Download presentation
Presentation is loading. Please wait.
Published byMarion Chase Modified over 9 years ago
1
Preliminary results Monarc Testbeds Working Group A.Brunengo (INFN- Ge), A.Ghiselli (INFN-Cnaf), L.Luminari (INFN-Roma1), L.Perini (INFN-Mi), S.Resconi (INFN-Mi), M.Sgaravatto (INFN-Pd), C.Vistoli (INFN-Cnaf)
2
14 September 1999Preliminary Results Configurations zATLFast++ stress tests: increasing number of concurrent jobs with read access to the Data Base zTested configurations: ySingle workstation (without AMS server) yLAN (Ethernet and Gigabit Ethernet) yWAN zMeasurements: yClient side: CPU, Memory, Wall clock time yServer side: CPU, Memory, Throughput
3
14 September 1999Preliminary Results Test 1 1000BaseT sunlab1gsun Server Client sunlab1, gsun: Sun Ultra5, 333 MHz, 128 MB, Solaris 2.7
4
14 September 1999Preliminary Results
5
14 September 1999Preliminary Results
6
14 September 1999Preliminary Results Test 2 10BaseT cmssun4vlsi06 Server Client cmssun4: Sun Ultra10, 333 MHz, 128 MB, Solaris 2.6 vlsi06: Sun SPARC20, 125 MHz, 128 MB, Solaris 2.6 (fast server, slow client)
7
14 September 1999Preliminary Results
8
14 September 1999Preliminary Results
9
14 September 1999Preliminary Results Test 3 2 Mbps sunlab1monarc01 ServerClient sunlab1: Sun Ultra5, 333 MHz, 128 MB, Solaris 2.7 monarc01: Sun Enterprise 450 - 4 X 400 MHz, 512 MB, Solaris 2.6
10
14 September 1999Preliminary Results
11
14 September 1999Preliminary Results
12
14 September 1999Preliminary Results Comments: zTest 1: yClient CPU: 100 % used with only 5 jobs yServer CPU: 100 % used with 50 jobs yCrashes after 50 concurrent jobs (causes to be investigated, swap area + server problems?) yServer CPU: 100 % used (system higher than user) when client jobs start crashing
13
14 September 1999Preliminary Results Comments: zTest 2: yClient CPU: 80 % used with 20 jobs or more yServer CPU: 30 % used with 60 jobs yCrashes after 70 concurrent jobs (causes to be investigated, swap area on client + ?) yServer CPU: 100 % used (system higher than user) when client jobs start crashing
14
14 September 1999Preliminary Results Comments: zTest 3: yClient CPU: 5% used yServer CPU: 10 % used yOccasional crashes with 10 and 15 concurrent jobs
15
14 September 1999Preliminary Results
16
14 September 1999Preliminary Results
17
14 September 1999Preliminary Results
18
14 September 1999Preliminary Results
19
14 September 1999Preliminary Results
20
14 September 1999Preliminary Results
21
14 September 1999Preliminary Results Comments: zWall time for 1 job with 10 concurrent jobs ytest 1: 400 sec. (1Gb/sec) x(2.5 times ethernet result) ytest 2: 1000 sec. (10Mb/sec) x(6 times 2Mb/s result) ytest 3: 6000 sec. (2Mb/sec) z1Gb/sec max. throughput only 25Mbit/sec
22
14 September 1999Preliminary Results Test 4 Server Clients sunlab1, gsun, cmssun4, atlsun1, atlas4: Sun Ultra5/10, 333 MHz, 128 MB vlsi06: Sun SPARC20, 125 MHz, 128 MB monarc01: Sun Enterprise 450, 4X 400 MHz, 512 MB 1000BaseT 2 Mbps 8 Mbps sunlab1 cmssun4vlsi06atlsun1atlas4 monarc01
23
14 September 1999Preliminary Results
24
14 September 1999Preliminary Results
25
14 September 1999Preliminary Results
26
14 September 1999Preliminary Results
27
14 September 1999Preliminary Results Test 4 Summary zClient CPU: never 100 % used zServer CPU: never 100 % used zMany jobs crash: “Timeout with AMS Server” zWall clock time for workstation connected with gigabit ethernet very high (i.e. for 10 jobs >1000’; 400’ without other clients in WAN): slow clients degrade performances on fast clients ???
28
14 September 1999Preliminary Results Future work zTests on LAN (100BaseT) with multiple clients zTests with write access to the database zFurther tests with QoS
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.