Hi,
Here is more on testing with simulated 4000 disks.
I mounted 4000 simulated (scsi_debug) disks. But
when I tried to do IO on 200 of them (just reads),
system is 100% busy. Here are the vmstat,
10-sec profile output and sysrq-t output.
I am wondering why 100% sys ?
vmstat:
--------
178 23 8 0 3381260 60392 147608 0 0 88786 10 1015 11314 0 100 0
177 24 8 0 3381252 60392 147608 0 0 88947 20 1022 11335 0 100 0
182 19 8 0 3381188 60400 147600 0 0 89301 16 1017 11368 0 100 0
179 23 8 0 3381180 60400 147600 0 0 89348 5 1011 11367 0 100 0
176 26 8 0 3381116 60400 147600 0 0 88906 3 1008 11311 0 100 0
184 18 8 0 3381180 60400 147600 0 0 88734 5 1008 11312 0 100 0
10-second profile output:
----------------------------
c0109224 ret_from_intr 1 0.0357
c01105e0 restore_fpu 1 0.0312
c0110a50 save_i387 1 0.0052
c0114820 flush_tlb_mm 1 0.0089
c01160c0 do_irq_balance 1 0.0007
c011d8c0 prepare_to_wait_exclusive 1 0.0063
c011dd50 copy_mm 1 0.0009
c011e300 copy_files 1 0.0012
c0120ee0 release_task 1 0.0023
c0121ad0 exit_notify 1 0.0006
c0124080 tasklet_action 1 0.0045
c0127b80 del_timer_sync 1 0.0063
c012c0d0 do_sigaction 1 0.0010
c012c7a0 sys_rt_sigaction 1 0.0048
c01187f0 pgd_ctor 2 0.0417
c011d820 prepare_to_wait 2 0.0125
c011d960 finish_wait 2 0.0114
c0123430 sys_time 2 0.0250
c0127690 add_timer_on 2 0.0096
c0128490 schedule_timeout 2 0.0104
c0105000 _stext 4 0.0357
c01092fc syscall_call 4 0.3636
c01188b0 do_page_fault 4 0.0038
c0107980 get_wchan 5 0.0446
c010b270 handle_IRQ_event 5 0.0521
c011d680 add_wait_queue 5 0.0347
c01197d0 kunmap_atomic 10 0.0893
c011d7a0 remove_wait_queue 10 0.0781
c011fb10 do_syslog 10 0.0079
c011b440 __wake_up 46 0.2396
c0109307 syscall_exit 55 5.0000
c011d4e0 __might_sleep 104 1.0833
c01092d0 system_call 180 4.0909
c01280c0 run_timer_softirq 323 0.6309
c011c910 io_schedule 324 5.0625
c01275b0 add_timer 334 1.4911
c0123d60 current_kernel_time 608 7.6000
c0123e00 do_softirq 782 3.7596
c011ae80 schedule 2205 1.6406
00000000 total 5044 0.0310
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Mon Apr 07 2003 - 22:00:32 EST