https://jira.whamcloud.com This file is an XML representation of an issue en-us 9.4.14 940014 05-12-2023 https://jira.whamcloud.com/browse/LU-4454 Lustre <p>We have some Lustre clients where hyperthreading is enabled and disabled, possibly on a per job basis. The admins are noting streams of scary messages on the console from Lustre:</p> <div class="preformatted panel" style="border-width: 1px;"><div class="preformattedContent panelContent"> <pre>2013-12-02 09:58:29 LNet: 5546:0:(linux-cpu.c:1035:cfs_cpu_notify()) Lustre: can't support CPU hotplug well now, performance and stability could be impacted[CPU 40 notify: 3] 2013-12-02 09:58:29 LNet: 5546:0:(linux-cpu.c:1035:cfs_cpu_notify()) Skipped 30 previous similar messages 2013-12-02 09:58:29 Booting Node 0 Processor 40 APIC 0x1 2013-12-02 09:58:30 microcode: CPU40 sig=0x206f2, pf=0x4, revision=0x37 2013-12-02 09:58:30 platform microcode: firmware: requesting intel-ucode/06-2f-02 2013-12-02 09:58:30 Booting Node 0 Processor 41 APIC 0x3 </pre> </div></div> <p>The above message is not acceptable. Please fix.</p> <p>Further, when I went to look into how this cpu partitions code worked, I wound up mighty confused. For instance, on a node with 4 sockets and 10 codes per socket, I see this:</p> <div class="preformatted panel" style="border-width: 1px;"><div class="preformattedContent panelContent"> <pre>/proc/sys/lnet$ cat cpu_partition_table 0 : 0 1 2 3 4 1 : 5 6 7 8 9 2 : 10 11 12 13 14 3 : 15 16 17 18 19 4 : 20 21 22 23 24 5 : 25 26 27 28 29 6 : 30 31 32 33 34 7 : 35 36 37 38 39 </pre> </div></div> <p>Why are there two parititions per socket? Is this by design, or a bug?</p> <p>What is going to happen when hyperthreading is enabled, and there are 80 "cpus" suddenly available?</p> LU-4454

"Lustre: can't support CPU hotplug well now"

Bug Major Resolved Fixed Liang Zhen Christopher Morrone Wed, 8 Jan 2014 02:21:24 +0000 Fri, 14 Feb 2014 17:16:49 +0000 Tue, 21 Jan 2014 22:20:59 +0000 Lustre 2.5.0 Lustre 2.4.2 Lustre 2.6.0 Lustre 2.5.1 0 7 <p>Liang</p> <p>Could you please advise?</p> <p>Thanks</p> <p>Peter</p> <p>Hi Chris, it is by design to have multiple partitions per socket, two different partitions (and thread pools) per socket should have better performance when there are many cores (HTs) on each socket, and it also can be set/changed by configuration. </p> <p>CPU partition is not well designed for hot plug-out CPU, e.g. all CPUs (or cores) in a specific CPU partition are offline, then threads on that CPU partition just lose affinity, we can do nothing for this so far. Hot plug-in new CPU is OK, but new added CPU will never be used by CPU affinity threads.</p> <p>Enabling/Disabling HT should be fine because HTs of a same core will be put in a same CPU partition:</p> <ul> <li>if HT is disable, when enabling HT, Lustre threads with CPU affinity will never run on those new appeared "CPUs", that's it.</li> <li>if HT is enabled, When disabling HT, Lustre threads with CPU affinity will still run on same cores.</li> </ul> <p>I can work out a patch which only print warnings when we lose a physical core (all HTs in a core are gone).</p> <p>patch is here: <a href="http://review.whamcloud.com/#/c/8770/" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/8770/</a></p> <p>What else needs to be completed in this ticket and what is the priority of that work (if any)?</p> <p>As per LLNL this ticket can be resolved.</p> Development Rank 1|hzwcdz: Rank (Obsolete) 12210 Severity