Skip to contentSkip to conversation

NFS: Add acreg{min,max} and acdir{min,max} in milliseconds

PATCH In review Amit Gud 4 participants 15 messages Jun 10, 2009 – Jun 17, 2009 6 messages not in the archive

Subsystems (2)
lore
Share & tools
lore

Amit Gud

author
#0 lore raw

PATCH 1/1 NFS: Add acreg{min,max} and acdir{min,max} in milliseconds

VGhpcyBwYXRjaCBhZGRzIDQgbmV3IE5GUyBtb3VudCBvcHRpb25zKGFjZGlybWlubXMsIGFjZGly bWF4bXMsIGFjcmVnbWlubXMsCmFjcmVnbWF4bXMpIGNvbnZlcnRpbmcgYWxyZWFkeSBleGlzdGlu ZyBvbmUgaW50byBhIG1pbGxpc2Vjb25kIHJlc29sdXRpb24KaW5zdGVhZCBvZiBzZWNvbmRzLgoK QWxzbywgbW9kaWZpZXMgdGhlIG1vdW50c3RhdHMgb3V0cHV0IHRvIG1pbGxpc2Vjb25kcyBpbnN0 ZWFkIG9mIHNlY29uZHMuCgpTaWduZWQtb2ZmLWJ5OiBBbWl0IEd1ZCA8YWd1ZEBha2FtYWkuY29t PgoKQUcKLS0KTWF5IHRoZSBzb3VyY2Ugd2l0aCB5b3UuCmh0dHA6Ly93d3cuY2lzLmtzdS5lZHUv fmd1ZAoKSW5kZXg6IGxpbnV4LTIuNi9mcy9uZnMvY2xpZW50LmMKPT09PT09PT09PT09PT09PT09 PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PQotLS0gbGlu dXgtMi42Lm9yaWcvZnMvbmZzL2NsaWVudC5jCisrKyBsaW51eC0yLjYvZnMvbmZzL2NsaWVudC5j CkBAIC03NzIsMTAgKzc3MiwxMCBAQCBzdGF0aWMgaW50IG5mc19pbml0X3NlcnZlcihzdHJ1Y3Qg bmZzX3NlCiAJaWYgKGRhdGEtPndzaXplKQogCQlzZXJ2ZXItPndzaXplID0gbmZzX2Jsb2NrX3Np emUoZGF0YS0+d3NpemUsIE5VTEwpOwogCi0Jc2VydmVyLT5hY3JlZ21pbiA9IGRhdGEtPmFjcmVn bWluICogSFo7Ci0Jc2VydmVyLT5hY3JlZ21heCA9IGRhdGEtPmFjcmVnbWF4ICogSFo7Ci0Jc2Vy dmVyLT5hY2Rpcm1pbiA9IGRhdGEtPmFjZGlybWluICogSFo7Ci0Jc2VydmVyLT5hY2Rpcm1heCA9 IGRhdGEtPmFjZGlybWF4ICogSFo7CisJc2VydmVyLT5hY3JlZ21pbiA9IChkYXRhLT5hY3JlZ21p bm1zICogSFopIC8gMTAwMDsKKwlzZXJ2ZXItPmFjcmVnbWF4ID0gKGRhdGEtPmFjcmVnbWF4bXMg KiBIWikgLyAxMDAwOworCXNlcnZlci0+YWNkaXJtaW4gPSAoZGF0YS0+YWNkaXJtaW5tcyAqIEha KSAvIDEwMDA7CisJc2VydmVyLT5hY2Rpcm1heCA9IChkYXRhLT5hY2Rpcm1heG1zICogSFopIC8g MTAwMDsKIAogCS8qIFN0YXJ0IGxvY2tkIGhlcmUsIGJlZm9yZSB3ZSBtaWdodCBlcnJvciBvdXQg Ki8KIAllcnJvciA9IG5mc19zdGFydF9sb2NrZChzZXJ2ZXIpOwpAQCAtMTE3MywxMCArMTE3Mywx MCBAQCBzdGF0aWMgaW50IG5mczRfaW5pdF9zZXJ2ZXIoc3RydWN0IG5mc19zCiAJaWYgKGRhdGEt PndzaXplKQogCQlzZXJ2ZXItPndzaXplID0gbmZzX2Jsb2NrX3NpemUoZGF0YS0+d3NpemUsIE5V TEwpOwogCi0Jc2VydmVyLT5hY3JlZ21pbiA9IGRhdGEtPmFjcmVnbWluICogSFo7Ci0Jc2VydmVy LT5hY3JlZ21heCA9IGRhdGEtPmFjcmVnbWF4ICogSFo7Ci0Jc2VydmVyLT5hY2Rpcm1pbiA9IGRh dGEtPmFjZGlybWluICogSFo7Ci0Jc2VydmVyLT5hY2Rpcm1heCA9IGRhdGEtPmFjZGlybWF4ICog SFo7CisJc2VydmVyLT5hY3JlZ21pbiA9IChkYXRhLT5hY3JlZ21pbm1zICogSFopIC8gMTAwMDsK KwlzZXJ2ZXItPmFjcmVnbWF4ID0gKGRhdGEtPmFjcmVnbWF4bXMgKiBIWikgLyAxMDAwOworCXNl cnZlci0+YWNkaXJtaW4gPSAoZGF0YS0+YWNkaXJtaW5tcyAqIEhaKSAvIDEwMDA7CisJc2VydmVy LT5hY2Rpcm1heCA9IChkYXRhLT5hY2Rpcm1heG1zICogSFopIC8gMTAwMDsKIAogCXNlcnZlci0+ cG9ydCA9IGRhdGEtPm5mc19zZXJ2ZXIucG9ydDsKIApJbmRleDogbGludXgtMi42L2ZzL25mcy9p bnRlcm5hbC5oCj09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09 PT09PT09PT09PT09PT09PT09PT0KLS0tIGxpbnV4LTIuNi5vcmlnL2ZzL25mcy9pbnRlcm5hbC5o CisrKyBsaW51eC0yLjYvZnMvbmZzL2ludGVybmFsLmgKQEAgLTM2LDggKzM2LDggQEAgc3RydWN0 IG5mc19wYXJzZWRfbW91bnRfZGF0YSB7CiAJaW50CQkJZmxhZ3M7CiAJaW50CQkJcnNpemUsIHdz aXplOwogCWludAkJCXRpbWVvLCByZXRyYW5zOwotCWludAkJCWFjcmVnbWluLCBhY3JlZ21heCwK LQkJCQlhY2Rpcm1pbiwgYWNkaXJtYXg7CisJaW50CQkJYWNyZWdtaW5tcywgYWNyZWdtYXhtcywK KwkJCQlhY2Rpcm1pbm1zLCBhY2Rpcm1heG1zOwogCWludAkJCW5hbWxlbjsKIAl1bnNpZ25lZCBp bnQJCW9wdGlvbnM7CiAJdW5zaWduZWQgaW50CQlic2l6ZTsKSW5kZXg6IGxpbnV4LTIuNi9mcy9u ZnMvbmZzcm9vdC5jCj09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09 PT09PT09PT09PT09PT09PT09PT09PT0KLS0tIGxpbnV4LTIuNi5vcmlnL2ZzL25mcy9uZnNyb290 LmMKKysrIGxpbnV4LTIuNi9mcy9uZnMvbmZzcm9vdC5jCkBAIC0yOTcsMTAgKzI5NywxMCBAQCBz dGF0aWMgaW50IF9faW5pdCByb290X25mc19uYW1lKGNoYXIgKm5hCiAJbmZzX2RhdGEuZmxhZ3Mg ICAgPSBORlNfTU9VTlRfTk9OTE07CS8qIE5vIGxvY2tkIGluIG5mcyByb290IHlldCAqLwogCW5m c19kYXRhLnJzaXplICAgID0gTkZTX0RFRl9GSUxFX0lPX1NJWkU7CiAJbmZzX2RhdGEud3NpemUg ICAgPSBORlNfREVGX0ZJTEVfSU9fU0laRTsKLQluZnNfZGF0YS5hY3JlZ21pbiA9IE5GU19ERUZf QUNSRUdNSU47Ci0JbmZzX2RhdGEuYWNyZWdtYXggPSBORlNfREVGX0FDUkVHTUFYOwotCW5mc19k YXRhLmFjZGlybWluID0gTkZTX0RFRl9BQ0RJUk1JTjsKLQluZnNfZGF0YS5hY2Rpcm1heCA9IE5G U19ERUZfQUNESVJNQVg7CisJbmZzX2RhdGEuYWNyZWdtaW4gPSBORlNfREVGX0FDUkVHTUlOX01T IC8gMTAwMDsKKwluZnNfZGF0YS5hY3JlZ21heCA9IE5GU19ERUZfQUNSRUdNQVhfTVMgLyAxMDAw OworCW5mc19kYXRhLmFjZGlybWluID0gTkZTX0RFRl9BQ0RJUk1JTl9NUyAvIDEwMDA7CisJbmZz X2RhdGEuYWNkaXJtYXggPSBORlNfREVGX0FDRElSTUFYX01TIC8gMTAwMDsKIAlzdHJjcHkoYnVm LCBORlNfUk9PVCk7CiAKIAkvKiBQcm9jZXNzIG9wdGlvbnMgcmVjZWl2ZWQgZnJvbSB0aGUgcmVt b3RlIHNlcnZlciAqLwpJbmRleDogbGludXgtMi42L2ZzL25mcy9zdXBlci5jCj09PT09PT09PT09 PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT0K LS0tIGxpbnV4LTIuNi5vcmlnL2ZzL25mcy9zdXBlci5jCisrKyBsaW51eC0yLjYvZnMvbmZzL3N1 cGVyLmMKQEAgLTg1LDYgKzg1LDggQEAgZW51bSB7CiAJT3B0X3RpbWVvLCBPcHRfcmV0cmFucywK IAlPcHRfYWNyZWdtaW4sIE9wdF9hY3JlZ21heCwKIAlPcHRfYWNkaXJtaW4sIE9wdF9hY2Rpcm1h eCwKKwlPcHRfYWNyZWdtaW5tcywgT3B0X2FjcmVnbWF4bXMsCisJT3B0X2FjZGlybWlubXMsIE9w dF9hY2Rpcm1heG1zLAogCU9wdF9hY3RpbWVvLAogCU9wdF9uYW1lbGVuLAogCU9wdF9tb3VudHBv cnQsCkBAIC0xNDksNiArMTUxLDEwIEBAIHN0YXRpYyBjb25zdCBtYXRjaF90YWJsZV90IG5mc19t b3VudF9vcHQKIAl7IE9wdF9hY3JlZ21heCwgImFjcmVnbWF4PSV1IiB9LAogCXsgT3B0X2FjZGly bWluLCAiYWNkaXJtaW49JXUiIH0sCiAJeyBPcHRfYWNkaXJtYXgsICJhY2Rpcm1heD0ldSIgfSwK Kwl7IE9wdF9hY3JlZ21pbm1zLCAiYWNyZWdtaW5tcz0ldSIgfSwKKwl7IE9wdF9hY3JlZ21heG1z LCAiYWNyZWdtYXhtcz0ldSIgfSwKKwl7IE9wdF9hY2Rpcm1pbm1zLCAiYWNkaXJtaW5tcz0ldSIg fSwKKwl7IE9wdF9hY2Rpcm1heG1zLCAiYWNkaXJtYXhtcz0ldSIgfSwKIAl7IE9wdF9hY3RpbWVv LCAiYWN0aW1lbz0ldSIgfSwKIAl7IE9wdF9uYW1lbGVuLCAibmFtbGVuPSV1IiB9LAogCXsgT3B0 X21vdW50cG9ydCwgIm1vdW50cG9ydD0ldSIgfSwKQEAgLTUzNSwxNCArNTQxLDE0IEBAIHN0YXRp YyB2b2lkIG5mc19zaG93X21vdW50X29wdGlvbnMoc3RydWMKIAlpZiAobmZzcy0+YnNpemUgIT0g MCkKIAkJc2VxX3ByaW50ZihtLCAiLGJzaXplPSV1IiwgbmZzcy0+YnNpemUpOwogCXNlcV9wcmlu dGYobSwgIixuYW1sZW49JXUiLCBuZnNzLT5uYW1lbGVuKTsKLQlpZiAobmZzcy0+YWNyZWdtaW4g IT0gTkZTX0RFRl9BQ1JFR01JTipIWiB8fCBzaG93ZGVmYXVsdHMpCi0JCXNlcV9wcmludGYobSwg IixhY3JlZ21pbj0ldSIsIG5mc3MtPmFjcmVnbWluL0haKTsKLQlpZiAobmZzcy0+YWNyZWdtYXgg IT0gTkZTX0RFRl9BQ1JFR01BWCpIWiB8fCBzaG93ZGVmYXVsdHMpCi0JCXNlcV9wcmludGYobSwg IixhY3JlZ21heD0ldSIsIG5mc3MtPmFjcmVnbWF4L0haKTsKLQlpZiAobmZzcy0+YWNkaXJtaW4g IT0gTkZTX0RFRl9BQ0RJUk1JTipIWiB8fCBzaG93ZGVmYXVsdHMpCi0JCXNlcV9wcmludGYobSwg IixhY2Rpcm1pbj0ldSIsIG5mc3MtPmFjZGlybWluL0haKTsKLQlpZiAobmZzcy0+YWNkaXJtYXgg IT0gTkZTX0RFRl9BQ0RJUk1BWCpIWiB8fCBzaG93ZGVmYXVsdHMpCi0JCXNlcV9wcmludGYobSwg IixhY2Rpcm1heD0ldSIsIG5mc3MtPmFjZGlybWF4L0haKTsKKwlpZiAobmZzcy0+YWNyZWdtaW4g IT0gKE5GU19ERUZfQUNSRUdNSU5fTVMqSFopLzEwMDAgfHwgc2hvd2RlZmF1bHRzKQorCQlzZXFf cHJpbnRmKG0sICIsYWNyZWdtaW5tcz0ldSIsIChuZnNzLT5hY3JlZ21pbioxMDAwKS9IWik7CisJ aWYgKG5mc3MtPmFjcmVnbWF4ICE9IChORlNfREVGX0FDUkVHTUFYX01TKkhaKS8xMDAwIHx8IHNo b3dkZWZhdWx0cykKKwkJc2VxX3ByaW50ZihtLCAiLGFjcmVnbWF4bXM9JXUiLCAobmZzcy0+YWNy ZWdtYXgqMTAwMCkvSFopOworCWlmIChuZnNzLT5hY2Rpcm1pbiAhPSAoTkZTX0RFRl9BQ0RJUk1J Tl9NUypIWikvMTAwMCB8fCBzaG93ZGVmYXVsdHMpCisJCXNlcV9wcmludGYobSwgIixhY2Rpcm1p bm1zPSV1IiwgKG5mc3MtPmFjZGlybWluKjEwMDApL0haKTsKKwlpZiAobmZzcy0+YWNkaXJtYXgg IT0gKE5GU19ERUZfQUNESVJNQVhfTVMqSFopLzEwMDAgfHwgc2hvd2RlZmF1bHRzKQorCQlzZXFf cHJpbnRmKG0sICIsYWNkaXJtYXhtcz0ldSIsIChuZnNzLT5hY2Rpcm1heCoxMDAwKS9IWik7CiAJ Zm9yIChuZnNfaW5mb3AgPSBuZnNfaW5mbzsgbmZzX2luZm9wLT5mbGFnOyBuZnNfaW5mb3ArKykg ewogCQlpZiAobmZzcy0+ZmxhZ3MgJiBuZnNfaW5mb3AtPmZsYWcpCiAJCQlzZXFfcHV0cyhtLCBu ZnNfaW5mb3AtPnN0cik7CkBAIC0xMTM4LDM2ICsxMTQ0LDY0IEBAIHN0YXRpYyBpbnQgbmZzX3Bh cnNlX21vdW50X29wdGlvbnMoY2hhcgogCQkJCWVycm9ycysrOwogCQkJCW5mc19wYXJzZV9pbnZh bGlkX3ZhbHVlKCJhY3JlZ21pbiIpOwogCQkJfSBlbHNlCi0JCQkJbW50LT5hY3JlZ21pbiA9IG9w dGlvbjsKKwkJCQltbnQtPmFjcmVnbWlubXMgPSBvcHRpb24gKiAxMDAwOwogCQkJYnJlYWs7CiAJ CWNhc2UgT3B0X2FjcmVnbWF4OgogCQkJaWYgKG1hdGNoX2ludChhcmdzLCAmb3B0aW9uKSB8fCBv cHRpb24gPCAwKSB7CiAJCQkJZXJyb3JzKys7CiAJCQkJbmZzX3BhcnNlX2ludmFsaWRfdmFsdWUo ImFjcmVnbWF4Iik7CiAJCQl9IGVsc2UKLQkJCQltbnQtPmFjcmVnbWF4ID0gb3B0aW9uOworCQkJ CW1udC0+YWNyZWdtYXhtcyA9IG9wdGlvbiAqIDEwMDA7CiAJCQlicmVhazsKIAkJY2FzZSBPcHRf YWNkaXJtaW46CiAJCQlpZiAobWF0Y2hfaW50KGFyZ3MsICZvcHRpb24pIHx8IG9wdGlvbiA8IDAp IHsKIAkJCQllcnJvcnMrKzsKIAkJCQluZnNfcGFyc2VfaW52YWxpZF92YWx1ZSgiYWNkaXJtaW4i KTsKIAkJCX0gZWxzZQotCQkJCW1udC0+YWNkaXJtaW4gPSBvcHRpb247CisJCQkJbW50LT5hY2Rp cm1pbm1zID0gb3B0aW9uICogMTAwMDsKIAkJCWJyZWFrOwogCQljYXNlIE9wdF9hY2Rpcm1heDoK IAkJCWlmIChtYXRjaF9pbnQoYXJncywgJm9wdGlvbikgfHwgb3B0aW9uIDwgMCkgewogCQkJCWVy cm9ycysrOwogCQkJCW5mc19wYXJzZV9pbnZhbGlkX3ZhbHVlKCJhY2Rpcm1heCIpOwogCQkJfSBl bHNlCi0JCQkJbW50LT5hY2Rpcm1heCA9IG9wdGlvbjsKKwkJCQltbnQtPmFjZGlybWF4bXMgPSBv cHRpb24gKiAxMDAwOworCQkJYnJlYWs7CisJCWNhc2UgT3B0X2FjcmVnbWlubXM6CisJCQlpZiAo bWF0Y2hfaW50KGFyZ3MsICZvcHRpb24pIHx8IG9wdGlvbiA8IDApIHsKKwkJCQllcnJvcnMrKzsK KwkJCQluZnNfcGFyc2VfaW52YWxpZF92YWx1ZSgiYWNyZWdtaW4iKTsKKwkJCX0gZWxzZQorCQkJ CW1udC0+YWNyZWdtaW5tcyA9IG9wdGlvbjsKKwkJCWJyZWFrOworCQljYXNlIE9wdF9hY3JlZ21h eG1zOgorCQkJaWYgKG1hdGNoX2ludChhcmdzLCAmb3B0aW9uKSB8fCBvcHRpb24gPCAwKSB7CisJ CQkJZXJyb3JzKys7CisJCQkJbmZzX3BhcnNlX2ludmFsaWRfdmFsdWUoImFjcmVnbWF4Iik7CisJ CQl9IGVsc2UKKwkJCQltbnQtPmFjcmVnbWF4bXMgPSBvcHRpb247CisJCQlicmVhazsKKwkJY2Fz ZSBPcHRfYWNkaXJtaW5tczoKKwkJCWlmIChtYXRjaF9pbnQoYXJncywgJm9wdGlvbikgfHwgb3B0 aW9uIDwgMCkgeworCQkJCWVycm9ycysrOworCQkJCW5mc19wYXJzZV9pbnZhbGlkX3ZhbHVlKCJh Y2Rpcm1pbiIpOworCQkJfSBlbHNlCisJCQkJbW50LT5hY2Rpcm1pbm1zID0gb3B0aW9uOworCQkJ YnJlYWs7CisJCWNhc2UgT3B0X2FjZGlybWF4bXM6CisJCQlpZiAobWF0Y2hfaW50KGFyZ3MsICZv cHRpb24pIHx8IG9wdGlvbiA8IDApIHsKKwkJCQllcnJvcnMrKzsKKwkJCQluZnNfcGFyc2VfaW52 YWxpZF92YWx1ZSgiYWNkaXJtYXgiKTsKKwkJCX0gZWxzZQorCQkJCW1udC0+YWNkaXJtYXhtcyA9 IG9wdGlvbjsKIAkJCWJyZWFrOwogCQljYXNlIE9wdF9hY3RpbWVvOgogCQkJaWYgKG1hdGNoX2lu dChhcmdzLCAmb3B0aW9uKSB8fCBvcHRpb24gPCAwKSB7CiAJCQkJZXJyb3JzKys7CiAJCQkJbmZz X3BhcnNlX2ludmFsaWRfdmFsdWUoImFjdGltZW8iKTsKIAkJCX0gZWxzZQotCQkJCW1udC0+YWNy ZWdtaW4gPSBtbnQtPmFjcmVnbWF4ID0KLQkJCQltbnQtPmFjZGlybWluID0gbW50LT5hY2Rpcm1h eCA9IG9wdGlvbjsKKwkJCQltbnQtPmFjcmVnbWlubXMgPSBtbnQtPmFjcmVnbWF4bXMgPQorCQkJ CW1udC0+YWNkaXJtaW5tcyA9IG1udC0+YWNkaXJtYXhtcyA9IG9wdGlvbiAqIDEwMDA7CiAJCQli cmVhazsKIAkJY2FzZSBPcHRfbmFtZWxlbjoKIAkJCWlmIChtYXRjaF9pbnQoYXJncywgJm9wdGlv bikgfHwgb3B0aW9uIDwgMCkgewpAQCAtMTU5NiwxMCArMTYzMCwxMCBAQCBzdGF0aWMgaW50IG5m c192YWxpZGF0ZV9tb3VudF9kYXRhKHZvaWQKIAlhcmdzLT5mbGFncwkJPSAoTkZTX01PVU5UX1ZF UjMgfCBORlNfTU9VTlRfVENQKTsKIAlhcmdzLT5yc2l6ZQkJPSBORlNfTUFYX0ZJTEVfSU9fU0la RTsKIAlhcmdzLT53c2l6ZQkJPSBORlNfTUFYX0ZJTEVfSU9fU0laRTsKLQlhcmdzLT5hY3JlZ21p bgkJPSBORlNfREVGX0FDUkVHTUlOOwotCWFyZ3MtPmFjcmVnbWF4CQk9IE5GU19ERUZfQUNSRUdN QVg7Ci0JYXJncy0+YWNkaXJtaW4JCT0gTkZTX0RFRl9BQ0RJUk1JTjsKLQlhcmdzLT5hY2Rpcm1h eAkJPSBORlNfREVGX0FDRElSTUFYOworCWFyZ3MtPmFjcmVnbWlubXMJPSBORlNfREVGX0FDUkVH TUlOX01TOworCWFyZ3MtPmFjcmVnbWF4bXMJPSBORlNfREVGX0FDUkVHTUFYX01TOworCWFyZ3Mt PmFjZGlybWlubXMJPSBORlNfREVGX0FDRElSTUlOX01TOworCWFyZ3MtPmFjZGlybWF4bXMJPSBO RlNfREVGX0FDRElSTUFYX01TOwogCWFyZ3MtPm1vdW50X3NlcnZlci5wb3J0CT0gMDsJLyogYXV0 b2JpbmQgdW5sZXNzIHVzZXIgc2V0cyBwb3J0ICovCiAJYXJncy0+bmZzX3NlcnZlci5wb3J0CT0g MDsJLyogYXV0b2JpbmQgdW5sZXNzIHVzZXIgc2V0cyBwb3J0ICovCiAJYXJncy0+bmZzX3NlcnZl ci5wcm90b2NvbCA9IFhQUlRfVFJBTlNQT1JUX1RDUDsKQEAgLTE2NDMsMTAgKzE2NzcsMTAgQEAg c3RhdGljIGludCBuZnNfdmFsaWRhdGVfbW91bnRfZGF0YSh2b2lkCiAJCWFyZ3MtPndzaXplCQk9 IGRhdGEtPndzaXplOwogCQlhcmdzLT50aW1lbwkJPSBkYXRhLT50aW1lbzsKIAkJYXJncy0+cmV0 cmFucwkJPSBkYXRhLT5yZXRyYW5zOwotCQlhcmdzLT5hY3JlZ21pbgkJPSBkYXRhLT5hY3JlZ21p bjsKLQkJYXJncy0+YWNyZWdtYXgJCT0gZGF0YS0+YWNyZWdtYXg7Ci0JCWFyZ3MtPmFjZGlybWlu CQk9IGRhdGEtPmFjZGlybWluOwotCQlhcmdzLT5hY2Rpcm1heAkJPSBkYXRhLT5hY2Rpcm1heDsK KwkJYXJncy0+YWNyZWdtaW5tcwk9IGRhdGEtPmFjcmVnbWluICogMTAwMDsKKwkJYXJncy0+YWNy ZWdtYXhtcwk9IGRhdGEtPmFjcmVnbWF4ICogMTAwMDsKKwkJYXJncy0+YWNkaXJtaW5tcwk9IGRh dGEtPmFjZGlybWluICogMTAwMDsKKwkJYXJncy0+YWNkaXJtYXhtcwk9IGRhdGEtPmFjZGlybWF4 ICogMTAwMDsKIAogCQltZW1jcHkoJmFyZ3MtPm5mc19zZXJ2ZXIuYWRkcmVzcywgJmRhdGEtPmFk ZHIsCiAJCSAgICAgICBzaXplb2YoZGF0YS0+YWRkcikpOwpAQCAtMTc3NSwxMCArMTgwOSwxMCBA QCBuZnNfY29tcGFyZV9yZW1vdW50X2RhdGEoc3RydWN0IG5mc19zZXJ2CiAJICAgIGRhdGEtPndz aXplICE9IG5mc3MtPndzaXplIHx8CiAJICAgIGRhdGEtPnJldHJhbnMgIT0gbmZzcy0+Y2xpZW50 LT5jbF90aW1lb3V0LT50b19yZXRyaWVzIHx8CiAJICAgIGRhdGEtPmF1dGhfZmxhdm9yc1swXSAh PSBuZnNzLT5jbGllbnQtPmNsX2F1dGgtPmF1X2ZsYXZvciB8fAotCSAgICBkYXRhLT5hY3JlZ21p biAhPSBuZnNzLT5hY3JlZ21pbiAvIEhaIHx8Ci0JICAgIGRhdGEtPmFjcmVnbWF4ICE9IG5mc3Mt PmFjcmVnbWF4IC8gSFogfHwKLQkgICAgZGF0YS0+YWNkaXJtaW4gIT0gbmZzcy0+YWNkaXJtaW4g LyBIWiB8fAotCSAgICBkYXRhLT5hY2Rpcm1heCAhPSBuZnNzLT5hY2Rpcm1heCAvIEhaIHx8CisJ ICAgIGRhdGEtPmFjcmVnbWlubXMgIT0gKG5mc3MtPmFjcmVnbWluICogMTAwMCkgLyBIWiB8fAor CSAgICBkYXRhLT5hY3JlZ21heG1zICE9IChuZnNzLT5hY3JlZ21heCAqIDEwMDApIC8gSFogfHwK KwkgICAgZGF0YS0+YWNkaXJtaW5tcyAhPSAobmZzcy0+YWNkaXJtaW4gKiAxMDAwKSAvIEhaIHx8 CisJICAgIGRhdGEtPmFjZGlybWF4bXMgIT0gKG5mc3MtPmFjZGlybWF4ICogMTAwMCkgLyBIWiB8 fAogCSAgICBkYXRhLT50aW1lbyAhPSAoMTBVICogbmZzcy0+Y2xpZW50LT5jbF90aW1lb3V0LT50 b19pbml0dmFsIC8gSFopIHx8CiAJICAgIGRhdGEtPm5mc19zZXJ2ZXIuYWRkcmxlbiAhPSBuZnNz LT5uZnNfY2xpZW50LT5jbF9hZGRybGVuIHx8CiAJICAgIG1lbWNtcCgmZGF0YS0+bmZzX3NlcnZl ci5hZGRyZXNzLCAmbmZzcy0+bmZzX2NsaWVudC0+Y2xfYWRkciwKQEAgLTE4MTksMTAgKzE4NTMs MTAgQEAgbmZzX3JlbW91bnQoc3RydWN0IHN1cGVyX2Jsb2NrICpzYiwgaW50CiAJZGF0YS0+d3Np emUgPSBuZnNzLT53c2l6ZTsKIAlkYXRhLT5yZXRyYW5zID0gbmZzcy0+Y2xpZW50LT5jbF90aW1l b3V0LT50b19yZXRyaWVzOwogCWRhdGEtPmF1dGhfZmxhdm9yc1swXSA9IG5mc3MtPmNsaWVudC0+ Y2xfYXV0aC0+YXVfZmxhdm9yOwotCWRhdGEtPmFjcmVnbWluID0gbmZzcy0+YWNyZWdtaW4gLyBI WjsKLQlkYXRhLT5hY3JlZ21heCA9IG5mc3MtPmFjcmVnbWF4IC8gSFo7Ci0JZGF0YS0+YWNkaXJt aW4gPSBuZnNzLT5hY2Rpcm1pbiAvIEhaOwotCWRhdGEtPmFjZGlybWF4ID0gbmZzcy0+YWNkaXJt YXggLyBIWjsKKwlkYXRhLT5hY3JlZ21pbm1zID0gKG5mc3MtPmFjcmVnbWluICogMTAwMCkgLyBI WjsKKwlkYXRhLT5hY3JlZ21heG1zID0gKG5mc3MtPmFjcmVnbWF4ICogMTAwMCkgLyBIWjsKKwlk YXRhLT5hY2Rpcm1pbm1zID0gKG5mc3MtPmFjZGlybWluICogMTAwMCkgLyBIWjsKKwlkYXRhLT5h Y2Rpcm1heG1zID0gKG5mc3MtPmFjZGlybWF4ICogMTAwMCkgLyBIWjsKIAlkYXRhLT50aW1lbyA9 IDEwVSAqIG5mc3MtPmNsaWVudC0+Y2xfdGltZW91dC0+dG9faW5pdHZhbCAvIEhaOwogCWRhdGEt Pm5mc19zZXJ2ZXIuYWRkcmxlbiA9IG5mc3MtPm5mc19jbGllbnQtPmNsX2FkZHJsZW47CiAJbWVt Y3B5KCZkYXRhLT5uZnNfc2VydmVyLmFkZHJlc3MsICZuZnNzLT5uZnNfY2xpZW50LT5jbF9hZGRy LApAQCAtMjI1NCwxMCArMjI4OCwxMCBAQCBzdGF0aWMgaW50IG5mczRfdmFsaWRhdGVfbW91bnRf ZGF0YSh2b2lkCiAKIAlhcmdzLT5yc2l6ZQkJPSBORlNfTUFYX0ZJTEVfSU9fU0laRTsKIAlhcmdz LT53c2l6ZQkJPSBORlNfTUFYX0ZJTEVfSU9fU0laRTsKLQlhcmdzLT5hY3JlZ21pbgkJPSBORlNf REVGX0FDUkVHTUlOOwotCWFyZ3MtPmFjcmVnbWF4CQk9IE5GU19ERUZfQUNSRUdNQVg7Ci0JYXJn cy0+YWNkaXJtaW4JCT0gTkZTX0RFRl9BQ0RJUk1JTjsKLQlhcmdzLT5hY2Rpcm1heAkJPSBORlNf REVGX0FDRElSTUFYOworCWFyZ3MtPmFjcmVnbWlubXMJPSBORlNfREVGX0FDUkVHTUlOX01TOwor CWFyZ3MtPmFjcmVnbWF4bXMJPSBORlNfREVGX0FDUkVHTUFYX01TOworCWFyZ3MtPmFjZGlybWlu bXMJPSBORlNfREVGX0FDRElSTUlOX01TOworCWFyZ3MtPmFjZGlybWF4bXMJPSBORlNfREVGX0FD RElSTUFYX01TOwogCWFyZ3MtPm5mc19zZXJ2ZXIucG9ydAk9IE5GU19QT1JUOyAvKiAyMDQ5IHVu bGVzcyB1c2VyIHNldCBwb3J0PSAqLwogCWFyZ3MtPmF1dGhfZmxhdm9yc1swXQk9IFJQQ19BVVRI X1VOSVg7CiAJYXJncy0+YXV0aF9mbGF2b3JfbGVuCT0gMDsKQEAgLTIzMDYsMTUgKzIzNDAsMTUg QEAgc3RhdGljIGludCBuZnM0X3ZhbGlkYXRlX21vdW50X2RhdGEodm9pZAogCQkgKiBjYW4gZGVh bCB3aXRoLgogCQkgKi8KIAotCQlhcmdzLT5mbGFncwk9IGRhdGEtPmZsYWdzICYgTkZTNF9NT1VO VF9GTEFHTUFTSzsKLQkJYXJncy0+cnNpemUJPSBkYXRhLT5yc2l6ZTsKLQkJYXJncy0+d3NpemUJ PSBkYXRhLT53c2l6ZTsKLQkJYXJncy0+dGltZW8JPSBkYXRhLT50aW1lbzsKLQkJYXJncy0+cmV0 cmFucwk9IGRhdGEtPnJldHJhbnM7Ci0JCWFyZ3MtPmFjcmVnbWluCT0gZGF0YS0+YWNyZWdtaW47 Ci0JCWFyZ3MtPmFjcmVnbWF4CT0gZGF0YS0+YWNyZWdtYXg7Ci0JCWFyZ3MtPmFjZGlybWluCT0g ZGF0YS0+YWNkaXJtaW47Ci0JCWFyZ3MtPmFjZGlybWF4CT0gZGF0YS0+YWNkaXJtYXg7CisJCWFy Z3MtPmZsYWdzCQk9IGRhdGEtPmZsYWdzICYgTkZTNF9NT1VOVF9GTEFHTUFTSzsKKwkJYXJncy0+ cnNpemUJCT0gZGF0YS0+cnNpemU7CisJCWFyZ3MtPndzaXplCQk9IGRhdGEtPndzaXplOworCQlh cmdzLT50aW1lbwkJPSBkYXRhLT50aW1lbzsKKwkJYXJncy0+cmV0cmFucwkJPSBkYXRhLT5yZXRy YW5zOworCQlhcmdzLT5hY3JlZ21pbm1zCT0gZGF0YS0+YWNyZWdtaW4gKiAxMDAwOworCQlhcmdz LT5hY3JlZ21heG1zCT0gZGF0YS0+YWNyZWdtYXggKiAxMDAwOworCQlhcmdzLT5hY2Rpcm1pbm1z CT0gZGF0YS0+YWNkaXJtaW4gKiAxMDAwOworCQlhcmdzLT5hY2Rpcm1heG1zCT0gZGF0YS0+YWNk aXJtYXggKiAxMDAwOwogCQlhcmdzLT5uZnNfc2VydmVyLnByb3RvY29sID0gZGF0YS0+cHJvdG87 CiAJCW5mc192YWxpZGF0ZV90cmFuc3BvcnRfcHJvdG9jb2woYXJncyk7CiAKSW5kZXg6IGxpbnV4 LTIuNi9pbmNsdWRlL2xpbnV4L25mc19mcy5oCj09PT09PT09PT09PT09PT09PT09PT09PT09PT09 PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT09PT0KLS0tIGxpbnV4LTIuNi5vcmln L2luY2x1ZGUvbGludXgvbmZzX2ZzLmgKKysrIGxpbnV4LTIuNi9pbmNsdWRlL2xpbnV4L25mc19m cy5oCkBAIC0yMCwxMCArMjAsMTAgQEAKICNkZWZpbmUgTkZTX01BWF9VRFBfVElNRU9VVAkoNjAq SFopCiAjZGVmaW5lIE5GU19NQVhfVENQX1RJTUVPVVQJKDYwMCpIWikKIAotI2RlZmluZSBORlNf REVGX0FDUkVHTUlOCSgzKQotI2RlZmluZSBORlNfREVGX0FDUkVHTUFYCSg2MCkKLSNkZWZpbmUg TkZTX0RFRl9BQ0RJUk1JTgkoMzApCi0jZGVmaW5lIE5GU19ERUZfQUNESVJNQVgJKDYwKQorI2Rl ZmluZSBORlNfREVGX0FDUkVHTUlOX01TCSgzMDAwKQorI2RlZmluZSBORlNfREVGX0FDUkVHTUFY X01TCSg2MDAwMCkKKyNkZWZpbmUgTkZTX0RFRl9BQ0RJUk1JTl9NUwkoMzAwMDApCisjZGVmaW5l IE5GU19ERUZfQUNESVJNQVhfTVMJKDYwMDAwKQogCiAvKgogICogV2hlbiBmbHVzaGluZyBhIGNs dXN0ZXIgb2YgZGlydHkgcGFnZXMsIHRoZXJlIGNhbiBiZSBkaWZmZXJlbnQKAAo=

#1 lore raw
Quoted 5 lines · Amit Gud

This patch adds 4 new NFS mount options(acdirminms, acdirmaxms, acregminms, acregmaxms) converting already existing one into a millisecond resolution instead of seconds.

Also, modifies the mountstats output to milliseconds instead of seconds.

Why, exactly, do you need to control cache timeouts down to the millisecond level?

Trond

A message that is not in the archive (sent off-list or not yet received): 1244636844.24750.23.camel-rJ7iovZKK19ZJLDQqaL3InhyD016LWXt@public.gmane.org

author
#3 lore raw
Quoted 10 lines · Trond Myklebust
Quoted 5 lines · Amit Gud

This patch adds 4 new NFS mount options(acdirminms, acdirmaxms, acregminms, acregmaxms) converting already existing one into a millisecond resolution instead of seconds.

Also, modifies the mountstats output to milliseconds instead of seconds.

Why, exactly, do you need to control cache timeouts down to the millisecond level?

The problem is to make the updates visible from one client to the other in less than a second and turning off caching entirely has an unacceptably high penalty.

AG
--
May the source be with you.
http://www.cis.ksu.edu/~gud

#4 lore raw
Quoted 8 lines · Amit Gud
Quoted 7 lines · Trond Myklebust
Quoted 5 lines · Amit Gud

This patch adds 4 new NFS mount options(acdirminms, acdirmaxms, acregminms, acregmaxms) converting already existing one into a millisecond resolution instead of seconds.

Also, modifies the mountstats output to milliseconds instead of seconds.

Quoted 7 lines
Quoted 3 lines

Why, exactly, do you need to control cache timeouts down to the millisecond level?

The problem is to make the updates visible from one client to the other in less than a second and turning off caching entirely has an unacceptably high penalty.

Specifics, please: updates of what, exactly? Are we talking attributes, data or directory contents?

What is your application, and why does 1ms constitute an acceptable caching timeout, while 1s does not?

Trond

author
#5 lore raw
Quoted 21 lines · Trond Myklebust
Quoted 11 lines · Amit Gud
Quoted 10 lines · Trond Myklebust
Quoted 8 lines · Amit Gud

This patch adds 4 new NFS mount options(acdirminms, acdirmaxms, acregminms,
acregmaxms) converting already existing one into a millisecond resolution
instead of seconds.

Also, modifies the mountstats output to milliseconds instead of seconds.

Quoted 7 lines
Quoted 3 lines

Why, exactly, do you need to control cache timeouts down to the millisecond level?

The problem is to make the updates visible from one client to the other in less than a second and turning off caching entirely has an unacceptably high penalty.

Quoted 6 lines

Specifics, please: updates of what, exactly? Are we talking attributes, data or directory contents?

What is your application, and why does 1ms constitute an acceptable caching timeout, while 1s does not?

We have a system in which machine A needs a change made to an NFS directory. But, the actual change must be executed by machine B, so A makes an request to B to make the update. But, A is allowed to read the directory directly, so A can't in general continue until it is able to see the effect of the update. With 1s caching, that means a 1s "sleep" after each update.

Setting caching to "0s" means that consecutive stats performed by machine A must always revalidate every node of each path walked. In many cases, we end up wanting to stat every path component in some path, which would result in O(N2) getattr or lookup calls for N levels of directory depth.

Using a very small acdirmax (e.g. 10ms) gives us a significant performance boost on these consecutive stats without increasing the post-update "sleep" to 1s. (Of course, if the file server delays more than 10ms at any step, then we will have to start over for the next operation. But, the file server often has everything necessary in cache such that each response is well below a millisecond.)

AG
--
May the source be with you.

#6 lore raw
Quoted 42 lines · Amit Gud
Quoted 21 lines · Trond Myklebust
Quoted 11 lines · Amit Gud
Quoted 10 lines · Trond Myklebust
Quoted 8 lines · Amit Gud

This patch adds 4 new NFS mount options(acdirminms, acdirmaxms, acregminms,
acregmaxms) converting already existing one into a millisecond resolution
instead of seconds.

Also, modifies the mountstats output to milliseconds instead of seconds.

Quoted 7 lines
Quoted 3 lines

Why, exactly, do you need to control cache timeouts down to the millisecond level?

The problem is to make the updates visible from one client to the other in less than a second and turning off caching entirely has an unacceptably high penalty.

Quoted 6 lines

Specifics, please: updates of what, exactly? Are we talking attributes, data or directory contents?

What is your application, and why does 1ms constitute an acceptable caching timeout, while 1s does not?

We have a system in which machine A needs a change made to an NFS directory. But, the actual change must be executed by machine B, so A makes an request to B to make the update. But, A is allowed to read the directory directly, so A can't in general continue until it is able to see the effect of the update. With 1s caching, that means a 1s "sleep" after each update.

Setting caching to "0s" means that consecutive stats performed by machine A must always revalidate every node of each path walked. In many cases, we end up wanting to stat every path component in some path, which would result in O(N2) getattr or lookup calls for N levels of directory depth.

Quoted 6 lines

Using a very small acdirmax (e.g. 10ms) gives us a significant performance boost on these consecutive stats without increasing the post-update "sleep" to 1s. (Of course, if the file server delays more than 10ms at any step, then we will have to start over for the next operation. But, the file server often has everything necessary in cache such that each response is well below a millisecond.)

I'm still not sure I fully understand, but here are a couple of comments.

Firstly, opendir() will _always_ force a revalidation of the directory attributes, so if your machine A is relying on doing an 'ls' in order to figure out the directory contents, then that shouldn't need extra attribute timeouts.

Secondly, we have already introduced finer control over the lookup caching as of Linux 2.6.28 and newer:
- if you want to ensure that machine A always see new files and links immediately once they have been created, then '-olookupcache=positive' should turn off negative dentry caching.
- if you also want to ensure that it immediately sees renames, unlinks and such, then '-olookupcache=none' will turn off lookup caching altogether.
Both of these lookup cache options are more reliable than relying on the directory attribute cache timeouts, and they have the added benefit that they also work around the problem that Linux servers tend to have poor mtime resolution. A 1ms cache timeout on the client won't help you much if the server only registers changes in 1s increments.

Trond

A message that is not in the archive (sent off-list or not yet received): 1244754888.5047.132.camel-rJ7iovZKK19ZJLDQqaL3InhyD016LWXt@public.gmane.org

author
#8 lore raw
Quoted 54 lines · Trond Myklebust
Quoted 38 lines · Amit Gud
Quoted 15 lines · Trond Myklebust
Quoted 13 lines · Amit Gud
Quoted 12 lines · Trond Myklebust
Quoted 8 lines · Amit Gud

This patch adds 4 new NFS mount options(acdirminms, acdirmaxms, acregminms,
acregmaxms) converting already existing one into a millisecond resolution
instead of seconds.

Also, modifies the mountstats output to milliseconds instead of seconds.

Why, exactly, do you need to control cache timeouts down to the millisecond level?

Quoted 9 lines
Quoted 3 lines

The problem is to make the updates visible from one client to the other in less than a second and turning off caching entirely has an unacceptably high penalty.

Specifics, please: updates of what, exactly? Are we talking attributes, data or directory contents?

What is your application, and why does 1ms constitute an acceptable caching timeout, while 1s does not?

We have a system in which machine A needs a change made to an NFS directory. But, the actual change must be executed by machine B, so A makes an request to B to make the update. But, A is allowed to read the directory directly, so A can't in general continue until it is able to see the effect of the update. With 1s caching, that means a 1s "sleep" after each update.

Setting caching to "0s" means that consecutive stats performed by machine A must always revalidate every node of each path walked. In many cases, we end up wanting to stat every path component in some path, which would result in O(N2) getattr or lookup calls for N levels of directory depth.

Quoted 6 lines

Using a very small acdirmax (e.g. 10ms) gives us a significant performance boost on these consecutive stats without increasing the post-update "sleep" to 1s. (Of course, if the file server delays more than 10ms at any step, then we will have to start over for the next operation. But, the file server often has everything necessary in cache such that each response is well below a millisecond.)

I'm still not sure I fully understand, but here are a couple of comments.

Firstly, opendir() will _always_ force a revalidation of the directory attributes, so if your machine A is relying on doing an 'ls' in order to figure out the directory contents, then that shouldn't need extra attribute timeouts.

Quoted 14 lines

Secondly, we have already introduced finer control over the lookup caching as of Linux 2.6.28 and newer:
- if you want to ensure that machine A always see new files and links immediately once they have been created, then '-olookupcache=positive' should turn off negative dentry caching.
- if you also want to ensure that it immediately sees renames, unlinks and such, then '-olookupcache=none' will turn off lookup caching altogether.
Both of these lookup cache options are more reliable than relying on the directory attribute cache timeouts, and they have the added benefit that they also work around the problem that Linux servers tend to have poor mtime resolution. A 1ms cache timeout on the client won't help you much if the server only registers changes in 1s increments.

Those options don't seem particularly useful.

Machine A doesn't necessarily use ls to figure out changes in the directory content. So, revalidation of the directory attribute wouldn't happen.

We definitely want lookup caching turned on, always, including both positive and negative caching. But, we need to see new files, unlinks, and renames much quicker than a second.

And mtime resolution may not be a problem if NFS servers are not on Linux.

AG
--
May the source be with you.
http://www.cis.ksu.edu/~gud

#9 lore raw
Quoted 3 lines · Amit Gud

We definitely want lookup caching turned on, always, including both positive and negative caching. But, we need to see new files, unlinks, and renames much quicker than a second.

Then use the lookupcache option, since that's what it is for.

Trond

A message that is not in the archive (sent off-list or not yet received): 1244836259.19533.19.camel-rJ7iovZKK19ZJLDQqaL3InhyD016LWXt@public.gmane.org

author
#11 lore raw
Quoted 7 lines · Trond Myklebust
Quoted 3 lines · Amit Gud

We definitely want lookup caching turned on, always, including both positive and negative caching. But, we need to see new files, unlinks, and renames much quicker than a second.

Then use the lookupcache option, since that's what it is for.

Sorry, I don't understand.

Copying from your last mail:

Quoted 9 lines

Secondly, we have already introduced finer control over the lookup caching as of Linux 2.6.28 and newer:
- if you want to ensure that machine A always see new files and links immediately once they have been created, then '-olookupcache=positive' should turn off negative dentry caching.
- if you also want to ensure that it immediately sees renames, unlinks and such, then '-olookupcache=none' will turn off lookup caching altogether.

How is it possible to _not_ disable any caching (positive or negative dentries) and still be able to see renames, unlinks and such in << 1s?

AG
--
May the source be with you.
http://www.cis.ksu.edu/~gud

#12 lore raw
Quoted 23 lines · Amit Gud
Quoted 7 lines · Trond Myklebust
Quoted 3 lines · Amit Gud

We definitely want lookup caching turned on, always, including both positive and negative caching. But, we need to see new files, unlinks, and renames much quicker than a second.

Then use the lookupcache option, since that's what it is for.

Sorry, I don't understand.

Copying from your last mail:

Quoted 9 lines

Secondly, we have already introduced finer control over the lookup caching as of Linux 2.6.28 and newer:
- if you want to ensure that machine A always see new files and links immediately once they have been created, then '-olookupcache=positive' should turn off negative dentry caching.
- if you also want to ensure that it immediately sees renames, unlinks and such, then '-olookupcache=none' will turn off lookup caching altogether.

Quoted 2 lines

How is it possible to _not_ disable any caching (positive or negative dentries) and still be able to see renames, unlinks and such in << 1s?

You could set acdirmin/acdirmax to 0, but that just floods your server with GETATTR calls instead of LOOKUPs. Then again, so will your millisecond acdirmin/acdirmax.
Furthermore, you would be adjusting the _attribute_ cache timeout (not just the lookup cache), which comes at a cost to all the other operations that depend on those attributes. IOW: readdir(), permissions checking, stat() calls, ...

It boils down to this: I'm extremely reluctant to get into an arms race of adding ever more mount options for increasingly finer-tuned attribute cache timeouts. While such an option may meet _your_ machine room requirements here and now, it becomes tiresome over the years as machines gain power, and people first start lobbying for millisecond timeouts, then microseconds, nanoseconds, pico... in order to catch up.

Trond

A message that is not in the archive (sent off-list or not yet received): 1244846673.32257.69.camel-rJ7iovZKK19ZJLDQqaL3InhyD016LWXt@public.gmane.org

author
#14 lore raw
Quoted 7 lines · Trond Myklebust

It boils down to this: I'm extremely reluctant to get into an arms race of adding ever more mount options for increasingly finer-tuned attribute cache timeouts. While such an option may meet _your_ machine room requirements here and now, it becomes tiresome over the years as machines gain power, and people first start lobbying for millisecond timeouts, then microseconds, nanoseconds, pico... in order to catch up.

It only makes sense to make machines more powerful and put that power to optimum use. If keeping up with increased resolution is an issue, you think something like "-o unit=ms acregmin=..." would be better? 'unit' can apply to all the time related options defaulting to seconds.

AG

Signature · 2 lines
May the source be with you.
http://cis.ksu.edu/~gud
#15 lore raw

Re: [PATCH] NFS: Add acreg{min,max} and acdir{min, max} in milliseconds

Quoted 9 lines · Amit Gud
Quoted 7 lines · Trond Myklebust

It boils down to this: I'm extremely reluctant to get into an arms race of adding ever more mount options for increasingly finer-tuned attribute cache timeouts. While such an option may meet _your_ machine room requirements here and now, it becomes tiresome over the years as machines gain power, and people first start lobbying for millisecond timeouts, then microseconds, nanoseconds, pico... in order to catch up.

Quoted 4 lines

It only makes sense to make machines more powerful and put that power to optimum use. If keeping up with increased resolution is an issue, you think something like "-o unit=ms acregmin=..." would be better? 'unit' can apply to all the time related options defaulting to seconds.

Wasn't this problem solved hundreds of years ago by the invention of the decimal point :-)

-o acregmin=0.0012

Write the code to use as much precision as makes sense given the value of HZ - and round up. No new mount options.

NeilBrown

A message that is not in the archive (sent off-list or not yet received): 3786d1f06aae533fa82740d68985fd50.squirrel-eq65iwfR9nKIECXXMXunQA@public.gmane.org

#17 lore raw

Re: [PATCH] NFS: Add acreg{min,max} and acdir{min, max} in milliseconds

Quoted 15 lines · NeilBrown
Quoted 9 lines · Amit Gud
Quoted 7 lines · Trond Myklebust

It boils down to this: I'm extremely reluctant to get into an arms race of adding ever more mount options for increasingly finer-tuned attribute cache timeouts. While such an option may meet _your_ machine room requirements here and now, it becomes tiresome over the years as machines gain power, and people first start lobbying for millisecond timeouts, then microseconds, nanoseconds, pico... in order to catch up.

Quoted 4 lines

It only makes sense to make machines more powerful and put that power to optimum use. If keeping up with increased resolution is an issue, you think something like "-o unit=ms acregmin=..." would be better? 'unit' can apply to all the time related options defaulting to seconds.

Quoted 7 lines

Wasn't this problem solved hundreds of years ago by the invention of the decimal point :-)

-o acregmin=0.0012

Write the code to use as much precision as makes sense given the value of HZ - and round up. No new mount options.

That works for me...

Trond

A message that is not in the archive (sent off-list or not yet received): 1245107980.7470.0.camel-rJ7iovZKK19ZJLDQqaL3InhyD016LWXt@public.gmane.org

#19 lore raw

Re: [PATCH] NFS: Add acreg{min,max} and acdir{min, max} in milliseconds

Quoted 17 lines · Trond Myklebust
Quoted 16 lines · NeilBrown
Quoted 8 lines · Amit Gud
Quoted 7 lines · Trond Myklebust

It boils down to this: I'm extremely reluctant to get into an arms race of adding ever more mount options for increasingly finer-tuned attribute cache timeouts. While such an option may meet _your_ machine room requirements here and now, it becomes tiresome over the years as machines gain power, and people first start lobbying for millisecond timeouts, then microseconds, nanoseconds, pico... in order to catch up.

Quoted 4 lines

It only makes sense to make machines more powerful and put that power to optimum use. If keeping up with increased resolution is an issue, you think something like "-o unit=ms acregmin=..." would be better? 'unit' can apply to all the time related options defaulting to seconds.

Wasn't this problem solved hundreds of years ago by the invention of the decimal point :-)

Quoted 6 lines
Quoted 4 lines

-o acregmin=0.0012

Write the code to use as much precision as makes sense given the value of HZ - and round up. No new mount options.

That works for me...

Or better how about -o acregmin=12micro

steved

Quoted 7 lines

Trond

--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html

#20 lore raw

Re: [PATCH] NFS: Add acreg{min,max} and acdir{min, max} in milliseconds

Quoted 10 lines · On Tuesday June 16, [email protected] wrote:
Quoted 9 lines
Quoted 7 lines

Wasn't this problem solved hundreds of years ago by the invention of the decimal point :-)

-o acregmin=0.0012

Write the code to use as much precision as makes sense given the value of HZ - and round up. No new mount options.

That works for me...

Or better how about -o acregmin=12micro

How can you consider that to be better?
I might almost consider "12usec" a little better as it makes the unit explicit, and it is a fairly standard abbreviation. But I've never seen "micro" as a suffix before.

NeilBrown