<!-- 
RSS generated by JIRA (9.4.14#940014-sha1:734e6822bbf0d45eff9af51f82432957f73aa32c) at Sat Feb 10 01:15:08 UTC 2024

It is possible to restrict the fields that are returned in this document by specifying the 'field' parameter in your request.
For example, to request only the issue key and summary append 'field=key&field=summary' to the URL of your request.
-->
<rss version="0.92" >
<channel>
    <title>Whamcloud Community JIRA</title>
    <link>https://jira.whamcloud.com</link>
    <description>This file is an XML representation of an issue</description>
    <language>en-us</language>    <build-info>
        <version>9.4.14</version>
        <build-number>940014</build-number>
        <build-date>05-12-2023</build-date>
    </build-info>


<item>
            <title>[LU-1269] speed up ASTs sending</title>
                <link>https://jira.whamcloud.com/browse/LU-1269</link>
                <project id="10000" key="LU">Lustre</project>
                    <description>&lt;p&gt;The goal of this ticket is to land into WC 1.8 branch next patches from Vladimir Saveliev (Oracle):&lt;/p&gt;

&lt;p&gt;&lt;a href=&quot;https://bugzilla.lustre.org/attachment.cgi?id=33145&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://bugzilla.lustre.org/attachment.cgi?id=33145&lt;/a&gt;&lt;br/&gt;
&lt;a href=&quot;https://bugzilla.lustre.org/attachment.cgi?id=33137&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://bugzilla.lustre.org/attachment.cgi?id=33137&lt;/a&gt;&lt;br/&gt;
&lt;a href=&quot;https://bugzilla.lustre.org/attachment.cgi?id=33106&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://bugzilla.lustre.org/attachment.cgi?id=33106&lt;/a&gt;&lt;br/&gt;
&lt;a href=&quot;https://bugzilla.lustre.org/attachment.cgi?id=33099&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://bugzilla.lustre.org/attachment.cgi?id=33099&lt;/a&gt;&lt;/p&gt;

&lt;p&gt;(details of these patches are in the &lt;a href=&quot;https://bugzilla.lustre.org/show_bug.cgi?id=24450&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;https://bugzilla.lustre.org/show_bug.cgi?id=24450&lt;/a&gt;).&lt;/p&gt;

&lt;p&gt;Patches summary:&lt;/p&gt;

&lt;p&gt;ldlm_run_bl_ast_work() sends ASTs in set of PARALLEL_AST_LIMIT&lt;br/&gt;
requests and waits for whole set to complete and then sends another&lt;br/&gt;
set of requests and waits again. If there is a least one request per&lt;br/&gt;
set which timeouts, we have timeout serialization.&lt;/p&gt;

&lt;p&gt;This patch changes ldlm_run_bl_ast_work() so that having sent one&lt;br/&gt;
set it then waits for any of its requests to complete and refills&lt;br/&gt;
the running set with requests which are yet to be sent. For a case&lt;br/&gt;
where number of timeout-ing requests is smaller than&lt;br/&gt;
PARALLEL_AST_LIMIT it is supposed to eliminate possibility of timeout&lt;br/&gt;
serailization.&lt;/p&gt;

&lt;p&gt;This patch uses posibility to specify wait condition for&lt;br/&gt;
ptlrpc_set_wait().&lt;/p&gt;
</description>
                <environment></environment>
        <key id="13770">LU-1269</key>
            <summary>speed up ASTs sending</summary>
                <type id="4" iconUrl="https://jira.whamcloud.com/secure/viewavatar?size=xsmall&amp;avatarId=11310&amp;avatarType=issuetype">Improvement</type>
                                            <priority id="4" iconUrl="https://jira.whamcloud.com/images/icons/priorities/minor.svg">Minor</priority>
                        <status id="6" iconUrl="https://jira.whamcloud.com/images/icons/statuses/closed.png" description="The issue is considered finished, the resolution is correct. Issues which are closed can be reopened.">Closed</status>
                    <statusCategory id="3" key="done" colorName="success"/>
                                    <resolution id="2">Won&apos;t Fix</resolution>
                                        <assignee username="jay">Jinshan Xiong</assignee>
                                    <reporter username="igolovach">Iurii Golovach</reporter>
                        <labels>
                    </labels>
                <created>Thu, 29 Mar 2012 08:52:29 +0000</created>
                <updated>Thu, 8 Feb 2018 18:18:51 +0000</updated>
                            <resolved>Thu, 8 Feb 2018 18:18:51 +0000</resolved>
                                    <version>Lustre 1.8.7</version>
                                                        <due></due>
                            <votes>0</votes>
                                    <watches>10</watches>
                                                                            <comments>
                            <comment id="32826" author="igolovach" created="Thu, 29 Mar 2012 09:07:05 +0000"  >&lt;p&gt;&lt;a href=&quot;http://review.whamcloud.com/#change,2406&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;http://review.whamcloud.com/#change,2406&lt;/a&gt; - link on the submitted patch&lt;/p&gt;</comment>
                            <comment id="32881" author="adilger" created="Fri, 30 Mar 2012 00:21:42 +0000"  >&lt;p&gt;Jinshan, didn&apos;t something similar to this already get implemented for 2.2?  I&apos;d prefer to keep the implementations on 1.8 and 2.x as close as possible to avoid future complications with other patches that affect the same code.&lt;/p&gt;</comment>
                            <comment id="32884" author="jay" created="Fri, 30 Mar 2012 00:47:41 +0000"  >&lt;p&gt;Yes, I think we have done the similar thing. Sorry about that.&lt;/p&gt;</comment>
                            <comment id="32907" author="igolovach" created="Fri, 30 Mar 2012 07:45:03 +0000"  >&lt;p&gt;Andreas, Jinshan, do you mean that there is a plan to port your changes with such functionality from 2.2 into the 1.8? If yes - let me know the ticket where this is tracked and we may close this one then.&lt;/p&gt;</comment>
                            <comment id="34847" author="pjones" created="Mon, 16 Apr 2012 19:39:32 +0000"  >&lt;p&gt;No there are no plans to backport new features to b1_8. We are landing bugfixes only into b1_8 and new feature development is limited to master&lt;/p&gt;</comment>
                            <comment id="35011" author="iurii" created="Wed, 18 Apr 2012 09:20:53 +0000"  >&lt;p&gt;Peter, this ticket is about landing &lt;em&gt;bugfixes&lt;/em&gt; which are committed on review at &lt;a href=&quot;http://review.whamcloud.com/#change,2406&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;http://review.whamcloud.com/#change,2406&lt;/a&gt;&lt;/p&gt;

&lt;p&gt;it&apos;s NOT about back-porting.&lt;/p&gt;

&lt;p&gt;Please, don&apos;t close this ticket like &quot;Won&apos;t Fix&quot; since these fixes require landing into 1.8 branch.&lt;/p&gt;

&lt;p&gt;Thank you,&lt;br/&gt;
    Iurii&lt;/p&gt;</comment>
                            <comment id="38454" author="ihara" created="Wed, 9 May 2012 18:30:07 +0000"  >&lt;p&gt;Hi, we also got very similar problem on lustre-1.8.7-wc1 too, and MDS hanged.&lt;/p&gt;

&lt;div class=&quot;preformatted panel&quot; style=&quot;border-width: 1px;&quot;&gt;&lt;div class=&quot;preformattedContent panelContent&quot;&gt;
&lt;pre&gt;Apr 23 15:58:34 ALPL505 kernel: Call Trace:
Apr 23 15:58:34 ALPL505 kernel:  [&amp;lt;ffffffff88953a00&amp;gt;] ldlm_expired_completion_wait+0x0/0x250 [ptlrpc]
Apr 23 15:58:34 ALPL505 kernel:  [&amp;lt;ffffffff88955542&amp;gt;] ldlm_completion_ast+0x4c2/0x880 [ptlrpc]
Apr 23 15:58:34 ALPL505 kernel:  [&amp;lt;ffffffff8893a709&amp;gt;] ldlm_lock_enqueue+0x9d9/0xb20 [ptlrpc]
Apr 23 15:58:34 ALPL505 kernel:  [&amp;lt;ffffffff8008e421&amp;gt;] default_wake_function+0x0/0xe
Apr 23 15:58:34 ALPL505 kernel:  [&amp;lt;ffffffff88935b6a&amp;gt;] ldlm_lock_addref_internal_nolock+0x3a/0x90 [ptlrpc]
Apr 23 15:58:34 ALPL505 kernel:  [&amp;lt;ffffffff889540bb&amp;gt;] ldlm_cli_enqueue_local+0x46b/0x520 [ptlrpc]
Apr 23 15:58:34 ALPL505 kernel:  [&amp;lt;ffffffff88caa157&amp;gt;] enqueue_ordered_locks+0x387/0x4d0 [mds]
Apr 23 15:58:34 ALPL505 kernel:  [&amp;lt;ffffffff889519a0&amp;gt;] ldlm_blocking_ast+0x0/0x2a0 [ptlrpc]
Apr 23 15:58:34 ALPL505 kernel:  [&amp;lt;ffffffff88955080&amp;gt;] ldlm_completion_ast+0x0/0x880 [ptlrpc]
Apr 23 15:58:34 ALPL505 kernel:  [&amp;lt;ffffffff88caa8e9&amp;gt;] mds_get_parent_child_locked+0x649/0x960 [mds]
Apr 23 15:58:34 ALPL505 kernel:  [&amp;lt;ffffffff88c9b652&amp;gt;] mds_getattr_lock+0x632/0xc90 [mds]
Apr 23 15:58:34 ALPL505 kernel:  [&amp;lt;ffffffff88c96dda&amp;gt;] fixup_handle_for_resent_req+0x5a/0x2c0 [mds]
Apr 23 15:58:34 ALPL505 kernel:  [&amp;lt;ffffffff88ca1d83&amp;gt;] mds_intent_policy+0x623/0xc20 [mds]
Apr 23 15:58:34 ALPL505 kernel:  [&amp;lt;ffffffff8893c270&amp;gt;] ldlm_resource_putref_internal+0x230/0x460 [ptlrpc]
Apr 23 15:58:34 ALPL505 kernel:  [&amp;lt;ffffffff88939eb6&amp;gt;] ldlm_lock_enqueue+0x186/0xb20 [ptlrpc]
Apr 23 15:58:34 ALPL505 kernel:  [&amp;lt;ffffffff889367fd&amp;gt;] ldlm_lock_create+0x9bd/0x9f0 [ptlrpc]
Apr 23 15:58:34 ALPL505 kernel:  [&amp;lt;ffffffff8895e870&amp;gt;] ldlm_server_blocking_ast+0x0/0x83d [ptlrpc]
Apr 23 15:58:34 ALPL505 kernel:  [&amp;lt;ffffffff8895bb39&amp;gt;] ldlm_handle_enqueue+0xc09/0x1210 [ptlrpc]
Apr 23 15:58:34 ALPL505 kernel:  [&amp;lt;ffffffff88ca0b30&amp;gt;] mds_handle+0x40e0/0x4d10 [mds]
Apr 23 15:58:34 ALPL505 kernel:  [&amp;lt;ffffffff800774ed&amp;gt;] smp_send_reschedule+0x4e/0x53
Apr 23 15:58:34 ALPL505 kernel:  [&amp;lt;ffffffff8008ddcd&amp;gt;] enqueue_task+0x41/0x56
Apr 23 15:58:34 ALPL505 kernel:  [&amp;lt;ffffffff8897fd55&amp;gt;] lustre_msg_get_conn_cnt+0x35/0xf0 [ptlrpc]
Apr 23 15:58:34 ALPL505 kernel:  [&amp;lt;ffffffff889896d9&amp;gt;] ptlrpc_server_handle_request+0x989/0xe00 [ptlrpc]
Apr 23 15:58:34 ALPL505 kernel:  [&amp;lt;ffffffff88989e35&amp;gt;] ptlrpc_wait_event+0x2e5/0x310 [ptlrpc]
Apr 23 15:58:34 ALPL505 kernel:  [&amp;lt;ffffffff8008c85d&amp;gt;] __wake_up_common+0x3e/0x68
Apr 23 15:58:34 ALPL505 kernel:  [&amp;lt;ffffffff8898adc6&amp;gt;] ptlrpc_main+0xf66/0x1120 [ptlrpc]
Apr 23 15:58:34 ALPL505 kernel:  [&amp;lt;ffffffff8005dfb1&amp;gt;] child_rip+0xa/0x11
Apr 23 15:58:34 ALPL505 kernel:  [&amp;lt;ffffffff88989e60&amp;gt;] ptlrpc_main+0x0/0x1120 [ptlrpc]
Apr 23 15:58:34 ALPL505 kernel:  [&amp;lt;ffffffff8005dfa7&amp;gt;] child_rip+0x0/0x11
&lt;/pre&gt;
&lt;/div&gt;&lt;/div&gt;</comment>
                            <comment id="39283" author="adilger" created="Wed, 23 May 2012 14:08:28 +0000"  >&lt;p&gt;Reopening issue due to problem reports hit on 1.8.&lt;/p&gt;

&lt;p&gt;Jinshan, can you please find the patch set for master that resolved this problem?  I believe it was one of the early patches in the Imperative Recovery feature.&lt;/p&gt;</comment>
                            <comment id="39286" author="spitzcor" created="Wed, 23 May 2012 14:46:53 +0000"  >&lt;p&gt;Also, it might be worthwhile to hear from Johann.  I had a conversation with him and he suggested that b1_8 might be better off simply by removing the PARALLEL_AST_LIMIT.  Cray has been using the patches listed in the description from bz 24450.  I&apos;m not sure what the correct approach should be for b1_8 though.&lt;/p&gt;</comment>
                            <comment id="39288" author="jay" created="Wed, 23 May 2012 14:54:24 +0000"  >&lt;p&gt;the hash # in master is: 0bd27be7f20a671e7128f341a070838a2bd318dc&lt;/p&gt;

&lt;p&gt;and johann is working on an improvement at: &lt;a href=&quot;http://review.whamcloud.com/2650&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;http://review.whamcloud.com/2650&lt;/a&gt; and you might be interested.&lt;/p&gt;</comment>
                            <comment id="39292" author="spitzcor" created="Wed, 23 May 2012 15:20:13 +0000"  >&lt;p&gt;Thanks, Jinshan.  Change #2650/&lt;a href=&quot;https://jira.whamcloud.com/browse/LU-1373&quot; title=&quot;ptlrpcd shouldn&amp;#39;t do disk I/O&quot; class=&quot;issue-link&quot; data-issue-key=&quot;LU-1373&quot;&gt;&lt;del&gt;LU-1373&lt;/del&gt;&lt;/a&gt; does look interesting.&lt;/p&gt;

&lt;p&gt;BTW, &lt;a href=&quot;http://jira.whamcloud.com/browse/LU-571&quot; class=&quot;external-link&quot; rel=&quot;nofollow&quot;&gt;http://jira.whamcloud.com/browse/LU-571&lt;/a&gt;, &lt;a href=&quot;http://review.whamcloud.com/#change,1190&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;http://review.whamcloud.com/#change,1190&lt;/a&gt;, and &lt;a href=&quot;http://review.whamcloud.com/#change,1608&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;http://review.whamcloud.com/#change,1608&lt;/a&gt; are a few handy links for master commit 0bd27be7f20a671e7128f341a070838a2bd318dc.&lt;/p&gt;</comment>
                            <comment id="48256" author="nrutman" created="Wed, 21 Nov 2012 19:34:27 +0000"  >&lt;p&gt;Xyratex-bug-id: &lt;a href=&quot;http://jira-nss.xy01.xyratex.com:8080/browse/MRP-478&quot; class=&quot;external-link&quot; target=&quot;_blank&quot; rel=&quot;nofollow noopener&quot;&gt;MRP-478&lt;/a&gt;&lt;/p&gt;</comment>
                            <comment id="220454" author="jay" created="Thu, 8 Feb 2018 18:18:51 +0000"  >&lt;p&gt;close old tickets&lt;/p&gt;</comment>
                    </comments>
                    <attachments>
                    </attachments>
                <subtasks>
                    </subtasks>
                <customfields>
                                                                                                                                    <customfield id="customfield_10020" key="com.atlassian.jira.plugin.system.customfieldtypes:float">
                        <customfieldname>Bugzilla ID</customfieldname>
                        <customfieldvalues>
                            <customfieldvalue>24450.0</customfieldvalue>
                        </customfieldvalues>
                    </customfield>
                                                                                            <customfield id="customfield_10890" key="com.atlassian.jira.plugins.jira-development-integration-plugin:devsummary">
                        <customfieldname>Development</customfieldname>
                        <customfieldvalues>
                            
                        </customfieldvalues>
                    </customfield>
                                                                                                                                                                                                                                                                                                                                                        <customfield id="customfield_10390" key="com.pyxis.greenhopper.jira:gh-lexo-rank">
                        <customfieldname>Rank</customfieldname>
                        <customfieldvalues>
                            <customfieldvalue>1|hzvyan:</customfieldvalue>

                        </customfieldvalues>
                    </customfield>
                                                                <customfield id="customfield_10090" key="com.pyxis.greenhopper.jira:gh-global-rank">
                        <customfieldname>Rank (Obsolete)</customfieldname>
                        <customfieldvalues>
                            <customfieldvalue>9740</customfieldvalue>
                        </customfieldvalues>
                    </customfield>
                                                                                                                                                                                                                                                                                                                                                                                                                </customfields>
    </item>
</channel>
</rss>