10-2-18

Owned by Stephen Willson (Unlicensed)
Last updated: Aug 26, 2021 by Jelon Anderson (Deactivated)Version comment

Tip of master, commit 32aeb8b47ae0bdd69da80d3b51026865226295b1

All tests run with ofi+psm2, ib0.

daos_test: Run with 8 server (boro-[4-11]), 2 client (boro-12,16). Killed servers, cleaned /mnt/daos in between runs listed below.

Tests requiring pool to be created via dmg used 4GB pool. These used boro-12 as client.

mpich tests used boro-4 as server, boro-12 as client, with a 1GB pool.

Test Results

daos_test

Separate runs with cleanup in between:

  • -mpcCAeioRdOr - PASS

daosperf

1K Records

CREDITS=1

[sdwillso@boro-4 daos_m]$ orterun --mca mtl ^psm2,ofi -np 1 -quiet --hostfile ~/scripts/host.cli.1 --ompi-server file:~/scripts/uri.txt -x DD_SUBSYS= -x DD_MASK= -x D_LOG_FILE=/tmp/daos_perf.log daos_perf -T daos -P 2G -d 1 -a 200 -r 1000 -s 1K -C 1 -t -z
ModuleCmd_Load.c(213):ERROR:105: Unable to locate a modulefile for 'openmpi-x86_64'
Test :
	DAOS (full stack)
Parameters :
	pool size     : 2048 MB
	credits       : 1 (sync I/O for -ve)
	obj_per_cont  : 1 x 1 (procs)
	dkey_per_obj  : 1
	akey_per_dkey : 200
	recx_per_akey : 1000
	value type    : single
	value size    : 1024
	zero copy     : yes
	overwrite     : yes
	verify fetch  : no
	VOS file      : <NULL>
87426454: rank 1 became pool service leader 0
Started...
update successfully completed:
	duration : 111.352682 sec
	bandwith : 1.754      MB/sec
	rate     : 1796.10    IO/sec
	latency  : 556.763    us (nonsense if credits > 1)
Duration across processes:
	MAX duration : 111.352682 sec
	MIN duration : 111.352682 sec
	Average duration : 111.352682 sec
87426454: rank 1 no longer pool service leader 0

CREDITS=8

CART-496 - Getting issue details... STATUS

4K Records

CREDITS=1

CART-496 - Getting issue details... STATUS

IOR, 50GB pool, data verification enabled

[sdwillso@boro-4 daos_m]$ orterun -x FI_PSM2_DISCONNECT=1 -N 1 --hostfile ~/hostlists/daos_client_hostlist --mca mtl ^psm2,ofi  --ompi-server file:~/scripts/uri.txt ior -v -W -i 1 -a DAOS -w -o `uuidgen` -b 5g -t 1m -- -p 9c8b96e6-964d-4c07-bfbc-aac53ec066e9 -v 1 -r 1m -s 1m -c 1024 -a 16 -o LARGE -e 1
ModuleCmd_Load.c(213):ERROR:105: Unable to locate a modulefile for 'openmpi-x86_64'
ior WARNING: assuming POSIX-based backend for DAOS statfs call.
ior WARNING: assuming POSIX-based backend for DAOS mkdir call.
ior WARNING: assuming POSIX-based backend for DAOS rmdir call.
ior WARNING: assuming POSIX-based backend for DAOS access call.
ior WARNING: assuming POSIX-based backend for DAOS stat call.
ior WARNING: assuming POSIX-based backend for DAOS statfs call.
ior WARNING: assuming POSIX-based backend for DAOS mkdir call.
ior WARNING: assuming POSIX-based backend for DAOS rmdir call.
ior WARNING: assuming POSIX-based backend for DAOS access call.
ior WARNING: assuming POSIX-based backend for DAOS stat call.
IOR-3.1.0: MPI Coordinated Test of Parallel I/O
Began               : Tue Oct  2 22:31:12 2018
Command line        : ior -v -W -i 1 -a DAOS -w -o 1c36ddfa-51c6-43db-96a0-934696fbc0f9 -b 5g -t 1m -- -p 9c8b96e6-964d-4c07-bfbc-aac53ec066e9 -v 1 -r 1m -s 1m -c 1024 -a 16 -o LARGE -e 1
Machine             : Linux boro-12.boro.hpdd.intel.com
Start time skew across all tasks: 14690266.15 sec
TestID              : 0
StartTime           : Tue Oct  2 22:31:12 2018
Path                : /home/sdwillso/daos_m
FS                  : 3.8 TiB   Used FS: 14.0%   Inodes: 250.0 Mi   Used Inodes: 3.0%
Participating tasks: 2
[0] WARNING: USING daosStripeMax CAUSES READS TO RETURN INVALID DATA

Options: 
api                 : DAOS
apiVersion          : DAOS
test filename       : 1c36ddfa-51c6-43db-96a0-934696fbc0f9
access              : single-shared-file
type                : independent
segments            : 1
ordering in a file  : sequential
ordering inter file : no tasks offsets
tasks               : 2
clients per node    : 1
repetitions         : 1
xfersize            : 1 MiB
blocksize           : 5 GiB
aggregate filesize  : 10 GiB

Results: 

access    bw(MiB/s)  block(KiB) xfer(KiB)  open(s)    wr/rd(s)   close(s)   total(s)   iter
------    ---------  ---------- ---------  --------   --------   --------   --------   ----
Commencing write performance test: Tue Oct  2 22:31:14 2018
write     4479       5242880    1024.00    0.044826   2.21       0.027054   2.29       0   
Verifying contents of the file(s) just written.
Tue Oct  2 22:31:16 2018

remove    -          -          -          -          -          -          0.000068   0   
Max Write: 4479.36 MiB/sec (4696.95 MB/sec)

Summary of all tests:
Operation   Max(MiB)   Min(MiB)  Mean(MiB)     StdDev   Max(OPs)   Min(OPs)  Mean(OPs)     StdDev    Mean(s) Test# #Tasks tPN reps fPP reord reordoff reordrand seed segcnt   blksiz    xsize aggs(MiB)   API RefNum
write        4479.36    4479.36    4479.36       0.00    4479.36    4479.36    4479.36       0.00    2.28604     0      2   1    1   0     0        1         0    0      1 5368709120  1048576   10240.0 DAOS      0
Finished            : Tue Oct  2 22:31:25 2018

daos_bench

kv-idx-update

Time: 614.043987 seconds (1628.547826 ops per second)

DAOS-1243 - Getting issue details... STATUS 

[sdwillso@boro-4 daos_m]$ orterun -np 1 --mca mtl ^psm2,ofi  --hostfile ~/hostlists/daos_client_hostlist --ompi-server file:~/scripts/uri.txt daosbench --test=kv-idx-update --testid=1 --svc=1 --dpool=32b9e029-a757-45c1-a1fc-cf8b346fc18f --container=`uuidgen` --object-class=tiny --aios=32 --indexes=1000000
ModuleCmd_Load.c(213):ERROR:105: Unable to locate a modulefile for 'openmpi-x86_64'
================================
DAOSBENCH (KV)
Started at
Tue Oct  2 22:44:24 2018
=================================
===============================
Test Setup
---------------
Test: kv-idx-update
DAOS pool :32b9e029-a757-45c1-a1fc-cf8b346fc18f
DAOS container :6f4c6523-5fc0-42e4-a9b7-8ead4463d9ea
Value buffer size: 64
Number of processes: 1
Number of indexes/process: 1000000
Number of asynchronous I/O: 32
===============================

kv-idx-update
Time: 614.043987 seconds (1628.547826 ops per second)
daosbench:0:src/tests/daosbench.c:765: Unknown error 2001: Container destroy failed

kv-dkey-update

Time: 0.137489 seconds (727.331513 ops per second)
[sdwillso@boro-4 daos_m]$ orterun -np 1 --mca mtl ^psm2,ofi  --hostfile ~/hostlists/daos_client_hostlist --ompi-server file:~/scripts/uri.txt daosbench --test=kv-dkey-update --testid=1 --svc=1 --dpool=fa67ca50-bbe9-40be-ae42-9a384fa9fd37 --container=`uuidgen` --object-class=tiny --aios=32 --indexes=1000000
ModuleCmd_Load.c(213):ERROR:105: Unable to locate a modulefile for 'openmpi-x86_64'
================================
DAOSBENCH (KV)
Started at
Tue Oct  2 22:56:49 2018
=================================
===============================
Test Setup
---------------
Test: kv-dkey-update
DAOS pool :fa67ca50-bbe9-40be-ae42-9a384fa9fd37
DAOS container :333d6f06-b3f8-4589-b841-57a76d9fea47
Value buffer size: 64
Number of processes: 1
Number of keys/process: 100
Number of asynchronous I/O: 32
===============================
kv-dkey-update
Time: 0.137489 seconds (727.331513 ops per second)

Ended at Tue Oct  2 22:56:51 2018

kv-akey-update

Time: 0.070309 seconds (1422.285973 ops per second)
[sdwillso@boro-4 daos_m]$ orterun -np 1 --mca mtl ^psm2,ofi  --hostfile ~/hostlists/daos_client_hostlist --ompi-server file:~/scripts/uri.txt daosbench --test=kv-akey-update --testid=1 --svc=1 --dpool=9327cb08-5121-4586-b58d-22160e2d11d1 --container=`uuidgen` --object-class=tiny --aios=32 --indexes=1000000
ModuleCmd_Load.c(213):ERROR:105: Unable to locate a modulefile for 'openmpi-x86_64'
================================
DAOSBENCH (KV)
Started at
Tue Oct  2 22:58:09 2018
=================================
===============================
Test Setup
---------------
Test: kv-akey-update
DAOS pool :9327cb08-5121-4586-b58d-22160e2d11d1
DAOS container :c0459b84-5fa0-46fa-a372-5c4cab702b80
Value buffer size: 64
Number of processes: 1
Number of keys/process: 100
Number of asynchronous I/O: 32
===============================
kv-akey-update
Time: 0.070309 seconds (1422.285973 ops per second)

Ended at Tue Oct  2 22:58:11 2018

kv-dkey-fetch

Time: 0.071141 seconds (1405.663142 ops per second)
[sdwillso@boro-4 daos_m]$ orterun -np 1 --mca mtl ^psm2,ofi  --hostfile ~/hostlists/daos_client_hostlist --ompi-server file:~/scripts/uri.txt daosbench --test=kv-dkey-fetch --testid=1 --svc=1 --dpool=9c67989d-19e8-4b2c-a4c3-6c6ec6df8196 --container=`uuidgen` --object-class=tiny --aios=32 --indexes=1000000
ModuleCmd_Load.c(213):ERROR:105: Unable to locate a modulefile for 'openmpi-x86_64'
================================
DAOSBENCH (KV)
Started at
Tue Oct  2 22:59:12 2018
=================================
===============================
Test Setup
---------------
Test: kv-dkey-fetch
DAOS pool :9c67989d-19e8-4b2c-a4c3-6c6ec6df8196
DAOS container :4fd98e33-ef0d-4d6c-a8a1-5b17fcd47aef
Value buffer size: 64
Number of processes: 1
Number of keys/process: 100
Number of asynchronous I/O: 32
===============================
kv-dkey-fetch
Time: 0.071141 seconds (1405.663142 ops per second)

Ended at Tue Oct  2 22:59:13 2018

kv-akey-fetch

Time: 0.042142 seconds (2372.908955 ops per second)
[sdwillso@boro-4 daos_m]$ orterun -np 1 --mca mtl ^psm2,ofi  --hostfile ~/hostlists/daos_client_hostlist --ompi-server file:~/scripts/uri.txt daosbench --test=kv-akey-fetch --testid=1 --svc=1 --dpool=1d714278-cef5-4cf8-b9ad-273a47dc2b3f --container=`uuidgen` --object-class=tiny --aios=32 --indexes=1000000
ModuleCmd_Load.c(213):ERROR:105: Unable to locate a modulefile for 'openmpi-x86_64'
================================
DAOSBENCH (KV)
Started at
Tue Oct  2 23:00:16 2018
=================================
===============================
Test Setup
---------------
Test: kv-akey-fetch
DAOS pool :1d714278-cef5-4cf8-b9ad-273a47dc2b3f
DAOS container :91781881-2477-47d5-8bd7-2c1f22f127c4
Value buffer size: 64
Number of processes: 1
Number of keys/process: 100
Number of asynchronous I/O: 32
===============================
kv-akey-fetch
Time: 0.042142 seconds (2372.908955 ops per second)

Ended at Tue Oct  2 23:00:17 2018

CaRT Self-Test

Small IO

[sdwillso@boro-4 daos_m]$ orterun -np 1 -ompi-server file:~/scripts/uri.txt self_test --group-name daos_server --endpoint 0:0 --message-sizes 0 --max-inflight-rpcs 16 --repetitions 100000
Adding endpoints:
  ranks: 0 (# ranks = 1)
  tags: 0 (# tags = 1)
Warning: No --master-endpoint specified; using this command line application as the master endpoint
Self Test Parameters:
  Group name to test against: daos_server
  # endpoints:                1
  Message sizes:              [(0-EMPTY 0-EMPTY)]
  Buffer addresses end with:  <Default>
  Repetitions per size:       100000
  Max inflight RPCs:          16

host boro-4.boro.hpdd.intel.com finished self_test duration 19.502825 S.
##################################################
Results for message size (0-EMPTY 0-EMPTY) (max_inflight_rpcs = 16):

Master Endpoint 0:0
-------------------
	RPC Bandwidth (MB/sec): 0.00
	RPC Throughput (RPCs/sec): 5127
	RPC Latencies (us):
		Min    : 1126
		25th  %: 3051
		Median : 3080
		75th  %: 3112
		Max    : 17075
		Average: 3087
		Std Dev: 100.32
	RPC Failures: 0

	Endpoint results (rank:tag - Median Latency (us)):
		0:0 - 3080

Large IO Bulk PUT

[sdwillso@boro-4 daos_m]$ orterun -np 1 -ompi-server file:~/scripts/uri.txt self_test --group-name daos_server --endpoint 0:0 --message-sizes "0 b1048576" --max-inflight-rpcs 16 --repetitions 1000
Adding endpoints:
  ranks: 0 (# ranks = 1)
  tags: 0 (# tags = 1)
Warning: No --master-endpoint specified; using this command line application as the master endpoint
Self Test Parameters:
  Group name to test against: daos_server
  # endpoints:                1
  Message sizes:              [(0-EMPTY 1048576-BULK_PUT)]
  Buffer addresses end with:  <Default>
  Repetitions per size:       1000
  Max inflight RPCs:          16

host boro-4.boro.hpdd.intel.com finished self_test duration 0.338606 S.
##################################################
Results for message size (0-EMPTY 1048576-BULK_PUT) (max_inflight_rpcs = 16):

Master Endpoint 0:0
-------------------
	RPC Bandwidth (MB/sec): 2953.28
	RPC Throughput (RPCs/sec): 2953
	RPC Latencies (us):
		Min    : 2272
		25th  %: 5332
		Median : 5361
		75th  %: 5401
		Max    : 6320
		Average: 5352
		Std Dev: 255.75
	RPC Failures: 0

	Endpoint results (rank:tag - Median Latency (us)):
		0:0 - 5361

Large IO Bulk GET

[sdwillso@boro-4 daos_m]$ orterun -np 1 -ompi-server file:~/scripts/uri.txt self_test --group-name daos_server --endpoint 0:0 --message-sizes “b1048576 0” --max-inflight-rpcs 16 --repetitions 1000
Adding endpoints:
  ranks: 0 (# ranks = 1)
  tags: 0 (# tags = 1)
Warning: No --master-endpoint specified; using this command line application as the master endpoint
Self Test Parameters:
  Group name to test against: daos_server
  # endpoints:                1
  Message sizes:              [(1048576-BULK_GET 1048576-BULK_PUT)]
  Buffer addresses end with:  <Default>
  Repetitions per size:       1000
  Max inflight RPCs:          16

host boro-4.boro.hpdd.intel.com finished self_test duration 0.548675 S.
##################################################
Results for message size (1048576-BULK_GET 1048576-BULK_PUT) (max_inflight_rpcs = 16):

Master Endpoint 0:0
-------------------
	RPC Bandwidth (MB/sec): 3645.14
	RPC Throughput (RPCs/sec): 1823
	RPC Latencies (us):
		Min    : 3590
		25th  %: 8701
		Median : 8770
		75th  %: 8829
		Max    : 12066
		Average: 8705
		Std Dev: 598.18
	RPC Failures: 0

	Endpoint results (rank:tag - Median Latency (us)):
		0:0 - 8770

mpich tests