Difference between revisions of "Infiniband testing 19-dec-2012"
From GlueXWiki
m |
m |
||
| Line 18: | Line 18: | ||
* Single remote consumer running in blaster mode gets events at 74 kHz (4.4 Gbit/s), 75% cpu. | * Single remote consumer running in blaster mode gets events at 74 kHz (4.4 Gbit/s), 75% cpu. | ||
** producer 25%, et 23%. | ** producer 25%, et 23%. | ||
| − | * Two consumers 148 kHz aggregate (8.8 Gbit/s), 75% cpu. | + | * Two consumers (different nodes) 148 kHz aggregate (8.8 Gbit/s), 75% cpu. |
** producer 48%, et 42%. | ** producer 48%, et 42%. | ||
* Three consumers 188 kHz (11.1 Gbit/s), 63% cpu. | * Three consumers 188 kHz (11.1 Gbit/s), 63% cpu. | ||
** producer 60%, et 58%. | ** producer 60%, et 58%. | ||
| + | * Adding more consumers on the nodes doesn't change aggregate bandwidth. | ||
Revision as of 10:22, 18 December 2012
Testing Infiniband in Rack Room
Setup
- Have 4 nodes, 16 cores each.
- Each node has one GBit and one Infiniband port.
- Infiniband switch rated at 20 Gbit/sec.
- Running IP over Infiniband, which decreases effective throughput.
- Run ET system and event producer on one node, run remote consumers on the others.
- Event producer continually reads from file and inserts events into ET system.
- Some consumers just get events and dump them (blaster mode), others process the events.
- Note: when using Ethernet instead of IB got about 95% bandwidth of a Gbit link (950 Mbits/sec).
Observations
- Single (local) producer can insert events at 380 kHz, avg event size about 7.4 kBytes.
- producer uses 98% of one core, et system uses 8%.
- Single remote consumer running in blaster mode gets events at 74 kHz (4.4 Gbit/s), 75% cpu.
- producer 25%, et 23%.
- Two consumers (different nodes) 148 kHz aggregate (8.8 Gbit/s), 75% cpu.
- producer 48%, et 42%.
- Three consumers 188 kHz (11.1 Gbit/s), 63% cpu.
- producer 60%, et 58%.
- Adding more consumers on the nodes doesn't change aggregate bandwidth.
