /z/bin/traffic_server - STACK TRACE: /z/lib/libtsutil.so.5(+0x1e837)[0x2b6251b3d837] /z/lib/libtsutil.so.5(ats_malloc+0x30)[0x2b6251b40c50] /z/bin/traffic_server(HdrHeap::coalesce_str_heaps(int)+0x34)[0x62e834] /z/bin/traffic_server(http_hdr_clone(HTTPHdrImpl*, HdrHeap*, HdrHeap*)+0x8f)[0x62a54f] /z/bin/traffic_server(HttpTransactHeaders::copy_header_fields(HTTPHdr*, HTTPHdr*, bool, long)+0x1ae)[0x5d08de] /z/bin/traffic_server(HttpTransact::build_request(HttpTransact::State*, HTTPHdr*, HTTPHdr*, HTTPVersion)+0x5c)[0x5b280c] /z/bin/traffic_server(HttpTransact::HandleCacheOpenReadMiss(HttpTransact::State*)+0x2c8)[0x5c2ce8] /z/bin/traffic_server(HttpSM::call_transact_and_set_next_state(void (*)(HttpTransact::State*))+0x66)[0x58e356] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::do_hostdb_lookup()+0x27a)[0x58e84a] /z/bin/traffic_server(HttpSM::set_next_state()+0xd48)[0x5a1038] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/x3me_dscp.so(http_txn_hook(tsapi_cont*, TSEvent, void*)+0x236)[0x2b626342b508] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_cache_open_read(int, void*)+0x180)[0x59b070] /z/bin/traffic_server(HttpSM::main_handler(int, void*)+0xd8)[0x59ad98] /z/bin/traffic_server(HttpCacheSM::state_cache_open_read(int, void*)+0x173)[0x57bbb3] /z/bin/traffic_server(Cache::open_read(Continuation*, INK_MD5*, HTTPHdr*, CacheLookupHttpConfig*, CacheFragType, char*, int)+0x616)[0x6d65a6] /z/bin/traffic_server(CacheProcessor::open_read(Continuation*, URL*, bool, HTTPHdr*, CacheLookupHttpConfig*, long, CacheFragType)+0xb0)[0x6b1af0] /z/bin/traffic_server(HttpCacheSM::open_read(URL*, HTTPHdr*, CacheLookupHttpConfig*, long)+0x83)[0x57c2d3] /z/bin/traffic_server(HttpSM::do_cache_lookup_and_read()+0xfb)[0x58baeb] /z/bin/traffic_server(HttpSM::set_next_state()+0x888)[0x5a0b78] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::set_next_state()+0x7e2)[0x5a0ad2] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::set_next_state()+0x238)[0x5a0528] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x343)[0x599c03] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/cacheurl.so(+0x17dc)[0x2b6263a477dc] /z/bin/traffic_server(HttpSM::state_api_callout(int, void*)+0x102)[0x5999c2] /z/bin/traffic_server(HttpSM::state_api_callback(int, void*)+0x8a)[0x59c81a] /z/bin/traffic_server(TSHttpTxnReenable+0x141)[0x4caa51] /z/lib/plugins/tslua.so(+0x596f)[0x2b626363396f]