Bug 1917560
| Summary: | hwloc does not work on Power10 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Product: | Red Hat Enterprise Linux 8 | Reporter: | Jiri Hladky <jhladky> | ||||||||
| Component: | hwloc | Assignee: | Prarit Bhargava <prarit> | ||||||||
| Status: | CLOSED ERRATA | QA Contact: | Jeff Bastian <jbastian> | ||||||||
| Severity: | high | Docs Contact: | Jaroslav Klech <jklech> | ||||||||
| Priority: | unspecified | ||||||||||
| Version: | 8.4 | CC: | borgan, bugproxy, fnovak, janani, jbastian, jhladky, jvozar, kkolakow, prarit | ||||||||
| Target Milestone: | rc | Keywords: | Patch, Triaged | ||||||||
| Target Release: | 8.5 | Flags: | pm-rhel:
mirror+
|
||||||||
| Hardware: | ppc64le | ||||||||||
| OS: | Linux | ||||||||||
| Whiteboard: | |||||||||||
| Fixed In Version: | hwloc-2.2.0-2.el8 | Doc Type: | Bug Fix | ||||||||
| Doc Text: |
.The `hwloc` commands now return correct data on single CPU Power9 and Power10 logical partitions
With the `hwloc` utility of version 2.2.0, any single-node Non-Uniform Memory Access (NUMA) system that ran a Power9 or Power10 CPU was considered to be "disallowed". Consequently, all `hwloc` commands did not work, because NODE0 (socket 0, CPU 0) was offline and the `hwloc` source code expected NODE0 to be online. The following error message was displayed:
----
Topology does not contain any NUMA node, aborting!
----
With this update, `hwloc` has been fixed so that its source code checks to see if NODE0 is online before querying it. If NODE0 is not online, the code proceeds to the next online NODE.
As a result, the `hwloc` command does not return any errors in the described scenario.
|
Story Points: | --- | ||||||||
| Clone Of: | Environment: | ||||||||||
| Last Closed: | 2021-11-09 19:42:12 UTC | Type: | Bug | ||||||||
| Regression: | --- | Mount Type: | --- | ||||||||
| Documentation: | --- | CRM: | |||||||||
| Verified Versions: | Category: | --- | |||||||||
| oVirt Team: | --- | RHEL 7.3 requirements from Atomic Host: | |||||||||
| Cloudforms Team: | --- | Target Upstream Version: | |||||||||
| Embargoed: | |||||||||||
| Bug Depends On: | |||||||||||
| Bug Blocks: | 1916117 | ||||||||||
| Attachments: |
|
||||||||||
|
Description
Jiri Hladky
2021-01-18 18:13:17 UTC
Jiri -- do you know what happens when you run it on a LPAR with multiple cores ? For e.g. rhyzden1-lp11 and rhyzden-12 have multiple NUMA nodes. lp12 looks good. It seems the problem is only on the single CPU LPARs.
[root@rhyzden1-lp12 ~]# hwloc-calc -N core machine:0
4
[root@rhyzden1-lp12 ~]# lstopo-no-graphics
Machine (62GB total)
Package L#0
NUMANode L#0 (P#0 14GB)
L3 L#0 (8KB) + Core L#0
L2 L#0 (256KB) + L1d L#0 (64KB) + L1i L#0 (32KB)
Die L#0 + PU L#0 (P#0)
PU L#1 (P#2)
PU L#2 (P#4)
PU L#3 (P#6)
L2 L#1 (256KB) + L1d L#1 (64KB) + L1i L#1 (32KB)
PU L#4 (P#1)
PU L#5 (P#3)
PU L#6 (P#5)
PU L#7 (P#7)
Package L#1
NUMANode L#1 (P#1 16GB)
L3 L#1 (8KB) + Core L#1
L2 L#2 (256KB) + L1d L#2 (64KB) + L1i L#2 (32KB)
Die L#1 + PU L#8 (P#8)
PU L#9 (P#10)
PU L#10 (P#12)
PU L#11 (P#14)
L2 L#3 (256KB) + L1d L#3 (64KB) + L1i L#3 (32KB)
PU L#12 (P#9)
PU L#13 (P#11)
PU L#14 (P#13)
PU L#15 (P#15)
Package L#2
NUMANode L#2 (P#2 16GB)
L3 L#2 (8KB) + Core L#2
L2 L#4 (256KB) + L1d L#4 (64KB) + L1i L#4 (32KB)
Die L#2 + PU L#16 (P#16)
PU L#17 (P#18)
PU L#18 (P#20)
PU L#19 (P#22)
L2 L#5 (256KB) + L1d L#5 (64KB) + L1i L#5 (32KB)
PU L#20 (P#17)
PU L#21 (P#19)
PU L#22 (P#21)
PU L#23 (P#23)
Package L#3
NUMANode L#3 (P#3 16GB)
L3 L#3 (8KB) + Core L#3
L2 L#6 (256KB) + L1d L#6 (64KB) + L1i L#6 (32KB)
Die L#3 + PU L#24 (P#24)
PU L#25 (P#26)
PU L#26 (P#28)
PU L#27 (P#30)
L2 L#7 (256KB) + L1d L#7 (64KB) + L1i L#7 (32KB)
PU L#28 (P#25)
PU L#29 (P#27)
PU L#30 (P#29)
PU L#31 (P#31)
Block(Disk) "sda"
Net "env2"
Note: hwloc is getting a rebase in RHEL-8.4.0. See Red Hat bug 1841354. RHEL-8.3.0: hwloc-1.11.9-3.el8 RHEL-8.4.0: hwloc-2.2.0-1.el8 The older 1.11.9-3.el8 rpm works on a single CPU (8 threads) P10 system:
[root@rhyzden1-lp1 ~]# lscpu | grep -i -e cpu -e thread -e core -e socket
CPU(s): 8
On-line CPU(s) list: 0-7
Thread(s) per core: 8
Core(s) per socket: 1
Socket(s): 1
NUMA node2 CPU(s): 0-7
Physical sockets: 2
Physical cores/chip: 11
[root@rhyzden1-lp1 ~]# rpm -q hwloc
hwloc-1.11.9-3.el8.ppc64le
[root@rhyzden1-lp1 ~]# hwloc-calc -N core machine:0
1
[root@rhyzden1-lp1 ~]# lstopo-no-graphics
Machine (7614MB) + Package L#0 + L3 L#0 (8KB) + Core L#0
L2 L#0 (256KB) + L1d L#0 (64KB) + L1i L#0 (32KB)
PU L#0 (P#0)
PU L#1 (P#2)
PU L#2 (P#4)
PU L#3 (P#6)
L2 L#1 (256KB) + L1d L#1 (64KB) + L1i L#1 (32KB)
PU L#4 (P#1)
PU L#5 (P#3)
PU L#6 (P#5)
PU L#7 (P#7)
But the update to version 2.2.0 does not like it:
[root@rhyzden1-lp1 ~]# yum -y update hwloc
...
[root@rhyzden1-lp1 ~]# rpm -q hwloc
hwloc-2.2.0-1.el8.ppc64le
[root@rhyzden1-lp1 ~]# hwloc-calc -N core machine:0
Topology does not contain any NUMA node, aborting!
[root@rhyzden1-lp1 ~]# lstopo-no-graphics
Topology does not contain any NUMA node, aborting!
hwloc_topology_load() failed (No such file or directory).
The relevant chunk of code from each version:
hwloc-1.11.9/src/topology.c
============================
2665 hwloc_debug("%s", "\nRemoving empty objects except numa nodes and PCI devices\n");
2666 remove_empty(topology, &topology->levels[0][0]);
2667 if (!topology->levels[0][0]) {
2668 fprintf(stderr, "Topology became empty, aborting!\n");
2669 abort();
2670 }
2671 hwloc_debug_print_objects(0, topology->levels[0][0]);
hwloc-2.2.0/hwloc/topology.c
============================
3449 hwloc_debug("%s", "\nRemoving empty objects\n");
3450 remove_empty(topology, &topology->levels[0][0]);
3451 if (!topology->levels[0][0]) {
3452 fprintf(stderr, "Topology became empty, aborting!\n");
3453 return -1;
3454 }
3455 if (hwloc_bitmap_iszero(topology->levels[0][0]->cpuset)) {
3456 fprintf(stderr, "Topology does not contain any PU, aborting!\n");
3457 return -1;
3458 }
3459 if (hwloc_bitmap_iszero(topology->levels[0][0]->nodeset)) {
3460 fprintf(stderr, "Topology does not contain any NUMA node, aborting!\n");
3461 return -1;
3462 }
3463 hwloc_debug_print_objects(0, topology->levels[0][0]);
I recompiled hwloc-1.11.9 and hwloc-2.2.0 from source and added --enable-debug to the configure flags. Set the HWLOC_DEBUG_VERBOSE environment variable to 1 to get the debug output. [root@rhyzden1-lp1 ~]# HWLOC_DEBUG_VERBOSE=1 hwloc-calc -N core machine:0 2>&1 | tee $(rpm -q hwloc).debug Attaching the output of each version. Created attachment 1748571 [details]
debug output of hwloc-1.11.9-3.el8
Created attachment 1748572 [details]
debug output of hwloc-2.2.0-1.el8
hwloc-2.2.0 is removing the single NUMA node for some reason: $ grep Removing.empty /tmp/hwloc-2.2.0-1.el8.dbg.ppc64le.debug Removing empty objects Removing empty object NUMANode#0(local=7797120KB total=0KB) cpuset 0x000000ff complete 0x000000ff nodeset 0x0 completeN 0x00000001 The older version doesn't remove any objects: $ grep Removing.empty /tmp/hwloc-1.11.9-3.el8.dbg.ppc64le.debug Removing empty objects except numa nodes and PCI devices Good news (if you can call it that): this also fails on POWER9 single CPU LPARs. [root@ibm-p9z-20-lp15 ~]# lscpu | grep -i -e cpu -e socket -e thread -e model CPU(s): 8 On-line CPU(s) list: 0-7 Thread(s) per core: 8 Core(s) per socket: 1 Socket(s): 1 Model: 2.2 (pvr 004e 0202) Model name: POWER9 (architected), altivec supported NUMA node1 CPU(s): 0-7 Physical sockets: 2 [root@ibm-p9z-20-lp15 ~]# hwloc-calc -N core machine:0 Topology does not contain any NUMA node, aborting! [root@ibm-p9z-20-lp15 ~]# lstopo-no-graphics Topology does not contain any NUMA node, aborting! hwloc_topology_load() failed (No such file or directory). Truly good news: with hwloc-2.1.0 and newer, single-node NUMA systems are considered "disallowed" and thus it prints the errors and exits early. But you can override this with the --disallowed flag:
[root@rhyzden1-lp1 ~]# rpm -q hwloc
hwloc-2.2.0-1.el8.ppc64le
[root@rhyzden1-lp1 ~]# hwloc-calc -N core machine:0
Topology does not contain any NUMA node, aborting!
[root@rhyzden1-lp1 ~]# hwloc-calc --disallowed -N core machine:0
1
[root@rhyzden1-lp1 ~]# lstopo-no-graphics
Topology does not contain any NUMA node, aborting!
hwloc_topology_load() failed (No such file or directory).
[root@rhyzden1-lp1 ~]# lstopo-no-graphics --disallowed
Machine (7614MB total)
Package L#0
NUMANode L#0 (P#0 7614MB)
L3 L#0 (8KB) + Core L#0
L2 L#0 (256KB) + L1d L#0 (64KB) + L1i L#0 (32KB)
Die L#0 + PU L#0 (P#0)
PU L#1 (P#2)
PU L#2 (P#4)
PU L#3 (P#6)
L2 L#1 (256KB) + L1d L#1 (64KB) + L1i L#1 (32KB)
PU L#4 (P#1)
PU L#5 (P#3)
PU L#6 (P#5)
PU L#7 (P#7)
Block(Disk) "sda"
Net "env2"
Jirka, can you update your tests to add the --disallowed flag and try again?
For the record, I discovered the --disallowed flag by checking the 'git blame' output of the remove_empty() function in topology.c. In particular, this commit caught my eye because it removed a check for NUMA node objects:
- if (obj->type != HWLOC_OBJ_NUMANODE
commit 1cfb5af0ad21a809d9e82ea4c65f20350ccac31c
Author: Brice Goglin <Brice.Goglin>
Date: Thu Nov 2 23:27:26 2017 +0100
core: remove disallowed nodes entirely (unless WHOLE_SYSTEM)
Now that NUMA nodes are (memory-child) leaves, there's no need
to keep them with memory=0, just remove them entirely.
In v1.X, things were different because NUMA nodes may have CPU
children. Removing NUMA nodes without their children would
make the topology asymmetric, etc.
Signed-off-by: Brice Goglin <Brice.Goglin>
That clue led to this note in the NEWS file:
+ Improve the API for dealing with disallowed resources
- HWLOC_TOPOLOGY_FLAG_WHOLE_SYSTEM is replaced with FLAG_INCLUDE_DISALLOWED
and --whole-system command-line options with --disallowed.
. Former names are still accepted for backward compatibility.
- Add hwloc_topology_allow() for changing allowed sets after load().
- Add the HWLOC_ALLOW=all environment variable to totally ignore
administrative restrictions such as Linux Cgroups.
- Add disallowed_pu and disallowed_numa bits to the discovery support
structure.
Hi Jeff, thanks a lot for the quick resolution and all the details! The fix is very simple at the end - you just need to set HWLOC_ALLOW=all env variable and all my scripts work again. From my side, we can close this BZ. Thanks a lot! Jirka I think we should document this change in hwloc's behavior. I have proposed a doc text, feel free to modify it. I'm adding the "Documentation" Keyword to this BZ since there's nothing to actually fix in hwloc itself, but we need to keep the BZ open until the RHEL-8.4.0 Release Notes (or Tech Notes) are updated. Hi, I have talked to upstream and there were very responsive. We got a fix. I will attach it. For RHEL-8.4, I think documenting this issue is fine. For RHEL-8.5, we should backport the patch. @Prarit - should I open a new BZ for RHEL-8.5 or can we use this one? Thanks a lot Jirka Created attachment 1775677 [details] Patch I got from upstream The patch is easy - I have manually applied it and tested that it works on rhyzden1-lp8.yz.ibm. It should appear soon on GitHub as well (it's not there yet): https://github.com/open-mpi/hwloc/commits/master Prarit, pls could you look at c#22? Thanks The patch is now available on github: https://github.com/open-mpi/hwloc/commit/0114c2b0b3e39265e0829eebfff87ac9f4412fe9 I'll see if I can get this into RHEL8.5. P. jhladky, could you test with https://brewweb.engineering.redhat.com/brew/taskinfo?taskID=36851005 to confirm the fix? P. I'll let Jiri run some more detailed tests, but a quick smoke test of the brew build in comment 29 looks good on a POWER10 Rainier LPAR. :::::::::::: :: Before :: :::::::::::: [root@rhyzrain2-lp19 ~]# rpm -q hwloc hwloc-2.2.0-1.el8.ppc64le [root@rhyzrain2-lp19 ~]# hwloc-calc -N core machine:0 Topology does not contain any NUMA node, aborting! [root@rhyzrain2-lp19 ~]# lstopo-no-graphics Topology does not contain any NUMA node, aborting! hwloc_topology_load() failed (No such file or directory). ::::::::::: :: After :: ::::::::::: [root@rhyzrain2-lp19 ~]# rpm -q hwloc hwloc-2.2.0-2.el8.ppc64le [root@rhyzrain2-lp19 ~]# hwloc-calc -N core machine:0 4 [root@rhyzrain2-lp19 ~]# lstopo-no-graphics Machine (15GB total) Package L#0 NUMANode L#0 (P#2 15GB) Core L#0 L1d L#0 (32KB) + L1i L#0 (48KB) Die L#0 + PU L#0 (P#0) PU L#1 (P#2) PU L#2 (P#4) PU L#3 (P#6) L1d L#1 (32KB) + L1i L#1 (48KB) PU L#4 (P#1) PU L#5 (P#3) PU L#6 (P#5) PU L#7 (P#7) Core L#1 L1d L#2 (32KB) + L1i L#2 (48KB) Die L#1 + PU L#8 (P#8) PU L#9 (P#10) PU L#10 (P#12) PU L#11 (P#14) L1d L#3 (32KB) + L1i L#3 (48KB) PU L#12 (P#9) PU L#13 (P#11) PU L#14 (P#13) PU L#15 (P#15) Core L#2 L1d L#4 (32KB) + L1i L#4 (48KB) Die L#2 + PU L#16 (P#16) PU L#17 (P#18) PU L#18 (P#20) PU L#19 (P#22) L1d L#5 (32KB) + L1i L#5 (48KB) PU L#20 (P#17) PU L#21 (P#19) PU L#22 (P#21) PU L#23 (P#23) Core L#3 L1d L#6 (32KB) + L1i L#6 (48KB) Die L#3 + PU L#24 (P#24) PU L#25 (P#26) PU L#26 (P#28) PU L#27 (P#30) L1d L#7 (32KB) + L1i L#7 (48KB) PU L#28 (P#25) PU L#29 (P#27) PU L#30 (P#29) PU L#31 (P#31) Block(Disk) "sdd" Block(Disk) "sdb" Block(Disk) "sdc" Block(Disk) "sda" Net "env2" Hi Jeff and Prarit, thanks for the great news! I have tested a new version of hwloc on rhyzden1-lp9.yz.ibm running RHEL-8.5.0-20210506.d.3 hwloc-2.2.0-1.el8.ppc64le.rpm => confirmed that issue can be reproduced hwloc-2.2.0-2.el8.ppc64le.rpm => problem is fixed! hwloc-calc -N core machine:0 1 Setting the state to Verified: Tested. Jirka Verified with hwloc-2.2.0-2.el8
:::::::::::::::::::::::::::::::
:: ppc64le - POWER10 PowerVM ::
:::::::::::::::::::::::::::::::
[root@rhyzrain2-lp21 ~]# rpm -q hwloc
hwloc-2.2.0-2.el8.ppc64le
[root@rhyzrain2-lp21 ~]# lscpu
Architecture: ppc64le
Byte Order: Little Endian
CPU(s): 8
On-line CPU(s) list: 0-7
Thread(s) per core: 8
Core(s) per socket: 1
Socket(s): 1
NUMA node(s): 1
Model: 1.0 (pvr 0080 0100)
Model name: POWER10 (architected), altivec supported
Hypervisor vendor: pHyp
Virtualization type: para
L1d cache: 32K
L1i cache: 48K
L2 cache: 1024K
L3 cache: 4096K
NUMA node0 CPU(s): 0-7
Physical sockets: 1
Physical chips: 4
Physical cores/chip: 14
[root@rhyzrain2-lp21 ~]# hwloc-calc -N core machine:0
1
[root@rhyzrain2-lp21 ~]# lstopo-no-graphics
Machine (15GB total)
Package L#0
NUMANode L#0 (P#0 15GB)
L3 L#0 (4096KB) + Core L#0
L2 L#0 (1024KB) + L1d L#0 (32KB) + L1i L#0 (48KB)
Die L#0 + PU L#0 (P#0)
PU L#1 (P#2)
PU L#2 (P#4)
PU L#3 (P#6)
L2 L#1 (1024KB) + L1d L#1 (32KB) + L1i L#1 (48KB)
PU L#4 (P#1)
PU L#5 (P#3)
PU L#6 (P#5)
PU L#7 (P#7)
Block(Disk) "sdd"
Block(Disk) "sdb"
Block(Disk) "sdc"
Block(Disk) "sda"
Net "env2"
::::::::::::::::::::::::::::::
:: ppc64le - POWER9 PowerNV ::
::::::::::::::::::::::::::::::
[root@raven ~]# rpm -q hwloc
hwloc-2.2.0-2.el8.ppc64le
[root@raven ~]# lscpu
Architecture: ppc64le
Byte Order: Little Endian
CPU(s): 16
On-line CPU(s) list: 0-15
Thread(s) per core: 4
Core(s) per socket: 4
Socket(s): 1
NUMA node(s): 1
Model: 2.2 (pvr 004e 1202)
Model name: POWER9, altivec supported
CPU max MHz: 3800.0000
CPU min MHz: 2166.0000
L1d cache: 32K
L1i cache: 32K
L2 cache: 512K
L3 cache: 10240K
NUMA node0 CPU(s): 0-15
[root@raven ~]# hwloc-calc -N core machine:0
4
[root@raven ~]# lstopo-no-graphics
Machine (31GB total)
Package L#0
NUMANode L#0 (P#0 31GB)
L3 L#0 (10MB) + L2 L#0 (512KB) + L1d L#0 (32KB) + L1i L#0 (32KB) + Core L#0
Die L#0 + PU L#0 (P#0)
PU L#1 (P#1)
PU L#2 (P#2)
PU L#3 (P#3)
L3 L#1 (10MB) + L2 L#1 (512KB) + L1d L#1 (32KB) + L1i L#1 (32KB) + Core L#1
Die L#1 + PU L#4 (P#4)
PU L#5 (P#5)
PU L#6 (P#6)
PU L#7 (P#7)
L3 L#2 (10MB) + L2 L#2 (512KB) + L1d L#2 (32KB) + L1i L#2 (32KB) + Core L#2
Die L#2 + PU L#8 (P#8)
PU L#9 (P#9)
PU L#10 (P#10)
PU L#11 (P#11)
L3 L#3 (10MB) + L2 L#3 (512KB) + L1d L#3 (32KB) + L1i L#3 (32KB) + Core L#3
Die L#3 + PU L#12 (P#12)
PU L#13 (P#13)
PU L#14 (P#14)
PU L#15 (P#15)
HostBridge
PCIBridge
PCI 0001:01:00.0 (NVMExp)
Block(Disk) "nvme0n1"
HostBridge
PCIBridge
PCI 0002:01:00.0 (SATA)
HostBridge
PCIBridge
PCI 0004:01:00.0 (Ethernet)
Net "enP4p1s0f0"
PCI 0004:01:00.1 (Ethernet)
Net "enP4p1s0f1"
PCI 0004:01:00.2 (Ethernet)
Net "enP4p1s0f2"
HostBridge
PCIBridge
PCIBridge
PCI 0005:02:00.0 (VGA)
::::::::::::::::::::::::::
:: ppc64le - POWER9 KVM ::
::::::::::::::::::::::::::
[root@localhost ~]# rpm -q hwloc
hwloc-2.2.0-2.el8.ppc64le
[root@localhost ~]# lscpu
Architecture: ppc64le
Byte Order: Little Endian
CPU(s): 1
On-line CPU(s) list: 0
Thread(s) per core: 1
Core(s) per socket: 1
Socket(s): 1
NUMA node(s): 1
Model: 2.2 (pvr 004e 1202)
Model name: POWER9 (architected), altivec supported
Hypervisor vendor: KVM
Virtualization type: para
L1d cache: 32K
L1i cache: 32K
NUMA node0 CPU(s): 0
[root@localhost ~]# hwloc-calc -N core machine:0
1
[root@localhost ~]# lstopo-no-graphics
Machine (3528MB total)
Package L#0
NUMANode L#0 (P#0 3528MB)
L1d L#0 (32KB) + L1i L#0 (32KB) + Core L#0 + PU L#0 (P#0)
HostBridge
PCI 00:01.0 (Ethernet)
Net "enp0s1"
PCI 00:04.0 (SCSI)
Block "vda"
::::::::::::
:: x86_64 ::
::::::::::::
[root@dell-per7425-07 ~]# rpm -q hwloc
hwloc-2.2.0-2.el8.x86_64
[root@dell-per7425-07 ~]# lscpu
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Byte Order: Little Endian
CPU(s): 32
On-line CPU(s) list: 0-31
Thread(s) per core: 2
Core(s) per socket: 8
Socket(s): 2
NUMA node(s): 8
Vendor ID: AuthenticAMD
BIOS Vendor ID: AMD
CPU family: 23
Model: 1
Model name: AMD EPYC 7251 8-Core Processor
BIOS Model name: AMD EPYC 7251 8-Core Processor
Stepping: 2
CPU MHz: 2325.228
CPU max MHz: 2100.0000
CPU min MHz: 1200.0000
BogoMIPS: 4192.05
Virtualization: AMD-V
L1d cache: 32K
L1i cache: 64K
L2 cache: 512K
L3 cache: 4096K
NUMA node0 CPU(s): 0,8,16,24
NUMA node1 CPU(s): 2,10,18,26
NUMA node2 CPU(s): 4,12,20,28
NUMA node3 CPU(s): 6,14,22,30
NUMA node4 CPU(s): 1,9,17,25
NUMA node5 CPU(s): 3,11,19,27
NUMA node6 CPU(s): 5,13,21,29
NUMA node7 CPU(s): 7,15,23,31
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid amd_dcm aperfmperf pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb hw_pstate sme ssbd sev ibpb vmmcall sev_es fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt sha_ni xsaveopt xsavec xgetbv1 xsaves clzero irperf xsaveerptr arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif overflow_recov succor smca
[root@dell-per7425-07 ~]# hwloc-calc -N core machine:0
16
[root@dell-per7425-07 ~]# lstopo-no-graphics
Machine (31GB total)
Package L#0
Group0 L#0
L3 L#0 (4096KB) + L2 L#0 (512KB) + L1d L#0 (32KB) + L1i L#0 (64KB) + Core L#0
PU L#0 (P#0)
PU L#1 (P#16)
L3 L#1 (4096KB) + L2 L#1 (512KB) + L1d L#1 (32KB) + L1i L#1 (64KB) + Core L#1
PU L#2 (P#8)
PU L#3 (P#24)
HostBridge
PCIBridge
PCI 02:00.0 (Ethernet)
Net "eno3"
PCI 02:00.1 (Ethernet)
Net "eno4"
PCIBridge
PCI 01:00.0 (Ethernet)
Net "eno1"
PCI 01:00.1 (Ethernet)
Net "eno2"
PCIBridge
PCIBridge
PCI 04:00.0 (VGA)
PCIBridge
PCI 06:00.2 (SATA)
Group0 L#1
NUMANode L#0 (P#1 15GB)
L3 L#2 (4096KB) + L2 L#2 (512KB) + L1d L#2 (32KB) + L1i L#2 (64KB) + Core L#2
PU L#4 (P#2)
PU L#5 (P#18)
L3 L#3 (4096KB) + L2 L#3 (512KB) + L1d L#3 (32KB) + L1i L#3 (64KB) + Core L#3
PU L#6 (P#10)
PU L#7 (P#26)
Group0 L#2
L3 L#4 (4096KB) + L2 L#4 (512KB) + L1d L#4 (32KB) + L1i L#4 (64KB) + Core L#4
PU L#8 (P#4)
PU L#9 (P#20)
L3 L#5 (4096KB) + L2 L#5 (512KB) + L1d L#5 (32KB) + L1i L#5 (64KB) + Core L#5
PU L#10 (P#12)
PU L#11 (P#28)
Group0 L#3
L3 L#6 (4096KB) + L2 L#6 (512KB) + L1d L#6 (32KB) + L1i L#6 (64KB) + Core L#6
PU L#12 (P#6)
PU L#13 (P#22)
L3 L#7 (4096KB) + L2 L#7 (512KB) + L1d L#7 (32KB) + L1i L#7 (64KB) + Core L#7
PU L#14 (P#14)
PU L#15 (P#30)
HostBridge
PCIBridge
PCI 61:00.0 (RAID)
Block(Disk) "sda"
Package L#1
Group0 L#4
L3 L#8 (4096KB) + L2 L#8 (512KB) + L1d L#8 (32KB) + L1i L#8 (64KB) + Core L#8
PU L#16 (P#1)
PU L#17 (P#17)
L3 L#9 (4096KB) + L2 L#9 (512KB) + L1d L#9 (32KB) + L1i L#9 (64KB) + Core L#9
PU L#18 (P#9)
PU L#19 (P#25)
Group0 L#5
NUMANode L#1 (P#5 16GB)
L3 L#10 (4096KB) + L2 L#10 (512KB) + L1d L#10 (32KB) + L1i L#10 (64KB) + Core L#10
PU L#20 (P#3)
PU L#21 (P#19)
L3 L#11 (4096KB) + L2 L#11 (512KB) + L1d L#11 (32KB) + L1i L#11 (64KB) + Core L#11
PU L#22 (P#11)
PU L#23 (P#27)
Group0 L#6
L3 L#12 (4096KB) + L2 L#12 (512KB) + L1d L#12 (32KB) + L1i L#12 (64KB) + Core L#12
PU L#24 (P#5)
PU L#25 (P#21)
L3 L#13 (4096KB) + L2 L#13 (512KB) + L1d L#13 (32KB) + L1i L#13 (64KB) + Core L#13
PU L#26 (P#13)
PU L#27 (P#29)
Group0 L#7
L3 L#14 (4096KB) + L2 L#14 (512KB) + L1d L#14 (32KB) + L1i L#14 (64KB) + Core L#14
PU L#28 (P#7)
PU L#29 (P#23)
L3 L#15 (4096KB) + L2 L#15 (512KB) + L1d L#15 (32KB) + L1i L#15 (64KB) + Core L#15
PU L#30 (P#15)
PU L#31 (P#31)
Misc(MemoryModule)
Misc(MemoryModule)
Misc(MemoryModule)
Misc(MemoryModule)
:::::::::::::
:: aarch64 ::
:::::::::::::
[root@ampere-hr330a-04 ~]# rpm -q hwloc
hwloc-2.2.0-2.el8.aarch64
[root@ampere-hr330a-04 ~]# lscpu
Architecture: aarch64
Byte Order: Little Endian
CPU(s): 32
On-line CPU(s) list: 0-31
Thread(s) per core: 1
Core(s) per socket: 32
Socket(s): 1
NUMA node(s): 1
Vendor ID: APM
BIOS Vendor ID: Ampere(TM)
Model: 2
Model name: X-Gene
BIOS Model name: eMAG
Stepping: 0x3
CPU max MHz: 3300.0000
CPU min MHz: 375.0000
BogoMIPS: 80.00
L1d cache: 32K
L1i cache: 32K
L2 cache: 256K
NUMA node0 CPU(s): 0-31
Flags: fp asimd evtstrm aes pmull sha1 sha2 crc32 cpuid
[root@ampere-hr330a-04 ~]# hwloc-calc -N core machine:0
32
[root@ampere-hr330a-04 ~]# lstopo-no-graphics
Machine (127GB total)
Package L#0
NUMANode L#0 (P#0 127GB)
L2 L#0 (256KB)
Die L#0 + L1d L#0 (32KB) + L1i L#0 (32KB) + Core L#0 + PU L#0 (P#0)
Die L#1 + L1d L#1 (32KB) + L1i L#1 (32KB) + Core L#1 + PU L#1 (P#1)
L2 L#1 (256KB)
Die L#2 + L1d L#2 (32KB) + L1i L#2 (32KB) + Core L#2 + PU L#2 (P#2)
Die L#3 + L1d L#3 (32KB) + L1i L#3 (32KB) + Core L#3 + PU L#3 (P#3)
L2 L#2 (256KB)
Die L#4 + L1d L#4 (32KB) + L1i L#4 (32KB) + Core L#4 + PU L#4 (P#4)
Die L#5 + L1d L#5 (32KB) + L1i L#5 (32KB) + Core L#5 + PU L#5 (P#5)
L2 L#3 (256KB)
Die L#6 + L1d L#6 (32KB) + L1i L#6 (32KB) + Core L#6 + PU L#6 (P#6)
Die L#7 + L1d L#7 (32KB) + L1i L#7 (32KB) + Core L#7 + PU L#7 (P#7)
L2 L#4 (256KB)
Die L#8 + L1d L#8 (32KB) + L1i L#8 (32KB) + Core L#8 + PU L#8 (P#8)
Die L#9 + L1d L#9 (32KB) + L1i L#9 (32KB) + Core L#9 + PU L#9 (P#9)
L2 L#5 (256KB)
Die L#10 + L1d L#10 (32KB) + L1i L#10 (32KB) + Core L#10 + PU L#10 (P#10)
Die L#11 + L1d L#11 (32KB) + L1i L#11 (32KB) + Core L#11 + PU L#11 (P#11)
L2 L#6 (256KB)
Die L#12 + L1d L#12 (32KB) + L1i L#12 (32KB) + Core L#12 + PU L#12 (P#12)
Die L#13 + L1d L#13 (32KB) + L1i L#13 (32KB) + Core L#13 + PU L#13 (P#13)
L2 L#7 (256KB)
Die L#14 + L1d L#14 (32KB) + L1i L#14 (32KB) + Core L#14 + PU L#14 (P#14)
Die L#15 + L1d L#15 (32KB) + L1i L#15 (32KB) + Core L#15 + PU L#15 (P#15)
L2 L#8 (256KB)
Die L#16 + L1d L#16 (32KB) + L1i L#16 (32KB) + Core L#16 + PU L#16 (P#16)
Die L#17 + L1d L#17 (32KB) + L1i L#17 (32KB) + Core L#17 + PU L#17 (P#17)
L2 L#9 (256KB)
Die L#18 + L1d L#18 (32KB) + L1i L#18 (32KB) + Core L#18 + PU L#18 (P#18)
Die L#19 + L1d L#19 (32KB) + L1i L#19 (32KB) + Core L#19 + PU L#19 (P#19)
L2 L#10 (256KB)
Die L#20 + L1d L#20 (32KB) + L1i L#20 (32KB) + Core L#20 + PU L#20 (P#20)
Die L#21 + L1d L#21 (32KB) + L1i L#21 (32KB) + Core L#21 + PU L#21 (P#21)
L2 L#11 (256KB)
Die L#22 + L1d L#22 (32KB) + L1i L#22 (32KB) + Core L#22 + PU L#22 (P#22)
Die L#23 + L1d L#23 (32KB) + L1i L#23 (32KB) + Core L#23 + PU L#23 (P#23)
L2 L#12 (256KB)
Die L#24 + L1d L#24 (32KB) + L1i L#24 (32KB) + Core L#24 + PU L#24 (P#24)
Die L#25 + L1d L#25 (32KB) + L1i L#25 (32KB) + Core L#25 + PU L#25 (P#25)
L2 L#13 (256KB)
Die L#26 + L1d L#26 (32KB) + L1i L#26 (32KB) + Core L#26 + PU L#26 (P#26)
Die L#27 + L1d L#27 (32KB) + L1i L#27 (32KB) + Core L#27 + PU L#27 (P#27)
L2 L#14 (256KB)
Die L#28 + L1d L#28 (32KB) + L1i L#28 (32KB) + Core L#28 + PU L#28 (P#28)
Die L#29 + L1d L#29 (32KB) + L1i L#29 (32KB) + Core L#29 + PU L#29 (P#29)
L2 L#15 (256KB)
Die L#30 + L1d L#30 (32KB) + L1i L#30 (32KB) + Core L#30 + PU L#30 (P#30)
Die L#31 + L1d L#31 (32KB) + L1i L#31 (32KB) + Core L#31 + PU L#31 (P#31)
HostBridge
PCIBridge
PCI 0000:01:00.0 (Ethernet)
Net "enp1s0f0"
OpenFabrics "mlx5_0"
PCI 0000:01:00.1 (Ethernet)
Net "enp1s0f1"
OpenFabrics "mlx5_1"
HostBridge
PCIBridge
PCI 0002:01:00.0 (Ethernet)
Net "enP2p1s0"
HostBridge
PCIBridge
PCIBridge
PCI 0007:02:00.0 (VGA)
Block(Disk) "sda"
Misc(MemoryModule)
Misc(MemoryModule)
Misc(MemoryModule)
Misc(MemoryModule)
Misc(MemoryModule)
Misc(MemoryModule)
Misc(MemoryModule)
Misc(MemoryModule)
Misc(MemoryModule)
Misc(MemoryModule)
Misc(MemoryModule)
Misc(MemoryModule)
Misc(MemoryModule)
Misc(MemoryModule)
Misc(MemoryModule)
Misc(MemoryModule)
:::::::::::
:: s390x ::
:::::::::::
[root@ibm-z-137 ~]# rpm -q hwloc
hwloc-2.2.0-2.el8.s390x
[root@ibm-z-137 ~]# lscpu
Architecture: s390x
CPU op-mode(s): 32-bit, 64-bit
Byte Order: Big Endian
CPU(s): 2
On-line CPU(s) list: 0,1
Thread(s) per core: 1
Core(s) per socket: 1
Socket(s) per book: 1
Book(s) per drawer: 1
Drawer(s): 2
NUMA node(s): 1
Vendor ID: IBM/S390
Machine type: 2964
CPU dynamic MHz: 5000
CPU static MHz: 5000
BogoMIPS: 3033.00
Hypervisor: z/VM 6.4.0
Hypervisor vendor: IBM
Virtualization type: full
Dispatching mode: horizontal
L1d cache: 128K
L1i cache: 96K
L2d cache: 2048K
L2i cache: 2048K
L3 cache: 65536K
L4 cache: 491520K
NUMA node0 CPU(s): 0,1
Flags: esan3 zarch stfle msa ldisp eimm dfp edat etf3eh highgprs te vx sie
[root@ibm-z-137 ~]# hwloc-calc -N core machine:0
2
[root@ibm-z-137 ~]# lstopo-no-graphics
Machine (3807MB total)
NUMANode L#0 (P#0 3807MB)
Package L#0 + L2d L#0 (2048KB) + L2i L#0 (2048KB) + L1d L#0 (128KB) + L1i L#0 (96KB) + Core L#0 + PU L#0 (P#0)
Package L#1 + L2d L#1 (2048KB) + L2i L#1 (2048KB) + L1d L#1 (128KB) + L1i L#1 (96KB) + Core L#1 + PU L#1 (P#1)
Block "dasda"
Block "dasdb"
Net "enc8000"
Since the problem described in this bug report should be resolved in a recent advisory, it has been closed with a resolution of ERRATA. For information on the advisory (hwloc bug fix and enhancement update), and where to find the updated files, follow the link below. If the solution does not work for you, open a new bug report. https://access.redhat.com/errata/RHBA-2021:4416 |