search for: readv

...tl(11, F_SETLKW, {type=F_UNLCK, whence=SEEK_SET, start=6032, len=1}) = 0 writev(44, [{"\5\0\2\3\20\0\0\0P\0\20\0\270])\1\30\0\0\0\0\0\0\0\271\366\345\26sb\276\220"..., 80}], 1) = 80 epoll_wait(9, {{EPOLLIN, {u32=1836735552, u64=140507396856896}}}, 1, 30000) = 1 readv(44, [{"\5\0\0\3\20\0\0\0P\0", 10}], 1) = 10 readv(44, [{"\20\0\271])\1\26\0\0\0\0\0\24\0\20\203W\342\366\230\256RH\300.\31\346\327\24k'|"..., 70}], 1) = 70 gettimeofday({1399964809, 80707}, NULL) = 0 time(NULL) = 1399964809...

...73) --> (http://bugzilla.mindrot.org/attachment.cgi?id=1373) Output of ./configure and make Compilation of OpenSSH 4.7p1 fails under Tru64 4.0f. See error below. Full output of ./configure and make are attached. . . . cc: Error: atomicio.c, line 101: In this statement, "f" and "readv" cannot be compared for equality or inequality. (noequality) pfd.events = f == readv ? POLLIN : POLLOUT; ---------------------^ *** Exit 1 Stop. -- Configure bugmail: https://bugzilla.mindrot.org/userprefs.cgi?tab=email ------- You are receiving this mail because: ------- You are wat...

...> to control packet flow within QEMU. (CC's reduced, context added, Dmitry Fleytman added for vmxnet3 thoughts). Then I'm really confused as to what this would look like. A zero copy sendmsg? We should be able to implement that today. On the receive side, what can we do better than readv? If we need to return to userspace to tell the guest that we've got a new packet, we don't win on latency. We might reduce syscall overhead with a multi-dimensional readv to read multiple packets at once? Confused, Rusty.

...> to control packet flow within QEMU. (CC's reduced, context added, Dmitry Fleytman added for vmxnet3 thoughts). Then I'm really confused as to what this would look like. A zero copy sendmsg? We should be able to implement that today. On the receive side, what can we do better than readv? If we need to return to userspace to tell the guest that we've got a new packet, we don't win on latency. We might reduce syscall overhead with a multi-dimensional readv to read multiple packets at once? Confused, Rusty.

hi, I've some issue with geo-replication (since 3.2.0) and nfs auth (since initial release). Geo-replication --------------- System : Debian 6.0 amd64 Glusterfs: 3.2.0 MASTER (volume) => SLAVE (directory) For some volume it works, but for others i can't enable geo-replication and have this error with a faulty status: 2011-05-03 09:57:40.315774] E

...;strace -ff -p" to the process using ~100% CPU >>> >>> writev(75, [{"\250\r\0\0\2\0\0\0S-1-5-21-2097307442-3435"..., 3496}], >>> 1) = 3496 >>> epoll_wait(9, {{EPOLLIN, {u32=2539833808, u64=140271876753872}}}, 1, >>> 30000) = 1 >>> readv(91, >>> [{"\34\0\0\0\0\0\0\0rT\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0"..., >>> 2092}], >>> 1) = 2092 >>> gettimeofday({1419854003, 222035}, NULL) = 0 >>> gettimeofday({1419854003, 222103}, NULL) = 0 >>> gettimeofday({1419854003, 2...

...to quotactl every minute when no one is trying to access the share. An strace of one of the processes shows the following: poll([{fd=13, events=POLLIN|POLLHUP}, {fd=6, events=POLLIN|POLLHUP}, {fd=12, events=POLLIN|POLLHUP}, {fd=31, events=POLLIN|POLLHUP}], 4, 60000) = 1 ([{fd=31, revents=POLLIN}]) readv(31, [{"\0\0\0\230", 4}], 1) = 4 readv(31, [{"\376SMB@\0\1\0\0\0\0\0\5\0\1\0000\0\0\0\0\0\0\0V\1\0\0\0\0\0\0"..., 152}], 1) = 152 gettimeofday({1530539063, 52936}, NULL) = 0 geteuid32() = 0 getegid32() = 0 setgroups32(...

...4(13, F_SETLKW64, {type=F_UNLCK, whence=SEEK_SET, start=9400, len=1}, 0xbff3ce24) = 0 writev(50, [{"0\0", 2}, {"\5\0\2\3\20\0\0\0000\0\0\0\2\0\0\0\30\0\0\0\0\0\0\0\0\0\0\0\336\210/g"..., 48}], 2) = 50 epoll_wait(11, {{EPOLLIN, {u32=2962349656, u64=2962349656}}}, 1, 30000) = 1 readv(49, [{"\204\0", 2}], 1) = 2 readv(49, [{"\5\0\0\3\20\0\0\0\204\0\0\0\3\0\0\0", 16}, {"l\0\0\0\0\0D\0\0\0\0\0\37\215\27\1; \345N\273\216}\4\227\311\214|\1\0\0\0"..., 116}], 2) = 132 gettimeofday({1493714662, 571764}, NULL) = 0 time(NULL)...

...> Hi, > > Here is some output of "strace -ff -p" to the process using ~100% CPU > > writev(75, [{"\250\r\0\0\2\0\0\0S-1-5-21-2097307442-3435"..., 3496}], > 1) = 3496 > epoll_wait(9, {{EPOLLIN, {u32=2539833808, u64=140271876753872}}}, 1, > 30000) = 1 > readv(91, > [{"\34\0\0\0\0\0\0\0rT\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0"..., 2092}], > 1) = 2092 > gettimeofday({1419854003, 222035}, NULL) = 0 > gettimeofday({1419854003, 222103}, NULL) = 0 > gettimeofday({1419854003, 222169}, NULL) = 0 > fcntl(16, F_SETLKW, {type=F_RD...

Hi, I'm having problems in a second domain controller machine. Every time a restart samba, few time after a samba process starts using almost 100% cpu. It's a Centos 6.5 x86_64 with the following: sernet-samba-libsmbclient0-4.1.6-7.el6.x86_64 sernet-samba-ad-4.1.6-7.el6.x86_64 sernet-build-key-1.1-4.noarch sernet-samba-libs-4.1.6-7.el6.x86_64 sernet-samba-client-4.1.6-7.el6.x86_64

...(CC's reduced, context added, Dmitry Fleytman added for vmxnet3 thoughts). >> >> Then I'm really confused as to what this would look like. A zero copy >> sendmsg? We should be able to implement that today. >> >> On the receive side, what can we do better than readv? If we need to >> return to userspace to tell the guest that we've got a new packet, we >> don't win on latency. We might reduce syscall overhead with a >> multi-dimensional readv to read multiple packets at once? > > Sounds like recvmmsg(2). Could we map this to...

...nce=SEEK_SET, start=9400, > len=1}, 0xbff3ce24) = 0 > writev(50, [{"0\0", 2}, > {"\5\0\2\3\20\0\0\0000\0\0\0\2\0\0\0\30\0\0\0\0\0\0\0\0\0\0\0\336\210/g"..., > 48}], 2) = 50 > epoll_wait(11, {{EPOLLIN, {u32=2962349656, u64=2962349656}}}, 1, > 30000) = 1 > readv(49, [{"\204\0", 2}], 1) = 2 > readv(49, [{"\5\0\0\3\20\0\0\0\204\0\0\0\3\0\0\0", 16}, > {"l\0\0\0\0\0D\0\0\0\0\0\37\215\27\1; > \345N\273\216}\4\227\311\214|\1\0\0\0"..., 116}], 2) = 132 > gettimeofday({1493714662, 571764}, NULL) = 0 > time(N...

...(CC's reduced, context added, Dmitry Fleytman added for vmxnet3 thoughts). >> >> Then I'm really confused as to what this would look like. A zero copy >> sendmsg? We should be able to implement that today. >> >> On the receive side, what can we do better than readv? If we need to >> return to userspace to tell the guest that we've got a new packet, we >> don't win on latency. We might reduce syscall overhead with a >> multi-dimensional readv to read multiple packets at once? > > Sounds like recvmmsg(2). Could we map this to...

Hi, Here is some output of "strace -ff -p" to the process using ~100% CPU writev(75, [{"\250\r\0\0\2\0\0\0S-1-5-21-2097307442-3435"..., 3496}], 1) = 3496 epoll_wait(9, {{EPOLLIN, {u32=2539833808, u64=140271876753872}}}, 1, 30000) = 1 readv(91, [{"\34\0\0\0\0\0\0\0rT\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0"..., 2092}], 1) = 2092 gettimeofday({1419854003, 222035}, NULL) = 0 gettimeofday({1419854003, 222103}, NULL) = 0 gettimeofday({1419854003, 222169}, NULL) = 0 fcntl(16, F_SETLKW, {type=F_RDLCK, whence=SEEK_SET, start=17...

...is some output of "strace -ff -p" to the process using ~100% CPU >> >> writev(75, [{"\250\r\0\0\2\0\0\0S-1-5-21-2097307442-3435"..., 3496}], >> 1) = 3496 >> epoll_wait(9, {{EPOLLIN, {u32=2539833808, u64=140271876753872}}}, 1, >> 30000) = 1 >> readv(91, >> [{"\34\0\0\0\0\0\0\0rT\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0"..., 2092}], >> 1) = 2092 >> gettimeofday({1419854003, 222035}, NULL) = 0 >> gettimeofday({1419854003, 222103}, NULL) = 0 >> gettimeofday({1419854003, 222169}, NULL) = 0 >> fcntl(...

...the process using ~100% CPU >>>> >>>> writev(75, [{"\250\r\0\0\2\0\0\0S-1-5-21-2097307442-3435"..., 3496}], >>>> 1) = 3496 >>>> epoll_wait(9, {{EPOLLIN, {u32=2539833808, u64=140271876753872}}}, 1, >>>> 30000) = 1 >>>> readv(91, >>>> [{"\34\0\0\0\0\0\0\0rT\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0"..., >>>> 2092}], >>>> 1) = 2092 >>>> gettimeofday({1419854003, 222035}, NULL) = 0 >>>> gettimeofday({1419854003, 222103}, NULL) = 0 >>>> get...

...nce=SEEK_SET, start=9400, > len=1}, 0xbff3ce24) = 0 > writev(50, [{"0\0", 2}, > {"\5\0\2\3\20\0\0\0000\0\0\0\2\0\0\0\30\0\0\0\0\0\0\0\0\0\0\0\336\210/g"..., > 48}], 2) = 50 > epoll_wait(11, {{EPOLLIN, {u32=2962349656, u64=2962349656}}}, 1, > 30000) = 1 > readv(49, [{"\204\0", 2}], 1) = 2 > readv(49, [{"\5\0\0\3\20\0\0\0\204\0\0\0\3\0\0\0", 16}, > {"l\0\0\0\0\0D\0\0\0\0\0\37\215\27\1; > \345N\273\216}\4\227\311\214|\1\0\0\0"..., 116}], 2) = 132 > gettimeofday({1493714662, 571764}, NULL) = 0 > time(N...

..., >> len=1}, 0xbff3ce24) = 0 >> writev(50, [{"0\0", 2}, >> {"\5\0\2\3\20\0\0\0000\0\0\0\2\0\0\0\30\0\0\0\0\0\0\0\0\0\0\0\336\210/g"..., >> 48}], 2) = 50 >> epoll_wait(11, {{EPOLLIN, {u32=2962349656, u64=2962349656}}}, 1, >> 30000) = 1 >> readv(49, [{"\204\0", 2}], 1) = 2 >> readv(49, [{"\5\0\0\3\20\0\0\0\204\0\0\0\3\0\0\0", 16}, >> {"l\0\0\0\0\0D\0\0\0\0\0\37\215\27\1; >> \345N\273\216}\4\227\311\214|\1\0\0\0"..., 116}], 2) = 132 >> gettimeofday({1493714662, 571764}, NULL) =...

...MESSAGE----- Hash: SHA1 ============================================================================= FreeBSD-SA-03:16.filedesc Security Advisory The FreeBSD Project Topic: file descriptor leak in readv Category: core Module: kernel Announced: 2003-10-02 Credits: Joost Pol <joost@pine.nl> Affects: FreeBSD 4.3-RELEASE through 4.8-RELEASE 4-STABLE prior to the correction date Corrected: 2003-10-02 15:08:01 UTC (RELENG_4, 4.9-RC)...

...MESSAGE----- Hash: SHA1 ============================================================================= FreeBSD-SA-03:16.filedesc Security Advisory The FreeBSD Project Topic: file descriptor leak in readv Category: core Module: kernel Announced: 2003-10-02 Credits: Joost Pol <joost@pine.nl> Affects: FreeBSD 4.3-RELEASE through 4.8-RELEASE 4-STABLE prior to the correction date Corrected: 2003-10-02 15:08:01 UTC (RELENG_4, 4.9-RC)...