From 2d60b2ee513b0e04fc8e9288e8d918bee8eadd02 Mon Sep 17 00:00:00 2001 From: Richard Henwood Date: Fri, 20 May 2011 13:53:05 -0500 Subject: [PATCH] FIX: validation, ulink -> link --- LustreProc.xml | 250 +++++++++++++++++++++++++++++---------------------------- 1 file changed, 126 insertions(+), 124 deletions(-) diff --git a/LustreProc.xml b/LustreProc.xml index 6ec2582..a40c96c 100644 --- a/LustreProc.xml +++ b/LustreProc.xml @@ -73,28 +73,28 @@ lustre-MDT0000 Specific Lustre timeouts are described below. - /proc/sys/lustre/timeout + /proc/sys/lustre/timeout This is the time period that a client waits for a server to complete an RPC (default is 100s). Servers wait half of this time for a normal client RPC to complete and a quarter of this time for a single bulk request (read or write of up to 1 MB) to complete. The client pings recoverable targets (MDS and OSTs) at one quarter of the timeout, and the server waits one and a half times the timeout before evicting a client for being "stale." Lustre sends periodic 'PING' messages to servers with which it had no communication for a specified period of time. Any network activity on the file system that triggers network traffic toward servers also works as a health check. - /proc/sys/lustre/ldlm_timeout + /proc/sys/lustre/ldlm_timeout This is the time period for which a server will wait for a client to reply to an initial AST (lock cancellation request) where default is 20s for an OST and 6s for an MDS. If the client replies to the AST, the server will give it a normal timeout (half of the client timeout) to flush any dirty data and release the lock. - /proc/sys/lustre/fail_loc + /proc/sys/lustre/fail_loc This is the internal debugging failure hook. See lustre/include/linux/obd_support.h for the definitions of individual failure locations. The default value is 0 (zero). sysctl -w lustre.fail_loc=0x80000122 # drop a single reply - /proc/sys/lustre/dump_on_timeout + /proc/sys/lustre/dump_on_timeout This triggers dumps of the Lustre debug log when timeouts occur. The default value is 0 (zero). - /proc/sys/lustre/dump_on_eviction + /proc/sys/lustre/dump_on_eviction This triggers dumps of the Lustre debug log when an eviction occurs. The default value is 0 (zero). By default, debug logs are dumped to the /tmp folder; this location can be changed via /proc. @@ -128,7 +128,7 @@ lustre-MDT0000 - at_min + at_min @@ -138,7 +138,7 @@ lustre-MDT0000 - at_max + at_max @@ -152,7 +152,7 @@ lustre-MDT0000 - at_history + at_history @@ -162,7 +162,7 @@ lustre-MDT0000 - at_early_margin + at_early_margin @@ -174,7 +174,7 @@ lustre-MDT0000 - at_extra + at_extra @@ -187,7 +187,7 @@ lustre-MDT0000 - ldlm_enqueue_min + ldlm_enqueue_min @@ -236,7 +236,7 @@ req_timeout 6 samples [sec] 1 10 15 105 31.1.4 LNET Information This section describes /proc entries for LNET information. - /proc/sys/lnet/peers + /proc/sys/lnet/peers Shows all NIDs known to this node and also gives information on the queue state. # cat /proc/sys/lnet/peers @@ -263,9 +263,9 @@ nid refs state max rtr - - refs - + + refs + A reference count (principally used for debugging) @@ -273,9 +273,9 @@ nid refs state max rtr - - state - + + state + Only valid to refer to routers. Possible values: @@ -295,7 +295,7 @@ nid refs state max rtr - max + max @@ -305,7 +305,7 @@ nid refs state max rtr - rtr + rtr @@ -314,9 +314,9 @@ nid refs state max rtr - - min - + + min + Minimum routing buffer credits seen. @@ -325,7 +325,7 @@ nid refs state max rtr - tx + tx @@ -334,9 +334,9 @@ nid refs state max rtr - - min - + + min + Minimum send credits seen. @@ -344,9 +344,9 @@ nid refs state max rtr - - queue - + + queue + Total bytes in active/queued sends. @@ -360,7 +360,7 @@ nid refs state max rtr If rtr/tx is greater that max, there are operations blocking. LNET also limits concurrent sends and router buffers allocated to a single peer so that no peer can occupy all these resources. - /proc/sys/lnet/nis + /proc/sys/lnet/nis # cat /proc/sys/lnet/nis nid refs peer max tx min @@ -386,7 +386,7 @@ nid refs peer max - nid + nid @@ -396,7 +396,7 @@ nid refs peer max - refs + refs @@ -405,9 +405,9 @@ nid refs peer max - - peer - + + peer + Number of peer-to-peer send credits on this NID. Credits are used to size buffer pools @@ -416,7 +416,7 @@ nid refs peer max - max + max @@ -425,9 +425,9 @@ nid refs peer max - - tx - + + tx + Current number of send credits available on this NID. @@ -435,9 +435,9 @@ nid refs peer max - - min - + + min + Lowest number of send credits available on this NID. @@ -445,9 +445,9 @@ nid refs peer max - - queue - + + queue + Total bytes in active/queued sends. @@ -505,7 +505,7 @@ nid refs peer max 31.2 Lustre I/O Tunables The section describes I/O tunables. - /proc/fs/lustre/llite/<fsname>-<uid>/max_cache_mb + /proc/fs/lustre/llite/<fsname>-<uid>/max_cache_mb # cat /proc/fs/lustre/llite/lustre-ce63ca00/max_cached_mb 128 This tunable is the maximum amount of inactive data cached by the client (default is 3/4 of RAM). @@ -521,26 +521,26 @@ blocksizefilesfree max_dirty_mb ost_server_uuid stats ... and so on. RPC stream tunables are described below. - /proc/fs/lustre/osc/<object name>/max_dirty_mb + /proc/fs/lustre/osc/<object name>/max_dirty_mb This tunable controls how many MBs of dirty data can be written and queued up in the OSC. POSIX file writes that are cached contribute to this count. When the limit is reached, additional writes stall until previously-cached writes are written to the server. This may be changed by writing a single ASCII integer to the file. Only values between 0 and 512 are allowable. If 0 is given, no writes are cached. Performance suffers noticeably unless you use large writes (1 MB or more). - /proc/fs/lustre/osc/<object name>/cur_dirty_bytes + /proc/fs/lustre/osc/<object name>/cur_dirty_bytes This tunable is a read-only value that returns the current amount of bytes written and cached on this OSC. - /proc/fs/lustre/osc/<object name>/max_pages_per_rpc + /proc/fs/lustre/osc/<object name>/max_pages_per_rpc This tunable is the maximum number of pages that will undergo I/O in a single RPC to the OST. The minimum is a single page and the maximum for this setting is platform dependent (256 for i386/x86_64, possibly less for ia64/PPC with larger PAGE_SIZE), though generally amounts to a total of 1 MB in the RPC. - /proc/fs/lustre/osc/<object name>/max_rpcs_in_flight + /proc/fs/lustre/osc/<object name>/max_rpcs_in_flight This tunable is the maximum number of concurrent RPCs in flight from an OSC to its OST. If the OSC tries to initiate an RPC but finds that it already has the same number of RPCs outstanding, it will wait to issue further RPCs until some complete. The minimum setting is 1 and maximum setting is 32. If you are looking to improve small file I/O performance, increase the max_rpcs_in_flight value. To maximize performance, the value for max_dirty_mb is recommended to be 4 * max_pages_per_rpc * max_rpcs_in_flight. - The - <object name> - varies depending on the specific Lustre configuration. For <object name> examples, refer to the sample command output. + The + <object name> + varies depending on the specific Lustre configuration. For <object name> examples, refer to the sample command output.
@@ -658,7 +658,7 @@ R 8385 500 600 100 - R/W + R/W @@ -667,9 +667,9 @@ R 8385 500 600 100 - - PID - + + PID + Process ID which made the read/write call. @@ -678,7 +678,7 @@ R 8385 500 600 100 - Range Start/Range End + Range Start/Range End @@ -688,7 +688,7 @@ R 8385 500 600 100 - Smallest Extent + Smallest Extent @@ -698,7 +698,7 @@ R 8385 500 600 100 - Largest Extent + Largest Extent @@ -708,7 +708,7 @@ R 8385 500 600 100 - Offset + Offset @@ -833,7 +833,7 @@ disk io size rpcs % cum % | rpcs % cum % - pages per brw + pages per brw @@ -843,7 +843,7 @@ disk io size rpcs % cum % | rpcs % cum % - discont pages + discont pages @@ -853,7 +853,7 @@ disk io size rpcs % cum % | rpcs % cum % - discont blocks + discont blocks @@ -892,11 +892,11 @@ disk io size rpcs % cum % | rpcs % cum % 31.2.6.1 Tuning File Readahead File readahead is triggered when two or more sequential reads by an application fail to be satisfied by the Linux buffer cache. The size of the initial readahead is 1 MB. Additional readaheads grow linearly, and increment until the readahead cache on the client is full at 40 MB. - /proc/fs/lustre/llite/<fsname>-<uid>/max_read_ahead_mb + /proc/fs/lustre/llite/<fsname>-<uid>/max_read_ahead_mb This tunable controls the maximum amount of data readahead on a file. Files are read ahead in RPC-sized chunks (1 MB or the size of read() call, if larger) after the second sequential read on a file descriptor. Random reads are done at the size of the read() call only (no readahead). Reads to non-contiguous regions of the file reset the readahead algorithm, and readahead is not triggered again until there are sequential reads again. To disable readahead, set this tunable to 0. The default value is 40 MB. - /proc/fs/lustre/llite/<fsname>-<uid>/max_read_ahead_whole_mb + /proc/fs/lustre/llite/<fsname>-<uid>/max_read_ahead_whole_mb This tunable controls the maximum size of a file that is read in its entirety, regardless of the size of the read().
@@ -904,7 +904,7 @@ disk io size rpcs % cum % | rpcs % cum % 31.2.6.2 Tuning Directory Statahead When the ls -l process opens a directory, its process ID is recorded. When the first directory entry is ''stated'' with this recorded process ID, a statahead thread is triggered which stats ahead all of the directory entries, in order. The ls -l process can use the stated directory entries directly, improving performance. - /proc/fs/lustre/llite/*/statahead_max + /proc/fs/lustre/llite/*/statahead_max This tunable controls whether directory statahead is enabled and the maximum statahead count. By default, statahead is active. To disable statahead, set this tunable to: @@ -912,11 +912,13 @@ disk io size rpcs % cum % | rpcs % cum % To set the maximum statahead count (n), set this tunable to: echo n > /proc/fs/lustre/llite/*/statahead_max The maximum value of n is 8192. - + - /proc/fs/lustre/llite/*/statahead_status + + /proc/fs/lustre/llite/*/statahead_status + - + This is a read-only interface that indicates the current statahead status. @@ -1030,7 +1032,7 @@ obdfilter.lol-OST0001.sync_on_lock_cancel=never
31.2.9 <literal>mballoc</literal> History - /proc/fs/ldiskfs/sda/mb_history + /proc/fs/ldiskfs/sda/mb_history Multi-Block-Allocate (mballoc), enables Lustre to ask ldiskfs to allocate multiple blocks with a single request to the block allocator. Typically, an ldiskfs file system allocates only one block per time. Each mballoc-enabled partition has this file. This is sample output: pid inode goal result found grps cr \ merge tail broken @@ -1230,7 +1232,7 @@ obdfilter.lol-OST0001.sync_on_lock_cancel=never - max_to_scan + max_to_scan @@ -1240,7 +1242,7 @@ obdfilter.lol-OST0001.sync_on_lock_cancel=never - min_to_scan + min_to_scan @@ -1250,7 +1252,7 @@ obdfilter.lol-OST0001.sync_on_lock_cancel=never - order2_req + order2_req @@ -1260,7 +1262,7 @@ obdfilter.lol-OST0001.sync_on_lock_cancel=never - stream_req + stream_req @@ -1288,9 +1290,9 @@ obdfilter.lol-OST0001.sync_on_lock_cancel=never - - stats - + + stats + Enables/disables the collection of statistics. Collected statistics can be found in /proc/fs/ldiskfs2/<dev>/mb_history. @@ -1299,7 +1301,7 @@ obdfilter.lol-OST0001.sync_on_lock_cancel=never - max_to_scan + max_to_scan @@ -1309,7 +1311,7 @@ obdfilter.lol-OST0001.sync_on_lock_cancel=never - min_to_scan + min_to_scan @@ -1319,7 +1321,7 @@ obdfilter.lol-OST0001.sync_on_lock_cancel=never - order2_req + order2_req @@ -1329,7 +1331,7 @@ obdfilter.lol-OST0001.sync_on_lock_cancel=never - small_req + small_req @@ -1343,14 +1345,14 @@ obdfilter.lol-OST0001.sync_on_lock_cancel=never - large_req + large_req - prealloc_table + prealloc_table @@ -1360,7 +1362,7 @@ obdfilter.lol-OST0001.sync_on_lock_cancel=never - group_prealloc + group_prealloc @@ -1374,7 +1376,7 @@ obdfilter.lol-OST0001.sync_on_lock_cancel=never
31.2.11 Locking - /proc/fs/lustre/ldlm/ldlm/namespaces/<OSC name|MDC name>/lru_size + /proc/fs/lustre/ldlm/ldlm/namespaces/<OSC name|MDC name>/lru_size The lru_size parameter is used to control the number of client-side locks in an LRU queue. LRU size is dynamic, based on load. This optimizes the number of locks available to nodes that have different workloads (e.g., login/build nodes vs. compute nodes vs. backup nodes). The total number of locks available is a function of the server's RAM. The default limit is 50 locks/1 MB of RAM. If there is too much memory pressure, then the LRU size is shrunk. The number of locks on the server is limited to {number of OST/MDT on node} * {number of clients} * {client lru_size}. @@ -1417,7 +1419,7 @@ obdfilter.lol-OST0001.sync_on_lock_cancel=never - mdt.MDS.mds + mdt.MDS.mds @@ -1427,7 +1429,7 @@ obdfilter.lol-OST0001.sync_on_lock_cancel=never - mdt.MDS.mds_readpage + mdt.MDS.mds_readpage @@ -1437,7 +1439,7 @@ obdfilter.lol-OST0001.sync_on_lock_cancel=never - mdt.MDS.mds_setattr + mdt.MDS.mds_setattr @@ -1447,7 +1449,7 @@ obdfilter.lol-OST0001.sync_on_lock_cancel=never - ost.OSS.ost + ost.OSS.ost @@ -1457,7 +1459,7 @@ obdfilter.lol-OST0001.sync_on_lock_cancel=never - ost.OSS.ost_io + ost.OSS.ost_io @@ -1467,7 +1469,7 @@ obdfilter.lol-OST0001.sync_on_lock_cancel=never - ost.OSS.ost_create + ost.OSS.ost_create @@ -1477,7 +1479,7 @@ obdfilter.lol-OST0001.sync_on_lock_cancel=never - ldlm.services.ldlm_canceld + ldlm.services.ldlm_canceld @@ -1487,7 +1489,7 @@ obdfilter.lol-OST0001.sync_on_lock_cancel=never - ldlm.services.ldlm_cbd + ldlm.services.ldlm_cbd @@ -1550,7 +1552,7 @@ obdfilter.lol-OST0001.sync_on_lock_cancel=never
31.3 Debug - /proc/sys/lnet/debug + /proc/sys/lnet/debug By default, Lustre generates a detailed log of all operations to aid in debugging. The level of debugging can affect the performance or speed you achieve with Lustre. Therefore, it is useful to reduce this overhead by turning down the debug level This controls the level of Lustre debugging kept in the internal log buffer. It does not alter the level of debugging that goes to syslog. @@ -1594,11 +1596,11 @@ neterror warning ha # cat /proc/sys/lnet/debug neterror ha - /proc/sys/lnet/subsystem_debug + /proc/sys/lnet/subsystem_debug This controls the debug logs for subsystems (see S_* definitions). - /proc/sys/lnet/debug_path + /proc/sys/lnet/debug_path This indicates the location where debugging symbols should be stored for gdb. The default is set to /r/tmp/lustre-log-localhost.localdomain. These values can also be set via sysctl -w lnet.debug={value} @@ -1606,11 +1608,11 @@ neterror ha The above entries only exist when Lustre has already been loaded. - /proc/sys/lnet/panic_on_lbug + /proc/sys/lnet/panic_on_lbug This causes Lustre to call ''panic'' when it detects an internal problem (an LBUG); panic crashes the node. This is particularly useful when a kernel crash dump utility is configured. The crash dump is triggered when the internal inconsistency is detected by Lustre. - /proc/sys/lnet/upcall + /proc/sys/lnet/upcall This allows you to specify the path to the binary which will be invoked when an LBUG is encountered. This binary is called with four parameters. The first one is the string ''LBUG''. The second one is the file where the LBUG occurred. The third one is the function name. The fourth one is the line number in the file.
@@ -1694,7 +1696,7 @@ ost_write 21 2 59 [bytes] 7648424\ 1 - Cur. Count + Cur. Count @@ -1704,7 +1706,7 @@ ost_write 21 2 59 [bytes] 7648424\ 1 - Cur. Rate + Cur. Rate @@ -1714,7 +1716,7 @@ ost_write 21 2 59 [bytes] 7648424\ 1 - #Events + #Events @@ -1723,9 +1725,9 @@ ost_write 21 2 59 [bytes] 7648424\ 1 - - Unit - + + Unit + Unit of measurement for that statistic (microseconds, requests, buffers) @@ -1733,9 +1735,9 @@ ost_write 21 2 59 [bytes] 7648424\ 1 - - last - + + last + Average rate of these events (in units/event) for the last interval during which they arrived. For instance, in the above mentioned case of ost_destroy it took an average of 736 microseconds per destroy for the 400 object destroys in the previous 10 seconds. @@ -1743,9 +1745,9 @@ ost_write 21 2 59 [bytes] 7648424\ 1 - - min - + + min + Minimum rate (in units/events) since the service started @@ -1753,9 +1755,9 @@ ost_write 21 2 59 [bytes] 7648424\ 1 - - avg - + + avg + Average rate @@ -1763,9 +1765,9 @@ ost_write 21 2 59 [bytes] 7648424\ 1 - - max - + + max + Maximum rate @@ -1773,9 +1775,9 @@ ost_write 21 2 59 [bytes] 7648424\ 1 - - stddev - + + stddev + Standard deviation (not measured in all cases) @@ -1803,7 +1805,7 @@ ost_write 21 2 59 [bytes] 7648424\ 1 - req_waittime + req_waittime @@ -1813,7 +1815,7 @@ ost_write 21 2 59 [bytes] 7648424\ 1 - req_qdepth + req_qdepth @@ -1823,7 +1825,7 @@ ost_write 21 2 59 [bytes] 7648424\ 1 - req_active + req_active -- 1.8.3.1