AFS Server Performance Comparisons Bo Tretta Kimball Jet Propulsion Laboratory Information Services - FIL Service http: //fil. jpl. nasa. gov SLAC AFS Best Practices Workshop March 24, 2004 JPLIS-FIL Server Performance Comparisons
n Performance benchmarks of various hardware configurations n Range of ages for hardware n Different AFS versions n Most hardware is already in operation and limits the testing we can perform n Partitioned network n Testing was performed on both sides of the network firewall. n Operational Implications JPLIS-FIL Server Performance Comparisons 22
Can we use less expensive hardware and still meet performance goals? JPLIS-FIL Server Performance Comparisons 33
Cell Configuration n At the Jet Propulsion Laboratory in Pasadena, the AFS cell is configured with a firewall that splits the database servers as well as the fileservers. JPLIS-FIL Server Performance Comparisons 44
Internet Clients Test Cell Firewall afs 06, afs 07, afs 20 Flight Ops Firewall Database Servers File Servers Clients Database Servers JPLIS-FIL Database Servers Server Performance Comparisons File Servers 55
Benchmarking n First assessment of Open. AFS fileserver hardware using Andrew Benchmark. n Initial goal: Determine if further assessment of inexpensive fileservers is warranted – without wasting time and resources in the initial trials. JPLIS-FIL Server Performance Comparisons 66
Methodology n Compare Andrew Benchmark results from inexpensive Intel-based fileservers with results from existing Sun Solaris fileservers. JPLIS-FIL Server Performance Comparisons 77
JPLIS-FIL Server Performance Comparisons 88
Performance test from a client outside of the firewall JPLIS-FIL Server Performance Comparisons 99
Observations n afslinux 02 was not performing the same as afslinux 01 which is identical hardware. n After examining afslinux 02, it was found that the L 2 cache module was not installed. n The subsequent tests were performed with the L 2 cache module installed. JPLIS-FIL Server Performance Comparisons 10 10
Performance test from a client outside of the firewall with L 2 cache installed JPLIS-FIL Server Performance Comparisons 11 11
Performance test from a client inside of the firewall. Did not test to the test cell systems because the production servers can not be modified. JPLIS-FIL Server Performance Comparisons 12 12
Conclusions n Inexpensive hardware for Open. AFS fileservers is not ruled out. n Follow on: Proceed to stress testing to determine feasible transaction rates. JPLIS-FIL Server Performance Comparisons 13 13
Examining a Myth n Expensive “big iron” is frequently purchased because “we know it will get the job done. ” n The result can be a collection of a small number of expensive fileservers. JPLIS-FIL Server Performance Comparisons 14 14
But… n A larger number of inexpensive fileservers may provide equivalent performance. n It may be that the initial investment in the larger number of less expensive fileservers does not significantly differ from the smaller collection of “big iron” for a given aggregate transaction load. JPLIS-FIL Server Performance Comparisons 15 15
Benefits n Initial cost aside, the “more and cheaper fileserver” approach offers: w Inexpensive incremental increase in capacity. w Cost effective redundancy. w Better manageability. JPLIS-FIL Server Performance Comparisons 16 16
Cost effective redundancy n If a fileserver fails, it can be immediately replaced, with similar (or identical) hardware kept for this purpose. JPLIS-FIL Server Performance Comparisons 17 17
Better manageability n We theorize that it will be easier to take a machine out of service when it houses less RW data. JPLIS-FIL Server Performance Comparisons 18 18
Assumption n That the time required to move the Read/Write volumes in the Open. AFS namei implementation does not increase to a point that volume moves are truly abysmal. JPLIS-FIL Server Performance Comparisons 19 19
Benefit n It will be easier to recover from unexpected hardware failure. It’s easier to justify a “spare server” at $10, 000 than at $100, 000. JPLIS-FIL Server Performance Comparisons 20 20
Contact Information Bo Tretta – botretta@jpl. nasa. gov Kimball – Kimball@jpl. nasa. gov JPLIS-FIL Server Performance Comparisons 21 21
Скачать презентацию AFS Server Performance Comparisons Bo Tretta Kimball Jet
f4e8c3c5f458186bfc8a495eb75f9054.ppt