[Moosefs-users] mfschunkserver eats 100% CPU

[Davies L. <dav...@gm...>]

Hi，

Found one bug of mfschunkserver, it eats 100% CPU without any activities.

strace shows:

[pid  7754] gettimeofday({1320117856, 191716}, NULL) = 0
[pid  7754] read(222, 0x7f397c978d08, 408) = -1 EAGAIN (Resource
temporarily unavailable)
[pid  7754] read(29, 0x7f397cad2268, 29368) = -1 EAGAIN (Resource
temporarily unavailable)
[pid  7754] poll([{fd=12, events=POLLIN}, {fd=11, events=POLLIN},
{fd=6, events=POLLIN}, {fd=9, events=POLLIN}, {fd=224,
events=POLLIN|POLLOUT}, {fd=222, events=POLLIN}, {fd=125,
events=POLLIN|POLLOUT}, {fd=29, events=POLLIN}], 8, 50) = 2 ([{fd=224,
revents=POLLOUT}, {fd=125, revents=POLLOUT}])
[pid  7754] gettimeofday({1320117856, 192052}, NULL) = 0
[pid  7754] read(222, 0x7f397c978d08, 408) = -1 EAGAIN (Resource
temporarily unavailable)
[pid  7754] read(29, 0x7f397cad2268, 29368) = -1 EAGAIN (Resource
temporarily unavailable)
[pid  7754] poll([{fd=12, events=POLLIN}, {fd=11, events=POLLIN},
{fd=6, events=POLLIN}, {fd=9, events=POLLIN}, {fd=224,
events=POLLIN|POLLOUT}, {fd=222, events=POLLIN}, {fd=125,
events=POLLIN|POLLOUT}, {fd=29, events=POLLIN}], 8, 50) = 2 ([{fd=224,
revents=POLLOUT}, {fd=125, revents=POLLOUT}])
[pid  7754] gettimeofday({1320117856, 192404}, NULL) = 0
[pid  7754] read(222, 0x7f397c978d08, 408) = -1 EAGAIN (Resource
temporarily unavailable)
[pid  7754] read(29, 0x7f397cad2268, 29368) = -1 EAGAIN (Resource
temporarily unavailable)
[pid  7754] poll([{fd=12, events=POLLIN}, {fd=11, events=POLLIN},
{fd=6, events=POLLIN}, {fd=9, events=POLLIN}, {fd=224,
events=POLLIN|POLLOUT}, {fd=222, events=POLLIN}, {fd=125,
events=POLLIN|POLLOUT}, {fd=29, events=POLLIN}], 8, 50) = 2 ([{fd=224,
revents=POLLOUT}, {fd=125, revents=POLLOUT}])
[pid  7754] gettimeofday({1320117856, 192740}, NULL) = 0
[pid  7754] read(222, 0x7f397c978d08, 408) = -1 EAGAIN (Resource
temporarily unavailable)
[pid  7754] read(29, 0x7f397cad2268, 29368) = -1 EAGAIN (Resource
temporarily unavailable)
[pid  7754] poll([{fd=12, events=POLLIN}, {fd=11, events=POLLIN},
{fd=6, events=POLLIN}, {fd=9, events=POLLIN}, {fd=224,
events=POLLIN|POLLOUT}, {fd=222, events=POLLIN}, {fd=125,
events=POLLIN|POLLOUT}, {fd=29, events=POLLIN}], 8, 50) = 2 ([{fd=224,
revents=POLLOUT}, {fd=125, revents=POLLOUT}])
[pid  7754] gettimeofday({1320117856, 193063}, NULL) = 0
[pid  7754] read(222, 0x7f397c978d08, 408) = -1 EAGAIN (Resource
temporarily unavailable)
[pid  7754] read(29, 0x7f397cad2268, 29368) = -1 EAGAIN (Resource
temporarily unavailable)
[pid  7754] poll([{fd=12, events=POLLIN}, {fd=11, events=POLLIN},
{fd=6, events=POLLIN}, {fd=9, events=POLLIN}, {fd=224,
events=POLLIN|POLLOUT}, {fd=222, events=POLLIN}, {fd=125,
events=POLLIN|POLLOUT}, {fd=29, events=POLLIN}], 8, 50) = 2 ([{fd=224,
revents=POLLOUT}, {fd=125, revents=POLLOUT}])
[pid  7754] gettimeofday({1320117856, 193386}, NULL) = 0
[pid  7754] read(222, 0x7f397c978d08, 408) = -1 EAGAIN (Resource
temporarily unavailable)
[pid  7754] read(29, 0x7f397cad2268, 29368) = -1 EAGAIN (Resource
temporarily unavailable)
[pid  7754] poll([{fd=12, events=POLLIN}, {fd=11, events=POLLIN},
{fd=6, events=POLLIN}, {fd=9, events=POLLIN}, {fd=224,
events=POLLIN|POLLOUT}, {fd=222, events=POLLIN}, {fd=125,
events=POLLIN|POLLOUT}, {fd=29, events=POLLIN}], 8, 50) = 2 ([{fd=224,
revents=POLLOUT}, {fd=125, revents=POLLOUT}])
[pid  7754] gettimeofday({1320117856, 193710}, NULL) = 0
[pid  7754] read(222, 0x7f397c978d08, 408) = -1 EAGAIN (Resource
temporarily unavailable)
[pid  7754] read(29, 0x7f397cad2268, 29368) = -1 EAGAIN (Resource
temporarily unavailable)
[pid  7754] poll([{fd=12, events=POLLIN}, {fd=11, events=POLLIN},
{fd=6, events=POLLIN}, {fd=9, events=POLLIN}, {fd=224,
events=POLLIN|POLLOUT}, {fd=222, events=POLLIN}, {fd=125,
events=POLLIN|POLLOUT}, {fd=29, events=POLLIN}], 8, 50) = 2 ([{fd=224,
revents=POLLOUT}, {fd=125, revents=POLLOUT}])
[pid  7754] gettimeofday({1320117856, 194033}, NULL) = 0
[pid  7754] read(222, 0x7f397c978d08, 408) = -1 EAGAIN (Resource
temporarily unavailable)
[pid  7754] read(29, 0x7f397cad2268, 29368) = -1 EAGAIN (Resource
temporarily unavailable)
[pid  7754] poll([{fd=12, events=POLLIN}, {fd=11, events=POLLIN},
{fd=6, events=POLLIN}, {fd=9, events=POLLIN}, {fd=224,
events=POLLIN|POLLOUT}, {fd=222, events=POLLIN}, {fd=125,
events=POLLIN|POLLOUT}, {fd=29, events=POLLIN}], 8, 50) = 2 ([{fd=224,
revents=POLLOUT}, {fd=125, revents=POLLOUT}])
[pid  7754] gettimeofday({1320117856, 194893}, NULL) = 0
[pid  7754] read(222, 0x7f397c978d08, 408) = -1 EAGAIN (Resource
temporarily unavailable)
[pid  7754] read(29, 0x7f397cad2268, 29368) = -1 EAGAIN (Resource
temporarily unavailable)
[pid  7754] poll([{fd=12, events=POLLIN}, {fd=11, events=POLLIN},
{fd=6, events=POLLIN}, {fd=9, events=POLLIN}, {fd=224,
events=POLLIN|POLLOUT}, {fd=222, events=POLLIN}, {fd=125,
events=POLLIN|POLLOUT}, {fd=29, events=POLLIN}], 8, 50) = 2 ([{fd=224,
revents=POLLOUT}, {fd=125, revents=POLLOUT}])

It seems that fd 224 and 125 are ready , but it read fd 29 and 222,
with -1, then fall into infinite loop.

-- 
 - Davies