Whamcloud Community JIRA

Whamcloud Community JIRA https://jira.whamcloud.com This file is an XML representation of an issue en-us

9.4.14

940014

05-12-2023

[LU-850] Test failure on test suite ost-pools, subtest test_23,dd did not fail with EDQUOT https://jira.whamcloud.com/browse/LU-850 Lustre <p>This issue was created by maloo for sarah <sarah@whamcloud.com></p> <p>This issue relates to the following test suite run: <a href="https://maloo.whamcloud.com/test_sets/901ac12c-0f89-11e1-aad7-52540025f9af" class="external-link" target="_blank" rel="nofollow noopener">https://maloo.whamcloud.com/test_sets/901ac12c-0f89-11e1-aad7-52540025f9af</a>.</p> <p>The sub-test test_23 failed with the following error:</p> <blockquote> <p>dd did not fail with EDQUOT.</p></blockquote> <p>Info required for matching: ost-pools 23</p> LU-850

Test failure on test suite ost-pools, subtest test_23,dd did not fail with EDQUOT

Bug Minor Resolved Won't Fix Niu Yawei Maloo Tue, 15 Nov 2011 18:13:04 +0000 Tue, 10 Apr 2012 02:08:50 +0000 Tue, 10 Apr 2012 02:08:50 +0000 0 3 <p>Niu</p> <p>Would LU745 have any bearing on this?</p> <p>Thanks</p> <p>Peter</p> <p>The test log shows that the quota limit isn't set on OST6:</p> <div class="code panel" style="border-width: 1px;"><div class="codeContent panelContent"> <pre class="code-java">Disk quotas <span class="code-keyword">for</span> user quota_usr (uid 60000): Filesystem kbytes quota limit grace files quota limit grace /mnt/lustre/d0.ost-pools/d23/dir 1024 8192 8192 - 1 5000040 5250042 - lustre-MDT0000_UUID 0 - 1024 - 1 - 5120 - lustre-OST0000_UUID 0 - 1024 - - - - - lustre-OST0001_UUID 0 - 1024 - - - - - lustre-OST0002_UUID 0 - 1024 - - - - - lustre-OST0003_UUID 0 - 1024 - - - - - lustre-OST0004_UUID 0 - 1024 - - - - - lustre-OST0005_UUID 0 - 1024 - - - - - lustre-OST0006_UUID 1024 - 0 - - - - - </pre> </div></div> <p>But I can't tell why it's not set from the log. Sarah, could you reproduce it with D_TRACE & D_QUOTA enabled? Thank you.</p> <p>sure, will keep you updated.</p> <p>I reran this test and got oom:<br/> ------<br/> running: ost-pools ONLY=23 <br/> run_suite ost-pools /usr/lib64/lustre/tests/ost-pools.sh<br/> Lustre: DEBUG MARKER: ----<del>============= acceptance-small: ost-pools ============</del>---- Mon Nov 21 16:05:09 PST 2011<br/> Lustre: DEBUG MARKER: Using TIMEOUT=20<br/> Lustre: 5368:0:(debug.c:326:libcfs_debug_str2mask()) You are trying to use a numerical value for the mask - this will be deprecated in a future release.<br/> Lustre: 5368:0:(debug.c:326:libcfs_debug_str2mask()) Skipped 3 previous similar messages<br/> Lustre: DEBUG MARKER: only running test 23<br/> Lustre: DEBUG MARKER: excepting tests:<br/> Lustre: DEBUG MARKER: == ost-pools test 23: OST pools and quota == 16:05:17 (1321920317)<br/> LustreError: 5998:0:(quota_ctl.c:328:client_quota_ctl()) ptlrpc_queue_wait failed, rc: -114<br/> LustreError: 11-0: an error occurred while communicating with 192.168.4.131@o2ib. The ost_write operation failed with -122<br/> LustreError: 6006:0:(vvp_io.c:1017:vvp_io_commit_write()) Write page 280 of inode e72d2980 failed -122<br/> Lustre: DEBUG MARKER: cancel_lru_locks osc start<br/> Lustre: DEBUG MARKER: cancel_lru_locks osc stop<br/> Lustre: 2443:0:(client.c:1789:ptlrpc_expire_one_request()) @@@ Request sent has timed out for slow reply: <span class="error">[sent 1321920490/real 1321920490]</span> req@c2a2e400 x1386133843884950/t0(0) o400->MGC192.168.4.2@o2ib@192.168.4.2@o2ib:26/25 lens 192/192 e 0 to 1 dl 1321920497 ref 1 fl Rpc:XN/0/ffffffff rc 0/-1<br/> LustreError: 166-1: MGC192.168.4.2@o2ib: Connection to service MGS via nid 192.168.4.2@o2ib was lost; in progress operations using this service will fail.<br/> Lustre: lustre-MDT0000-mdc-c33e2400: Connection to service lustre-MDT0000 via nid 192.168.4.2@o2ib was lost; in progress operations using this service will wait for recovery to complete.<br/> LustreError: 11-0: an error occurred while communicating with 192.168.4.131@o2ib. The obd_ping operation failed with -107<br/> Lustre: lustre-OST0000-osc-c33e2400: Connection to service lustre-OST0000 via nid 192.168.4.131@o2ib was lost; in progress operations using this service will wait for recovery to complete.<br/> Lustre: 2441:0:(import.c:849:ptlrpc_connect_interpret()) MGS@192.168.4.2@o2ib changed server handle from 0x749fb9a0e2f2648d to 0x749fb9a0e2f26ef8<br/> Lustre: MGC192.168.4.2@o2ib: Reactivating import<br/> Lustre: MGC192.168.4.2@o2ib: Connection restored to service MGS using nid 192.168.4.2@o2ib.<br/> LustreError: 167-0: This client was evicted by lustre-OST0000; in progress operations using this service will fail.<br/> LustreError: 2445:0:(client.c:1076:ptlrpc_import_delay_req()) @@@ IMP_INVALID req@e708ec00 x1386133843884962/t0(0) o4->lustre-OST0000-osc-c33e2400@192.168.4.131@o2ib:6/4 lens 456/416 e 0 to 0 dl 0 ref 2 fl Rpc:/0/ffffffff rc 0/-1<br/> LustreError: 6047:0:(osc_lock.c:809:osc_ldlm_completion_ast()) lock@e82aed14<span class="error">[2 3 0 1 1 00000000]</span> W(2):<span class="error">[0, 4294967295]</span>@<span class="error">[0x100000000:0x2:0x0]</span> </p> { LustreError: 6047:0:(osc_lock.c:809:osc_ldlm_completion_ast()) lovsub@e81425a0: [0 e6d3a848 W(2):[256, 4294967295]@[0x200000400:0xc:0x0]] LustreError: 6047:0:(osc_lock.c:809:osc_ldlm_completion_ast()) osc@e8bd2ea4: e6d01800 40100001 0xeded2fbddbaf7554 3 e737d098 size: 0 mtime: 18446744071562154368 atime: 18446744071562154368 ctime: 18446744071562154368 blocks: 0 LustreError: 6047:0:(osc_lock.c:809:osc_ldlm_completion_ast()) } <p> lock@e82aed14<br/> LustreError: 6047:0:(osc_lock.c:809:osc_ldlm_completion_ast()) dlmlock returned -5<br/> LustreError: 6047:0:(ldlm_resource.c:750:ldlm_resource_complain()) Namespace lustre-OST0000-osc-c33e2400 resource refcount nonzero (1) after lock cleanup; forcing cleanup.<br/> LustreError: 6047:0:(ldlm_resource.c:756:ldlm_resource_complain()) Resource: e73f0a80 (2/0/0/0) (rc: 1)<br/> LustreError: Skipped 5 previous similar messages<br/> LustreError: 2443:0:(client.c:1076:ptlrpc_import_delay_req()) @@@ IMP_INVALID req@e71a3c00 x1386133843884986/t0(0) o4->lustre-OST0003-osc-c33e2400@192.168.4.131@o2ib:6/4 lens 456/416 e 0 to 0 dl 0 ref 2 fl Rpc:/0/ffffffff rc 0/-1<br/> Lustre: lustre-OST0003-osc-c33e2400: Connection restored to service lustre-OST0003 using nid 192.168.4.131@o2ib.<br/> Lustre: Skipped 6 previous similar messages<br/> LustreError: 6030:0:(cl_lock.c:1408:cl_unuse_try()) result = -5, this is unlikely!<br/> LustreError: 6030:0:(cl_lock.c:1426:cl_unuse_locked()) lock@e82aed94<span class="error">[1 3 -5 1 0 00000006]</span> W(2):<span class="error">[256, 4294967295]</span>@<span class="error">[0x200000400:0xc:0x0]</span> </p> { LustreError: 6030:0:(cl_lock.c:1426:cl_unuse_locked()) vvp@e6c54504: LustreError: 6030:0:(cl_lock.c:1426:cl_unuse_locked()) lov@e6d3a848: 1 LustreError: 6030:0:(cl_lock.c:1426:cl_unuse_locked()) 0 0: --- LustreError: 6030:0:(cl_lock.c:1426:cl_unuse_locked()) LustreError: 6030:0:(cl_lock.c:1426:cl_unuse_locked()) } <p> lock@e82aed94<br/> LustreError: 6030:0:(cl_lock.c:1426:cl_unuse_locked()) unuse return -5<br/> irqbalance invoked oom-killer: gfp_mask=0x80d0, order=0, oom_adj=0<br/> irqbalance cpuset=/ mems_allowed=0<br/> Pid: 1486, comm: irqbalance Not tainted 2.6.32-131.6.1.el6.i686 #1<br/> Call Trace:<br/> <span class="error">[<c04df510>]</span> ? oom_kill_process+0xb0/0x2d0<br/> <span class="error">[<c04dfbba>]</span> ? __out_of_memory+0x4a/0x90<br/> <span class="error">[<c04dfc55>]</span> ? out_of_memory+0x55/0xb0<br/> <span class="error">[<c04eda4b>]</span> ? __alloc_pages_nodemask+0x7fb/0x810<br/> <span class="error">[<c04eda74>]</span> ? __get_free_pages+0x14/0x30<br/> <span class="error">[<c058315a>]</span> ? sysfs_read_file+0x10a/0x190<br/> <span class="error">[<c0506723>]</span> ? mmap_region+0x1f3/0x4e0<br/> <span class="error">[<c059d18c>]</span> ? security_file_permission+0xc/0x10<br/> <span class="error">[<c0583050>]</span> ? sysfs_read_file+0x0/0x190<br/> <span class="error">[<c05285fd>]</span> ? vfs_read+0x9d/0x190<br/> <span class="error">[<c04adc5c>]</span> ? audit_syscall_entry+0x21c/0x240<br/> <span class="error">[<c0528731>]</span> ? sys_read+0x41/0x70<br/> <span class="error">[<c0409bdf>]</span> ? sysenter_do_call+0x12/0x28<br/> Mem-Info:<br/> DMA per-cpu:<br/> CPU 0: hi: 0, btch: 1 usd: 0<br/> CPU 1: hi: 0, btch: 1 usd: 0<br/> CPU 2: hi: 0, btch: 1 usd: 0<br/> CPU 3: hi: 0, btch: 1 usd: 0<br/> Normal per-cpu:<br/> CPU 0: hi: 186, btch: 31 usd: 0<br/> CPU 1: hi: 186, btch: 31 usd: 84<br/> CPU 2: hi: 186, btch: 31 usd: 174<br/> CPU 3: hi: 186, btch: 31 usd: 154<br/> HighMem per-cpu:<br/> CPU 0: hi: 186, btch: 31 usd: 0<br/> CPU 1: hi: 186, btch: 31 usd: 17<br/> CPU 2: hi: 186, btch: 31 usd: 21<br/> CPU 3: hi: 186, btch: 31 usd: 25<br/> active_anon:3944 inactive_anon:448 isolated_anon:0<br/> active_<a href="file:2010" class="external-link" target="_blank" rel="nofollow noopener">file:2010</a> inactive_<a href="file:818797" class="external-link" target="_blank" rel="nofollow noopener">file:818797</a> isolated_<a href="file:0" class="external-link" target="_blank" rel="nofollow noopener">file:0</a><br/> unevictable:0 dirty:2 writeback:22 unstable:0<br/> free:2083650 slab_reclaimable:3908 slab_unreclaimable:127194<br/> mapped:3522 shmem:46 pagetables:452 bounce:0<br/> DMA free:3476kB min:64kB low:80kB high:96kB active_anon:0kB inactive_anon:0kB active_<a href="file:0kB" class="external-link" target="_blank" rel="nofollow noopener">file:0kB</a> inactive_<a href="file:0kB" class="external-link" target="_blank" rel="nofollow noopener">file:0kB</a> unevictable:0kB isolated(anon):0kB isolated(file):0kB present:15792kB mlocked:0kB dirty:0kB writeback:0kB mapped:0kB shmem:0kB slab_reclaimable:156kB slab_unreclaimable:4544kB kernel_stack:0kB pagetables:0kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:0 all_unreclaimable? no<br/> lowmem_reserve[]: 0 863 12159 12159<br/> Normal free:4164kB min:3724kB low:4652kB high:5584kB active_anon:0kB inactive_anon:0kB active_<a href="file:84kB" class="external-link" target="_blank" rel="nofollow noopener">file:84kB</a> inactive_<a href="file:12kB" class="external-link" target="_blank" rel="nofollow noopener">file:12kB</a> unevictable:0kB isolated(anon):0kB isolated(file):0kB present:883912kB mlocked:0kB dirty:0kB writeback:0kB mapped:4kB shmem:0kB slab_reclaimable:15476kB slab_unreclaimable:504232kB kernel_stack:2168kB pagetables:0kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:0 all_unreclaimable? no<br/> lowmem_reserve[]: 0 0 90370 90370<br/> HighMem free:8326960kB min:512kB low:12700kB high:24888kB active_anon:15776kB inactive_anon:1792kB active_<a href="file:7956kB" class="external-link" target="_blank" rel="nofollow noopener">file:7956kB</a> inactive_<a href="file:3275176kB" class="external-link" target="_blank" rel="nofollow noopener">file:3275176kB</a> unevictable:0kB isolated(anon):0kB isolated(file):0kB present:11567412kB mlocked:0kB dirty:8kB writeback:88kB mapped:14084kB shmem:184kB slab_reclaimable:0kB slab_unreclaimable:0kB kernel_stack:0kB pagetables:1808kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:0 all_unreclaimable? no<br/> lowmem_reserve[]: 0 0 0 0<br/> DMA: 3*4kB 1*8kB 0*16kB 2*32kB 1*64kB 2*128kB 2*256kB 1*512kB 0*1024kB 1*2048kB 0*4096kB = 3476kB<br/> Normal: 73*4kB 7*8kB 2*16kB 2*32kB 2*64kB 0*128kB 0*256kB 1*512kB 1*1024kB 1*2048kB 0*4096kB = 4156kB<br/> HighMem: 70*4kB 31*8kB 9*16kB 7*32kB 9*64kB 11*128kB 8*256kB 6*512kB 6*1024kB 1*2048kB 2029*4096kB = 8326976kB<br/> 820864 total pagecache pages<br/> 0 pages in swap cache<br/> Swap cache stats: add 0, delete 0, find 0/0<br/> Free swap = 14565368kB<br/> Total swap = 14565368kB<br/> 3145712 pages RAM<br/> 2918914 pages HighMem<br/> 62162 pages reserved<br/> 834421 pages shared<br/> 169306 pages non-shared<br/> Out of memory: kill process 1875 (qmgr) score 2582 or a child<br/> Killed process 1875 (qmgr) vsz:10328kB, anon-rss:436kB, file-rss:1664kB<br/> irqbalance invoked oom-killer: gfp_mask=0xd0, order=0, oom_adj=0<br/> irqbalance cpuset=/ mems_allowed=0<br/> Pid: 1486, comm: irqbalance Not tainted 2.6.32-131.6.1.el6.i686 #1<br/> Call Trace:<br/> <span class="error">[<c04df510>]</span> ? oom_kill_process+0xb0/0x2d0<br/> <span class="error">[<c04dfbba>]</span> ? __out_of_memory+0x4a/0x90<br/> <span class="error">[<c04dfc55>]</span> ? out_of_memory+0x55/0xb0<br/> <span class="error">[<c04eda4b>]</span> ? __alloc_pages_nodemask+0x7fb/0x810<br/> <span class="error">[<c0519a5c>]</span> ? cache_alloc_refill+0x2bc/0x510<br/> <span class="error">[<c0519df2>]</span> ? __kmalloc+0x142/0x180<br/> <span class="error">[<c057c927>]</span> ? stat_open+0x47/0x90<br/> <span class="error">[<c057c927>]</span> ? stat_open+0x47/0x90<br/> <span class="error">[<c05748b4>]</span> ? proc_reg_open+0x94/0x180<br/> <span class="error">[<c05340eb>]</span> ? __link_path_walk+0x42b/0x6b0<br/> <span class="error">[<c0543ba0>]</span> ? single_release+0x0/0x30<br/> <span class="error">[<c05256bc>]</span> ? __dentry_open+0xdc/0x2a0<br/> <span class="error">[<c0525971>]</span> ? nameidata_to_filp+0x51/0x70<br/> <span class="error">[<c0574820>]</span> ? proc_reg_open+0x0/0x180<br/> <span class="error">[<c0535ab1>]</span> ? do_filp_open+0x5c1/0xb30<br/> <span class="error">[<c0478d42>]</span> ? hrtimer_try_to_cancel+0x32/0xb0<br/> <span class="error">[<c0519982>]</span> ? cache_alloc_refill+0x1e2/0x510<br/> <span class="error">[<c0478dd1>]</span> ? hrtimer_cancel+0x11/0x20<br/> <span class="error">[<c0525448>]</span> ? do_sys_open+0x58/0x130<br/> <span class="error">[<c04adc5c>]</span> ? audit_syscall_entry+0x21c/0x240<br/> <span class="error">[<c052559c>]</span> ? sys_open+0x2c/0x40<br/> <span class="error">[<c0409bdf>]</span> ? sysenter_do_call+0x12/0x28<br/> Mem-Info:<br/> DMA per-cpu:<br/> CPU 0: hi: 0, btch: 1 usd: 0<br/> CPU 1: hi: 0, btch: 1 usd: 0<br/> CPU 2: hi: 0, btch: 1 usd: 0<br/> CPU 3: hi: 0, btch: 1 usd: 0<br/> Normal per-cpu:<br/> CPU 0: hi: 186, btch: 31 usd: 26<br/> CPU 1: hi: 186, btch: 31 usd: 149<br/> CPU 2: hi: 186, btch: 31 usd: 178<br/> CPU 3: hi: 186, btch: 31 usd: 103<br/> HighMem per-cpu:<br/> CPU 0: hi: 186, btch: 31 usd: 51<br/> CPU 1: hi: 186, btch: 31 usd: 17<br/> CPU 2: hi: 186, btch: 31 usd: 3<br/> CPU 3: hi: 186, btch: 31 usd: 21<br/> active_anon:3841 inactive_anon:448 isolated_anon:0<br/> active_<a href="file:2012" class="external-link" target="_blank" rel="nofollow noopener">file:2012</a> inactive_<a href="file:823715" class="external-link" target="_blank" rel="nofollow noopener">file:823715</a> isolated_<a href="file:0" class="external-link" target="_blank" rel="nofollow noopener">file:0</a><br/> unevictable:0 dirty:1 writeback:9 unstable:0<br/> free:2078702 slab_reclaimable:3910 slab_unreclaimable:127269<br/> mapped:3476 shmem:46 pagetables:441 bounce:0<br/> DMA free:3508kB min:64kB low:80kB high:96kB active_anon:0kB inactive_anon:0kB active_<a href="file:0kB" class="external-link" target="_blank" rel="nofollow noopener">file:0kB</a> inactive_<a href="file:0kB" class="external-link" target="_blank" rel="nofollow noopener">file:0kB</a> unevictable:0kB isolated(anon):0kB isolated(file):0kB present:15792kB mlocked:0kB dirty:0kB writeback:0kB mapped:0kB shmem:0kB slab_reclaimable:172kB slab_unreclaimable:4496kB kernel_stack:0kB pagetables:0kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:0 all_unreclaimable? yes<br/> lowmem_reserve[]: 0 863 12159 12159<br/> Normal free:3668kB min:3724kB low:4652kB high:5584kB active_anon:0kB inactive_anon:0kB active_<a href="file:84kB" class="external-link" target="_blank" rel="nofollow noopener">file:84kB</a> inactive_<a href="file:0kB" class="external-link" target="_blank" rel="nofollow noopener">file:0kB</a> unevictable:0kB isolated(anon):0kB isolated(file):0kB present:883912kB mlocked:0kB dirty:0kB writeback:0kB mapped:4kB shmem:0kB slab_reclaimable:15468kB slab_unreclaimable:504580kB kernel_stack:2168kB pagetables:0kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:359 all_unreclaimable? yes<br/> lowmem_reserve[]: 0 0 90370 90370<br/> HighMem free:8307632kB min:512kB low:12700kB high:24888kB active_anon:15364kB inactive_anon:1792kB active_<a href="file:7964kB" class="external-link" target="_blank" rel="nofollow noopener">file:7964kB</a> inactive_<a href="file:3294860kB" class="external-link" target="_blank" rel="nofollow noopener">file:3294860kB</a> unevictable:0kB isolated(anon):0kB isolated(file):0kB present:11567412kB mlocked:0kB dirty:4kB writeback:36kB mapped:13900kB shmem:184kB slab_reclaimable:0kB slab_unreclaimable:0kB kernel_stack:0kB pagetables:1764kB unstable:0kB bounce:0kB writeback_tmp:0kB pages_scanned:0 all_unreclaimable? no<br/> lowmem_reserve[]: 0 0 0 0<br/> DMA: 3*4kB 7*8kB 1*16kB 1*32kB 1*64kB 2*128kB 2*256kB 1*512kB 0*1024kB 1*2048kB 0*4096kB = 3508kB<br/> Normal: 19*4kB 1*8kB 0*16kB 0*32kB 0*64kB 0*128kB 0*256kB 1*512kB 1*1024kB 1*2048kB 0*4096kB = 3668kB<br/> HighMem: 36*4kB 30*8kB 9*16kB 7*32kB 9*64kB 11*128kB 9*256kB 6*512kB 5*1024kB 2*2048kB 2024*4096kB = 8307632kB<br/> 825784 total pagecache pages<br/> 0 pages in swap cache<br/> Swap cache stats: add 0, delete 0, find 0/0<br/> Free swap = 14565368kB<br/> Total swap = 14565368kB<br/> 3145712 pages RAM<br/> 2918914 pages HighMem<br/> 62162 pages reserved<br/> 815056 pages shared<br/> 169309 pages non-shared<br/> Out of memory: kill process 1874 (pickup) score 2565 or a child<br/> Killed process 1874 (pickup) vsz:10260kB, anon-rss:440kB, file-rss:1632kB<br/> irqbalance invoked oom-killer: gfp_mask=0xd0, order=0, oom_adj=0<br/> irqbalance cpuset=/ mems_allowed=0<br/> Pid: 1486, comm: irqbalance Not tainted 2.6.32-131.6.1.el6.i686 #1</p> <p>hmm, I'm not sure why such test could cause OOM. Hi, Sahara, I think the OOM is not reproducible, right? Is the "dd did not fail with EDQUOT" reproducible? Is it possible to get the D_QUOTA & D_TRACE debug log for it? Thanks.</p> <p>the OOM can be reproducible and the attached is the debug log. Since it's OOM every time in my test, I am not sure if the "dd error" is reproducible. </p> <p><a href="https://jira.whamcloud.com/browse/LU-851" title="Test failure on test suite parallel-scale, subtest test_iorssf" class="issue-link" data-issue-key="LU-851"><del>LU-851</del></a> is another OOM issue.</p> <p>Ah, the client is i686. Has this test ever passed (w/o OOM) with 2.1?</p> <p>We are deprecating i686 clients for 2.2 so if this problem is limited to i686 then we should not worry about it</p> <blockquote> <p>Ah, the client is i686. Has this test ever passed (w/o OOM) with 2.1?</p></blockquote> <p>Hi, Johann, any reason that the OOM only happened on 32bit arch?</p> <p>The "Normal" zone (vs HighMem) is rather limited on i686 and i wonder if this combined with async journal commit (which can pin a significant amount of pages, see bugzilla 23529) is causing this problem. That's why i asked Sarah to try to reproduce with async journal commit disabled in <a href="https://jira.whamcloud.com/browse/LU-851" title="Test failure on test suite parallel-scale, subtest test_iorssf" class="issue-link" data-issue-key="LU-851"><del>LU-851</del></a>.</p> <p>After disable async journal commit, got oom again.</p> <p><span class="error">[root@fat-amd-2 ~]</span># lctl get_param obdfilter.lustre-OST*.sync_journal<br/> obdfilter.lustre-OST0000.sync_journal=0<br/> obdfilter.lustre-OST0001.sync_journal=0<br/> obdfilter.lustre-OST0002.sync_journal=0<br/> obdfilter.lustre-OST0003.sync_journal=0<br/> obdfilter.lustre-OST0004.sync_journal=0<br/> obdfilter.lustre-OST0005.sync_journal=0</p> <p>Out of memory: kill process 1758 (sssd) score 310 or a child<br/> Killed process 1785 (sssd_pam) vsz:9436kB, anon-rss:284kB, file-rss:1900kB<br/> sssd invoked oom-killer: gfp_mask=0x84d0, order=0, oom_adj=0<br/> sssd cpuset=/ mems_allowed=0<br/> Pid: 1758, comm: sssd Tainted: G ---------------- T 2.6.32-131.6.1.el6.i686 #1<br/> Call Trace:<br/> <span class="error">[<c04df510>]</span> ? oom_kill_process+0xb0/0x2d0<br/> <span class="error">[<c04dfbba>]</span> ? __out_of_memory+0x4a/0x90<br/> <span class="error">[<c04dfc55>]</span> ? out_of_memory+0x55/0xb0<br/> <span class="error">[<c04eda4b>]</span> ? __alloc_pages_nodemask+0x7fb/0x810<br/> <span class="error">[<c04eda74>]</span> ? __get_free_pages+0x14/0x30<br/> <span class="error">[<c0436e7c>]</span> ? pgd_alloc+0x6c/0x2b0<br/> <span class="error">[<c043a5a7>]</span> ? sched_slice+0x57/0xb0<br/> <span class="error">[<c04502c9>]</span> ? mm_init+0xb9/0xf0<br/> <span class="error">[<c0450893>]</span> ? dup_mm+0x93/0x420<br/> <span class="error">[<c0466f37>]</span> ? lock_task_sighand+0x37/0x70<br/> <span class="error">[<c044ad2b>]</span> ? sched_autogroup_fork+0x4b/0x80<br/> <span class="error">[<c0451655>]</span> ? copy_process+0x9e5/0xf80<br/> <span class="error">[<c0451c6a>]</span> ? do_fork+0x7a/0x3e0<br/> <span class="error">[<c04563a7>]</span> ? sys_wait4+0x97/0xe0<br/> <span class="error">[<c047d886>]</span> ? getnstimeofday+0x46/0xf0<br/> <span class="error">[<c04adc5c>]</span> ? audit_syscall_entry+0x21c/0x240<br/> <span class="error">[<c0408383>]</span> ? sys_clone+0x33/0x40<br/> <span class="error">[<c0409bdf>]</span> ? sysenter_do_call+0x12/0x28</p> <p>To disable async journal commit, obdfilter.lustre-OST*.sync_journal must be set to 1 in order to flush the journal.</p> <p>i686 is not a valid platform for 2.2. Can this ticket be closed, or could it also affect x86_64?</p> <p>the "OOM with asyn journal" could happen with x86_64, but it should be a separate issue as that's quite a bit of development work to properly overcome that situation. Believed to only happen if there is little memory on the client and a lot of streaming writes, but actually that might happen more often than we suspect too, just in a somewhat hidden way.</p> <p>i686 isn't supportted anymore.</p> Development Rank 1|hzvhqn: Rank (Obsolete) 6523 Severity